Move exceptions in a separate file.

This enables the user to use std::istream_iterator as the underlying iterator.

LICENSE

@@ -0,0 +1,23 @@
+Boost Software License - Version 1.0 - August 17th, 2003
+
+Permission is hereby granted, free of charge, to any person or organization
+obtaining a copy of the software and accompanying documentation covered by
+this license (the "Software") to use, reproduce, display, distribute,
+execute, and transmit the Software, and to prepare derivative works of the
+Software, and to permit third-parties to whom the Software is furnished to
+do so, all subject to the following:
+
+The copyright notices in the Software and this entire statement, including
+the above license grant, this restriction and the following disclaimer,
+must be included in all copies of the Software, in whole or in part, and
+all derivative works of the Software, unless such copies or derivative
+works are solely in the form of machine-executable object code generated by
+a source language processor.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
+SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
+FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.

src/utf8.h

@@ -1,4 +1,4 @@
-// Copyright 2006-2013 Nemanja Trifunovic
+// Copyright 2006 Nemanja Trifunovic
 
 /*
 Permission is hereby granted, free of charge, to any person or organization
@@ -28,120 +28,7 @@ DEALINGS IN THE SOFTWARE.
 #ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
 #define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
 
-// By default, utf8 cpp requires C++ Standard Library strings and exceptions
-// The following macros can be used to change the default behavior 
-
-// #define UTF_CPP_NO_STD_STRING
-// #define UTF_CPP_NO_EXCEPTIONS
-
-#ifndef UTF_CPP_NO_EXCEPTIONS
-#include <stdexcept>
-
-#ifndef UTF_CPP_NO_STD_STRING
-#include <string>
-#include <iterator>
-
-#endif // #ifndef UTF_CPP_NO_STD_STRING
-#endif // #ifndef UTF_CPP_NO_EXCEPTIONS
-
-namespace utf8
-{
-
-// Error codes - used internally and if exceptions disabled
-enum class utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD,
-                     INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT};
-
-#ifndef UTF_CPP_NO_EXCEPTIONS
-// Base for the exceptions that may be thrown from the library
-class exception : public ::std::exception {
-};
-// Exceptions that may be thrown from the library functions.
-
-class invalid_code_point : public exception {
-    char32_t cp;
-public:
-    invalid_code_point(char32_t cp) : cp(cp) {}
-    virtual const char* what() const noexcept { return "Invalid code point"; }
-    char32_t code_point() const {return cp;}
-};
-
-#endif // #ifndef UTF_CPP_NO_EXCEPTIONS
-
-// 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 char32_t LEAD_SURROGATE_MIN  = 0x0000d800;
-    const char32_t LEAD_SURROGATE_MAX  = 0x0000dbff;
-    const char32_t TRAIL_SURROGATE_MIN = 0x0000dc00;
-    const char32_t TRAIL_SURROGATE_MAX = 0x0000dfff;
-
-    // Maximum valid value for a Unicode code point
-    const char32_t CODE_POINT_MAX      = 0x0010ffff;
-
-
-    inline bool is_surrogate(char32_t cp)
-    {
-        return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
-    }
-
-    inline bool is_code_point_valid(char32_t cp)
-    {
-        return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp));
-    }
-} // namespace internal
-
-    /// The library API - functions intended to be called by the users
-
-    template <typename octet_iterator>
-    octet_iterator append(char32_t cp, octet_iterator result, utf_error& error)
-    {
-        if (!utf8::internal::is_code_point_valid(cp)) {
-            error = utf8::utf_error::INVALID_CODE_POINT;
-            return result;
-        }
-
-        if (cp < 0x80)                        // one octet
-            *(result++) = static_cast<char>(cp);
-        else if (cp < 0x800) {                // two octets
-            *(result++) = static_cast<char>((cp >> 6)            | 0xc0);
-            *(result++) = static_cast<char>((cp & 0x3f)          | 0x80);
-        }
-        else if (cp < 0x10000) {              // three octets
-            *(result++) = static_cast<char>((cp >> 12)           | 0xe0);
-            *(result++) = static_cast<char>(((cp >> 6) & 0x3f)   | 0x80);
-            *(result++) = static_cast<char>((cp & 0x3f)          | 0x80);
-        }
-        else {                                // four octets
-            *(result++) = static_cast<char>((cp >> 18)           | 0xf0);
-            *(result++) = static_cast<char>(((cp >> 12) & 0x3f)  | 0x80);
-            *(result++) = static_cast<char>(((cp >> 6) & 0x3f)   | 0x80);
-            *(result++) = static_cast<char>((cp & 0x3f)          | 0x80);
-        }
-        return result;
-    }
-
-#ifndef UTF_CPP_NO_EXCEPTIONS
-    template <typename octet_iterator>
-    octet_iterator append(char32_t cp, octet_iterator result)
-    {
-        utf8::utf_error err {utf8::utf_error::UTF8_OK};
-        utf8::append(cp, result, err);
-        if (err != utf8::utf_error::UTF8_OK)
-            throw utf8::invalid_code_point(cp);
-	return result;
-    }
-#ifndef UTF_CPP_NO_STD_STRING
-    inline void append(char32_t cp, std::string& str)
-    {
-        utf8::append(cp, std::back_inserter(str)); 
-    }
-#endif // #ifndef UTF_CPP_NO_STD_STRING
-#endif // #ifndef UTF_CPP_NO_EXCEPTIONS
-
-} // namespace utf8
+#include "utf8/checked.h"
+#include "utf8/unchecked.h"
 
