King_DuckZ/utfcpp
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Added boost directory, updated documentation, fixed a typo in a local variable in the code

Browse source 
git-svn-id: http://svn.code.sf.net/p/utfcpp/code@71 a809a056-fc17-0410-9590-b4f493f8b08e
This commit is contained in:
ntrifunovic 2006-12-07 02:34:42 +00:00
parent 6f08efdc90
commit 77c267b49e
8 changed files with 2000 additions and 29 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

530
boost/boost/utf8.hpp Normal file
View file

@ -0,0 +1,530 @@
// utf8.hpp header file
/*
Copyright 2006 Nemanja Trifunovic
Distributed under the Boost Software License, Version 1.0. (See
accompanying file LICENSE_1_0.txt or copy at
http://www.boost.org/LICENSE_1_0.txt)
*/
#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include <exception>
#include <boost/config.hpp>
namespace boost {
namespace utf8 {
// Exceptions that may be thrown from the library functions.
class invalid_code_point : public std::exception {
uint32_t cp;
public:
invalid_code_point(uint32_t cp) : cp(cp) {}
virtual const char* what() const throw() { return "Invalid code point"; }
uint32_t code_point() const {return cp;}
};
class invalid_utf8 : public std::exception {
uint8_t u8;
public:
invalid_utf8 (uint8_t u) : u8(u) {}
virtual const char* what() const throw() { return "Invalid UTF-8"; }
uint8_t utf8_octet() const {return u8;}
};
class invalid_utf16 : public std::exception {
uint16_t u16;
public:
invalid_utf16 (uint16_t u) : u16(u) {}
virtual const char* what() const throw() { return "Invalid UTF-16"; }
uint16_t utf16_word() const {return u16;}
};
class not_enough_room : public std::exception {
public:
virtual const char* what() const throw() { return "Not enough space"; }
};
// Helper code - not intended to be directly called by the library users. May be changed at any time
namespace internal
{
// Unicode constants
// Leading (high) surrogates: 0xd800 - 0xdbff
// Trailing (low) surrogates: 0xdc00 - 0xdfff
const uint16_t LEAD_SURROGATE_MIN = 0xd800u;
const uint16_t LEAD_SURROGATE_MAX = 0xdbffu;
const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u;
const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu;
const uint16_t LEAD_OFFSET = LEAD_SURROGATE_MIN - (0x10000 >> 10);
const uint32_t SURROGATE_OFFSET = 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN;
// Maximum valid value for a Unicode code point
const uint32_t CODE_POINT_MAX = 0x0010ffffu;
template<typename octet_type>
inline uint8_t mask8(octet_type oc)
{
return static_cast<uint8_t>(0xff & oc);
}
template<typename u16_type>
inline uint16_t mask16(u16_type oc)
{
return static_cast<uint16_t>(0xffff & oc);
}
template<typename octet_type>
inline bool is_trail(octet_type oc)
{
return ((mask8(oc) >> 6) == 0x2);
}
template <typename u16>
inline bool is_surrogate(u16 cp)
{
return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
}
template <typename u32>
inline bool is_code_point_valid(u32 cp)
{
return (cp <= CODE_POINT_MAX && !is_surrogate(cp) && cp != 0xfffe && cp != 0xffff);
}
template <typename octet_iterator>
inline typename std::iterator_traits<octet_iterator>::difference_type
sequence_length(octet_iterator lead_it)
{
uint8_t lead = mask8(*lead_it);
if (lead < 0x80)
return 1;
else if ((lead >> 5) == 0x6)
return 2;
else if ((lead >> 4) == 0xe)
return 3;
else if ((lead >> 3) == 0x1e)
return 4;
else
return 0;
}
enum utf_error {OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT};
template <typename octet_iterator>
utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t* code_point = 0)
{
uint32_t cp = mask8(*it);
// Check the lead octet
typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type;
octet_difference_type length = sequence_length(it);
// "Shortcut" for ASCII characters
if (length == 1) {
if (end - it > 0) {
if (code_point)
*code_point = cp;
++it;
return OK;
}
else
return NOT_ENOUGH_ROOM;
}
// Do we have enough memory?
if (end - it < length)
return NOT_ENOUGH_ROOM;
// Check trail octets and calculate the code point
switch (length) {
case 0:
return INVALID_LEAD;
break;
case 2:
if (is_trail(*(++it))) {
cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f);
}
else {
--it;
return INCOMPLETE_SEQUENCE;
}
break;
case 3:
if (is_trail(*(++it))) {
cp = ((cp << 12) & 0xffff) + ((mask8(*it) << 6) & 0xfff);
if (is_trail(*(++it))) {
cp += (*it) & 0x3f;
}
