xref: /aoo41x/main/sal/textenc/tencinfo.c (revision cdf0e10c)
1 /*************************************************************************
2  *
3  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4  *
5  * Copyright 2000, 2010 Oracle and/or its affiliates.
6  *
7  * OpenOffice.org - a multi-platform office productivity suite
8  *
9  * This file is part of OpenOffice.org.
10  *
11  * OpenOffice.org is free software: you can redistribute it and/or modify
12  * it under the terms of the GNU Lesser General Public License version 3
13  * only, as published by the Free Software Foundation.
14  *
15  * OpenOffice.org is distributed in the hope that it will be useful,
16  * but WITHOUT ANY WARRANTY; without even the implied warranty of
17  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
18  * GNU Lesser General Public License version 3 for more details
19  * (a copy is included in the LICENSE file that accompanied this code).
20  *
21  * You should have received a copy of the GNU Lesser General Public License
22  * version 3 along with OpenOffice.org.  If not, see
23  * <http://www.openoffice.org/license.html>
24  * for a copy of the LGPLv3 License.
25  *
26  ************************************************************************/
27 
28 #include "rtl/tencinfo.h"
29 #include "gettextencodingdata.h"
30 #include "tenchelp.h"
31 
32 #ifndef _RTL_ALLOC_H
33 #include "rtl/alloc.h"
34 #endif
35 
36 #ifndef INCLUDED_STDDEF_H
37 #include <stddef.h>
38 #define INCLUDED_STDDEF_H
39 #endif
40 #ifndef INCLUDED_STRING_H
41 #include <string.h>
42 #define INCLUDED_STRING_H
43 #endif
44 
45 sal_Bool SAL_CALL rtl_isOctetTextEncoding(rtl_TextEncoding nEncoding)
46 {
47     return (sal_Bool)
48         (nEncoding > RTL_TEXTENCODING_DONTKNOW
49          && (nEncoding <= RTL_TEXTENCODING_ADOBE_DINGBATS)
50              /* always update this! */
51          && nEncoding != 9); /* RTL_TEXTENCODING_SYSTEM */
52 }
53 
54 /* ======================================================================= */
55 
56 static void Impl_toAsciiLower( const sal_Char* pName, sal_Char* pBuf )
57 {
58     while ( *pName )
59     {
60         /* A-Z */
61         if ( (*pName >= 0x41) && (*pName <= 0x5A) )
62             *pBuf = (*pName)+0x20;  /* toAsciiLower */
63         else
64             *pBuf = *pName;
65 
66         pBuf++;
67         pName++;
68     }
69 
70     *pBuf = '\0';
71 }
72 
73 /* ----------------------------------------------------------------------- */
74 
75 static void Impl_toAsciiLowerAndRemoveNonAlphanumeric( const sal_Char* pName, sal_Char* pBuf )
76 {
77     while ( *pName )
78     {
79         /* A-Z */
80         if ( (*pName >= 0x41) && (*pName <= 0x5A) )
81         {
82             *pBuf = (*pName)+0x20;  /* toAsciiLower */
83             pBuf++;
84         }
85         /* a-z, 0-9 */
86         else if ( ((*pName >= 0x61) && (*pName <= 0x7A)) ||
87                   ((*pName >= 0x30) && (*pName <= 0x39)) )
88         {
89             *pBuf = *pName;
90             pBuf++;
91         }
92 
93         pName++;
94     }
95 
96     *pBuf = '\0';
97 }
98 
99 /* ----------------------------------------------------------------------- */
100 
101 /* pMatchStr must match with all characters in pCompStr */
102 static sal_Bool Impl_matchString( const sal_Char* pCompStr, const sal_Char* pMatchStr )
103 {
104     /* We test only for end in MatchStr, because the last 0 character from */
105     /* pCompStr is unequal a character in MatchStr, so the loop terminates */
106     while ( *pMatchStr )
107     {
108         if ( *pCompStr != *pMatchStr )
109             return sal_False;
110 
111         pCompStr++;
112         pMatchStr++;
113     }
114 
115     return sal_True;
116 }
117 
118 /* ======================================================================= */
119 
120 typedef struct
121 {
122     const sal_Char*             mpCharsetStr;
123     rtl_TextEncoding            meTextEncoding;
124 } ImplStrCharsetDef;
125 
126 typedef struct
127 {
128     const sal_Char*             mpCharsetStr;
129     const ImplStrCharsetDef*    mpSecondPartTab;
130 } ImplStrFirstPartCharsetDef;
131 
132 /* ======================================================================= */
133 
134 sal_Bool SAL_CALL rtl_getTextEncodingInfo( rtl_TextEncoding eTextEncoding, rtl_TextEncodingInfo* pEncInfo )
135 {
136     const ImplTextEncodingData* pData;
137 
138     pData = Impl_getTextEncodingData( eTextEncoding );
139     if ( !pData )
140     {
141         /* HACK: For not implemented encoding, because not all
142            calls handle the errors */
143         if ( pEncInfo->StructSize < 5 )
144             return sal_False;
145         pEncInfo->MinimumCharSize = 1;
146 
147         if ( pEncInfo->StructSize < 6 )
148             return sal_True;
149         pEncInfo->MaximumCharSize = 1;
150 
151         if ( pEncInfo->StructSize < 7 )
152             return sal_True;
153         pEncInfo->AverageCharSize = 1;
154 
155         if ( pEncInfo->StructSize < 12 )
156             return sal_True;
157         pEncInfo->Flags = 0;
158 
159         return sal_False;
160     }
161 
162     if ( pEncInfo->StructSize < 5 )
163         return sal_False;
164     pEncInfo->MinimumCharSize = pData->mnMinCharSize;
165 
166     if ( pEncInfo->StructSize < 6 )
167         return sal_True;
168     pEncInfo->MaximumCharSize = pData->mnMaxCharSize;
169 
170     if ( pEncInfo->StructSize < 7 )
171         return sal_True;
172     pEncInfo->AverageCharSize = pData->mnAveCharSize;
173 
174     if ( pEncInfo->StructSize < 12 )
175         return sal_True;
176     pEncInfo->Flags = pData->mnInfoFlags;
177 
178     return sal_True;
179 }
180 
181 /* ======================================================================= */
182 
183 rtl_TextEncoding SAL_CALL rtl_getTextEncodingFromWindowsCharset( sal_uInt8 nWinCharset )
184 {
185     rtl_TextEncoding eTextEncoding;
186 
187     switch ( nWinCharset )
188     {
189         case 0:     eTextEncoding = RTL_TEXTENCODING_MS_1252; break;    /* ANSI_CHARSET */
190         case 2:     eTextEncoding = RTL_TEXTENCODING_SYMBOL; break;     /* SYMBOL_CHARSET */
191         case 77:    eTextEncoding = RTL_TEXTENCODING_APPLE_ROMAN; break;/* MAC_CHARSET */
192         case 128:   eTextEncoding = RTL_TEXTENCODING_MS_932; break;     /* SHIFTJIS_CHARSET */
193         case 129:   eTextEncoding = RTL_TEXTENCODING_MS_949; break;     /* HANGEUL_CHARSET */
194         case 130:   eTextEncoding = RTL_TEXTENCODING_MS_1361; break;    /* JOHAB_CHARSET */
195         case 134:   eTextEncoding = RTL_TEXTENCODING_MS_936; break;     /* GB2312_CHARSET */
196         case 136:   eTextEncoding = RTL_TEXTENCODING_MS_950; break;     /* CHINESEBIG5_CHARSET */
197         case 161:   eTextEncoding = RTL_TEXTENCODING_MS_1253; break;    /* GREEK_CHARSET */
198         case 162:   eTextEncoding = RTL_TEXTENCODING_MS_1254; break;    /* TURKISH_CHARSET */