 #endif // header guard
-

src/utf8/checked.h

@@ -29,44 +29,12 @@ DEALINGS IN THE SOFTWARE.
 #define UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
 
 #include "core.h"
-#include <stdexcept>
+#include "exception.h"
+#include <cassert>
+#include <cstddef>
 
 namespace utf8
 {
-    // Base for the exceptions that may be thrown from the library
-    class exception : public ::std::exception {
-    };
-
-    // Exceptions that may be thrown from the library functions.
-    class invalid_code_point : public 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 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 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 exception {
-    public:
-        virtual const char* what() const throw() { return "Not enough space"; }
-    };
-
     /// The library API - functions intended to be called by the users
 
     template <typename octet_iterator>
@@ -263,9 +231,53 @@ namespace utf8
         return result;
     }
 
+	// Error policies for the iterator class
+    template <typename I>
+    class ErrorPolicyThrow {
+      public:
+      static void check_in_range(const I& it, const I& range_start, const I& range_end)
+	  {
+          if (it < range_start || it > range_end)
+              throw std::out_of_range("Invalid utf-8 iterator position");
+      }
+      static void check_same_range(const I& range_start_a, const I& range_start_b, const I& range_end_a, const I& range_end_b)
+	  {
+          if (range_start_a != range_start_b || range_end_a != range_end_b)
+              throw std::logic_error("Comparing utf-8 iterators defined with different ranges");
+      }
+    };
+    template <typename I>
+    class ErrorPolicyAssert {
+      public:
+      static void check_in_range(const I& it, const I& range_start, const I& range_end)
+	  {
+#if defined(NDEBUG)
+          (void)it;
+          (void)range_start;
+          (void)range_end;
+#else
+		  assert(it >= range_start && it <= range_end);
+#endif
+      }
+      static void check_same_range(const I& range_start_a, const I& range_start_b, const I& range_end_a, const I& range_end_b)
+	  {
+#if defined(NDEBUG)
+          (void)range_start_a;
+          (void)range_start_b;
+          (void)range_end_a;
+          (void)range_end_b;
+#else
+          assert(range_start_a == range_start_b && range_end_a == range_end_b);
+#endif
+      }
+    };
+
     // The iterator class
-    template <typename octet_iterator>
-    class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> {
+    template <
+		typename octet_iterator,
+		typename error_policy=ErrorPolicyThrow<octet_iterator>
+	>
+    class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t, std::ptrdiff_t, uint32_t*, uint32_t> {
       octet_iterator it;
       octet_iterator range_start;
       octet_iterator range_end;
@@ -276,8 +288,7 @@ namespace utf8
                          const octet_iterator& range_end) :
                it(octet_it), range_start(range_start), range_end(range_end)
       {
-          if (it < range_start || it > range_end)
-              throw std::out_of_range("Invalid utf-8 iterator position");
+          error_policy::check_in_range(it, range_start, range_end);
       }
       // the default "big three" are OK
       octet_iterator base () const { return it; }
@@ -288,8 +299,7 @@ namespace utf8
       }
       bool operator == (const iterator& rhs) const
       {
-          if (range_start != rhs.range_start || range_end != rhs.range_end)
-              throw std::logic_error("Comparing utf-8 iterators defined with different ranges");
+          error_policy::check_same_range(range_start, rhs.range_start, range_end, rhs.range_end);
           return (it == rhs.it);
       }
       bool operator != (const iterator& rhs) const
@@ -323,5 +333,3 @@ namespace utf8
 } // namespace utf8
 