else {
--it; --it;
return INCOMPLETE_SEQUENCE;
}
}
else {
--it;
return INCOMPLETE_SEQUENCE;
}
break;
case 4:
if (is_trail(*(++it))) {
cp = ((cp << 18) & 0x1fffff) + ((mask8(*it) << 12) & 0x3ffff);
if (is_trail(*(++it))) {
cp += (mask8(*it) << 6) & 0xfff;
if (is_trail(*(++it))) {
cp += (*it) & 0x3f;
}
else {
--it; --it; --it;
return INCOMPLETE_SEQUENCE;
}
}
else {
--it; --it;
return INCOMPLETE_SEQUENCE;
}
}
else {
--it;
return INCOMPLETE_SEQUENCE;
}
break;
}
// Is the code point valid?
if (!is_code_point_valid(cp)) {
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return INVALID_CODE_POINT;
}
if (code_point)
*code_point = cp;
if (cp < 0x80) {
if (length != 1) {
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return OVERLONG_SEQUENCE;
}
}
else if (cp < 0x800) {
if (length != 2) {
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return OVERLONG_SEQUENCE;
}
}
else if (cp < 0x10000) {
if (length != 3) {
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return OVERLONG_SEQUENCE;
}
}
++it;
return OK;
}
} // namespace internal
/// The library API - functions intended to be called by the users
// Byte order mark
const uint8_t bom[] = {0xef, 0xbb, 0xbf};
template <typename octet_iterator>
octet_iterator find_invalid(octet_iterator start, octet_iterator end)
{
octet_iterator result = start;
while (result != end) {
internal::utf_error err_code = internal::validate_next(result, end);
if (err_code != internal::OK)
return result;
}
return result;
}
template <typename octet_iterator>
bool is_valid(octet_iterator start, octet_iterator end)
{
return (find_invalid(start, end) == end);
}
template <typename octet_iterator>
bool is_bom (octet_iterator it)
{
return (
(internal::mask8(*it++)) == bom[0] &&
(internal::mask8(*it++)) == bom[1] &&
(internal::mask8(*it)) == bom[2]
);
}
template <typename octet_iterator>
octet_iterator append(uint32_t cp, octet_iterator result)
{
if (!internal::is_code_point_valid(cp))
throw invalid_code_point(cp);
if (cp < 0x80) // one octet
*(result++) = static_cast<uint8_t>(cp);
else if (cp < 0x800) { // two octets
*(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
else if (cp < 0x10000) { // three octets
*(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0);
*(result++) = static_cast<uint8_t>((cp >> 6) & 0x3f | 0x80);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
else if (cp <= internal::CODE_POINT_MAX) { // four octets
*(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0);
*(result++) = static_cast<uint8_t>((cp >> 12)& 0x3f | 0x80);
*(result++) = static_cast<uint8_t>((cp >> 6) & 0x3f | 0x80);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
else
throw invalid_code_point(cp);
return result;
}
template <typename octet_iterator>
uint32_t next(octet_iterator& it, octet_iterator end)
{
uint32_t cp = 0;
internal::utf_error err_code = internal::validate_next(it, end, &cp);
switch (err_code) {
case internal::OK :
break;
case internal::NOT_ENOUGH_ROOM :
throw not_enough_room();
case internal::INVALID_LEAD :
case internal::INCOMPLETE_SEQUENCE :
case internal::OVERLONG_SEQUENCE :
throw invalid_utf8(*it);
case internal::INVALID_CODE_POINT :
throw invalid_code_point(cp);
}
return cp;
}
template <typename octet_iterator>
uint32_t prior(octet_iterator& it, octet_iterator start)
{
octet_iterator end = it;
while (internal::is_trail(*(--it)))
if (it < start)
throw invalid_utf8(*it); // error - no lead byte in the sequence
octet_iterator temp = it;
return next(temp, end);
}
template <typename octet_iterator, typename distance_type>
void advance (octet_iterator& it, distance_type n, octet_iterator end)
{
for (distance_type i = 0; i < n; ++i)
next(it, end);
}
template <typename octet_iterator>
typename std::iterator_traits<octet_iterator>::difference_type
distance (octet_iterator first, octet_iterator last)
{
typename std::iterator_traits<octet_iterator>::difference_type dist;
for (dist = 0; first < last; ++dist)
next(first, last);
return dist;
}
template <typename u16bit_iterator, typename octet_iterator>
octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
{
while (start != end) {
uint32_t cp = internal::mask16(*start++);
// Take care of surrogate pairs first
if (internal::is_surrogate(cp)) {
if (start != end) {
uint32_t trail_surrogate = internal::mask16(*start++);
if (trail_surrogate >= internal::TRAIL_SURROGATE_MIN && trail_surrogate <= internal::TRAIL_SURROGATE_MAX)
cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
else
throw invalid_utf16(static_cast<uint16_t>(trail_surrogate));
}
else
throw invalid_utf16(static_cast<uint16_t>(*start));
}
result = append(cp, result);
}
return result;
}
template <typename u16bit_iterator, typename octet_iterator>
u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
{
while (start != end) {
uint32_t cp = next(start, end);
if (cp > 0xffff) { //make a surrogate pair
*result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET);
*result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
}
else
*result++ = static_cast<uint16_t>(cp);
}
return result;
}
template <typename octet_iterator, typename u32bit_iterator>
octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
{
while (start != end)
result = append(*(start++), result);
return result;
}
template <typename octet_iterator, typename u32bit_iterator>
u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
{
while (start < end)
(*result++) = next(start, end);
return result;
}
namespace unchecked
{
template <typename octet_iterator>
octet_iterator append(uint32_t cp, octet_iterator result)
{
if (cp < 0x80) // one octet
*(result++) = static_cast<uint8_t>(cp);
else if (cp < 0x800) { // two octets
*(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
else if (cp < 0x10000) { // three octets
*(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0);
*(result++) = static_cast<uint8_t>((cp >> 6) & 0x3f | 0x80);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
else { // four octets
*(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0);
*(result++) = static_cast<uint8_t>((cp >> 12)& 0x3f | 0x80);
*(result++) = static_cast<uint8_t>((cp >> 6) & 0x3f | 0x80);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
return result;
}
template <typename octet_iterator>
uint32_t next(octet_iterator& it)
{
uint32_t cp = internal::mask8(*it);
typename std::iterator_traits<octet_iterator>::difference_type length = utf8::internal::sequence_length(it);
switch (length) {
case 1:
break;
case 2:
it++;
cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f);
break;
case 3:
++it;
cp = ((cp << 12) & 0xffff) + ((internal::mask8(*it) << 6) & 0xfff);
++it;
cp += (*it) & 0x3f;
break;
case 4:
++it;
cp = ((cp << 18) & 0x1fffff) + ((internal::mask8(*it) << 12) & 0x3ffff);
++it;
cp += (internal::mask8(*it) << 6) & 0xfff;
++it;
cp += (*it) & 0x3f;
break;
}
++it;
return cp;
}
template <typename octet_iterator>
uint32_t prior(octet_iterator& it)
{
while (internal::is_trail(*(--it))) ;
octet_iterator temp = it;
return next(temp);
}
template <typename octet_iterator, typename distance_type>
void advance (octet_iterator& it, distance_type n)
{
for (distance_type i = 0; i < n; ++i)
next(it);
}
template <typename octet_iterator>
typename std::iterator_traits<octet_iterator>::difference_type
distance (octet_iterator first, octet_iterator last)
{
typename std::iterator_traits<octet_iterator>::difference_type dist;
for (dist = 0; first < last; ++dist)
next(first);
return dist;
}
template <typename u16bit_iterator, typename octet_iterator>
octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
{
while (start != end) {
uint32_t cp = internal::mask16(*start++);
// Take care of surrogate pairs first
if (internal::is_surrogate(cp)) {
uint32_t trail_surrogate = internal::mask16(*start++);
cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
}
result = append(cp, result);
}
return result;
}
template <typename u16bit_iterator, typename octet_iterator>
u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
{
while (start != end) {
uint32_t cp = next(start);
if (cp > 0xffff) { //make a surrogate pair
*result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET);
*result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
}
else
*result++ = static_cast<uint16_t>(cp);
}
return result;
}
template <typename octet_iterator, typename u32bit_iterator>
octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
{
while (start != end)
result = append(*(start++), result);
return result;
}
template <typename octet_iterator, typename u32bit_iterator>
u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
{
while (start < end)
(*result++) = next(start);
return result;
}
} // namespace utf8::unchecked
} // namespace utf8
} // namespace boost
#endif // header guard

