1 /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
2 /*
3 * This file is part of the LibreOffice project.
4 *
5 * This Source Code Form is subject to the terms of the Mozilla Public
6 * License, v. 2.0. If a copy of the MPL was not distributed with this
7 * file, You can obtain one at http://mozilla.org/MPL/2.0/.
8 *
9 * This file incorporates work covered by the following license notice:
10 *
11 * Licensed to the Apache Software Foundation (ASF) under one or more
12 * contributor license agreements. See the NOTICE file distributed
13 * with this work for additional information regarding copyright
14 * ownership. The ASF licenses this file to you under the Apache
15 * License, Version 2.0 (the "License"); you may not use this file
16 * except in compliance with the License. You may obtain a copy of
17 * the License at http://www.apache.org/licenses/LICENSE-2.0 .
18 */
19
20 #include <sal/config.h>
21
22 #include <cstring>
23
24 #include <rtl/tencinfo.h>
25
26 #include "gettextencodingdata.hxx"
27 #include "tenchelp.hxx"
28 #include <memory>
29
rtl_isOctetTextEncoding(rtl_TextEncoding nEncoding)30 sal_Bool SAL_CALL rtl_isOctetTextEncoding(rtl_TextEncoding nEncoding)
31 {
32 return
33 nEncoding > RTL_TEXTENCODING_DONTKNOW
34 && nEncoding != 9 // RTL_TEXTENCODING_SYSTEM
35 && nEncoding <= RTL_TEXTENCODING_MAZOVIA; // always update this!
36 }
37
38 /* ======================================================================= */
39
Impl_toAsciiLower(const char * pName,char * pBuf)40 static void Impl_toAsciiLower( const char* pName, char* pBuf )
41 {
42 while ( *pName )
43 {
44 /* A-Z */
45 if ( (*pName >= 0x41) && (*pName <= 0x5A) )
46 *pBuf = (*pName)+0x20; /* toAsciiLower */
47 else
48 *pBuf = *pName;
49
50 pBuf++;
51 pName++;
52 }
53
54 *pBuf = '\0';
55 }
56
57 /* ----------------------------------------------------------------------- */
58
Impl_toAsciiLowerAndRemoveNonAlphanumeric(const char * pName,char * pBuf)59 static void Impl_toAsciiLowerAndRemoveNonAlphanumeric( const char* pName, char* pBuf )
60 {
61 while ( *pName )
62 {
63 /* A-Z */
64 if ( (*pName >= 0x41) && (*pName <= 0x5A) )
65 {
66 *pBuf = (*pName)+0x20; /* toAsciiLower */
67 pBuf++;
68 }
69 /* a-z, 0-9 */
70 else if ( ((*pName >= 0x61) && (*pName <= 0x7A)) ||
71 ((*pName >= 0x30) && (*pName <= 0x39)) )
72 {
73 *pBuf = *pName;
74 pBuf++;
75 }
76
77 pName++;
78 }
79
80 *pBuf = '\0';
81 }
82
83 /* ----------------------------------------------------------------------- */
84
85 /* pMatchStr must match with all characters in pCompStr */
Impl_matchString(const char * pCompStr,const char * pMatchStr)86 static bool Impl_matchString( const char* pCompStr, const char* pMatchStr )
87 {
88 /* We test only for end in MatchStr, because the last 0 character from */
89 /* pCompStr is unequal a character in MatchStr, so the loop terminates */
90 while ( *pMatchStr )
91 {
92 if ( *pCompStr != *pMatchStr )
93 return false;
94
95 pCompStr++;
96 pMatchStr++;
97 }
98
99 return true;
100 }
101
102 /* ======================================================================= */
103
104 namespace {
105
106 struct ImplStrCharsetDef
107 {
108 const char* mpCharsetStr;
109 rtl_TextEncoding meTextEncoding;
110 };
111
112 struct ImplStrFirstPartCharsetDef
113 {
114 const char* mpCharsetStr;
115 const ImplStrCharsetDef* mpSecondPartTab;
116 };
117
118 }
119
120 /* ======================================================================= */
121
rtl_getTextEncodingInfo(rtl_TextEncoding eTextEncoding,rtl_TextEncodingInfo * pEncInfo)122 sal_Bool SAL_CALL rtl_getTextEncodingInfo( rtl_TextEncoding eTextEncoding, rtl_TextEncodingInfo* pEncInfo )
123 {
124 const ImplTextEncodingData* pData;
125
126 pData = Impl_getTextEncodingData( eTextEncoding );
127 if ( !pData )
128 {
129 /* HACK: For not implemented encoding, because not all
130 calls handle the errors */
131 if ( pEncInfo->StructSize < 5 )
132 return false;
133 pEncInfo->MinimumCharSize = 1;
134
135 if ( pEncInfo->StructSize < 6 )
136 return true;
137 pEncInfo->MaximumCharSize = 1;
138
139 if ( pEncInfo->StructSize < 7 )
140 return true;
141 pEncInfo->AverageCharSize = 1;
142
143 if ( pEncInfo->StructSize < 12 )
144 return true;
145 pEncInfo->Flags = 0;
146
147 return false;
148 }
149
150 if ( pEncInfo->StructSize < 5 )
151 return false;
152 pEncInfo->MinimumCharSize = pData->mnMinCharSize;
153
154 if ( pEncInfo->StructSize < 6 )
155 return true;
156 pEncInfo->MaximumCharSize = pData->mnMaxCharSize;
157
158 if ( pEncInfo->StructSize < 7 )
159 return true;
160 pEncInfo->AverageCharSize = pData->mnAveCharSize;
161
162 if ( pEncInfo->StructSize < 12 )
163 return true;
164 pEncInfo->Flags = pData->mnInfoFlags;
165
166 return true;
167 }
168
169 /* ======================================================================= */
170
rtl_getTextEncodingFromWindowsCharset(sal_uInt8 nWinCharset)171 rtl_TextEncoding SAL_CALL rtl_getTextEncodingFromWindowsCharset( sal_uInt8 nWinCharset )
172 {
173 rtl_TextEncoding eTextEncoding;
174
175 switch ( nWinCharset )
176 {
177 case 0: eTextEncoding = RTL_TEXTENCODING_MS_1252; break; /* ANSI_CHARSET */
178 case 2: eTextEncoding = RTL_TEXTENCODING_SYMBOL; break; /* SYMBOL_CHARSET */
179 case 77: eTextEncoding = RTL_TEXTENCODING_APPLE_ROMAN; break;/* MAC_CHARSET */
180 case 128: eTextEncoding = RTL_TEXTENCODING_MS_932; break; /* SHIFTJIS_CHARSET */
181 case 129: eTextEncoding = RTL_TEXTENCODING_MS_949; break; /* HANGEUL_CHARSET */
182 case 130: eTextEncoding = RTL_TEXTENCODING_MS_1361; break; /* JOHAB_CHARSET */
183 case 134: eTextEncoding = RTL_TEXTENCODING_MS_936; break; /* GB2312_CHARSET */
184 case 136: eTextEncoding = RTL_TEXTENCODING_MS_950; break; /* CHINESEBIG5_CHARSET */
185 case 161: eTextEncoding = RTL_TEXTENCODING_MS_1253; break; /* GREEK_CHARSET */
186 case 162: eTextEncoding = RTL_TEXTENCODING_MS_1254; break; /* TURKISH_CHARSET */
187 case 163: eTextEncoding = RTL_TEXTENCODING_MS_1258; break; /* VIETNAMESE_CHARSET !!! */
188 case 177: eTextEncoding = RTL_TEXTENCODING_MS_1255; break; /* HEBREW_CHARSET */
189 case 178: eTextEncoding = RTL_TEXTENCODING_MS_1256; break; /* ARABIC_CHARSET */
190 case 186: eTextEncoding = RTL_TEXTENCODING_MS_1257; break; /* BALTIC_CHARSET */
191 case 204: eTextEncoding = RTL_TEXTENCODING_MS_1251; break; /* RUSSIAN_CHARSET */
192 case 222: eTextEncoding = RTL_TEXTENCODING_MS_874; break; /* THAI_CHARSET */
193 case 238: eTextEncoding = RTL_TEXTENCODING_MS_1250; break; /* EASTEUROPE_CHARSET */
194 case 255: eTextEncoding = RTL_TEXTENCODING_IBM_850; break; /* OEM_CHARSET */
195 default: eTextEncoding = RTL_TEXTENCODING_DONTKNOW; break;
196 }
197
198 return eTextEncoding;
199 }
200
201 /* ----------------------------------------------------------------------- */
202
rtl_getTextEncodingFromUnixCharset(const char * pUnixCharset)203 rtl_TextEncoding SAL_CALL rtl_getTextEncodingFromUnixCharset( const char* pUnixCharset )
204 {
205 /* See <ftp://ftp.x.org/pub/DOCS/registry>, section 14 ("Font Charset
206 * (Registry and Encoding) Names").
