Fixed Issue #395: [BUG] Infomation error when "Switch the comparison"
[TortoiseGit.git] / src / Utils / UnicodeUtils.cpp
blob8e6ee124117e09ee2b314c95a609d36955d7c9c0
1 // TortoiseSVN - a Windows shell extension for easy version control
3 // Copyright (C) 2003-2006, 2008 - TortoiseSVN
5 // This program is free software; you can redistribute it and/or
6 // modify it under the terms of the GNU General Public License
7 // as published by the Free Software Foundation; either version 2
8 // of the License, or (at your option) any later version.
10 // This program is distributed in the hope that it will be useful,
11 // but WITHOUT ANY WARRANTY; without even the implied warranty of
12 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 // GNU General Public License for more details.
15 // You should have received a copy of the GNU General Public License
16 // along with this program; if not, write to the Free Software Foundation,
17 // 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
19 #include "StdAfx.h"
20 #include "unicodeutils.h"
22 CUnicodeUtils::CUnicodeUtils(void)
26 CUnicodeUtils::~CUnicodeUtils(void)
30 #if defined(_MFC_VER) || defined(CSTRING_AVAILABLE)
32 struct CodeMap
34 int m_Code;
35 TCHAR * m_CodeName;
37 int CUnicodeUtils::GetCPCode(CString &codename)
39 static CodeMap map[]=
41 {037, _T("IBM037")},// IBM EBCDIC US-Canada
42 {437, _T("IBM437")},// OEM United States
43 {500, _T("IBM500")},// IBM EBCDIC International
44 {708, _T("ASMO-708")},// Arabic (ASMO 708)
45 {709, _T("Arabic")},// (ASMO-449+, BCON V4)
46 {710, _T("Arabic")},// - Transparent Arabic
47 {720, _T("DOS-720")},// Arabic (Transparent ASMO); Arabic (DOS)
48 {737, _T("ibm737")},// OEM Greek (formerly 437G); Greek (DOS)
49 {775, _T("ibm775")},// OEM Baltic; Baltic (DOS)
50 {850, _T("ibm850")},// OEM Multilingual Latin 1; Western European (DOS)
51 {852, _T("ibm852")},// OEM Latin 2; Central European (DOS)
52 {855, _T("IBM855")},// OEM Cyrillic (primarily Russian)
53 {857, _T("ibm857")},// OEM Turkish; Turkish (DOS)
54 {858, _T("IBM00858")},// OEM Multilingual Latin 1 + Euro symbol
55 {860, _T("IBM860")},// OEM Portuguese; Portuguese (DOS)
56 {861, _T("ibm861")},// OEM Icelandic; Icelandic (DOS)
57 {862, _T("DOS-862")},// OEM Hebrew; Hebrew (DOS)
58 {863, _T("IBM863")},// OEM French Canadian; French Canadian (DOS)
59 {864, _T("IBM864")},// OEM Arabic; Arabic (864)
60 {865, _T("IBM865")},// OEM Nordic; Nordic (DOS)
61 {866, _T("cp866")},// OEM Russian; Cyrillic (DOS)
62 {869, _T("ibm869")},// OEM Modern Greek; Greek, Modern (DOS)
63 {870, _T("IBM870")},// IBM EBCDIC Multilingual/ROECE (Latin 2); IBM EBCDIC Multilingual Latin 2
64 {874, _T("windows-874")},// ANSI/OEM Thai (same as 28605, ISO 8859-15); Thai (Windows)
65 {875, _T("cp875")},// IBM EBCDIC Greek Modern
66 {932, _T("shift_jis")},// ANSI/OEM Japanese; Japanese (Shift-JIS)
67 {936, _T("gb2312")},// ANSI/OEM Simplified Chinese (PRC, Singapore); Chinese Simplified (GB2312)