17
boost/libs/utf8/Jamfile Normal file
View file

@ -0,0 +1,17 @@
# Boost UTF8 Library test Jamfile
# Copyright Nemanja Trifunovic 2006
# Use, modification, and distribution is subject to the Boost Software
# License, Version 1.0. (See accompanying file LICENSE_1_0.txt or copy at
# http://www.boost.org/LICENSE_1_0.txt)
# bring in rules for testing
import testing ;
{
test-suite "utf8"
: [ run test.cpp ]
;
}

1102
boost/libs/utf8/index.html Normal file
View file

File diff suppressed because it is too large Load diff

220
boost/libs/utf8/test.cpp Normal file
View file

@ -0,0 +1,220 @@
#include <vector>
#include <iterator>
#include "boost/utf8.hpp"
#include <boost/detail/lightweight_test.hpp>
using namespace boost::utf8;
using namespace std;
int main()
{
//append
unsigned char u[5] = {0,0,0,0,0};
unsigned char* end = append(0x0448, u);
BOOST_TEST (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0);
end = append(0x65e5, u);
BOOST_TEST (u[0] == 0xe6 && u[1] == 0x97 && u[2] == 0xa5 && u[3] == 0 && u[4] == 0);
end = append(0x3044, u);
BOOST_TEST (u[0] == 0xe3 && u[1] == 0x81 && u[2] == 0x84 && u[3] == 0 && u[4] == 0);
end = append(0x10346, u);
BOOST_TEST (u[0] == 0xf0 && u[1] == 0x90 && u[2] == 0x8d && u[3] == 0x86 && u[4] == 0);
//next
char* twochars = "\xe6\x97\xa5\xd1\x88";
char* w = twochars;
int cp = next(w, twochars + 6);
BOOST_TEST (cp == 0x65e5);
BOOST_TEST (w == twochars + 3);
char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
w = threechars;
cp = next(w, threechars + 9);
BOOST_TEST (cp == 0x10346);
BOOST_TEST (w == threechars + 4);
cp = next(w, threechars + 9);
BOOST_TEST (cp == 0x65e5);
BOOST_TEST (w == threechars + 7);
cp = next(w, threechars + 9);
BOOST_TEST (cp == 0x0448);
BOOST_TEST (w == threechars + 9);
//prior
w = twochars + 3;
cp = prior (w, twochars - 1);
BOOST_TEST (cp == 0x65e5);
BOOST_TEST (w == twochars);
w = threechars + 9;
cp = prior(w, threechars - 1);
BOOST_TEST (cp == 0x0448);
BOOST_TEST (w == threechars + 7);
cp = prior(w, threechars -1);
BOOST_TEST (cp == 0x65e5);
BOOST_TEST (w == threechars + 4);
cp = prior(w, threechars - 1);
BOOST_TEST (cp == 0x10346);
BOOST_TEST (w == threechars);
// advance
w = twochars;
advance (w, 2, twochars + 6);
BOOST_TEST (w == twochars + 5);
// distance
size_t dist = boost::utf8::distance(twochars, twochars + 5);
BOOST_TEST (dist == 2);
// utf32to8
int utf32string[] = {0x448, 0x65E5, 0x10346, 0};
vector<char> utf8result;
utf32to8(utf32string, utf32string + 3, back_inserter(utf8result));
BOOST_TEST (utf8result.size() == 9);
// try it with the return value;
char* utf8_end = utf32to8(utf32string, utf32string + 3, &utf8result[0]);
BOOST_TEST (utf8_end == &utf8result[0] + 9);
//utf8to32
vector<int> utf32result;
utf8to32(twochars, twochars + 5, back_inserter(utf32result));
BOOST_TEST (utf32result.size() == 2);
// try it with the return value;
int* utf32_end = utf8to32(twochars, twochars + 5, &utf32result[0]);
BOOST_TEST (utf32_end == &utf32result[0] + 2);
//utf16to8
unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
utf8result.clear();
utf16to8(utf16string, utf16string + 5, back_inserter(utf8result));
BOOST_TEST (utf8result.size() == 10);
// try it with the return value;
utf8_end = utf16to8 (utf16string, utf16string + 5, &utf8result[0]);
BOOST_TEST (utf8_end == &utf8result[0] + 10);
//utf8to16
char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
vector <unsigned short> utf16result;
utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result));
BOOST_TEST (utf16result.size() == 4);