207 */
208
209 /* All Identifiers in the tables are lower case The function search */
210 /* for the first matching string in the tables. */
211 /* Sort order: unique (first 14, then 1), important */
212
213 static ImplStrCharsetDef const aUnixCharsetISOTab[] =
214 {
215 { "15", RTL_TEXTENCODING_ISO_8859_15 },
216 { "14", RTL_TEXTENCODING_ISO_8859_14 },
217 { "13", RTL_TEXTENCODING_ISO_8859_13 },
218 { "11", RTL_TEXTENCODING_TIS_620 },
219 { "10", RTL_TEXTENCODING_ISO_8859_10 },
220 { "1", RTL_TEXTENCODING_ISO_8859_1 },
221 { "2", RTL_TEXTENCODING_ISO_8859_2 },
222 { "3", RTL_TEXTENCODING_ISO_8859_3 },
223 { "4", RTL_TEXTENCODING_ISO_8859_4 },
224 { "5", RTL_TEXTENCODING_ISO_8859_5 },
225 { "6", RTL_TEXTENCODING_ISO_8859_6 },
226 { "7", RTL_TEXTENCODING_ISO_8859_7 },
227 { "8", RTL_TEXTENCODING_ISO_8859_8 },
228 { "9", RTL_TEXTENCODING_ISO_8859_9 },
229 { nullptr, RTL_TEXTENCODING_DONTKNOW }
230 };
231
232 static ImplStrCharsetDef const aUnixCharsetADOBETab[] =
233 {
234 { "fontspecific", RTL_TEXTENCODING_SYMBOL },
235 { nullptr, RTL_TEXTENCODING_DONTKNOW }
236 };
237
238 static ImplStrCharsetDef const aUnixCharsetMSTab[] =
239 {
240 { "1252", RTL_TEXTENCODING_MS_1252 },
241 { "1250", RTL_TEXTENCODING_MS_1250 },
242 { "1251", RTL_TEXTENCODING_MS_1251 },
243 { "1253", RTL_TEXTENCODING_MS_1253 },
244 { "1254", RTL_TEXTENCODING_MS_1254 },
245 { "1255", RTL_TEXTENCODING_MS_1255 },
246 { "1256", RTL_TEXTENCODING_MS_1256 },
247 { "1257", RTL_TEXTENCODING_MS_1257 },
248 { "1258", RTL_TEXTENCODING_MS_1258 },
249 { "932", RTL_TEXTENCODING_MS_932 },
250 { "936", RTL_TEXTENCODING_MS_936 },
251 { "949", RTL_TEXTENCODING_MS_949 },
252 { "950", RTL_TEXTENCODING_MS_950 },
253 { "1361", RTL_TEXTENCODING_MS_1361 },
254 { "cp1252", RTL_TEXTENCODING_MS_1252 },
255 { "cp1250", RTL_TEXTENCODING_MS_1250 },
256 { "cp1251", RTL_TEXTENCODING_MS_1251 },
257 { "cp1253", RTL_TEXTENCODING_MS_1253 },
258 { "cp1254", RTL_TEXTENCODING_MS_1254 },
259 { "cp1255", RTL_TEXTENCODING_MS_1255 },
260 { "cp1256", RTL_TEXTENCODING_MS_1256 },
261 { "cp1257", RTL_TEXTENCODING_MS_1257 },
262 { "cp1258", RTL_TEXTENCODING_MS_1258 },
263 { "cp932", RTL_TEXTENCODING_MS_932 },
264 { "cp936", RTL_TEXTENCODING_MS_936 },
265 { "cp949", RTL_TEXTENCODING_MS_949 },
266 { "cp950", RTL_TEXTENCODING_MS_950 },
267 { "cp1361", RTL_TEXTENCODING_MS_1361 },
268 { nullptr, RTL_TEXTENCODING_DONTKNOW }
269 };
270
271 static ImplStrCharsetDef const aUnixCharsetIBMTab[] =
272 {
273 { "437", RTL_TEXTENCODING_IBM_437 },
274 { "850", RTL_TEXTENCODING_IBM_850 },
275 { "860", RTL_TEXTENCODING_IBM_860 },
276 { "861", RTL_TEXTENCODING_IBM_861 },
277 { "863", RTL_TEXTENCODING_IBM_863 },
278 { "865", RTL_TEXTENCODING_IBM_865 },
279 { "737", RTL_TEXTENCODING_IBM_737 },
280 { "775", RTL_TEXTENCODING_IBM_775 },
281 { "852", RTL_TEXTENCODING_IBM_852 },
282 { "855", RTL_TEXTENCODING_IBM_855 },
283 { "857", RTL_TEXTENCODING_IBM_857 },
284 { "862", RTL_TEXTENCODING_IBM_862 },
285 { "864", RTL_TEXTENCODING_IBM_864 },
286 { "866", RTL_TEXTENCODING_IBM_866 },
287 { "869", RTL_TEXTENCODING_IBM_869 },
288 { "874", RTL_TEXTENCODING_MS_874 },
289 { "1004", RTL_TEXTENCODING_MS_1252 },
290 { "65400", RTL_TEXTENCODING_SYMBOL },
291 { nullptr, RTL_TEXTENCODING_DONTKNOW }
292 };
293
294 static ImplStrCharsetDef const aUnixCharsetKOI8Tab[] =
295 {
296 { "r", RTL_TEXTENCODING_KOI8_R },
297 { "u", RTL_TEXTENCODING_KOI8_U },
298 { nullptr, RTL_TEXTENCODING_DONTKNOW }
299 };
300
301 static ImplStrCharsetDef const aUnixCharsetJISX0208Tab[] =
302 {
303 { nullptr, RTL_TEXTENCODING_JIS_X_0208 }
304 };
305
306 static ImplStrCharsetDef const aUnixCharsetJISX0201Tab[] =
307 {
308 { nullptr, RTL_TEXTENCODING_JIS_X_0201 }
309 };
310
311 static ImplStrCharsetDef const aUnixCharsetJISX0212Tab[] =
312 {
313 { nullptr, RTL_TEXTENCODING_JIS_X_0212 }
314 };
315
316 static ImplStrCharsetDef const aUnixCharsetGBTab[] =
317 {
318 { nullptr, RTL_TEXTENCODING_GB_2312 }
319 };
320
321 static ImplStrCharsetDef const aUnixCharsetGBKTab[] =
322 {
323 { nullptr, RTL_TEXTENCODING_GBK }
324 };
325
326 static ImplStrCharsetDef const aUnixCharsetBIG5Tab[] =
327 {
328 { nullptr, RTL_TEXTENCODING_BIG5 }
329 };
330
331 static ImplStrCharsetDef const aUnixCharsetKSC56011987Tab[] =
332 {
333 { nullptr, RTL_TEXTENCODING_EUC_KR }
334 };
335
336 static ImplStrCharsetDef const aUnixCharsetKSC56011992Tab[] =
337 {
338 { nullptr, RTL_TEXTENCODING_MS_1361 }
339 };
340
341 static ImplStrCharsetDef const aUnixCharsetISO10646Tab[] =
342 {