199         case 163:   eTextEncoding = RTL_TEXTENCODING_MS_1258; break;    /* VIETNAMESE_CHARSET !!! */
200         case 177:   eTextEncoding = RTL_TEXTENCODING_MS_1255; break;    /* HEBREW_CHARSET */
201         case 178:   eTextEncoding = RTL_TEXTENCODING_MS_1256; break;    /* ARABIC_CHARSET */
202         case 186:   eTextEncoding = RTL_TEXTENCODING_MS_1257; break;    /* BALTIC_CHARSET */
203         case 204:   eTextEncoding = RTL_TEXTENCODING_MS_1251; break;    /* RUSSIAN_CHARSET */
204         case 222:   eTextEncoding = RTL_TEXTENCODING_MS_874; break;     /* THAI_CHARSET */
205         case 238:   eTextEncoding = RTL_TEXTENCODING_MS_1250; break;    /* EASTEUROPE_CHARSET */
206         case 255:   eTextEncoding = RTL_TEXTENCODING_IBM_850; break;    /* OEM_CHARSET */
207         default:    eTextEncoding = RTL_TEXTENCODING_DONTKNOW; break;
208     };
209 
210     return eTextEncoding;
211 }
212 
213 /* ----------------------------------------------------------------------- */
214 
215 #if 0
216 
217 rtl_TextEncoding SAL_CALL rtl_getTextEncodingFromMacTextEncoding( sal_uInt32 nMacTextEncoding )
218 {
219     rtl_TextEncoding eTextEncoding;
220 
221     switch ( nMacTextEncoding )
222     {
223         case 0:     eTextEncoding = RTL_TEXTENCODING_APPLE_ROMAN; break;
224         case 1:     eTextEncoding = RTL_TEXTENCODING_APPLE_JAPANESE; break;
225         case 2:     eTextEncoding = RTL_TEXTENCODING_APPLE_CHINTRAD; break;
226         case 3:     eTextEncoding = RTL_TEXTENCODING_APPLE_KOREAN; break;
227         case 4:     eTextEncoding = RTL_TEXTENCODING_APPLE_ARABIC; break;
228         case 5:     eTextEncoding = RTL_TEXTENCODING_APPLE_HEBREW; break;
229         case 6:     eTextEncoding = RTL_TEXTENCODING_APPLE_GREEK; break;
230         case 7:     eTextEncoding = RTL_TEXTENCODING_APPLE_CYRILLIC; break;
231         /* RIGHT-TO-LEFT SYMBOLS = 8  ??? */
232         case 9:     eTextEncoding = RTL_TEXTENCODING_APPLE_DEVANAGARI; break;
233         case 10:    eTextEncoding = RTL_TEXTENCODING_APPLE_GURMUKHI; break;
234         case 11:    eTextEncoding = RTL_TEXTENCODING_APPLE_GUJARATI; break;
235         /* MacOriya = 12 */
236         /* MacBengali = 13 */
237         /* MacTamil = 14 */
238         /* MacTelugu = 15 */
239         /* MacKannada = 16 */
240         /* MacMalayalam = 17 */
241         /* MacSinhalese = 18 */
242         /* MacBurmese = 19 */
243         /* MacKhmer = 20 */
244         case 21:    eTextEncoding = RTL_TEXTENCODING_APPLE_THAI; break;
245         /* MacLaotian = 22 */
246         /* MacGeorgian = 23 */
247         /* MacArmenian = 24 */
248         case 25:    eTextEncoding = RTL_TEXTENCODING_APPLE_CHINSIMP; break;
249         /* MacTibetan = 26 */
250         /* MacMongolian = 27 */
251         /* MacEthiopic = 28 */
252         case 29:    eTextEncoding = RTL_TEXTENCODING_APPLE_CENTEURO; break;     /* MacCentralEurRoman */
253         /* MacVietnamese = 30 */
254         /* MacExtArabic = 31 */
255         case 32:    eTextEncoding = RTL_TEXTENCODING_SYMBOL; break;
256         case 33:    eTextEncoding = RTL_TEXTENCODING_SYMBOL; break;     /* MacSymbol */
257         case 34:    eTextEncoding = RTL_TEXTENCODING_SYMBOL; break;     /* MacDingbats */
258         case 35:    eTextEncoding = RTL_TEXTENCODING_APPLE_TURKISH; break;      /* MacTurkish */
259         case 36:    eTextEncoding = RTL_TEXTENCODING_APPLE_CROATIAN; break;     /* MacCroatian */
260         case 37:    eTextEncoding = RTL_TEXTENCODING_APPLE_ICELAND; break;      /* MacIcelandic */
261         case 38:    eTextEncoding = RTL_TEXTENCODING_APPLE_ROMANIAN; break;     /* MacRomanian */
262         /* MacCeltic = 39 */
263         /* MacGaelic = 40 */
264         /* Beginning in Mac OS 8.5, the set of Mac OS script codes has been */
265         /* extended for some Mac OS components to include Unicode. Some of */
266         /* these components have only 7 bits available for script code, so */
267         /* kTextEncodingUnicodeDefault cannot be used to indicate Unicode. */
268         /* Instead, the following meta-value is used to indicate Unicode */
269         /* handled as a special Mac OS script code; TEC handles this value */
270         /* like kTextEncodingUnicodeDefault. */
271         /* The following use script code 4, smArabic */
272         case 0x08C: eTextEncoding = RTL_TEXTENCODING_APPLE_FARSI; break;        /* MacFarsi */
273         /* The following use script code 7, smCyrillic */
274         case 0x098: eTextEncoding = RTL_TEXTENCODING_APPLE_UKRAINIAN; break;    /* MacUkrainian */
275         /* The following use script code 28, smEthiopic */
276         /* MacInuit = 0xEC */
277         /* The following use script code 32, smUninterp */
278         case 0x0FC: eTextEncoding = RTL_TEXTENCODING_SYMBOL; break;       /* MacVT100 - VT100/102 font */
279         /* Special Mac OS encodings */
280         /* MacHFS = 0xFF */ /* metavalue. */
281         /* Unicode & ISO UCS encodings begin at 0x100 */
282         case 0x100: eTextEncoding = RTL_TEXTENCODING_UNICODE; break;    /* UnicodeDefault */
283         case 0x101: eTextEncoding = RTL_TEXTENCODING_UNICODE; break;    /* UnicodeV1_1 / ISO10646_1993 */
284         case 0x103: eTextEncoding = RTL_TEXTENCODING_UNICODE; break;    /* UnicodeV2_1 - new location for Korean Hangul / UnicodeV2_1 */
285         /* ISO 8-bit and 7-bit encodings begin at 0x200 */
286         case 0x201: eTextEncoding = RTL_TEXTENCODING_ISO_8859_1; break; /* ISOLatin1 - ISO 8859-1 */
287         case 0x202: eTextEncoding = RTL_TEXTENCODING_ISO_8859_2; break; /* ISOLatin2 - ISO 8859-2 */
288         case 0x203: eTextEncoding = RTL_TEXTENCODING_ISO_8859_3; break; /* ISOLatin3 - ISO 8859-3 */
289         case 0x204: eTextEncoding = RTL_TEXTENCODING_ISO_8859_4; break; /* ISOLatin4 - ISO 8859-4 */
290         case 0x205: eTextEncoding = RTL_TEXTENCODING_ISO_8859_5; break; /* ISOLatinCyrillic - ISO 8859-5 */
291         case 0x206: eTextEncoding = RTL_TEXTENCODING_ISO_8859_6; break; /* ISOLatinArabic - ISO 8859-6, = ASMO 708, =DOS CP 708 */
292         case 0x207: eTextEncoding = RTL_TEXTENCODING_ISO_8859_7; break; /* ISOLatinGreek - ISO 8859-7 */
293         case 0x208: eTextEncoding = RTL_TEXTENCODING_ISO_8859_8; break; /* ISOLatinHebrew - ISO 8859-8 */
294         case 0x209: eTextEncoding = RTL_TEXTENCODING_ISO_8859_9; break; /* ISOLatin5 - ISO 8859-9 */
295         /* MS-DOS & Windows encodings begin at 0x400 */
296         case 0x400: eTextEncoding = RTL_TEXTENCODING_IBM_437; break;    /* DOSLatinUS - code page 437 */
297         case 0x405: eTextEncoding = RTL_TEXTENCODING_IBM_737; break;    /* DOSGreek - code page 737 (formerly 437G) */
298         case 0x406: eTextEncoding = RTL_TEXTENCODING_IBM_775; break;    /* DOSBalticRim - code page 775 */
299         case 0x410: eTextEncoding = RTL_TEXTENCODING_IBM_850; break;    /* DOSLatin1 - code page 850, "Multilingual" */