BOOST_TEST (utf16result[2] == 0xd834);
BOOST_TEST (utf16result[3] == 0xdd1e);
// try it with the return value;
unsigned short* utf16_end = utf8to16 (utf8_with_surrogates, utf8_with_surrogates + 9, &utf16result[0]);
BOOST_TEST (utf16_end == &utf16result[0] + 4);
//find_invalid
char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa";
char* invalid = find_invalid(utf_invalid, utf_invalid + 6);
BOOST_TEST (invalid == utf_invalid + 5);
//is_valid
bool bvalid = is_valid(utf_invalid, utf_invalid + 6);
BOOST_TEST (bvalid == false);
bvalid = is_valid(utf8_with_surrogates, utf8_with_surrogates + 9);
BOOST_TEST (bvalid == true);
//is_bom
unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf};
bool bbom = is_bom(byte_order_mark);
BOOST_TEST (bbom == true);
//////////////////////////////////////////////////////////
//// Unchecked variants
//////////////////////////////////////////////////////////
//append
memset(u, 0, 5);
end = unchecked::append(0x0448, u);
BOOST_TEST (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0);
end = unchecked::append(0x65e5, u);
BOOST_TEST (u[0] == 0xe6 && u[1] == 0x97 && u[2] == 0xa5 && u[3] == 0 && u[4] == 0);
end = unchecked::append(0x10346, u);
BOOST_TEST (u[0] == 0xf0 && u[1] == 0x90 && u[2] == 0x8d && u[3] == 0x86 && u[4] == 0);
//next
w = twochars;
cp = unchecked::next(w);
BOOST_TEST (cp == 0x65e5);
BOOST_TEST (w == twochars + 3);
w = threechars;
cp = unchecked::next(w);
BOOST_TEST (cp == 0x10346);
BOOST_TEST (w == threechars + 4);
cp = unchecked::next(w);
BOOST_TEST (cp == 0x65e5);
BOOST_TEST (w == threechars + 7);
cp = unchecked::next(w);
BOOST_TEST (cp == 0x0448);
BOOST_TEST (w == threechars + 9);
//prior
w = twochars + 3;
cp = unchecked::prior (w);
BOOST_TEST (cp == 0x65e5);
BOOST_TEST (w == twochars);
w = threechars + 9;
cp = unchecked::prior(w);
BOOST_TEST (cp == 0x0448);
BOOST_TEST (w == threechars + 7);
cp = unchecked::prior(w);
BOOST_TEST (cp == 0x65e5);
BOOST_TEST (w == threechars + 4);
cp = unchecked::prior(w);
BOOST_TEST (cp == 0x10346);
BOOST_TEST (w == threechars);
// advance
w = twochars;
unchecked::advance (w, 2);
BOOST_TEST (w == twochars + 5);
// distance
dist = unchecked::distance(twochars, twochars + 5);
BOOST_TEST (dist == 2);
// utf32to8
utf8result.clear();
unchecked::utf32to8(utf32string, utf32string + 3, back_inserter(utf8result));
BOOST_TEST (utf8result.size() == 9);
// try it with the return value;
utf8_end = utf32to8(utf32string, utf32string + 3, &utf8result[0]);
BOOST_TEST(utf8_end == &utf8result[0] + 9);
//utf8to32
utf32result.clear();
unchecked::utf8to32(twochars, twochars + 5, back_inserter(utf32result));
BOOST_TEST (utf32result.size() == 2);
// try it with the return value;
utf32_end = utf8to32(twochars, twochars + 5, &utf32result[0]);
BOOST_TEST (utf32_end == &utf32result[0] + 2);
//utf16to8
utf8result.clear();
unchecked::utf16to8(utf16string, utf16string + 5, back_inserter(utf8result));
BOOST_TEST (utf8result.size() == 10);
// try it with the return value;
utf8_end = utf16to8 (utf16string, utf16string + 5, &utf8result[0]);
BOOST_TEST (utf8_end == &utf8result[0] + 10);
//utf8to16
utf16result.clear();
unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result));
BOOST_TEST (utf16result.size() == 4);
BOOST_TEST (utf16result[2] == 0xd834);
BOOST_TEST (utf16result[3] == 0xdd1e);
// try it with the return value;
utf16_end = utf8to16 (utf8_with_surrogates, utf8_with_surrogates + 9, &utf16result[0]);
BOOST_TEST (utf16_end == &utf16result[0] + 4);
return boost::report_errors();
}