343 { nullptr, RTL_TEXTENCODING_UNICODE }
344 };
345
346 static ImplStrCharsetDef const aUnixCharsetUNICODETab[] =
347 {
348 /* Currently every Unicode Encoding is for us Unicode */
349 /* { "fontspecific", RTL_TEXTENCODING_UNICODE }, */
350 { nullptr, RTL_TEXTENCODING_UNICODE }
351 };
352
353 static ImplStrCharsetDef const aUnixCharsetSymbolTab[] =
354 {
355 { nullptr, RTL_TEXTENCODING_SYMBOL }
356 };
357
358 /* See <http://cvs.freedesktop.org/xorg/xc/fonts/encodings/iso8859-11.enc?
359 rev=1.1.1.1>: */
360 static ImplStrCharsetDef const aUnixCharsetTIS620Tab[] =
361 {
362 { "0", RTL_TEXTENCODING_TIS_620 },
363 { "2529", RTL_TEXTENCODING_TIS_620 },
364 { "2533", RTL_TEXTENCODING_TIS_620 },
365 { nullptr, RTL_TEXTENCODING_DONTKNOW }
366 };
367 static ImplStrCharsetDef const aUnixCharsetTIS6202529Tab[] =
368 {
369 { "1", RTL_TEXTENCODING_TIS_620 },
370 { nullptr, RTL_TEXTENCODING_DONTKNOW }
371 };
372 static ImplStrCharsetDef const aUnixCharsetTIS6202533Tab[] =
373 {
374 { "0", RTL_TEXTENCODING_TIS_620 },
375 { "1", RTL_TEXTENCODING_TIS_620 },
376 { nullptr, RTL_TEXTENCODING_DONTKNOW }
377 };
378
379 static ImplStrFirstPartCharsetDef const aUnixCharsetFirstPartTab[] =
380 {
381 { "iso8859", aUnixCharsetISOTab },
382 { "adobe", aUnixCharsetADOBETab },
383 { "ansi", aUnixCharsetMSTab },
384 { "microsoft", aUnixCharsetMSTab },
385 { "ibm", aUnixCharsetIBMTab },
386 { "koi8", aUnixCharsetKOI8Tab },
387 { "jisx0208", aUnixCharsetJISX0208Tab },
388 { "jisx0208.1983", aUnixCharsetJISX0208Tab },
389 { "jisx0201", aUnixCharsetJISX0201Tab },
390 { "jisx0201.1976", aUnixCharsetJISX0201Tab },
391 { "jisx0212", aUnixCharsetJISX0212Tab },
392 { "jisx0212.1990", aUnixCharsetJISX0212Tab },
393 { "gb2312", aUnixCharsetGBTab },
394 { "gbk", aUnixCharsetGBKTab },
395 { "big5", aUnixCharsetBIG5Tab },
396 { "iso10646", aUnixCharsetISO10646Tab },
397 /* { "unicode", aUnixCharsetUNICODETab }, */ /* fonts contain only default chars */
398 { "sunolcursor", aUnixCharsetSymbolTab },
399 { "sunolglyph", aUnixCharsetSymbolTab },
400 { "iso10646", aUnixCharsetUNICODETab },
401 { "ksc5601.1987", aUnixCharsetKSC56011987Tab },
402 { "ksc5601.1992", aUnixCharsetKSC56011992Tab },
403 { "tis620.2529", aUnixCharsetTIS6202529Tab },
404 { "tis620.2533", aUnixCharsetTIS6202533Tab },
405 { "tis620", aUnixCharsetTIS620Tab },
406 /* { "sunudcja.1997", }, */
407 /* { "sunudcko.1997", }, */
408 /* { "sunudczh.1997", }, */
409 /* { "sunudczhtw.1997", }, */
410 { nullptr, nullptr }
411 };
412
413 rtl_TextEncoding eEncoding = RTL_TEXTENCODING_DONTKNOW;
414 char* pTempBuf;
415 sal_uInt32 nBufLen = strlen( pUnixCharset )+1;
416 const char* pFirstPart;
417 const char* pSecondPart;
418
419 /* Alloc Buffer and map to lower case */
420 std::unique_ptr<char[]> pBuf(new char[nBufLen]);
421 Impl_toAsciiLower( pUnixCharset, pBuf.get() );
422
423 /* Search FirstPart */
424 pFirstPart = pBuf.get();
425 pSecondPart = nullptr;
426 pTempBuf = pBuf.get();
427 while ( *pTempBuf )
428 {
429 if ( *pTempBuf == '-' )
430 {
431 *pTempBuf = '\0';
432 pSecondPart = pTempBuf+1;
433 break;
434 }
435
436 pTempBuf++;
437 }
438
439 /* found part separator */
440 if ( pSecondPart )
441 {
442 /* Search for the part tab */
443 const ImplStrFirstPartCharsetDef* pFirstPartData = aUnixCharsetFirstPartTab;
444 while ( pFirstPartData->mpCharsetStr )
445 {
446 if ( Impl_matchString( pFirstPart, pFirstPartData->mpCharsetStr ) )
447 {
448 /* Search for the charset in the second part tab */
449 const ImplStrCharsetDef* pData = pFirstPartData->mpSecondPartTab;
450 while ( pData->mpCharsetStr )
451 {
452 if ( Impl_matchString( pSecondPart, pData->mpCharsetStr ) )
453 {
454 break;
455 }
456
457 pData++;
458 }
459
460 /* use default encoding for first part */
461 eEncoding = pData->meTextEncoding;
462 break;
463 }
464
465 pFirstPartData++;
466 }
467 }
468
469 return eEncoding;
470 }
471
472 /* ----------------------------------------------------------------------- */
473
rtl_getTextEncodingFromMimeCharset(const char * pMimeCharset)474 rtl_TextEncoding SAL_CALL rtl_getTextEncodingFromMimeCharset( const char* pMimeCharset )
475 {
476 /* All Identifiers are in lower case and contain only alphanumeric */
477 /* characters. The function search for the first equal string in */
478 /* the table. In this table are only the most used mime types. */
479 /* Sort order: important */
480 static ImplStrCharsetDef const aVIPMimeCharsetTab[] =
481 {
482 { "usascii", RTL_TEXTENCODING_ASCII_US },
483 { "utf8", RTL_TEXTENCODING_UTF8 },