68 {949, _T("ks_c_5601-1987")},// ANSI/OEM Korean (Unified Hangul Code)
69 {950, _T("big5")},// ANSI/OEM Traditional Chinese (Taiwan; Hong Kong SAR, PRC); Chinese Traditional (Big5)
70 {1026,_T("IBM1026")},// IBM EBCDIC Turkish (Latin 5)
71 {1047,_T("IBM01047")},// IBM EBCDIC Latin 1/Open System
72 {1140,_T("IBM01140")},// IBM EBCDIC US-Canada (037 + Euro symbol); IBM EBCDIC (US-Canada-Euro)
73 {1141, _T("IBM01141")},// IBM EBCDIC Germany (20273 + Euro symbol); IBM EBCDIC (Germany-Euro)
74 {1142, _T("IBM01142")},// IBM EBCDIC Denmark-Norway (20277 + Euro symbol); IBM EBCDIC (Denmark-Norway-Euro)
75 {1143, _T("IBM01143")},// IBM EBCDIC Finland-Sweden (20278 + Euro symbol); IBM EBCDIC (Finland-Sweden-Euro)
76 {1144, _T("IBM01144")},// IBM EBCDIC Italy (20280 + Euro symbol); IBM EBCDIC (Italy-Euro)
77 {1145, _T("IBM01145")},// IBM EBCDIC Latin America-Spain (20284 + Euro symbol); IBM EBCDIC (Spain-Euro)
78 {1146, _T("IBM01146")},// IBM EBCDIC United Kingdom (20285 + Euro symbol); IBM EBCDIC (UK-Euro)
79 {1147, _T("IBM01147")},// IBM EBCDIC France (20297 + Euro symbol); IBM EBCDIC (France-Euro)
80 {1148, _T("IBM01148")},// IBM EBCDIC International (500 + Euro symbol); IBM EBCDIC (International-Euro)
81 {1149, _T("IBM01149")},// IBM EBCDIC Icelandic (20871 + Euro symbol); IBM EBCDIC (Icelandic-Euro)
82 {1200, _T("utf-16")},// Unicode UTF-16, little endian byte order (BMP of ISO 10646); available only to managed applications
83 {1201, _T("unicodeFFFE")},// Unicode UTF-16, big endian byte order; available only to managed applications
84 {1250, _T("windows-1250")},// ANSI Central European; Central European (Windows)
85 {1251, _T("windows-1251")},// ANSI Cyrillic; Cyrillic (Windows)
86 {1251, _T("cp1251")},
87 {1251, _T("cp-1251")},
88 {1251, _T("cp_1251")},
89 {1252, _T("windows-1252")},// ANSI Latin 1; Western European (Windows)
90 {1253, _T("windows-1253")},// ANSI Greek; Greek (Windows)
91 {1254, _T("windows-1254")},// ANSI Turkish; Turkish (Windows)
92 {1255, _T("windows-1255")},// ANSI Hebrew; Hebrew (Windows)
93 {1256, _T("windows-1256")},// ANSI Arabic; Arabic (Windows)
94 {1257, _T("windows-1257")},// ANSI Baltic; Baltic (Windows)
95 {1258, _T("windows-1258")},// ANSI/OEM Vietnamese; Vietnamese (Windows)
96 {1361, _T("Johab")},// Korean (Johab)
97 {10000,_T("macintosh")},// MAC Roman; Western European (Mac)
98 {10001, _T("x-mac-japanese")},// Japanese (Mac)
99 {10002, _T("x-mac-chinesetrad")},// MAC Traditional Chinese (Big5); Chinese Traditional (Mac)
100 {10003, _T("x-mac-korean")},// Korean (Mac)
101 {10004, _T("x-mac-arabic")},// Arabic (Mac)
102 {10005, _T("x-mac-hebrew")},// Hebrew (Mac)
103 {10006, _T("x-mac-greek")},// Greek (Mac)
104 {10007, _T("x-mac-cyrillic")},// Cyrillic (Mac)
105 {10008, _T("x-mac-chinesesimp")},// MAC Simplified Chinese (GB 2312); Chinese Simplified (Mac)
106 {10010, _T("x-mac-romanian")},// Romanian (Mac)
107 {10017, _T("x-mac-ukrainian")},// Ukrainian (Mac)