2
v1_0/doc/utf8cpp.html
View file

@ -133,7 +133,7 @@
}
<span class="comment">// Play with all the lines in the file</span>
<span class="keyword">do</span> {
// check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function)
<span class="comment">// check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function)</span>
string::iterator end_it = utf8::find_invalid(line.begin(), line.end());
<span class="keyword">if</span> (end_it != line.end()) {
cout &lt;&lt; <span class=

12
v1_0/source/utf8.h
View file

@ -140,8 +140,8 @@ namespace internal
{
uint32_t cp = mask8(*it);
// Check the lead octet
typedef typename std::iterator_traits<octet_iterator>::difference_type octet_differece_type;
octet_differece_type length = sequence_length(it);
typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type;
octet_difference_type length = sequence_length(it);
// "Shortcut" for ASCII characters
if (length == 1) {
@ -215,7 +215,7 @@ namespace internal
}
// Is the code point valid?
if (!is_code_point_valid(cp)) {
for (octet_differece_type i = 0; i < length - 1; ++i)
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return INVALID_CODE_POINT;
}
@ -225,21 +225,21 @@ namespace internal
if (cp < 0x80) {
if (length != 1) {
for (octet_differece_type i = 0; i < length - 1; ++i)
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return OVERLONG_SEQUENCE;
}
}
else if (cp < 0x800) {
if (length != 2) {
for (octet_differece_type i = 0; i < length - 1; ++i)
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return OVERLONG_SEQUENCE;
}
}
else if (cp < 0x10000) {
if (length != 3) {
for (octet_differece_type i = 0; i < length - 1; ++i)
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return OVERLONG_SEQUENCE;
}