484 { "utf7", RTL_TEXTENCODING_UTF7 },
485 { "iso88591", RTL_TEXTENCODING_ISO_8859_1 },
486 { "iso88592", RTL_TEXTENCODING_ISO_8859_2 },
487 { "iso88593", RTL_TEXTENCODING_ISO_8859_3 },
488 { "iso88594", RTL_TEXTENCODING_ISO_8859_4 },
489 { "iso88595", RTL_TEXTENCODING_ISO_8859_5 },
490 { "iso88596", RTL_TEXTENCODING_ISO_8859_6 },
491 { "iso88597", RTL_TEXTENCODING_ISO_8859_7 },
492 { "iso88598", RTL_TEXTENCODING_ISO_8859_8 },
493 { "iso88599", RTL_TEXTENCODING_ISO_8859_9 },
494 { "iso885910", RTL_TEXTENCODING_ISO_8859_10 },
495 { "iso885913", RTL_TEXTENCODING_ISO_8859_13 },
496 { "iso885914", RTL_TEXTENCODING_ISO_8859_14 },
497 { "iso885915", RTL_TEXTENCODING_ISO_8859_15 },
498 { "iso2022jp", RTL_TEXTENCODING_ISO_2022_JP },
499 { "iso2022jp2", RTL_TEXTENCODING_ISO_2022_JP },
500 { "iso2022cn", RTL_TEXTENCODING_ISO_2022_CN },
501 { "iso2022cnext", RTL_TEXTENCODING_ISO_2022_CN },
502 { "iso2022kr", RTL_TEXTENCODING_ISO_2022_KR },
503 { "eucjp", RTL_TEXTENCODING_EUC_JP },
504 { "shiftjis", RTL_TEXTENCODING_SHIFT_JIS },
505 { "mskanji", RTL_TEXTENCODING_MS_932 },
506 { "gb2312", RTL_TEXTENCODING_GB_2312 },
507 { "cngb", RTL_TEXTENCODING_GB_2312 },
508 { "big5", RTL_TEXTENCODING_BIG5 },
509 { "cnbig5", RTL_TEXTENCODING_BIG5 },
510 { "cngb12345", RTL_TEXTENCODING_GBT_12345 },
511 { "euckr", RTL_TEXTENCODING_EUC_KR },
512 { "koi8r", RTL_TEXTENCODING_KOI8_R },
513 { "windows1252", RTL_TEXTENCODING_MS_1252 },
514 { "windows1250", RTL_TEXTENCODING_MS_1250 },
515 { "windows1251", RTL_TEXTENCODING_MS_1251 },
516 { "windows1253", RTL_TEXTENCODING_MS_1253 },
517 { "windows1254", RTL_TEXTENCODING_MS_1254 },
518 { "windows1255", RTL_TEXTENCODING_MS_1255 },
519 { "windows1256", RTL_TEXTENCODING_MS_1256 },
520 { "windows1257", RTL_TEXTENCODING_MS_1257 },
521 { "windows1258", RTL_TEXTENCODING_MS_1258 },
522 { nullptr, RTL_TEXTENCODING_DONTKNOW }
523 };
524
525 /* All Identifiers are in lower case and contain only alphanumeric */
526 /* characters. The function search for the first matching string in */
527 /* the table. */
528 /* Sort order: unique (first iso885914, then iso88591), important */
529 static ImplStrCharsetDef const aMimeCharsetTab[] =
530 {
531 { "unicode11utf7", RTL_TEXTENCODING_UTF7 },
532 { "caunicode11utf7", RTL_TEXTENCODING_UTF7 },
533 { "iso88591windows30", RTL_TEXTENCODING_ISO_8859_1 },
534 { "iso88591win", RTL_TEXTENCODING_MS_1252 },
535 { "iso88592win", RTL_TEXTENCODING_MS_1250 },
536 { "iso88599win", RTL_TEXTENCODING_MS_1254 },
537 { "iso885915", RTL_TEXTENCODING_ISO_8859_15 },
538 { "iso885914", RTL_TEXTENCODING_ISO_8859_14 },
539 { "iso885913", RTL_TEXTENCODING_ISO_8859_13 },
540 { "iso885911", RTL_TEXTENCODING_TIS_620 },
541 /* This is no official MIME character set name, but it might be in
542 use in Thailand. */
543 { "iso885910", RTL_TEXTENCODING_ISO_8859_10 },
544 { "iso88591", RTL_TEXTENCODING_ISO_8859_1 },
545 { "iso88592", RTL_TEXTENCODING_ISO_8859_2 },
546 { "iso88593", RTL_TEXTENCODING_ISO_8859_3 },
547 { "iso88594", RTL_TEXTENCODING_ISO_8859_4 },
548 { "iso88595", RTL_TEXTENCODING_ISO_8859_5 },
549 { "iso88596", RTL_TEXTENCODING_ISO_8859_6 },
550 { "iso88597", RTL_TEXTENCODING_ISO_8859_7 },
551 { "iso88598", RTL_TEXTENCODING_ISO_8859_8 },
552 { "iso88599", RTL_TEXTENCODING_ISO_8859_9 },
553 { "isoir100", RTL_TEXTENCODING_ISO_8859_1 },
554 { "latin1", RTL_TEXTENCODING_ISO_8859_1 },
555 { "l1", RTL_TEXTENCODING_ISO_8859_1 },
556 { "cp819", RTL_TEXTENCODING_ISO_8859_1 },
557 { "ibm819", RTL_TEXTENCODING_ISO_8859_1 },
558 { "csisolatin1", RTL_TEXTENCODING_ISO_8859_1 },
559 { "isoir101", RTL_TEXTENCODING_ISO_8859_2 },
560 { "latin2", RTL_TEXTENCODING_ISO_8859_2 },
561 { "l2", RTL_TEXTENCODING_ISO_8859_2 },
562 { "csisolatin2", RTL_TEXTENCODING_ISO_8859_2 },
563 { "isoir109", RTL_TEXTENCODING_ISO_8859_3 },
564 { "latin3", RTL_TEXTENCODING_ISO_8859_3 },
565 { "l3", RTL_TEXTENCODING_ISO_8859_3 },
566 { "csisolatin3", RTL_TEXTENCODING_ISO_8859_3 },
567 { "isoir110", RTL_TEXTENCODING_ISO_8859_4 },
568 { "latin4", RTL_TEXTENCODING_ISO_8859_4 },
569 { "l4", RTL_TEXTENCODING_ISO_8859_4 },
570 { "csisolatin4", RTL_TEXTENCODING_ISO_8859_4 },
571 { "isoir144", RTL_TEXTENCODING_ISO_8859_5 },
572 { "cyrillicasian", RTL_TEXTENCODING_PT154 },
573 { "cyrillic", RTL_TEXTENCODING_ISO_8859_5 },
574 { "csisolatincyrillic", RTL_TEXTENCODING_ISO_8859_5 },
575 { "isoir127", RTL_TEXTENCODING_ISO_8859_6 },
576 { "arabic", RTL_TEXTENCODING_ISO_8859_6 },
577 { "csisolatinarabic", RTL_TEXTENCODING_ISO_8859_6 },
578 { "ecma114", RTL_TEXTENCODING_ISO_8859_6 },