300 /* !!!       case 0x411: eTextEncoding = RTL_TEXTENCODING_IBM_851; break; */    /* DOSGreek1 - code page 851 */
301         case 0x412: eTextEncoding = RTL_TEXTENCODING_IBM_852; break;    /* DOSLatin2 - code page 852, Slavic */
302         case 0x413: eTextEncoding = RTL_TEXTENCODING_IBM_855; break;    /* DOSCyrillic - code page 855, IBM Cyrillic */
303         case 0x414: eTextEncoding = RTL_TEXTENCODING_IBM_857; break;    /* DOSTurkish - code page 857, IBM Turkish */
304         case 0x415: eTextEncoding = RTL_TEXTENCODING_IBM_860; break;    /* DOSPortuguese - code page 860 */
305         case 0x416: eTextEncoding = RTL_TEXTENCODING_IBM_861; break;    /* DOSIcelandic - code page 861 */
306         case 0x417: eTextEncoding = RTL_TEXTENCODING_IBM_862; break;    /* DOSHebrew - code page 862 */
307         case 0x418: eTextEncoding = RTL_TEXTENCODING_IBM_863; break;    /* DOSCanadianFrench - code page 863 */
308         case 0x419: eTextEncoding = RTL_TEXTENCODING_IBM_864; break;    /* DOSArabic - code page 864 */
309         case 0x41A: eTextEncoding = RTL_TEXTENCODING_IBM_865; break;    /* DOSNordic - code page 865 */
310         case 0x41B: eTextEncoding = RTL_TEXTENCODING_IBM_866; break;    /* DOSRussian - code page 866 */
311         case 0x41C: eTextEncoding = RTL_TEXTENCODING_IBM_869; break;    /* DOSGreek2 - code page 869, IBM Modern Greek */
312         case 0x41D: eTextEncoding = RTL_TEXTENCODING_MS_874; break;     /* DOSThai - code page 874, also for Windows */
313         case 0x420: eTextEncoding = RTL_TEXTENCODING_MS_932; break;     /* DOSJapanese - code page 932, also for Windows */
314         case 0x421: eTextEncoding = RTL_TEXTENCODING_MS_936; break;     /* DOSChineseSimplif - code page 936, also for Windows */
315         case 0x422: eTextEncoding = RTL_TEXTENCODING_MS_949; break;     /* DOSKorean - code page 949, also for Windows;Unified Hangul */
316         case 0x423: eTextEncoding = RTL_TEXTENCODING_MS_950; break;     /* DOSChineseTrad - code page 950, also for Windows */
317         case 0x500: eTextEncoding = RTL_TEXTENCODING_MS_1252; break;    /* WindowsLatin1 / WindowsANSI - code page 1252 */
318         case 0x501: eTextEncoding = RTL_TEXTENCODING_MS_1250; break;    /* WindowsLatin2 - code page 1250, Central Europe */
319         case 0x502: eTextEncoding = RTL_TEXTENCODING_MS_1251; break;    /* WindowsCyrillic - code page 1251, Slavic Cyrillic */
320         case 0x503: eTextEncoding = RTL_TEXTENCODING_MS_1253; break;    /* WindowsGreek - code page 1253 */
321         case 0x504: eTextEncoding = RTL_TEXTENCODING_MS_1254; break;    /* WindowsLatin5 - code page 1254, Turkish */
322         case 0x505: eTextEncoding = RTL_TEXTENCODING_MS_1255; break;    /* WindowsHebrew - code page 1255 */
323         case 0x506: eTextEncoding = RTL_TEXTENCODING_MS_1256; break;    /* WindowsArabic - code page 1256 */
324         case 0x507: eTextEncoding = RTL_TEXTENCODING_MS_1257; break;    /* WindowsBalticRim - code page 1257 */
325         case 0x508: eTextEncoding = RTL_TEXTENCODING_MS_1258; break;    /* WindowsVietnamese - code page 1258 */
326         case 0x510: eTextEncoding = RTL_TEXTENCODING_MS_1361; break;    /* WindowsKoreanJohab - code page 1361, for Windows NT */
327         /* Various national standards begin at 0x600 */
328         case 0x600: eTextEncoding = RTL_TEXTENCODING_ASCII_US; break;    /* US_ASCII */
329         case 0x620: eTextEncoding = RTL_TEXTENCODING_JIS_X_0201; break;  /* JIS_X0201_76 */
330         case 0x621: eTextEncoding = RTL_TEXTENCODING_JIS_X_0208; break;  /* JIS_X0208_83 */
331         case 0x622: eTextEncoding = RTL_TEXTENCODING_JIS_X_0208; break;  /* JIS_X0208_90 */
332         case 0x623: eTextEncoding = RTL_TEXTENCODING_JIS_X_0212; break;  /* JIS_X0212_90 */
333         /* !!! JIS_C6226_78 = 0x624 */
334         /* !!! GB_2312_80 = 0x630 */
335         /* !!! GBK_95 = 0x631 */ /* annex to GB 13000-93; for Windows 95 */
336 //        case 0x640: eTextEncoding = RTL_TEXTENCODING_KSC_5601_1987; break; /* KSC_5601_87 */ /* same as KSC 5601-92 without Johab annex */
337 //        case 0x641: eTextEncoding = RTL_TEXTENCODING_KSC_5601_1992; break; /* KSC 5601-92 Johab annex */
338         /* !!! CNS_11643_92_P1 = 0x651 */ /* CNS 11643-1992 plane 1 */
339         /* !!! CNS_11643_92_P2 = 0x652 */ /* CNS 11643-1992 plane 2 */
340         /* !!! CNS_11643_92_P3 = 0x653 */ /* CNS 11643-1992 plane 3 (11643-1986 plane 14) */
341         /* ISO 2022 collections begin at 0x800 */
342         case 0x820: eTextEncoding = RTL_TEXTENCODING_ISO_2022_JP; break;    /* ISO_2022_JP */
343         case 0x821: eTextEncoding = RTL_TEXTENCODING_ISO_2022_JP; break;    /* ISO_2022_JP_2 */
344         case 0x830: eTextEncoding = RTL_TEXTENCODING_ISO_2022_CN; break;    /* ISO_2022_CN */
345         case 0x831: eTextEncoding = RTL_TEXTENCODING_ISO_2022_CN; break;    /* ISO_2022_CN_EXT */
346         /* !!! ISO_2022_KR = 0x840 */
347         /* EUC collections begin at 0x900 */
348         case 0x920: eTextEncoding = RTL_TEXTENCODING_EUC_JP; break;    /* EUC_JP - ISO 646,1-byte Katakana,JIS 208,JIS 212 */
349         case 0x930: eTextEncoding = RTL_TEXTENCODING_EUC_CN; break;    /* EUC_CN - ISO 646, GB 2312-80 */
350         case 0x931: eTextEncoding = RTL_TEXTENCODING_EUC_TW; break;    /* EUC_TW - ISO 646, CNS 11643-1992 Planes 1-16 */
351         case 0x940: eTextEncoding = RTL_TEXTENCODING_EUC_KR; break;    /* EUC_KR - ISO 646, KS C 5601-1987 */
352         /* Miscellaneous standards begin at 0xA00 */
353         case 0xA01: eTextEncoding = RTL_TEXTENCODING_SHIFT_JIS; break; /* ShiftJIS - plain Shift-JIS */
354         case 0xA02: eTextEncoding = RTL_TEXTENCODING_KOI8_R; break;    /* KOI8_R - Russian Internet standard */
355         case 0xA03: eTextEncoding = RTL_TEXTENCODING_BIG5; break;      /* Big5 - Big-5 */
356         /* !!! MacRomanLatin1 = 0xA04 */ /* Mac OS Roman permuted to align with 8859-1 */
357         /* !!! HZ_GB_2312 = 0xA05 */ /* HZ (RFC 1842, for Chinese mail & news) */
358         /* Other platform encodings */
359         /* !!! NextStepLatin = 0xB01 */ /* NextStep encoding */
360         /* EBCDIC & IBM host encodings begin at 0xC00 */
361         /* !!! EBCDIC_US = 0xC01 */ /* basic EBCDIC-US */
362         /* !!! EBCDIC_CP037 = 0xC02 */ /* code page 037, extended EBCDIC-US Latin1 */
363         /* Special value */
364         /* MultiRun = 0xFFF */ /* Multiple encoded text, external run info */
365         default:    eTextEncoding = RTL_TEXTENCODING_DONTKNOW; break;
366     };
367 
368     return eTextEncoding;
369 }
370 
371 #endif
372 
373 /* ----------------------------------------------------------------------- */
374 
375 rtl_TextEncoding SAL_CALL rtl_getTextEncodingFromUnixCharset( const sal_Char* pUnixCharset )
376 {
377     /* See <ftp://ftp.x.org/pub/DOCS/registry>, section 14 ("Font Charset
378      * (Registry and Encoding) Names").