108 {10021, _T("x-mac-thai")},// Thai (Mac)
109 {10029, _T("x-mac-ce")},// MAC Latin 2; Central European (Mac)
110 {10079, _T("x-mac-icelandic")},// Icelandic (Mac)
111 {10081, _T("x-mac-turkish")},// Turkish (Mac)
112 {10082, _T("x-mac-croatian")},// Croatian (Mac)
113 {12000, _T("utf-32")},// Unicode UTF-32, little endian byte order; available only to managed applications
114 {12001, _T("utf-32BE")},// Unicode UTF-32, big endian byte order; available only to managed applications
115 {20000, _T("x-Chinese_CNS")},// CNS Taiwan; Chinese Traditional (CNS)
116 {20001, _T("x-cp20001")},// TCA Taiwan
117 {20002, _T("x_Chinese-Eten")},// Eten Taiwan; Chinese Traditional (Eten)
118 {20003, _T("x-cp20003")},// IBM5550 Taiwan
119 {20004, _T("x-cp20004")},// TeleText Taiwan
120 {20005, _T("x-cp20005")},// Wang Taiwan
121 {20105, _T("x-IA5")},// IA5 (IRV International Alphabet No. 5, 7-bit); Western European (IA5)
122 {20106, _T("x-IA5-German")},// IA5 German (7-bit)
123 {20107, _T("x-IA5-Swedish")},// IA5 Swedish (7-bit)
124 {20108, _T("x-IA5-Norwegian")},// IA5 Norwegian (7-bit)
125 {20127, _T("us-ascii")},// US-ASCII (7-bit)
126 {20261, _T("x-cp20261")},// T.61
127 {20269, _T("x-cp20269")},// ISO 6937 Non-Spacing Accent
128 {20273, _T("IBM273")},// IBM EBCDIC Germany
129 {20277, _T("IBM277")},//IBM EBCDIC Denmark-Norway
130 {20278, _T("IBM278")},// IBM EBCDIC Finland-Sweden
131 {20280, _T("IBM280")},// IBM EBCDIC Italy
132 {20284, _T("IBM284")},// IBM EBCDIC Latin America-Spain
133 {20285, _T("IBM285")},// IBM EBCDIC United Kingdom
134 {20290, _T("IBM290")},// IBM EBCDIC Japanese Katakana Extended
135 {20297, _T("IBM297")},// IBM EBCDIC France
136 {20420, _T("IBM420")},// IBM EBCDIC Arabic
137 {20423, _T("IBM423")},// IBM EBCDIC Greek
138 {20424, _T("IBM424")},// IBM EBCDIC Hebrew
139 {20833, _T("x-EBCDIC-KoreanExtended")},// IBM EBCDIC Korean Extended
140 {20838, _T("IBM-Thai")},// IBM EBCDIC Thai
141 {20866, _T("koi8-r")},// Russian (KOI8-R); Cyrillic (KOI8-R)
142 {20871, _T("IBM871")},// IBM EBCDIC Icelandic
143 {20880, _T("IBM880")},// IBM EBCDIC Cyrillic Russian
144 {20905, _T("IBM905")},// IBM EBCDIC Turkish
145 {20924, _T("IBM00924")},// IBM EBCDIC Latin 1/Open System (1047 + Euro symbol)
146 {20932, _T("EUC-JP")},// Japanese (JIS 0208-1990 and 0121-1990)
147 {20936, _T("x-cp20936")},// Simplified Chinese (GB2312); Chinese Simplified (GB2312-80)
148 {20949, _T("x-cp20949")},// Korean Wansung
149 {21025, _T("cp1025")},// IBM EBCDIC Cyrillic Serbian-Bulgarian
150 {21027, _T("21027")},// (deprecated)
151 {21866, _T("koi8-u")},// Ukrainian (KOI8-U); Cyrillic (KOI8-U)
152 {28591, _T("iso-8859-1")},// ISO 8859-1 Latin 1; Western European (ISO)
153 {28592, _T("iso-8859-2")},// ISO 8859-2 Central European; Central European (ISO)
154 {28593, _T("iso-8859-3")},// ISO 8859-3 Latin 3
155 {28594, _T("iso-8859-4")},// ISO 8859-4 Baltic
156 {28595, _T("iso-8859-5")},// ISO 8859-5 Cyrillic
157 {28596, _T("iso-8859-6")},// ISO 8859-6 Arabic