579 { "asmo708", RTL_TEXTENCODING_ISO_8859_6 },
580 { "isoir126", RTL_TEXTENCODING_ISO_8859_7 },
581 { "greek", RTL_TEXTENCODING_ISO_8859_7 },
582 { "csisolatingreek", RTL_TEXTENCODING_ISO_8859_7 },
583 { "elot928", RTL_TEXTENCODING_ISO_8859_7 },
584 { "ecma118", RTL_TEXTENCODING_ISO_8859_7 },
585 { "isoir138", RTL_TEXTENCODING_ISO_8859_8 },
586 { "hebrew", RTL_TEXTENCODING_ISO_8859_8 },
587 { "csisolatinhebrew", RTL_TEXTENCODING_ISO_8859_8 },
588 { "isoir148", RTL_TEXTENCODING_ISO_8859_9 },
589 { "latin5", RTL_TEXTENCODING_ISO_8859_9 },
590 { "l5", RTL_TEXTENCODING_ISO_8859_9 },
591 { "csisolatin5", RTL_TEXTENCODING_ISO_8859_9 },
592 { "cswindows30latin1", RTL_TEXTENCODING_ISO_8859_1 },
593 { "cswindows30latin1", RTL_TEXTENCODING_ISO_8859_1 },
594 { "cswindows31latin1", RTL_TEXTENCODING_MS_1252 },
595 { "cswindows31latin2", RTL_TEXTENCODING_MS_1250 },
596 { "cswindows31latin5", RTL_TEXTENCODING_MS_1254 },
597 { "iso10646us", RTL_TEXTENCODING_ASCII_US },
598 { "iso646irv", RTL_TEXTENCODING_ASCII_US },
599 { "cskoi8r", RTL_TEXTENCODING_KOI8_R },
600 { "ibm437", RTL_TEXTENCODING_IBM_437 },
601 { "cp437", RTL_TEXTENCODING_IBM_437 },
602 { "437", RTL_TEXTENCODING_IBM_437 },
603 { "cspc8codepage437", RTL_TEXTENCODING_IBM_437 },
604 { "ansix34", RTL_TEXTENCODING_ASCII_US },
605 { "ibm367", RTL_TEXTENCODING_ASCII_US },
606 { "cp367", RTL_TEXTENCODING_ASCII_US },
607 { "csascii", RTL_TEXTENCODING_ASCII_US },
608 { "ibm775", RTL_TEXTENCODING_IBM_775 },
609 { "cp775", RTL_TEXTENCODING_IBM_775 },
610 { "cspc775baltic", RTL_TEXTENCODING_IBM_775 },
611 { "ibm850", RTL_TEXTENCODING_IBM_850 },
612 { "cp850", RTL_TEXTENCODING_IBM_850 },
613 { "850", RTL_TEXTENCODING_IBM_850 },
614 { "cspc850multilingual", RTL_TEXTENCODING_IBM_850 },
615 /* { "ibm851", RTL_TEXTENCODING_IBM_851 }, */
616 /* { "cp851", RTL_TEXTENCODING_IBM_851 }, */
617 /* { "851", RTL_TEXTENCODING_IBM_851 }, */
618 /* { "csibm851", RTL_TEXTENCODING_IBM_851 }, */
619 { "ibm852", RTL_TEXTENCODING_IBM_852 },
620 { "cp852", RTL_TEXTENCODING_IBM_852 },
621 { "852", RTL_TEXTENCODING_IBM_852 },
622 { "cspcp852", RTL_TEXTENCODING_IBM_852 },
623 { "ibm855", RTL_TEXTENCODING_IBM_855 },
624 { "cp855", RTL_TEXTENCODING_IBM_855 },
625 { "855", RTL_TEXTENCODING_IBM_855 },
626 { "csibm855", RTL_TEXTENCODING_IBM_855 },
627 { "ibm857", RTL_TEXTENCODING_IBM_857 },
628 { "cp857", RTL_TEXTENCODING_IBM_857 },
629 { "857", RTL_TEXTENCODING_IBM_857 },
630 { "csibm857", RTL_TEXTENCODING_IBM_857 },
631 { "ibm860", RTL_TEXTENCODING_IBM_860 },
632 { "cp860", RTL_TEXTENCODING_IBM_860 },
633 { "860", RTL_TEXTENCODING_IBM_860 },
634 { "csibm860", RTL_TEXTENCODING_IBM_860 },
635 { "ibm861", RTL_TEXTENCODING_IBM_861 },
636 { "cp861", RTL_TEXTENCODING_IBM_861 },
637 { "861", RTL_TEXTENCODING_IBM_861 },
638 { "csis", RTL_TEXTENCODING_IBM_861 },
639 { "csibm861", RTL_TEXTENCODING_IBM_861 },
640 { "ibm862", RTL_TEXTENCODING_IBM_862 },
641 { "cp862", RTL_TEXTENCODING_IBM_862 },
642 { "862", RTL_TEXTENCODING_IBM_862 },
643 { "cspc862latinhebrew", RTL_TEXTENCODING_IBM_862 },
644 { "ibm863", RTL_TEXTENCODING_IBM_863 },
645 { "cp863", RTL_TEXTENCODING_IBM_863 },
646 { "863", RTL_TEXTENCODING_IBM_863 },
647 { "csibm863", RTL_TEXTENCODING_IBM_863 },
648 { "ibm864", RTL_TEXTENCODING_IBM_864 },
649 { "cp864", RTL_TEXTENCODING_IBM_864 },
650 { "864", RTL_TEXTENCODING_IBM_864 },
651 { "csibm864", RTL_TEXTENCODING_IBM_864 },
652 { "ibm865", RTL_TEXTENCODING_IBM_865 },
653 { "cp865", RTL_TEXTENCODING_IBM_865 },
654 { "865", RTL_TEXTENCODING_IBM_865 },
655 { "csibm865", RTL_TEXTENCODING_IBM_865 },
656 { "ibm866", RTL_TEXTENCODING_IBM_866 },
657 { "cp866", RTL_TEXTENCODING_IBM_866 },
658 { "866", RTL_TEXTENCODING_IBM_866 },
659 { "csibm866", RTL_TEXTENCODING_IBM_866 },
660 /* { "ibm868", RTL_TEXTENCODING_IBM_868 }, */
661 /* { "cp868", RTL_TEXTENCODING_IBM_868 }, */
662 /* { "cpar", RTL_TEXTENCODING_IBM_868 }, */
663 /* { "csibm868", RTL_TEXTENCODING_IBM_868 }, */
664 { "ibm869", RTL_TEXTENCODING_IBM_869 },
665 { "cp869", RTL_TEXTENCODING_IBM_869 },
666 { "869", RTL_TEXTENCODING_IBM_869 },
667 { "cpgr", RTL_TEXTENCODING_IBM_869 },
668 { "csibm869", RTL_TEXTENCODING_IBM_869 },
669 { "ibm869", RTL_TEXTENCODING_IBM_869 },
670 { "cp869", RTL_TEXTENCODING_IBM_869 },
671 { "869", RTL_TEXTENCODING_IBM_869 },
672 { "cpgr", RTL_TEXTENCODING_IBM_869 },
673 { "csibm869", RTL_TEXTENCODING_IBM_869 },
674 { "mac", RTL_TEXTENCODING_APPLE_ROMAN },
675 { "csmacintosh", RTL_TEXTENCODING_APPLE_ROMAN },