379      */
380 
381     /* All Identifiers in the tables are lower case The function search */
382     /* for the first matching string in the tables. */
383     /* Sort order: unique (first 14, than 1), important */
384 
385     static ImplStrCharsetDef const aUnixCharsetISOTab[] =
386     {
387         { "15", RTL_TEXTENCODING_ISO_8859_15 },
388         { "14", RTL_TEXTENCODING_ISO_8859_14 },
389         { "13", RTL_TEXTENCODING_ISO_8859_13 },
390         { "11", RTL_TEXTENCODING_TIS_620 },
391         { "10", RTL_TEXTENCODING_ISO_8859_10 },
392         { "1", RTL_TEXTENCODING_ISO_8859_1 },
393         { "2", RTL_TEXTENCODING_ISO_8859_2 },
394         { "3", RTL_TEXTENCODING_ISO_8859_3 },
395         { "4", RTL_TEXTENCODING_ISO_8859_4 },
396         { "5", RTL_TEXTENCODING_ISO_8859_5 },
397         { "6", RTL_TEXTENCODING_ISO_8859_6 },
398         { "7", RTL_TEXTENCODING_ISO_8859_7 },
399         { "8", RTL_TEXTENCODING_ISO_8859_8 },
400         { "9", RTL_TEXTENCODING_ISO_8859_9 },
401         { NULL, RTL_TEXTENCODING_DONTKNOW }
402     };
403 
404     static ImplStrCharsetDef const aUnixCharsetADOBETab[] =
405     {
406         { "fontspecific", RTL_TEXTENCODING_SYMBOL },
407         { NULL, RTL_TEXTENCODING_DONTKNOW }
408     };
409 
410     static ImplStrCharsetDef const aUnixCharsetMSTab[] =
411     {
412         { "1252", RTL_TEXTENCODING_MS_1252 },
413         { "1250", RTL_TEXTENCODING_MS_1250 },
414         { "1251", RTL_TEXTENCODING_MS_1251 },
415         { "1253", RTL_TEXTENCODING_MS_1253 },
416         { "1254", RTL_TEXTENCODING_MS_1254 },
417         { "1255", RTL_TEXTENCODING_MS_1255 },
418         { "1256", RTL_TEXTENCODING_MS_1256 },
419         { "1257", RTL_TEXTENCODING_MS_1257 },
420         { "1258", RTL_TEXTENCODING_MS_1258 },
421         { "932", RTL_TEXTENCODING_MS_932 },
422         { "936", RTL_TEXTENCODING_MS_936 },
423         { "949", RTL_TEXTENCODING_MS_949 },
424         { "950", RTL_TEXTENCODING_MS_950 },
425         { "1361", RTL_TEXTENCODING_MS_1361 },
426         { "cp1252", RTL_TEXTENCODING_MS_1252 },
427         { "cp1250", RTL_TEXTENCODING_MS_1250 },
428         { "cp1251", RTL_TEXTENCODING_MS_1251 },
429         { "cp1253", RTL_TEXTENCODING_MS_1253 },
430         { "cp1254", RTL_TEXTENCODING_MS_1254 },
431         { "cp1255", RTL_TEXTENCODING_MS_1255 },
432         { "cp1256", RTL_TEXTENCODING_MS_1256 },
433         { "cp1257", RTL_TEXTENCODING_MS_1257 },
434         { "cp1258", RTL_TEXTENCODING_MS_1258 },
435         { "cp932", RTL_TEXTENCODING_MS_932 },
436         { "cp936", RTL_TEXTENCODING_MS_936 },
437         { "cp949", RTL_TEXTENCODING_MS_949 },
438         { "cp950", RTL_TEXTENCODING_MS_950 },
439         { "cp1361", RTL_TEXTENCODING_MS_1361 },
440         { NULL, RTL_TEXTENCODING_DONTKNOW }
441     };
442 
443     static ImplStrCharsetDef const aUnixCharsetIBMTab[] =
444     {
445         { "437", RTL_TEXTENCODING_IBM_437 },
446         { "850", RTL_TEXTENCODING_IBM_850 },
447         { "860", RTL_TEXTENCODING_IBM_860 },
448         { "861", RTL_TEXTENCODING_IBM_861 },
449         { "863", RTL_TEXTENCODING_IBM_863 },
450         { "865", RTL_TEXTENCODING_IBM_865 },
451         { "737", RTL_TEXTENCODING_IBM_737 },
452         { "775", RTL_TEXTENCODING_IBM_775 },
453         { "852", RTL_TEXTENCODING_IBM_852 },
454         { "855", RTL_TEXTENCODING_IBM_855 },
455         { "857", RTL_TEXTENCODING_IBM_857 },
456         { "862", RTL_TEXTENCODING_IBM_862 },
457         { "864", RTL_TEXTENCODING_IBM_864 },
458         { "866", RTL_TEXTENCODING_IBM_866 },
459         { "869", RTL_TEXTENCODING_IBM_869 },
460         { "874", RTL_TEXTENCODING_MS_874 },
461         { "1004", RTL_TEXTENCODING_MS_1252 },
462         { "65400", RTL_TEXTENCODING_SYMBOL },
463         { NULL, RTL_TEXTENCODING_DONTKNOW }
464     };
465 
466     static ImplStrCharsetDef const aUnixCharsetKOI8Tab[] =
467     {
468         { "r", RTL_TEXTENCODING_KOI8_R },
469         { "u", RTL_TEXTENCODING_KOI8_U },
470         { NULL, RTL_TEXTENCODING_DONTKNOW }
471     };
472 
473     static ImplStrCharsetDef aUnixCharsetJISX0208Tab[] =
474     {
475         { NULL, RTL_TEXTENCODING_JIS_X_0208 }
476     };
477 
478     static ImplStrCharsetDef aUnixCharsetJISX0201Tab[] =
479     {
480         { NULL, RTL_TEXTENCODING_JIS_X_0201 }
481     };
482 
483     static ImplStrCharsetDef aUnixCharsetJISX0212Tab[] =
484     {
485         { NULL, RTL_TEXTENCODING_JIS_X_0212 }
486     };
487 
488     static ImplStrCharsetDef aUnixCharsetGBTab[] =
489     {
490         { NULL, RTL_TEXTENCODING_GB_2312 }
491     };
492 
493     static ImplStrCharsetDef aUnixCharsetGBKTab[] =
494     {
495         { NULL, RTL_TEXTENCODING_GBK }
496     };
497 
498     static ImplStrCharsetDef aUnixCharsetBIG5Tab[] =
499     {
500         { NULL, RTL_TEXTENCODING_BIG5 }
501     };
502 
503     static ImplStrCharsetDef const aUnixCharsetKSC56011987Tab[] =
504     {
505         { NULL, RTL_TEXTENCODING_EUC_KR }
506     };
507 
508     static ImplStrCharsetDef const aUnixCharsetKSC56011992Tab[] =
509     {
510         { NULL, RTL_TEXTENCODING_MS_1361 }
511     };
512 
513     static ImplStrCharsetDef const aUnixCharsetISO10646Tab[] =
514     {
515         { NULL, RTL_TEXTENCODING_UNICODE }
516     };
517 
518     static ImplStrCharsetDef const aUnixCharsetUNICODETab[] =
519     {
520 /* Currently every Unicode Encoding is for us Unicode */
521 /*        { "fontspecific", RTL_TEXTENCODING_UNICODE }, */
522         { NULL, RTL_TEXTENCODING_UNICODE }
523     };
524 
525     static ImplStrCharsetDef const aUnixCharsetSymbolTab[] =
526     {
527         { NULL, RTL_TEXTENCODING_SYMBOL }
528     };
529 
530     /* See <http://cvs.freedesktop.org/xorg/xc/fonts/encodings/iso8859-11.enc?
531        rev=1.1.1.1>: */
532     static ImplStrCharsetDef const aUnixCharsetTIS620Tab[] =
533     {
534         { "0", RTL_TEXTENCODING_TIS_620 },
535         { "2529", RTL_TEXTENCODING_TIS_620 },
536         { "2533", RTL_TEXTENCODING_TIS_620 },
537         { NULL, RTL_TEXTENCODING_DONTKNOW }
538     };
539     static ImplStrCharsetDef const aUnixCharsetTIS6202529Tab[] =
540     {
541         { "1", RTL_TEXTENCODING_TIS_620 },
542         { NULL, RTL_TEXTENCODING_DONTKNOW }
543     };
544     static ImplStrCharsetDef const aUnixCharsetTIS6202533Tab[] =
545     {
546         { "0", RTL_TEXTENCODING_TIS_620 },
547         { "1", RTL_TEXTENCODING_TIS_620 },
548         { NULL, RTL_TEXTENCODING_DONTKNOW }
549     };
550 
551     static ImplStrFirstPartCharsetDef const aUnixCharsetFirstPartTab[] =
552     {
553         { "iso8859", aUnixCharsetISOTab },
554         { "adobe", aUnixCharsetADOBETab },
555         { "ansi", aUnixCharsetMSTab },
556         { "microsoft", aUnixCharsetMSTab },
557         { "ibm", aUnixCharsetIBMTab },
558         { "koi8", aUnixCharsetKOI8Tab },
559         { "jisx0208", aUnixCharsetJISX0208Tab },
560         { "jisx0208.1983", aUnixCharsetJISX0208Tab },
561         { "jisx0201", aUnixCharsetJISX0201Tab },
562         { "jisx0201.1976", aUnixCharsetJISX0201Tab },
