sal/textenc/tencinfo.cxx

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