 #endif //header guard
-
-

src/utf8/exception.h

@@ -0,0 +1,68 @@
+// Copyright 2006 Nemanja Trifunovic
+
+/*
+Permission is hereby granted, free of charge, to any person or organization
+obtaining a copy of the software and accompanying documentation covered by
+this license (the "Software") to use, reproduce, display, distribute,
+execute, and transmit the Software, and to prepare derivative works of the
+Software, and to permit third-parties to whom the Software is furnished to
+do so, all subject to the following:
+
+The copyright notices in the Software and this entire statement, including
+the above license grant, this restriction and the following disclaimer,
+must be included in all copies of the Software, in whole or in part, and
+all derivative works of the Software, unless such copies or derivative
+works are solely in the form of machine-executable object code generated by
+a source language processor.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
+SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
+FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.
+*/
+
+#ifndef id71B1E0983F3D4F7BAD0C091C4569AB37
+#define id71B1E0983F3D4F7BAD0C091C4569AB37
+
+#include <stdexcept>
+
+namespace utf8 {
+	// Base for the exceptions that may be thrown from the library
+	class exception : public ::std::exception {
+	};
+
+	// Exceptions that may be thrown from the library functions.
+	class invalid_code_point : public 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 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 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 exception {
+	public:
+		virtual const char* what() const throw() { return "Not enough space"; }
+	};
+} //namespace utf8
+
+#endif

tests/Makefile

@@ -1,6 +0,0 @@
-CC = g++
-CFLAGS = -g -Wall --std=c++11
-
-smoketest: unit.cpp ../src/utf8.h
-	$(CC) $(CFLAGS) unit.cpp -ounit -lboost_unit_test_framework
-	./unit

tests/unit.cpp

@@ -1,19 +0,0 @@
-#define BOOST_TEST_DYN_LINK
-#define BOOST_TEST_MODULE UTF8_CPP_UNIT
-#include <boost/test/unit_test.hpp>
-
-#include "../src/utf8.h"
-using namespace std;
-
-BOOST_AUTO_TEST_CASE(append)
-{
-	string s;
-    BOOST_CHECK_NO_THROW (utf8::append(U'\U00000448', s));
-	BOOST_CHECK (s.length() == 2 && s[0] == '\xd1' && s[1] == '\x88');
-
-	s.erase();
-	BOOST_CHECK_NO_THROW(utf8::append(U'\U000065e5', s));
-	BOOST_CHECK (s.length() == 3 && s[0] == '\xe6' && s[1] == '\x97' && s[2] == '\xa5');
-}
-
-