563         { "jisx0212", aUnixCharsetJISX0212Tab },
564         { "jisx0212.1990", aUnixCharsetJISX0212Tab },
565         { "gb2312", aUnixCharsetGBTab },
566         { "gbk", aUnixCharsetGBKTab },
567         { "big5", aUnixCharsetBIG5Tab },
568         { "iso10646", aUnixCharsetISO10646Tab },
569 /*      { "unicode", aUnixCharsetUNICODETab }, */ /* fonts contain only default chars */
570         { "sunolcursor", aUnixCharsetSymbolTab },
571         { "sunolglyph", aUnixCharsetSymbolTab },
572         { "iso10646", aUnixCharsetUNICODETab },
573         { "ksc5601.1987", aUnixCharsetKSC56011987Tab },
574         { "ksc5601.1992", aUnixCharsetKSC56011992Tab },
575         { "tis620.2529", aUnixCharsetTIS6202529Tab },
576         { "tis620.2533", aUnixCharsetTIS6202533Tab },
577         { "tis620", aUnixCharsetTIS620Tab },
578 /*        { "sunudcja.1997",  },        */
579 /*        { "sunudcko.1997",  },        */
580 /*        { "sunudczh.1997",  },        */
581 /*        { "sunudczhtw.1997",  },      */
582         { NULL, NULL }
583     };
584 
585     rtl_TextEncoding    eEncoding = RTL_TEXTENCODING_DONTKNOW;
586     sal_Char*           pBuf;
587     sal_Char*           pTempBuf;
588     sal_uInt32          nBufLen = strlen( pUnixCharset )+1;
589     const sal_Char*     pFirstPart;
590     const sal_Char*     pSecondPart;
591 
592     /* Alloc Buffer and map to lower case */
593     pBuf = (char*)rtl_allocateMemory( nBufLen );
594     Impl_toAsciiLower( pUnixCharset, pBuf );
595 
596     /* Search FirstPart */
597     pFirstPart = pBuf;
598     pSecondPart = NULL;
599     pTempBuf = pBuf;
600     while ( *pTempBuf )
601     {
602         if ( *pTempBuf == '-' )
603         {
604             *pTempBuf = '\0';
605             pSecondPart = pTempBuf+1;
606             break;
607         }
608 
609         pTempBuf++;
610     }
611 
612     /* Parttrenner gefunden */
613     if ( pSecondPart )
614     {
615         /* Search for the part tab */
616         const ImplStrFirstPartCharsetDef* pFirstPartData = aUnixCharsetFirstPartTab;
617         while ( pFirstPartData->mpCharsetStr )
618         {
619             if ( Impl_matchString( pFirstPart, pFirstPartData->mpCharsetStr ) )
620             {
621                 /* Search for the charset in the second part tab */
622                 const ImplStrCharsetDef* pData = pFirstPartData->mpSecondPartTab;
623                 while ( pData->mpCharsetStr )
624                 {
625                     if ( Impl_matchString( pSecondPart, pData->mpCharsetStr ) )
626                     {
627                         eEncoding = pData->meTextEncoding;
628                         break;
629                     }
630 
631                     pData++;
632                 }
633 
634                 /* use default encoding for first part */
635                 eEncoding = pData->meTextEncoding;
636                 break;
637             }
638 
639             pFirstPartData++;
640         }
641     }
642 
643     rtl_freeMemory( pBuf );
644 
645     return eEncoding;
646 }
647 
648 /* ----------------------------------------------------------------------- */
649 
650 rtl_TextEncoding SAL_CALL rtl_getTextEncodingFromMimeCharset( const sal_Char* pMimeCharset )
651 {
652     /* All Identifiers are in lower case and contain only alphanumeric */
653     /* characters. The function search for the first equal string in */
654     /* the table. In this table are only the most used mime types. */
655     /* Sort order: important */
656     static ImplStrCharsetDef const aVIPMimeCharsetTab[] =
657     {
658         { "usascii", RTL_TEXTENCODING_ASCII_US },
659         { "utf8", RTL_TEXTENCODING_UTF8 },
660         { "utf7", RTL_TEXTENCODING_UTF7 },
661         { "iso88591", RTL_TEXTENCODING_ISO_8859_1 },
662         { "iso88592", RTL_TEXTENCODING_ISO_8859_2 },
663         { "iso88593", RTL_TEXTENCODING_ISO_8859_3 },
664         { "iso88594", RTL_TEXTENCODING_ISO_8859_4 },
665         { "iso88595", RTL_TEXTENCODING_ISO_8859_5 },
666         { "iso88596", RTL_TEXTENCODING_ISO_8859_6 },
667         { "iso88597", RTL_TEXTENCODING_ISO_8859_7 },
668         { "iso88598", RTL_TEXTENCODING_ISO_8859_8 },
669         { "iso88599", RTL_TEXTENCODING_ISO_8859_9 },
670         { "iso885910", RTL_TEXTENCODING_ISO_8859_10 },
671         { "iso885913", RTL_TEXTENCODING_ISO_8859_13 },
672         { "iso885914", RTL_TEXTENCODING_ISO_8859_14 },
673         { "iso885915", RTL_TEXTENCODING_ISO_8859_15 },
674         { "iso2022jp", RTL_TEXTENCODING_ISO_2022_JP },
675         { "iso2022jp2", RTL_TEXTENCODING_ISO_2022_JP },
676         { "iso2022cn", RTL_TEXTENCODING_ISO_2022_CN },
677         { "iso2022cnext", RTL_TEXTENCODING_ISO_2022_CN },
678         { "iso2022kr", RTL_TEXTENCODING_ISO_2022_KR },
679         { "eucjp", RTL_TEXTENCODING_EUC_JP },
680         { "shiftjis", RTL_TEXTENCODING_SHIFT_JIS },
681         { "mskanji", RTL_TEXTENCODING_MS_932 },
682         { "gb2312", RTL_TEXTENCODING_GB_2312 },
683         { "cngb", RTL_TEXTENCODING_GB_2312 },
684         { "big5", RTL_TEXTENCODING_BIG5 },
685         { "cnbig5", RTL_TEXTENCODING_BIG5 },
686         { "cngb12345", RTL_TEXTENCODING_GBT_12345 },
687         { "euckr", RTL_TEXTENCODING_EUC_KR },
688         { "koi8r", RTL_TEXTENCODING_KOI8_R },
689         { "windows1252", RTL_TEXTENCODING_MS_1252 },
690         { "windows1250", RTL_TEXTENCODING_MS_1250 },
691         { "windows1251", RTL_TEXTENCODING_MS_1251 },
692         { "windows1253", RTL_TEXTENCODING_MS_1253 },
693         { "windows1254", RTL_TEXTENCODING_MS_1254 },
694         { "windows1255", RTL_TEXTENCODING_MS_1255 },
695         { "windows1256", RTL_TEXTENCODING_MS_1256 },
696         { "windows1257", RTL_TEXTENCODING_MS_1257 },
697         { "windows1258", RTL_TEXTENCODING_MS_1258 },
698         { NULL, RTL_TEXTENCODING_DONTKNOW }
699     };
700 
701     /* All Identifiers are in lower case and contain only alphanumeric */
702     /* characters. The function search for the first matching string in */
703     /* the table. */
704     /* Sort order: unique (first iso885914, than iso88591), important */
705     static ImplStrCharsetDef const aMimeCharsetTab[] =
706     {
707         { "unicode11utf7", RTL_TEXTENCODING_UTF7 },
708         { "caunicode11utf7", RTL_TEXTENCODING_UTF7 },
709         { "iso88591windows30", RTL_TEXTENCODING_ISO_8859_1 },
710         { "iso88591win", RTL_TEXTENCODING_MS_1252 },
711         { "iso88592win", RTL_TEXTENCODING_MS_1250 },
712         { "iso88599win", RTL_TEXTENCODING_MS_1254 },
713         { "iso885915", RTL_TEXTENCODING_ISO_8859_15 },
714         { "iso885914", RTL_TEXTENCODING_ISO_8859_14 },
715         { "iso885913", RTL_TEXTENCODING_ISO_8859_13 },
716         { "iso885911", RTL_TEXTENCODING_TIS_620 },
717             /* This is no official MIME character set name, but it might be in
718                use in Thailand. */
719         { "iso885910", RTL_TEXTENCODING_ISO_8859_10 },
720         { "iso88591", RTL_TEXTENCODING_ISO_8859_1 },
721         { "iso88592", RTL_TEXTENCODING_ISO_8859_2 },