158 {28597, _T("iso-8859-7")},// ISO 8859-7 Greek
159 {28598, _T("iso-8859-8")},// ISO 8859-8 Hebrew; Hebrew (ISO-Visual)
160 {28599, _T("iso-8859-9")},// ISO 8859-9 Turkish
161 {28603, _T("iso-8859-13")},// ISO 8859-13 Estonian
162 {28605, _T("iso-8859-15")},// ISO 8859-15 Latin 9
163 {29001, _T("x-Europa")},// Europa 3
164 {38598, _T("iso-8859-8-i")},// ISO 8859-8 Hebrew; Hebrew (ISO-Logical)
165 {50220, _T("iso-2022-jp")},// ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS)
166 {50221, _T("csISO2022JP")},// ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS-Allow 1 byte Kana)
167 {50222, _T("iso-2022-jp")},// ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS-Allow 1 byte Kana - SO/SI)
168 {50225, _T("iso-2022-kr")},// ISO 2022 Korean
169 {50227, _T("x-cp50227")},// ISO 2022 Simplified Chinese; Chinese Simplified (ISO 2022)
170 {50229, _T("ISO")},// 2022 Traditional Chinese
171 {50930, _T("EBCDIC")},// Japanese (Katakana) Extended
172 {50931, _T("EBCDIC")},// US-Canada and Japanese
173 {50933, _T("EBCDIC")},// Korean Extended and Korean
174 {50935, _T("EBCDIC")},// Simplified Chinese Extended and Simplified Chinese
175 {50936, _T("EBCDIC")},// Simplified Chinese
176 {50937, _T("EBCDIC")},// US-Canada and Traditional Chinese
177 {50939, _T("EBCDIC")},// Japanese (Latin) Extended and Japanese
178 {51932, _T("euc-jp")},// EUC Japanese
179 {51936, _T("EUC-CN")},// EUC Simplified Chinese; Chinese Simplified (EUC)
180 {51949, _T("euc-kr")},// EUC Korean
181 {51950, _T("EUC")},// Traditional Chinese
182 {52936, _T("hz-gb-2312")},// HZ-GB2312 Simplified Chinese; Chinese Simplified (HZ)
183 {54936, _T("GB18030")},// Windows XP and later: GB18030 Simplified Chinese (4 byte); Chinese Simplified (GB18030)
184 {57002, _T("x-iscii-de")},// ISCII Devanagari
185 {57003, _T("x-iscii-be")},// ISCII Bengali
186 {57004, _T("x-iscii-ta")},// ISCII Tamil
187 {57005, _T("x-iscii-te")},// ISCII Telugu
188 {57006, _T("x-iscii-as")},// ISCII Assamese
189 {57007, _T("x-iscii-or")},// ISCII Oriya
190 {57008, _T("x-iscii-ka")},// ISCII Kannada
191 {57009, _T("x-iscii-ma")},// ISCII Malayalam
192 {57010, _T("x-iscii-gu")},// ISCII Gujarati
193 {57011, _T("x-iscii-pa")},// ISCII Punjabi
194 {65000, _T("utf-7")},// Unicode (UTF-7)
195 {65001, _T("utf-8")},// Unicode (UTF-8)
196 {0,NULL}
199 static CodeMap *p=map;
200 codename=codename.MakeLower();
201 while(p->m_CodeName != NULL)
203 CString str = p->m_CodeName;
204 str=str.MakeLower();
206 if( str == codename)
207 return p->m_Code;
208 p++;
211 return CP_UTF8;
214 CStringA CUnicodeUtils::GetUTF8(const CStringW& string)
216 return GetMulti(string,CP_UTF8);
219 CStringA CUnicodeUtils::GetMulti(const CStringW& string,int acp)
221 char * buf;
222 CStringA retVal;
223 int len = string.GetLength();
224 if (len==0)
225 return retVal;
226 buf = retVal.GetBuffer(len*4 + 1);
227 // SecureZeroMemory(buf, (string.GetLength()*4 + 1)*sizeof(char));