676 { "shiftjis", RTL_TEXTENCODING_SHIFT_JIS },
677 { "mskanji", RTL_TEXTENCODING_MS_932 },
678 { "csshiftjis", RTL_TEXTENCODING_SHIFT_JIS },
679 { "jisx0208", RTL_TEXTENCODING_JIS_X_0208 },
680 { "jisc62261983", RTL_TEXTENCODING_JIS_X_0208 },
681 { "csiso87jisx0208", RTL_TEXTENCODING_JIS_X_0208 },
682 { "isoir86", RTL_TEXTENCODING_JIS_X_0208 },
683 { "x0208", RTL_TEXTENCODING_JIS_X_0208 },
684 { "jisx0201", RTL_TEXTENCODING_JIS_X_0201 },
685 { "cshalfwidthkatakana", RTL_TEXTENCODING_JIS_X_0201 },
686 { "x0201", RTL_TEXTENCODING_JIS_X_0201 },
687 { "jisx0212", RTL_TEXTENCODING_JIS_X_0212 },
688 { "csiso159jisx0212", RTL_TEXTENCODING_JIS_X_0212 },
689 { "isoir159", RTL_TEXTENCODING_JIS_X_0208 },
690 { "x0212", RTL_TEXTENCODING_JIS_X_0212 },
691 { "isoir6", RTL_TEXTENCODING_ASCII_US },
692 { "xsjis", RTL_TEXTENCODING_SHIFT_JIS },
693 { "sjis", RTL_TEXTENCODING_SHIFT_JIS },
694 { "ascii", RTL_TEXTENCODING_ASCII_US },
695 { "us", RTL_TEXTENCODING_ASCII_US },
696 { "gb180302000", RTL_TEXTENCODING_GB_18030 },
697 /* This is no actual MIME character set name, it is only in here
698 for backwards compatibility (before "GB18030" was officially
699 registered with IANA, this code contained some guesses of what
700 would become official names for GB18030). */
701 { "gb18030", RTL_TEXTENCODING_GB_18030 },
702 { "big5hkscs", RTL_TEXTENCODING_BIG5_HKSCS },
703 { "tis620", RTL_TEXTENCODING_TIS_620 },
704 { "gbk", RTL_TEXTENCODING_GBK },
705 { "cp936", RTL_TEXTENCODING_GBK },
706 { "ms936", RTL_TEXTENCODING_GBK },
707 { "windows936", RTL_TEXTENCODING_GBK },
708 { "cp874", RTL_TEXTENCODING_MS_874 },
709 /* This is no official MIME character set name, but it might be in
710 use in Thailand. */
711 { "ms874", RTL_TEXTENCODING_MS_874 },
712 /* This is no official MIME character set name, but it might be in
713 use in Thailand. */
714 { "windows874", RTL_TEXTENCODING_MS_874 },
715 /* This is no official MIME character set name, but it might be in
716 use in Thailand. */
717 { "koi8u", RTL_TEXTENCODING_KOI8_U },
718 { "cpis", RTL_TEXTENCODING_IBM_861 },
719 { "ksc56011987", RTL_TEXTENCODING_MS_949 },
720 { "isoir149", RTL_TEXTENCODING_MS_949 },
721 { "ksc56011989", RTL_TEXTENCODING_MS_949 },
722 { "ksc5601", RTL_TEXTENCODING_MS_949 },
723 { "korean", RTL_TEXTENCODING_MS_949 },
724 { "csksc56011987", RTL_TEXTENCODING_MS_949 },
725 /* Map KS_C_5601-1987 and aliases to MS-949 instead of EUC-KR, as
726 this character set identifier seems to be prominently used by MS
727 to stand for KS C 5601 plus MS-949 extensions */
728 { "latin9", RTL_TEXTENCODING_ISO_8859_15 },
729 { "adobestandardencoding", RTL_TEXTENCODING_ADOBE_STANDARD },
730 { "csadobestandardencoding", RTL_TEXTENCODING_ADOBE_STANDARD },
731 { "adobesymbolencoding", RTL_TEXTENCODING_ADOBE_SYMBOL },
732 { "cshppsmath", RTL_TEXTENCODING_ADOBE_SYMBOL },
733 { "ptcp154", RTL_TEXTENCODING_PT154 },
734 { "csptcp154", RTL_TEXTENCODING_PT154 },
735 { "pt154", RTL_TEXTENCODING_PT154 },
736 { "cp154", RTL_TEXTENCODING_PT154 },
737 { "xisciide", RTL_TEXTENCODING_ISCII_DEVANAGARI },
738 /* This is not an official MIME character set name, but is in use by
739 various windows APIs. */
740 { nullptr, RTL_TEXTENCODING_DONTKNOW }
741 };
742
743 rtl_TextEncoding eEncoding = RTL_TEXTENCODING_DONTKNOW;
744 const ImplStrCharsetDef* pData = aVIPMimeCharsetTab;
745 sal_uInt32 nBufLen = strlen( pMimeCharset )+1;
746
747 /* Alloc Buffer and map to lower case and remove non alphanumeric chars */
748 std::unique_ptr<char[]> pBuf(new char[nBufLen]);
749 Impl_toAsciiLowerAndRemoveNonAlphanumeric( pMimeCharset, pBuf.get() );
750
751 /* Search for equal in the VIP table */
752 while ( pData->mpCharsetStr )
753 {
754 if ( strcmp( pBuf.get(), pData->mpCharsetStr ) == 0 )
755 {
756 eEncoding = pData->meTextEncoding;
757 break;
758 }
759
760 pData++;
761 }
762
763 /* Search for matching in the mime table */
764 if ( eEncoding == RTL_TEXTENCODING_DONTKNOW )
765 {
766 pData = aMimeCharsetTab;
767 while ( pData->mpCharsetStr )
768 {
769 if ( Impl_matchString( pBuf.get(), pData->mpCharsetStr ) )
770 {
771 eEncoding = pData->meTextEncoding;
772 break;
773 }
774
775 pData++;
776 }
777 }
778
779 return eEncoding;
780 }
781
782 /* ======================================================================= */
783
rtl_getBestWindowsCharsetFromTextEncoding(rtl_TextEncoding eTextEncoding)784 sal_uInt8 SAL_CALL rtl_getBestWindowsCharsetFromTextEncoding( rtl_TextEncoding eTextEncoding )
785 {
786 const ImplTextEncodingData* pData = Impl_getTextEncodingData( eTextEncoding );