722         { "iso88593", RTL_TEXTENCODING_ISO_8859_3 },
723         { "iso88594", RTL_TEXTENCODING_ISO_8859_4 },
724         { "iso88595", RTL_TEXTENCODING_ISO_8859_5 },
725         { "iso88596", RTL_TEXTENCODING_ISO_8859_6 },
726         { "iso88597", RTL_TEXTENCODING_ISO_8859_7 },
727         { "iso88598", RTL_TEXTENCODING_ISO_8859_8 },
728         { "iso88599", RTL_TEXTENCODING_ISO_8859_9 },
729         { "isoir100", RTL_TEXTENCODING_ISO_8859_1 },
730         { "latin1", RTL_TEXTENCODING_ISO_8859_1 },
731         { "l1", RTL_TEXTENCODING_ISO_8859_1 },
732         { "cp819", RTL_TEXTENCODING_ISO_8859_1 },
733         { "ibm819", RTL_TEXTENCODING_ISO_8859_1 },
734         { "csisolatin1", RTL_TEXTENCODING_ISO_8859_1 },
735         { "isoir101", RTL_TEXTENCODING_ISO_8859_2 },
736         { "latin2", RTL_TEXTENCODING_ISO_8859_2 },
737         { "l2", RTL_TEXTENCODING_ISO_8859_2 },
738         { "csisolatin2", RTL_TEXTENCODING_ISO_8859_2 },
739         { "isoir109", RTL_TEXTENCODING_ISO_8859_3 },
740         { "latin3", RTL_TEXTENCODING_ISO_8859_3 },
741         { "l3", RTL_TEXTENCODING_ISO_8859_3 },
742         { "csisolatin3", RTL_TEXTENCODING_ISO_8859_3 },
743         { "isoir110", RTL_TEXTENCODING_ISO_8859_4 },
744         { "latin4", RTL_TEXTENCODING_ISO_8859_4 },
745         { "l4", RTL_TEXTENCODING_ISO_8859_4 },
746         { "csisolatin4", RTL_TEXTENCODING_ISO_8859_4 },
747         { "isoir144", RTL_TEXTENCODING_ISO_8859_5 },
748         { "cyrillicasian", RTL_TEXTENCODING_PT154 },
749         { "cyrillic", RTL_TEXTENCODING_ISO_8859_5 },
750         { "csisolatincyrillic", RTL_TEXTENCODING_ISO_8859_5 },
751         { "isoir127", RTL_TEXTENCODING_ISO_8859_6 },
752         { "arabic", RTL_TEXTENCODING_ISO_8859_6 },
753         { "csisolatinarabic", RTL_TEXTENCODING_ISO_8859_6 },
754         { "ecma114", RTL_TEXTENCODING_ISO_8859_6 },
755         { "asmo708", RTL_TEXTENCODING_ISO_8859_6 },
756         { "isoir126", RTL_TEXTENCODING_ISO_8859_7 },
757         { "greek", RTL_TEXTENCODING_ISO_8859_7 },
758         { "csisolatingreek", RTL_TEXTENCODING_ISO_8859_7 },
759         { "elot928", RTL_TEXTENCODING_ISO_8859_7 },
760         { "ecma118", RTL_TEXTENCODING_ISO_8859_7 },
761         { "isoir138", RTL_TEXTENCODING_ISO_8859_8 },
762         { "hebrew", RTL_TEXTENCODING_ISO_8859_8 },
763         { "csisolatinhebrew", RTL_TEXTENCODING_ISO_8859_8 },
764         { "isoir148", RTL_TEXTENCODING_ISO_8859_9 },
765         { "latin5", RTL_TEXTENCODING_ISO_8859_9 },
766         { "l5", RTL_TEXTENCODING_ISO_8859_9 },
767         { "csisolatin5", RTL_TEXTENCODING_ISO_8859_9 },
768         { "cswindows30latin1", RTL_TEXTENCODING_ISO_8859_1 },
769         { "cswindows30latin1", RTL_TEXTENCODING_ISO_8859_1 },
770         { "cswindows31latin1", RTL_TEXTENCODING_MS_1252 },
771         { "cswindows31latin2", RTL_TEXTENCODING_MS_1250 },
772         { "cswindows31latin5", RTL_TEXTENCODING_MS_1254 },
773         { "iso10646us", RTL_TEXTENCODING_ASCII_US },
774         { "iso646irv", RTL_TEXTENCODING_ASCII_US },
775         { "cskoi8r", RTL_TEXTENCODING_KOI8_R },
776         { "ibm437", RTL_TEXTENCODING_IBM_437 },
777         { "cp437", RTL_TEXTENCODING_IBM_437 },
778         { "437", RTL_TEXTENCODING_IBM_437 },
779         { "cspc8codepage437", RTL_TEXTENCODING_IBM_437 },
780         { "ansix34", RTL_TEXTENCODING_ASCII_US },
781         { "ibm367", RTL_TEXTENCODING_ASCII_US },
782         { "cp367", RTL_TEXTENCODING_ASCII_US },
783         { "csascii", RTL_TEXTENCODING_ASCII_US },
784         { "ibm775", RTL_TEXTENCODING_IBM_775 },
785         { "cp775", RTL_TEXTENCODING_IBM_775 },
786         { "cspc775baltic", RTL_TEXTENCODING_IBM_775 },
787         { "ibm850", RTL_TEXTENCODING_IBM_850 },
788         { "cp850", RTL_TEXTENCODING_IBM_850 },
789         { "850", RTL_TEXTENCODING_IBM_850 },
790         { "cspc850multilingual", RTL_TEXTENCODING_IBM_850 },
791 /*        { "ibm851", RTL_TEXTENCODING_IBM_851 }, */
792 /*        { "cp851", RTL_TEXTENCODING_IBM_851 }, */
793 /*        { "851", RTL_TEXTENCODING_IBM_851 }, */
794 /*        { "csibm851", RTL_TEXTENCODING_IBM_851 }, */
795         { "ibm852", RTL_TEXTENCODING_IBM_852 },
796         { "cp852", RTL_TEXTENCODING_IBM_852 },
797         { "852", RTL_TEXTENCODING_IBM_852 },
798         { "cspcp852", RTL_TEXTENCODING_IBM_852 },
799         { "ibm855", RTL_TEXTENCODING_IBM_855 },
800         { "cp855", RTL_TEXTENCODING_IBM_855 },
801         { "855", RTL_TEXTENCODING_IBM_855 },
802         { "csibm855", RTL_TEXTENCODING_IBM_855 },
803         { "ibm857", RTL_TEXTENCODING_IBM_857 },
804         { "cp857", RTL_TEXTENCODING_IBM_857 },
805         { "857", RTL_TEXTENCODING_IBM_857 },
806         { "csibm857", RTL_TEXTENCODING_IBM_857 },
807         { "ibm860", RTL_TEXTENCODING_IBM_860 },
808         { "cp860", RTL_TEXTENCODING_IBM_860 },
809         { "860", RTL_TEXTENCODING_IBM_860 },
810         { "csibm860", RTL_TEXTENCODING_IBM_860 },
811         { "ibm861", RTL_TEXTENCODING_IBM_861 },
812         { "cp861", RTL_TEXTENCODING_IBM_861 },
813         { "861", RTL_TEXTENCODING_IBM_861 },
814         { "csis", RTL_TEXTENCODING_IBM_861 },
815         { "csibm861", RTL_TEXTENCODING_IBM_861 },
816         { "ibm862", RTL_TEXTENCODING_IBM_862 },
817         { "cp862", RTL_TEXTENCODING_IBM_862 },
818         { "862", RTL_TEXTENCODING_IBM_862 },
819         { "cspc862latinhebrew", RTL_TEXTENCODING_IBM_862 },
820         { "ibm863", RTL_TEXTENCODING_IBM_863 },
821         { "cp863", RTL_TEXTENCODING_IBM_863 },
822         { "863", RTL_TEXTENCODING_IBM_863 },
823         { "csibm863", RTL_TEXTENCODING_IBM_863 },
824         { "ibm864", RTL_TEXTENCODING_IBM_864 },
825         { "cp864", RTL_TEXTENCODING_IBM_864 },
826         { "864", RTL_TEXTENCODING_IBM_864 },
827         { "csibm864", RTL_TEXTENCODING_IBM_864 },
828         { "ibm865", RTL_TEXTENCODING_IBM_865 },
829         { "cp865", RTL_TEXTENCODING_IBM_865 },
830         { "865", RTL_TEXTENCODING_IBM_865 },
831         { "csibm865", RTL_TEXTENCODING_IBM_865 },
832         { "ibm866", RTL_TEXTENCODING_IBM_866 },
833         { "cp866", RTL_TEXTENCODING_IBM_866 },
834         { "866", RTL_TEXTENCODING_IBM_866 },
835         { "csibm866", RTL_TEXTENCODING_IBM_866 },
836 /*        { "ibm868", RTL_TEXTENCODING_IBM_868 }, */
837 /*        { "cp868", RTL_TEXTENCODING_IBM_868 }, */
838 /*        { "cpar", RTL_TEXTENCODING_IBM_868 }, */
839 /*        { "csibm868", RTL_TEXTENCODING_IBM_868 }, */
840         { "ibm869", RTL_TEXTENCODING_IBM_869 },
841         { "cp869", RTL_TEXTENCODING_IBM_869 },
842         { "869", RTL_TEXTENCODING_IBM_869 },
843         { "cpgr", RTL_TEXTENCODING_IBM_869 },
844         { "csibm869", RTL_TEXTENCODING_IBM_869 },
845         { "ibm869", RTL_TEXTENCODING_IBM_869 },
846         { "cp869", RTL_TEXTENCODING_IBM_869 },
847         { "869", RTL_TEXTENCODING_IBM_869 },
848         { "cpgr", RTL_TEXTENCODING_IBM_869 },
849         { "csibm869", RTL_TEXTENCODING_IBM_869 },
850         { "mac", RTL_TEXTENCODING_APPLE_ROMAN },
851         { "csmacintosh", RTL_TEXTENCODING_APPLE_ROMAN },