228 int lengthIncTerminator = WideCharToMultiByte(acp, 0, string, -1, buf, len*4, NULL, NULL);
229 retVal.ReleaseBuffer(lengthIncTerminator-1);
230 return retVal;
234 CStringA CUnicodeUtils::GetUTF8(const CStringA& string)
236 WCHAR * buf;
237 int len = string.GetLength();
238 if (len==0)
239 return CStringA();
240 buf = new WCHAR[len*4 + 1];
241 SecureZeroMemory(buf, (len*4 + 1)*sizeof(WCHAR));
242 MultiByteToWideChar(CP_ACP, 0, string, -1, buf, len*4);
243 CStringW temp = CStringW(buf);
244 delete [] buf;
245 return (CUnicodeUtils::GetUTF8(temp));
248 CString CUnicodeUtils::GetUnicode(const CStringA& string, int acp)
250 WCHAR * buf;
251 int len = string.GetLength();
252 if (len==0)
253 return CString();
254 buf = new WCHAR[len*4 + 1];
255 SecureZeroMemory(buf, (len*4 + 1)*sizeof(WCHAR));
256 MultiByteToWideChar(acp, 0, string, -1, buf, len*4);
257 CString ret = CString(buf);
258 delete [] buf;
259 return ret;
262 CStringA CUnicodeUtils::ConvertWCHARStringToUTF8(const CString& string)
264 CStringA sRet;
265 char * buf;
266 buf = new char[string.GetLength()+1];
267 if (buf)
269 int i=0;
270 for ( ; i<string.GetLength(); ++i)
272 buf[i] = (char)string.GetAt(i);
274 buf[i] = 0;
275 sRet = CStringA(buf);
276 delete [] buf;
278 return sRet;
281 #endif //_MFC_VER
283 #ifdef UNICODE
284 std::string CUnicodeUtils::StdGetUTF8(const wide_string& wide)
286 int len = (int)wide.size();
287 if (len==0)
288 return std::string();
289 int size = len*4;
290 char * narrow = new char[size];
291 int ret = WideCharToMultiByte(CP_UTF8, 0, wide.c_str(), len, narrow, size-1, NULL, NULL);
292 narrow[ret] = 0;
293 std::string sRet = std::string(narrow);
294 delete [] narrow;
295 return sRet;
298 wide_string CUnicodeUtils::StdGetUnicode(const std::string& multibyte)
300 int len = (int)multibyte.size();
301 if (len==0)
302 return wide_string();
303 int size = len*4;
304 wchar_t * wide = new wchar_t[size];
305 int ret = MultiByteToWideChar(CP_UTF8, 0, multibyte.c_str(), len, wide, size - 1);
306 wide[ret] = 0;
307 wide_string sRet = wide_string(wide);
308 delete [] wide;
309 return sRet;
311 #endif
313 std::string WideToMultibyte(const wide_string& wide)
315 char * narrow = new char[wide.length()*3+2];
316 BOOL defaultCharUsed;
317 int ret = (int)WideCharToMultiByte(CP_ACP, 0, wide.c_str(), (int)wide.size(), narrow, (int)wide.length()*3 - 1, ".", &defaultCharUsed);
318 narrow[ret] = 0;
319 std::string str = narrow;
320 delete[] narrow;
321 return str;
324 std::string WideToUTF8(const wide_string& wide)
326 char * narrow = new char[wide.length()*3+2];
327 int ret = (int)WideCharToMultiByte(CP_UTF8, 0, wide.c_str(), (int)wide.size(), narrow, (int)wide.length()*3 - 1, NULL, NULL);
328 narrow[ret] = 0;
329 std::string str = narrow;
330 delete[] narrow;
331 return str;
334 wide_string MultibyteToWide(const std::string& multibyte)
336 size_t length = multibyte.length();
337 if (length == 0)
338 return wide_string();