787 if ( pData )
788 return pData->mnBestWindowsCharset;
789 return 1;
790 }
791
792 /* ----------------------------------------------------------------------- */
793
rtl_getBestUnixCharsetFromTextEncoding(rtl_TextEncoding eTextEncoding)794 const char* SAL_CALL rtl_getBestUnixCharsetFromTextEncoding( rtl_TextEncoding eTextEncoding )
795 {
796 const ImplTextEncodingData* pData = Impl_getTextEncodingData( eTextEncoding );
797 if ( pData )
798 return pData->mpBestUnixCharset;
799 if( eTextEncoding == RTL_TEXTENCODING_UNICODE )
800 return "iso10646-1";
801 return nullptr;
802 }
803
804 /* ----------------------------------------------------------------------- */
805
rtl_getMimeCharsetFromTextEncoding(rtl_TextEncoding nEncoding)806 char const * SAL_CALL rtl_getMimeCharsetFromTextEncoding(rtl_TextEncoding
807 nEncoding)
808 {
809 ImplTextEncodingData const * p = Impl_getTextEncodingData(nEncoding);
810 return p && (p->mnInfoFlags & RTL_TEXTENCODING_INFO_MIME) != 0 ?
811 p->mpBestMimeCharset : nullptr;
812 }
813
rtl_getBestMimeCharsetFromTextEncoding(rtl_TextEncoding eTextEncoding)814 const char* SAL_CALL rtl_getBestMimeCharsetFromTextEncoding( rtl_TextEncoding eTextEncoding )
815 {
816 const ImplTextEncodingData* pData = Impl_getTextEncodingData( eTextEncoding );
817 if ( pData )
818 return pData->mpBestMimeCharset;
819 return nullptr;
820 }
821
822 /* The following two functions are based on <http://www.sharmahd.com/tm/
823 codepages.html>, <http://msdn.microsoft.com/workshop/author/dhtml/reference/
824 charsets/charset4.asp>, and <http://www.iana.org/assignments/character-sets>.
825 */
826
827 rtl_TextEncoding SAL_CALL
rtl_getTextEncodingFromWindowsCodePage(sal_uInt32 nCodePage)828 rtl_getTextEncodingFromWindowsCodePage(sal_uInt32 nCodePage)
829 {
830 switch (nCodePage)
831 {
832 case 42: return RTL_TEXTENCODING_SYMBOL;
833 case 437: return RTL_TEXTENCODING_IBM_437;
834 case 708: return RTL_TEXTENCODING_ISO_8859_6;
835 case 737: return RTL_TEXTENCODING_IBM_737;
836 case 775: return RTL_TEXTENCODING_IBM_775;
837 case 850: return RTL_TEXTENCODING_IBM_850;
838 case 852: return RTL_TEXTENCODING_IBM_852;
839 case 855: return RTL_TEXTENCODING_IBM_855;
840 case 857: return RTL_TEXTENCODING_IBM_857;
841 case 860: return RTL_TEXTENCODING_IBM_860;
842 case 861: return RTL_TEXTENCODING_IBM_861;
843 case 862: return RTL_TEXTENCODING_IBM_862;
844 case 863: return RTL_TEXTENCODING_IBM_863;
845 case 864: return RTL_TEXTENCODING_IBM_864;
846 case 865: return RTL_TEXTENCODING_IBM_865;
847 case 866: return RTL_TEXTENCODING_IBM_866;
848 case 869: return RTL_TEXTENCODING_IBM_869;
849 case 874: return RTL_TEXTENCODING_MS_874;
850 case 932: return RTL_TEXTENCODING_MS_932;
851 case 936: return RTL_TEXTENCODING_MS_936;
852 case 949: return RTL_TEXTENCODING_MS_949;
853 case 950: return RTL_TEXTENCODING_MS_950;
854 case 1250: return RTL_TEXTENCODING_MS_1250;
855 case 1251: return RTL_TEXTENCODING_MS_1251;
856 case 1252: return RTL_TEXTENCODING_MS_1252;
857 case 1253: return RTL_TEXTENCODING_MS_1253;
858 case 1254: return RTL_TEXTENCODING_MS_1254;
859 case 1255: return RTL_TEXTENCODING_MS_1255;
860 case 1256: return RTL_TEXTENCODING_MS_1256;
861 case 1257: return RTL_TEXTENCODING_MS_1257;
862 case 1258: return RTL_TEXTENCODING_MS_1258;
863 case 1361: return RTL_TEXTENCODING_MS_1361;
864 case 10000: return RTL_TEXTENCODING_APPLE_ROMAN;
865 case 10001: return RTL_TEXTENCODING_APPLE_JAPANESE;
866 case 10002: return RTL_TEXTENCODING_APPLE_CHINTRAD;
867 case 10003: return RTL_TEXTENCODING_APPLE_KOREAN;
868 case 10004: return RTL_TEXTENCODING_APPLE_ARABIC;
869 case 10005: return RTL_TEXTENCODING_APPLE_HEBREW;
870 case 10006: return RTL_TEXTENCODING_APPLE_GREEK;
871 case 10007: return RTL_TEXTENCODING_APPLE_CYRILLIC;
872 case 10008: return RTL_TEXTENCODING_APPLE_CHINSIMP;
873 case 10010: return RTL_TEXTENCODING_APPLE_ROMANIAN;
874 case 10017: return RTL_TEXTENCODING_APPLE_UKRAINIAN;
875 case 10029: return RTL_TEXTENCODING_APPLE_CENTEURO;
876 case 10079: return RTL_TEXTENCODING_APPLE_ICELAND;
877 case 10081: return RTL_TEXTENCODING_APPLE_TURKISH;
878 case 10082: return RTL_TEXTENCODING_APPLE_CROATIAN;
879 case 20127: return RTL_TEXTENCODING_ASCII_US;
880 case 20866: return RTL_TEXTENCODING_KOI8_R;
881 case 21866: return RTL_TEXTENCODING_KOI8_U;
882 case 28591: return RTL_TEXTENCODING_ISO_8859_1;
883 case 28592: return RTL_TEXTENCODING_ISO_8859_2;
884 case 28593: return RTL_TEXTENCODING_ISO_8859_3;
885 case 28594: return RTL_TEXTENCODING_ISO_8859_4;