852         { "shiftjis", RTL_TEXTENCODING_SHIFT_JIS },
853         { "mskanji", RTL_TEXTENCODING_MS_932 },
854         { "csshiftjis", RTL_TEXTENCODING_SHIFT_JIS },
855         { "jisx0208", RTL_TEXTENCODING_JIS_X_0208 },
856         { "jisc62261983", RTL_TEXTENCODING_JIS_X_0208 },
857         { "csiso87jisx0208", RTL_TEXTENCODING_JIS_X_0208 },
858         { "isoir86", RTL_TEXTENCODING_JIS_X_0208 },
859         { "x0208", RTL_TEXTENCODING_JIS_X_0208 },
860         { "jisx0201", RTL_TEXTENCODING_JIS_X_0201 },
861         { "cshalfwidthkatakana", RTL_TEXTENCODING_JIS_X_0201 },
862         { "x0201", RTL_TEXTENCODING_JIS_X_0201 },
863         { "jisx0212", RTL_TEXTENCODING_JIS_X_0212 },
864         { "csiso159jisx0212", RTL_TEXTENCODING_JIS_X_0212 },
865         { "isoir159", RTL_TEXTENCODING_JIS_X_0208 },
866         { "x0212", RTL_TEXTENCODING_JIS_X_0212 },
867         { "isoir6", RTL_TEXTENCODING_ASCII_US },
868         { "xsjis", RTL_TEXTENCODING_SHIFT_JIS },
869         { "sjis", RTL_TEXTENCODING_SHIFT_JIS },
870         { "ascii", RTL_TEXTENCODING_ASCII_US },
871         { "us", RTL_TEXTENCODING_ASCII_US },
872         { "gb180302000", RTL_TEXTENCODING_GB_18030 },
873             /* This is no actual MIME character set name, it is only in here
874                for backwards compatibility (before "GB18030" was officially
875                registered with IANA, this code contained some guesses of what
876                would become official names for GB18030). */
877         { "gb18030", RTL_TEXTENCODING_GB_18030 },
878         { "big5hkscs", RTL_TEXTENCODING_BIG5_HKSCS },
879         { "tis620", RTL_TEXTENCODING_TIS_620 },
880         { "gbk", RTL_TEXTENCODING_GBK },
881         { "cp936", RTL_TEXTENCODING_GBK },
882         { "ms936", RTL_TEXTENCODING_GBK },
883         { "windows936", RTL_TEXTENCODING_GBK },
884         { "cp874", RTL_TEXTENCODING_MS_874 },
885             /* This is no official MIME character set name, but it might be in
886                use in Thailand. */
887         { "ms874", RTL_TEXTENCODING_MS_874 },
888             /* This is no official MIME character set name, but it might be in
889                use in Thailand. */
890         { "windows874", RTL_TEXTENCODING_MS_874 },
891             /* This is no official MIME character set name, but it might be in
892                use in Thailand. */
893         { "koi8u", RTL_TEXTENCODING_KOI8_U },
894         { "cpis", RTL_TEXTENCODING_IBM_861 },
895         { "ksc56011987", RTL_TEXTENCODING_MS_949 },
896         { "isoir149", RTL_TEXTENCODING_MS_949 },
897         { "ksc56011989", RTL_TEXTENCODING_MS_949 },
898         { "ksc5601", RTL_TEXTENCODING_MS_949 },
899         { "korean", RTL_TEXTENCODING_MS_949 },
900         { "csksc56011987", RTL_TEXTENCODING_MS_949 },
901             /* Map KS_C_5601-1987 and aliases to MS-949 instead of EUC-KR, as
902                this character set identifier seems to be prominently used by MS
903                to stand for KS C 5601 plus MS-949 extensions */
904         { "latin9", RTL_TEXTENCODING_ISO_8859_15 },
905         { "adobestandardencoding", RTL_TEXTENCODING_ADOBE_STANDARD },
906         { "csadobestandardencoding", RTL_TEXTENCODING_ADOBE_STANDARD },
907         { "adobesymbolencoding", RTL_TEXTENCODING_ADOBE_SYMBOL },
908         { "cshppsmath", RTL_TEXTENCODING_ADOBE_SYMBOL },
909         { "ptcp154", RTL_TEXTENCODING_PT154 },
910         { "csptcp154", RTL_TEXTENCODING_PT154 },
911         { "pt154", RTL_TEXTENCODING_PT154 },
912         { "cp154", RTL_TEXTENCODING_PT154 },
913         { "xisciide", RTL_TEXTENCODING_ISCII_DEVANAGARI },
914             /* This is no official MIME character set name, but is in use by
915                various windows APIs. */
916         { NULL, RTL_TEXTENCODING_DONTKNOW }
917     };
918 
919     rtl_TextEncoding            eEncoding = RTL_TEXTENCODING_DONTKNOW;
920     sal_Char*                   pBuf;
921     const ImplStrCharsetDef*    pData = aVIPMimeCharsetTab;
922     sal_uInt32                  nBufLen = strlen( pMimeCharset )+1;
923 
924     /* Alloc Buffer and map to lower case and remove non alphanumeric chars */
925     pBuf = (char*)rtl_allocateMemory( nBufLen );
926     Impl_toAsciiLowerAndRemoveNonAlphanumeric( pMimeCharset, pBuf );
927 
928     /* Search for equal in the VIP table */
929     while ( pData->mpCharsetStr )
930     {
931         if ( strcmp( pBuf, pData->mpCharsetStr ) == 0 )
932         {
933             eEncoding = pData->meTextEncoding;
934             break;
935         }
936 
937         pData++;
938     }
939 
940     /* Search for matching in the mime table */
941     if ( eEncoding == RTL_TEXTENCODING_DONTKNOW )
942     {
943         pData = aMimeCharsetTab;
944         while ( pData->mpCharsetStr )
945         {
946             if ( Impl_matchString( pBuf, pData->mpCharsetStr ) )
947             {
948                 eEncoding = pData->meTextEncoding;
949                 break;
950             }
951 
952             pData++;
953         }
954     }
955 
956     rtl_freeMemory( pBuf );
957 
958     return eEncoding;
959 }
960 
961 /* ======================================================================= */
962 
963 sal_uInt8 SAL_CALL rtl_getBestWindowsCharsetFromTextEncoding( rtl_TextEncoding eTextEncoding )
964 {
965     const ImplTextEncodingData* pData = Impl_getTextEncodingData( eTextEncoding );
966     if ( pData )
967         return pData->mnBestWindowsCharset;
968     else
969         return 1;
970 }
971 
972 /* ----------------------------------------------------------------------- */
973 
974 const sal_Char* SAL_CALL rtl_getBestUnixCharsetFromTextEncoding( rtl_TextEncoding eTextEncoding  )
975 {
976     const ImplTextEncodingData* pData = Impl_getTextEncodingData( eTextEncoding );
977     if ( pData )
978         return (sal_Char const *) pData->mpBestUnixCharset;
979     else if( eTextEncoding == RTL_TEXTENCODING_UNICODE )
980         return (sal_Char const *) "iso10646-1";
981     else
982         return 0;
983 }
984 
985 /* ----------------------------------------------------------------------- */
986 
987 char const * SAL_CALL rtl_getMimeCharsetFromTextEncoding(rtl_TextEncoding
988                                                              nEncoding)
989 {
990     ImplTextEncodingData const * p = Impl_getTextEncodingData(nEncoding);
991     return p && (p->mnInfoFlags & RTL_TEXTENCODING_INFO_MIME) != 0 ?
992                p->mpBestMimeCharset : NULL;
993 }
994 
995 const sal_Char* SAL_CALL rtl_getBestMimeCharsetFromTextEncoding( rtl_TextEncoding eTextEncoding )
996 {
997     const ImplTextEncodingData* pData = Impl_getTextEncodingData( eTextEncoding );
998     if ( pData )
999         return (sal_Char const *) pData->mpBestMimeCharset;
1000     else
1001         return 0;
1002 }
1003 
1004 /* The following two functions are based on <http://www.sharmahd.com/tm/
1005    codepages.html>, <http://msdn.microsoft.com/workshop/author/dhtml/reference/
1006    charsets/charset4.asp>, and <http://www.iana.org/assignments/character-sets>.