134
v2_0/doc/utf8cpp.html
View file

@ -80,8 +80,7 @@
In order to easily handle UTF-8 encoded Unicode strings, I have come up with a set
of template functions. For anybody used to work with STL algorithms, they should be
easy and natural to use. The code is freely available for any purpose - check out
the license at the beginning of the utf8.h file. Be aware, though, that while I did
some testing, this library has not been used in production yet. If you run into
the license at the beginning of the utf8.h file. If you run into
bugs or performance issues, please let me know and I'll do my best to address them.
</p>
<p>
@ -134,7 +133,7 @@
}
<span class="comment">// Play with all the lines in the file</span>
<span class="keyword">do</span> {
// check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function)
<span class="comment">// check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function)</span>
string::iterator end_it = utf8::find_invalid(line.begin(), line.end());
<span class="keyword">if</span> (end_it != line.end()) {
cout &lt;&lt; <span class=
@ -272,7 +271,62 @@ assert (w == twochars + <span class="literal">3</span>);
thrown.
</p>
<h4>
utf8::previous
utf8::prior
</h4>
<p>
Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
decreases the iterator until it hits the beginning of the previous UTF-8 encoded
code point and returns the 32 bits representation of the code point.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
uint32_t prior(octet_iterator&amp; it, octet_iterator start);
</pre>
<p>
<code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
After the function returns, it is decremented to point to the beginning of the
previous code point.<br>
<code>start</code>: an iterator to the beginning of the sequence where the search
for the beginning of a code point is performed. It is a
safety measure to prevent passing the beginning of the string in the search for a
UTF-8 lead octet.<br>
<span class="return_value">Return value</span>: the 32 bit representation of the
previous code point.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
<span class="keyword">unsigned char</span>* w = twochars + <span class=
"literal">3</span>;
<span class="keyword">int</span> cp = prior (w, twochars);
assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars);
</pre>
<p>
This function has two purposes: one is two iterate backwards through a UTF-8
encoded string. Note that it is usually a better idea to iterate forward instead,
since <code>utf8::next</code> is faster. The second purpose is to find a beginning
of a UTF-8 sequence if we have a random position within a string.
</p>
<p>
<code>it</code> will typically point to the beginning of
a code point, and <code>start</code> will point to the
beginning of the string to ensure we don't go backwards too far. <code>it</code> is
decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence
beginning with that octet is decoded to a 32 bit representation and returned.
</p>
<p>
In case <code>pass_end</code> is reached before a UTF-8 lead octet is hit, or if an
invalid UTF-8 sequence is started by the lead octet, an <code>invalid_utf8</code>
exception is thrown.
</p>
<h4>
utf8::previous (deprecated, see utf8::prior)
</h4>
<p>
Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
@ -310,8 +364,14 @@ assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars);
</pre>
<p>
The primary purpose of this function is to iterate backwards through a UTF-8
encoded string. Therefore, <code>it</code> will typically point to the beginning of
<code>utf8::previous</code> is deprecated, and <code>utf8::prior</code> should
be used instead, although the existing code can continue using this function.
The problem is the parameter <code>pass_start</code> that points to the position
just before the beginning of the sequence. Standard containers don't have the
concept of "pass start" and the function can not be used with their iterators.
</p>
<p>
<code>it</code> will typically point to the beginning of
a code point, and <code>pass_start</code> will point to the octet just before the
beginning of the string to ensure we don't go backwards too far. <code>it</code> is
decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence
@ -760,7 +820,7 @@ assert (u[<span class="literal">0</span>] == <span class=
"literal">0</span>);
</pre>
<p>
This is a quicker but less safe version of <code>utf8::append</code>. It does not
This is a faster but less safe version of <code>utf8::append</code>. It does not
check for validity of the supplied code point, and may produce an invalid UTF-8
sequence.
</p>
@ -796,11 +856,47 @@ assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars + <span class="literal">3</span>);
</pre>
<p>
This is a quicker but less safe version of <code>utf8::next</code>. It does not
This is a faster but less safe version of <code>utf8::next</code>. It does not
check for validity of the supplied UTF-8 sequence.
</p>
<h4>
utf8::unchecked::previous
utf8::unchecked::prior
</h4>
<p>
Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
decreases the iterator until it hits the beginning of the previous UTF-8 encoded
code point and returns the 32 bits representation of the code point.
</p>
<pre>