340 wchar_t * wide = new wchar_t[multibyte.length()*2+2];
341 if (wide == NULL)
342 return wide_string();
343 int ret = (int)MultiByteToWideChar(CP_ACP, 0, multibyte.c_str(), (int)multibyte.size(), wide, (int)length*2 - 1);
344 wide[ret] = 0;
345 wide_string str = wide;
346 delete[] wide;
347 return str;
350 wide_string UTF8ToWide(const std::string& multibyte)
352 size_t length = multibyte.length();
353 if (length == 0)
354 return wide_string();
356 wchar_t * wide = new wchar_t[length*2+2];
357 if (wide == NULL)
358 return wide_string();
359 int ret = (int)MultiByteToWideChar(CP_UTF8, 0, multibyte.c_str(), (int)multibyte.size(), wide, (int)length*2 - 1);
360 wide[ret] = 0;
361 wide_string str = wide;
362 delete[] wide;
363 return str;
365 #ifdef UNICODE
366 stdstring UTF8ToString(const std::string& string) {return UTF8ToWide(string);}
367 std::string StringToUTF8(const stdstring& string) {return WideToUTF8(string);}
368 #else
369 stdstring UTF8ToString(const std::string& string) {return WideToMultibyte(UTF8ToWide(string));}
370 std::string StringToUTF8(const stdstring& string) {return WideToUTF8(MultibyteToWide(string));}
371 #endif
374 #pragma warning(push)
375 #pragma warning(disable: 4200)
376 struct STRINGRESOURCEIMAGE
378 WORD nLength;
379 WCHAR achString[];
381 #pragma warning(pop) // C4200
383 int LoadStringEx(HINSTANCE hInstance, UINT uID, LPTSTR lpBuffer, int nBufferMax, WORD wLanguage)
385 const STRINGRESOURCEIMAGE* pImage;
386 const STRINGRESOURCEIMAGE* pImageEnd;
387 ULONG nResourceSize;
388 HGLOBAL hGlobal;
389 UINT iIndex;
390 #ifndef UNICODE
391 BOOL defaultCharUsed;
392 #endif
393 int ret;
395 if (lpBuffer == NULL)
396 return 0;
397 lpBuffer[0] = 0;
398 HRSRC hResource = FindResourceEx(hInstance, RT_STRING, MAKEINTRESOURCE(((uID>>4)+1)), wLanguage);
399 if (!hResource)
401 //try the default language before giving up!
402 hResource = FindResource(hInstance, MAKEINTRESOURCE(((uID>>4)+1)), RT_STRING);
403 if (!hResource)
404 return 0;
406 hGlobal = LoadResource(hInstance, hResource);
407 if (!hGlobal)
408 return 0;
409 pImage = (const STRINGRESOURCEIMAGE*)::LockResource(hGlobal);
410 if(!pImage)
411 return 0;
413 nResourceSize = ::SizeofResource(hInstance, hResource);
414 pImageEnd = (const STRINGRESOURCEIMAGE*)(LPBYTE(pImage)+nResourceSize);
415 iIndex = uID&0x000f;
417 while ((iIndex > 0) && (pImage < pImageEnd))
419 pImage = (const STRINGRESOURCEIMAGE*)(LPBYTE(pImage)+(sizeof(STRINGRESOURCEIMAGE)+(pImage->nLength*sizeof(WCHAR))));
420 iIndex--;
422 if (pImage >= pImageEnd)
423 return 0;
424 if (pImage->nLength == 0)
425 return 0;
426 #ifdef UNICODE
427 ret = pImage->nLength;
428 if (ret > nBufferMax)
429 ret = nBufferMax;
430 wcsncpy_s((wchar_t *)lpBuffer, nBufferMax, pImage->achString, ret);
431 lpBuffer[ret] = 0;
432 #else
433 ret = WideCharToMultiByte(CP_ACP, 0, pImage->achString, pImage->nLength, (LPSTR)lpBuffer, nBufferMax-1, ".", &defaultCharUsed);
434 lpBuffer[ret] = 0;
435 #endif
436 return ret;