886 case 28595: return RTL_TEXTENCODING_ISO_8859_5;
887 case 28596: return RTL_TEXTENCODING_ISO_8859_6;
888 case 28597: return RTL_TEXTENCODING_ISO_8859_7;
889 case 28598: return RTL_TEXTENCODING_ISO_8859_8;
890 case 28599: return RTL_TEXTENCODING_ISO_8859_9;
891 case 28605: return RTL_TEXTENCODING_ISO_8859_15;
892 case 50220: return RTL_TEXTENCODING_ISO_2022_JP;
893 case 50225: return RTL_TEXTENCODING_ISO_2022_KR;
894 case 51932: return RTL_TEXTENCODING_EUC_JP;
895 case 51936: return RTL_TEXTENCODING_EUC_CN;
896 case 51949: return RTL_TEXTENCODING_EUC_KR;
897 case 57002: return RTL_TEXTENCODING_ISCII_DEVANAGARI;
898 case 65000: return RTL_TEXTENCODING_UTF7;
899 case 65001: return RTL_TEXTENCODING_UTF8;
900 default: return RTL_TEXTENCODING_DONTKNOW;
901 }
902 }
903
904 sal_uInt32 SAL_CALL
rtl_getWindowsCodePageFromTextEncoding(rtl_TextEncoding nEncoding)905 rtl_getWindowsCodePageFromTextEncoding(rtl_TextEncoding nEncoding)
906 {
907 switch (nEncoding)
908 {
909 case RTL_TEXTENCODING_SYMBOL: return 42;
910 case RTL_TEXTENCODING_IBM_437: return 437;
911 /* case RTL_TEXTENCODING_ISO_8859_6: return 708; */
912 case RTL_TEXTENCODING_IBM_737: return 737;
913 case RTL_TEXTENCODING_IBM_775: return 775;
914 case RTL_TEXTENCODING_IBM_850: return 850;
915 case RTL_TEXTENCODING_IBM_852: return 852;
916 case RTL_TEXTENCODING_IBM_855: return 855;
917 case RTL_TEXTENCODING_IBM_857: return 857;
918 case RTL_TEXTENCODING_IBM_860: return 860;
919 case RTL_TEXTENCODING_IBM_861: return 861;
920 case RTL_TEXTENCODING_IBM_862: return 862;
921 case RTL_TEXTENCODING_IBM_863: return 863;
922 case RTL_TEXTENCODING_IBM_864: return 864;
923 case RTL_TEXTENCODING_IBM_865: return 865;
924 case RTL_TEXTENCODING_IBM_866: return 866;
925 case RTL_TEXTENCODING_IBM_869: return 869;
926 case RTL_TEXTENCODING_MS_874: return 874;
927 case RTL_TEXTENCODING_MS_932: return 932;
928 case RTL_TEXTENCODING_MS_936: return 936;
929 case RTL_TEXTENCODING_MS_949: return 949;
930 case RTL_TEXTENCODING_MS_950: return 950;
931 case RTL_TEXTENCODING_MS_1250: return 1250;
932 case RTL_TEXTENCODING_MS_1251: return 1251;
933 case RTL_TEXTENCODING_MS_1252: return 1252;
934 case RTL_TEXTENCODING_MS_1253: return 1253;
935 case RTL_TEXTENCODING_MS_1254: return 1254;
936 case RTL_TEXTENCODING_MS_1255: return 1255;
937 case RTL_TEXTENCODING_MS_1256: return 1256;
938 case RTL_TEXTENCODING_MS_1257: return 1257;
939 case RTL_TEXTENCODING_MS_1258: return 1258;
940 case RTL_TEXTENCODING_MS_1361: return 1361;
941 case RTL_TEXTENCODING_APPLE_ROMAN: return 10000;
942 case RTL_TEXTENCODING_APPLE_JAPANESE: return 10001;
943 case RTL_TEXTENCODING_APPLE_CHINTRAD: return 10002;
944 case RTL_TEXTENCODING_APPLE_KOREAN: return 10003;
945 case RTL_TEXTENCODING_APPLE_ARABIC: return 10004;
946 case RTL_TEXTENCODING_APPLE_HEBREW: return 10005;
947 case RTL_TEXTENCODING_APPLE_GREEK: return 10006;
948 case RTL_TEXTENCODING_APPLE_CYRILLIC: return 10007;
949 case RTL_TEXTENCODING_APPLE_CHINSIMP: return 10008;
950 case RTL_TEXTENCODING_APPLE_ROMANIAN: return 10010;
951 case RTL_TEXTENCODING_APPLE_UKRAINIAN: return 10017;
952 case RTL_TEXTENCODING_APPLE_CENTEURO: return 10029;
953 case RTL_TEXTENCODING_APPLE_ICELAND: return 10079;
954 case RTL_TEXTENCODING_APPLE_TURKISH: return 10081;
955 case RTL_TEXTENCODING_APPLE_CROATIAN: return 10082;
956 case RTL_TEXTENCODING_ASCII_US: return 20127;
957 case RTL_TEXTENCODING_KOI8_R: return 20866;
958 case RTL_TEXTENCODING_KOI8_U: return 21866;
959 case RTL_TEXTENCODING_ISO_8859_1: return 28591;
960 case RTL_TEXTENCODING_ISO_8859_2: return 28592;
961 case RTL_TEXTENCODING_ISO_8859_3: return 28593;
962 case RTL_TEXTENCODING_ISO_8859_4: return 28594;
963 case RTL_TEXTENCODING_ISO_8859_5: return 28595;
964 case RTL_TEXTENCODING_ISO_8859_6: return 28596;
965 case RTL_TEXTENCODING_ISO_8859_7: return 28597;
966 case RTL_TEXTENCODING_ISO_8859_8: return 28598;
967 case RTL_TEXTENCODING_ISO_8859_9: return 28599;
968 case RTL_TEXTENCODING_ISO_8859_15: return 28605;
969 case RTL_TEXTENCODING_ISO_2022_JP: return 50220;
970 case RTL_TEXTENCODING_ISO_2022_KR: return 50225;
971 case RTL_TEXTENCODING_EUC_JP: return 51932;
972 case RTL_TEXTENCODING_EUC_CN: return 51936;
973 case RTL_TEXTENCODING_EUC_KR: return 51949;
974 case RTL_TEXTENCODING_ISCII_DEVANAGARI: return 57002;
975 case RTL_TEXTENCODING_UTF7: return 65000;
976 case RTL_TEXTENCODING_UTF8: return 65001;
977 default: return 0;
978 }
979 }
980
981 /* vim:set shiftwidth=4 softtabstop=4 expandtab: */
982