<span class="keyword">template</span> &lt;<span class=
"keyword">typename</span> octet_iterator&gt;
uint32_t prior(octet_iterator&amp; it);
</pre>
<p>
<code>it</code>: a reference pointing to an octet within a UTF-8 encoded string.
After the function returns, it is decremented to point to the beginning of the
previous code point.<br>
<span class="return_value">Return value</span>: the 32 bit representation of the
previous code point.
</p>
<p>
Example of use:
</p>
<pre>
<span class="keyword">char</span>* twochars = <span class=
"literal">"\xe6\x97\xa5\xd1\x88"</span>;
<span class="keyword">char</span>* w = twochars + <span class="literal">3</span>;
<span class="keyword">int</span> cp = unchecked::prior (w);
assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars);
</pre>
<p>
This is a faster but less safe version of <code>utf8::prior</code>. It does not
check for validity of the supplied UTF-8 sequence and offers no boundary checking.
</p>
<h4>
utf8::unchecked::previous (deprecated, see utf8::unchecked::prior)
</h4>
<p>
Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it
@ -832,7 +928,13 @@ assert (cp == <span class="literal">0x65e5</span>);
assert (w == twochars);
</pre>
<p>
This is a quicker but less safe version of <code>utf8::previous</code>. It does not
The reason this function is deprecated is just the consistency with the "checked"
versions, where <code>prior</code> should be used instead of <code>previous</code>.
In fact, <code>unchecked::previous</code> behaves exactly the same as <code>
unchecked::prior</code>
</p>
<p>
This is a faster but less safe version of <code>utf8::previous</code>. It does not
check for validity of the supplied UTF-8 sequence and offers no boundary checking.
</p>
<h4>
@ -870,7 +972,7 @@ assert (w == twochars + <span class="literal">5</span>);
no effect.
</p>
<p>
This is a quicker but less safe version of <code>utf8::advance</code>. It does not
This is a faster but less safe version of <code>utf8::advance</code>. It does not
check for validity of the supplied UTF-8 sequence and offers no boundary checking.
</p>
<h4>
@ -905,7 +1007,7 @@ size_t dist = utf8::unchecked::distance(twochars, twochars + <span class=
assert (dist == <span class="literal">2</span>);
</pre>
<p>
This is a quicker but less safe version of <code>utf8::distance</code>. It does not
This is a faster but less safe version of <code>utf8::distance</code>. It does not
check for validity of the supplied UTF-8 sequence.
</p>
<h4>
@ -945,7 +1047,7 @@ unchecked::utf16to8(utf16string, utf16string + <span class=
assert (utf8result.size() == <span class="literal">10</span>);
</pre>
<p>
This is a quicker but less safe version of <code>utf8::utf16to8</code>. It does not
This is a faster but less safe version of <code>utf8::utf16to8</code>. It does not
check for validity of the supplied UTF-16 sequence.
</p>
<h4>
@ -985,7 +1087,7 @@ assert (utf16result[<span class="literal">3</span>] == <span class=
"literal">0xdd1e</span>);
</pre>
<p>
This is a quicker but less safe version of <code>utf8::utf8to16</code>. It does not
This is a faster but less safe version of <code>utf8::utf8to16</code>. It does not
check for validity of the supplied UTF-8 sequence.
</p>
<h4>
@ -1024,7 +1126,7 @@ utf32to8(utf32string, utf32string + <span class=
assert (utf8result.size() == <span class="literal">9</span>);
</pre>
<p>
This is a quicker but less safe version of <code>utf8::utf32to8</code>. It does not
This is a faster but less safe version of <code>utf8::utf32to8</code>. It does not
check for validity of the supplied UTF-32 sequence.
</p>
<h4>
@ -1061,7 +1163,7 @@ unchecked::utf8to32(twochars, twochars + <span class=
assert (utf32result.size() == <span class="literal">2</span>);
</pre>
<p>
This is a quicker but less safe version of <code>utf8::utf8to32</code>. It does not
This is a faster but less safe version of <code>utf8::utf8to32</code>. It does not
check for validity of the supplied UTF-8 sequence.
</p>
<h2 id="points">

12
v2_0/source/utf8/core.h
View file

@ -107,8 +107,8 @@ namespace internal
{
uint32_t cp = mask8(*it);
// Check the lead octet
typedef typename std::iterator_traits<octet_iterator>::difference_type octet_differece_type;
octet_differece_type length = sequence_length(it);
typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type;
octet_difference_type length = sequence_length(it);
// "Shortcut" for ASCII characters
if (length == 1) {
@ -182,7 +182,7 @@ namespace internal
}
// Is the code point valid?
if (!is_code_point_valid(cp)) {
for (octet_differece_type i = 0; i < length - 1; ++i)
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return INVALID_CODE_POINT;
}
@ -192,21 +192,21 @@ namespace internal
if (cp < 0x80) {
if (length != 1) {
for (octet_differece_type i = 0; i < length - 1; ++i)
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return OVERLONG_SEQUENCE;
}
}
else if (cp < 0x800) {
if (length != 2) {
for (octet_differece_type i = 0; i < length - 1; ++i)
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return OVERLONG_SEQUENCE;
}
}
else if (cp < 0x10000) {
if (length != 3) {
for (octet_differece_type i = 0; i < length - 1; ++i)
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return OVERLONG_SEQUENCE;
}