从宽字符转换到UTF8的代码

代码]cpp代码  http://www.oschina.net/code/snippet_170948_18231   

001

/*

002	Copyright (C) 2004-2005 Cory Nelson

003

004	This software is provided 'as-is', without any express or implied

005	warranty.  In no event will the authors be held liable for any damages

006	arising from the use of this software.

007

008	Permission is granted to anyone to use this software for any purpose,

009	including commercial applications, and to alter it and redistribute it

010	freely, subject to the following restrictions:

011

012	1. The origin of this software must not be misrepresented; you must not

013	claim that you wrote the original software. If you use this software

014	in a product, an acknowledgment in the product documentation would be

015	appreciated but is not required.

016	2. Altered source versions must be plainly marked as such, and must not be

017	misrepresented as being the original software.

018	3. This notice may not be removed or altered from any source distribution.

019

*/

020

021	// namespaces added by Arvid Norberg

022

023	#ifndef __UTF8_H__

024	#define __UTF8_H__

025

026	#include <string>

027	#include <iterator>

028	#include <stdexcept>

029	#include <cwchar>

030

031	namespace detail {

032

033	template<typename InputIterator>

034	wchar_t decode_utf8_mb(InputIterator &iter, InputIterator last)

035

{

036	if (iter == last) throw std::runtime_error("incomplete UTF-8 sequence");

037	if (((*iter) & 0xc0) != 0x80) throw std::runtime_error("invalid UTF-8 sequence");

038

039	return (wchar_t)((*iter++) & 0x3f);

040

}

041

042	template<typename InputIterator>

043	wchar_t decode_utf8(InputIterator &iter, InputIterator last)

044

{

045	wchar_t ret;

046

047	if (((*iter) & 0x80) == 0) // one byte

048

{

049	ret = *iter++;

050

}

051	else if (((*iter) & 0xe0) == 0xc0) // two bytes

052

{

053	wchar_t byte1 = (*iter++) & 0x1f;

054	wchar_t byte2 = decode_utf8_mb(iter, last);

055	ret = (byte1 << 6) | byte2;

056

}

057	else if (((*iter) & 0xf0) == 0xe0) // three bytes

058

{

059	wchar_t byte1 = (*iter++) & 0x0f;

060	wchar_t byte2 = decode_utf8_mb(iter, last);

061	wchar_t byte3 = decode_utf8_mb(iter, last);

062	ret = (byte1 << 12) | (byte2 << 6) | byte3;

063

}

064	// TODO: support surrogate pairs

065	else throw std::runtime_error("UTF-8 not convertable to UTF-16");

066

067	return ret;

068

}

069

070	template<typename InputIterator, typename OutputIterator>

071	OutputIterator utf8_wchar(InputIterator first, InputIterator last, OutputIterator dest)

072

{

073	for(; first!=last; ++dest)

074	*dest = decode_utf8(first, last);

075	return dest;

076

}

077

078	template<typename InputIterator, typename OutputIterator>

079	void encode_wchar(InputIterator iter, OutputIterator &dest)

080

{

081	if(*iter <= 0x007F)

082

{

083	*dest=(char)*iter;

084

++dest;

085

}

086	else if(*iter <= 0x07FF)

087

{

088	*dest = (char)(

089

0xC0 |

090	((*iter & 0x07C0) >> 6)

091

);

092

++dest;

093

094	*dest = (char)(

095

0x80 |

096	(*iter & 0x003F)

097

);

098

++dest;

099

}

100	else if(*iter <= 0xFFFF)

101

{

102	*dest = (char)(

103

0xE0 |

104	((*iter & 0xF000) >> 12)

105

);

106

++dest;

107

108	*dest = (char)(

109

0x80 |

110	((*iter & 0x0FC0) >> 6)

111

);

112

++dest;

113

114	*dest = (char)(

115

0x80 |

116	(*iter & 0x003F)

117

);

118

++dest;

119

}

120

}

121

122	template<typename InputIterator, typename OutputIterator>

123	OutputIterator wchar_utf8(InputIterator first, InputIterator last, OutputIterator dest)

124

{

125	for(; first!=last; ++first)

126	encode_wchar(first, dest);

127	return dest;

128

}

129

130

}

131

132	inline void utf8_wchar(const std::string &utf8, std::wstring &wide)

133

{

134	wide.clear();

135	detail::utf8_wchar(utf8.begin(), utf8.end(), std::back_inserter(wide));

136

}

137

138	inline std::wstring utf8_wchar(const std::string &str)

139

{

140	std::wstring ret;

141	utf8_wchar(str, ret);

142	return ret;

143

}

144

145	inline void wchar_utf8(const std::wstring &wide, std::string &utf8)

146

{

147	utf8.clear();

148	detail::wchar_utf8(wide.begin(), wide.end(), std::back_inserter(utf8));

149

}

150

151	inline std::string wchar_utf8(const std::wstring &str)

152

{

153	std::string ret;

154	wchar_utf8(str, ret);

155	return ret;

156

}

157

158	#endif // __UTF8_H__

举报