1007  */
1008 
1009 rtl_TextEncoding SAL_CALL
1010 rtl_getTextEncodingFromWindowsCodePage(sal_uInt32 nCodePage)
1011 {
1012     switch (nCodePage)
1013     {
1014     case 437: return RTL_TEXTENCODING_IBM_437;
1015     case 708: return RTL_TEXTENCODING_ISO_8859_6;
1016     case 737: return RTL_TEXTENCODING_IBM_737;
1017     case 775: return RTL_TEXTENCODING_IBM_775;
1018     case 850: return RTL_TEXTENCODING_IBM_850;
1019     case 852: return RTL_TEXTENCODING_IBM_852;
1020     case 855: return RTL_TEXTENCODING_IBM_855;
1021     case 857: return RTL_TEXTENCODING_IBM_857;
1022     case 860: return RTL_TEXTENCODING_IBM_860;
1023     case 861: return RTL_TEXTENCODING_IBM_861;
1024     case 862: return RTL_TEXTENCODING_IBM_862;
1025     case 863: return RTL_TEXTENCODING_IBM_863;
1026     case 864: return RTL_TEXTENCODING_IBM_864;
1027     case 865: return RTL_TEXTENCODING_IBM_865;
1028     case 866: return RTL_TEXTENCODING_IBM_866;
1029     case 869: return RTL_TEXTENCODING_IBM_869;
1030     case 874: return RTL_TEXTENCODING_MS_874;
1031     case 932: return RTL_TEXTENCODING_MS_932;
1032     case 936: return RTL_TEXTENCODING_MS_936;
1033     case 949: return RTL_TEXTENCODING_MS_949;
1034     case 950: return RTL_TEXTENCODING_MS_950;
1035     case 1250: return RTL_TEXTENCODING_MS_1250;
1036     case 1251: return RTL_TEXTENCODING_MS_1251;
1037     case 1252: return RTL_TEXTENCODING_MS_1252;
1038     case 1253: return RTL_TEXTENCODING_MS_1253;
1039     case 1254: return RTL_TEXTENCODING_MS_1254;
1040     case 1255: return RTL_TEXTENCODING_MS_1255;
1041     case 1256: return RTL_TEXTENCODING_MS_1256;
1042     case 1257: return RTL_TEXTENCODING_MS_1257;
1043     case 1258: return RTL_TEXTENCODING_MS_1258;
1044     case 1361: return RTL_TEXTENCODING_MS_1361;
1045     case 10000: return RTL_TEXTENCODING_APPLE_ROMAN;
1046     case 10001: return RTL_TEXTENCODING_APPLE_JAPANESE;
1047     case 10002: return RTL_TEXTENCODING_APPLE_CHINTRAD;
1048     case 10003: return RTL_TEXTENCODING_APPLE_KOREAN;
1049     case 10004: return RTL_TEXTENCODING_APPLE_ARABIC;
1050     case 10005: return RTL_TEXTENCODING_APPLE_HEBREW;
1051     case 10006: return RTL_TEXTENCODING_APPLE_GREEK;
1052     case 10007: return RTL_TEXTENCODING_APPLE_CYRILLIC;
1053     case 10008: return RTL_TEXTENCODING_APPLE_CHINSIMP;
1054     case 10010: return RTL_TEXTENCODING_APPLE_ROMANIAN;
1055     case 10017: return RTL_TEXTENCODING_APPLE_UKRAINIAN;
1056     case 10029: return RTL_TEXTENCODING_APPLE_CENTEURO;
1057     case 10079: return RTL_TEXTENCODING_APPLE_ICELAND;
1058     case 10081: return RTL_TEXTENCODING_APPLE_TURKISH;
1059     case 10082: return RTL_TEXTENCODING_APPLE_CROATIAN;
1060     case 20127: return RTL_TEXTENCODING_ASCII_US;
1061     case 20866: return RTL_TEXTENCODING_KOI8_R;
1062     case 21866: return RTL_TEXTENCODING_KOI8_U;
1063     case 28591: return RTL_TEXTENCODING_ISO_8859_1;
1064     case 28592: return RTL_TEXTENCODING_ISO_8859_2;
1065     case 28593: return RTL_TEXTENCODING_ISO_8859_3;
1066     case 28594: return RTL_TEXTENCODING_ISO_8859_4;
1067     case 28595: return RTL_TEXTENCODING_ISO_8859_5;
1068     case 28596: return RTL_TEXTENCODING_ISO_8859_6;
1069     case 28597: return RTL_TEXTENCODING_ISO_8859_7;
1070     case 28598: return RTL_TEXTENCODING_ISO_8859_8;
1071     case 28599: return RTL_TEXTENCODING_ISO_8859_9;
1072     case 28605: return RTL_TEXTENCODING_ISO_8859_15;
1073     case 50220: return RTL_TEXTENCODING_ISO_2022_JP;
1074     case 50225: return RTL_TEXTENCODING_ISO_2022_KR;
1075     case 51932: return RTL_TEXTENCODING_EUC_JP;
1076     case 51936: return RTL_TEXTENCODING_EUC_CN;
1077     case 51949: return RTL_TEXTENCODING_EUC_KR;
1078     case 57002: return RTL_TEXTENCODING_ISCII_DEVANAGARI;
1079     case 65000: return RTL_TEXTENCODING_UTF7;
1080     case 65001: return RTL_TEXTENCODING_UTF8;
1081     default: return RTL_TEXTENCODING_DONTKNOW;
1082     }
1083 }
1084 
1085 sal_uInt32 SAL_CALL
1086 rtl_getWindowsCodePageFromTextEncoding(rtl_TextEncoding nEncoding)
1087 {
1088     switch (nEncoding)
1089     {
1090     case RTL_TEXTENCODING_IBM_437: return 437;
1091  /* case RTL_TEXTENCODING_ISO_8859_6: return 708; */
1092     case RTL_TEXTENCODING_IBM_737: return 737;
1093     case RTL_TEXTENCODING_IBM_775: return 775;
1094     case RTL_TEXTENCODING_IBM_850: return 850;
1095     case RTL_TEXTENCODING_IBM_852: return 852;
1096     case RTL_TEXTENCODING_IBM_855: return 855;
1097     case RTL_TEXTENCODING_IBM_857: return 857;
1098     case RTL_TEXTENCODING_IBM_860: return 860;
1099     case RTL_TEXTENCODING_IBM_861: return 861;
1100     case RTL_TEXTENCODING_IBM_862: return 862;
1101     case RTL_TEXTENCODING_IBM_863: return 863;
1102     case RTL_TEXTENCODING_IBM_864: return 864;
1103     case RTL_TEXTENCODING_IBM_865: return 865;
1104     case RTL_TEXTENCODING_IBM_866: return 866;
1105     case RTL_TEXTENCODING_IBM_869: return 869;
1106     case RTL_TEXTENCODING_MS_874: return 874;
1107     case RTL_TEXTENCODING_MS_932: return 932;
1108     case RTL_TEXTENCODING_MS_936: return 936;
1109     case RTL_TEXTENCODING_MS_949: return 949;
1110     case RTL_TEXTENCODING_MS_950: return 950;
1111     case RTL_TEXTENCODING_MS_1250: return 1250;
1112     case RTL_TEXTENCODING_MS_1251: return 1251;
1113     case RTL_TEXTENCODING_MS_1252: return 1252;
1114     case RTL_TEXTENCODING_MS_1253: return 1253;
1115     case RTL_TEXTENCODING_MS_1254: return 1254;
1116     case RTL_TEXTENCODING_MS_1255: return 1255;
1117     case RTL_TEXTENCODING_MS_1256: return 1256;
1118     case RTL_TEXTENCODING_MS_1257: return 1257;
1119     case RTL_TEXTENCODING_MS_1258: return 1258;
1120     case RTL_TEXTENCODING_MS_1361: return 1361;
1121     case RTL_TEXTENCODING_APPLE_ROMAN: return 10000;
1122     case RTL_TEXTENCODING_APPLE_JAPANESE: return 10001;
1123     case RTL_TEXTENCODING_APPLE_CHINTRAD: return 10002;
1124     case RTL_TEXTENCODING_APPLE_KOREAN: return 10003;
1125     case RTL_TEXTENCODING_APPLE_ARABIC: return 10004;
1126     case RTL_TEXTENCODING_APPLE_HEBREW: return 10005;
1127     case RTL_TEXTENCODING_APPLE_GREEK: return 10006;
1128     case RTL_TEXTENCODING_APPLE_CYRILLIC: return 10007;
1129     case RTL_TEXTENCODING_APPLE_CHINSIMP: return 10008;
1130     case RTL_TEXTENCODING_APPLE_ROMANIAN: return 10010;
1131     case RTL_TEXTENCODING_APPLE_UKRAINIAN: return 10017;
1132     case RTL_TEXTENCODING_APPLE_CENTEURO: return 10029;
1133     case RTL_TEXTENCODING_APPLE_ICELAND: return 10079;
1134     case RTL_TEXTENCODING_APPLE_TURKISH: return 10081;
1135     case RTL_TEXTENCODING_APPLE_CROATIAN: return 10082;
1136     case RTL_TEXTENCODING_ASCII_US: return 20127;
1137     case RTL_TEXTENCODING_KOI8_R: return 20866;
1138     case RTL_TEXTENCODING_KOI8_U: return 21866;
1139     case RTL_TEXTENCODING_ISO_8859_1: return 28591;
1140     case RTL_TEXTENCODING_ISO_8859_2: return 28592;
1141     case RTL_TEXTENCODING_ISO_8859_3: return 28593;
1142     case RTL_TEXTENCODING_ISO_8859_4: return 28594;
1143     case RTL_TEXTENCODING_ISO_8859_5: return 28595;
1144     case RTL_TEXTENCODING_ISO_8859_6: return 28596;
1145     case RTL_TEXTENCODING_ISO_8859_7: return 28597;
1146     case RTL_TEXTENCODING_ISO_8859_8: return 28598;
1147     case RTL_TEXTENCODING_ISO_8859_9: return 28599;
1148     case RTL_TEXTENCODING_ISO_8859_15: return 28605;
1149     case RTL_TEXTENCODING_ISO_2022_JP: return 50220;
1150     case RTL_TEXTENCODING_ISO_2022_KR: return 50225;
1151     case RTL_TEXTENCODING_EUC_JP: return 51932;
1152     case RTL_TEXTENCODING_EUC_CN: return 51936;
1153     case RTL_TEXTENCODING_EUC_KR: return 51949;
1154     case RTL_TEXTENCODING_ISCII_DEVANAGARI: return 57002;
1155     case RTL_TEXTENCODING_UTF7: return 65000;
1156     case RTL_TEXTENCODING_UTF8: return 65001;
1157     default: return 0;
1158     }
1159 }
1160