?  search:
summary | log | graphiclog1 | graphiclog2 | commit | commitdiff | tree | refs | edit | fork
blame | history | raw | HEAD
Version 3.6.0.2, tag libreoffice-3.6.0.2
[LibreOffice.git] / i18npool / source / isolang / isolang.cxx
blob05090796510abf3af832f9445334dedb4e3bfc14
1 /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
2 /*************************************************************************
3 *
4 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
5 *
6 * Copyright 2000, 2010 Oracle and/or its affiliates.
7 *
8 * OpenOffice.org - a multi-platform office productivity suite
9 *
10 * This file is part of OpenOffice.org.
11 *
12 * OpenOffice.org is free software: you can redistribute it and/or modify
13 * it under the terms of the GNU Lesser General Public License version 3
14 * only, as published by the Free Software Foundation.
15 *
16 * OpenOffice.org is distributed in the hope that it will be useful,
17 * but WITHOUT ANY WARRANTY; without even the implied warranty of
18 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19 * GNU Lesser General Public License version 3 for more details
20 * (a copy is included in the LICENSE file that accompanied this code).
21 *
22 * You should have received a copy of the GNU Lesser General Public License
23 * version 3 along with OpenOffice.org. If not, see
24 * <http://www.openoffice.org/license.html>
25 * for a copy of the LGPLv3 License.
26 *
27 ************************************************************************/
28
29 #include <rtl/ustring.hxx>
30 #include <rtl/string.hxx>
31 #include <rtl/ustrbuf.hxx>
32 #include <rtl/strbuf.hxx>
33
34 #include "i18npool/mslangid.hxx"
35
36 // =======================================================================
37
38 struct IsoLangEngEntry
39 {
40 LanguageType mnLang;
41 sal_Char maCountry[3];
42 };
43
44 struct IsoLangNoneStdEntry
45 {
46 LanguageType mnLang;
47 sal_Char maLangStr[4];
48 sal_Char maCountry[9];
49 };
50
51 struct IsoLangOtherEntry
52 {
53 LanguageType mnLang;
54 const sal_Char* mpLangStr;
55 };
56
57 // -----------------------------------------------------------------------
58
59 // Entries for languages are lower case, for countries upper case, as
60 // recommended by rfc4646 (obsoletes rfc3066 (obsoletes rfc1766)).
61 // convertIsoNamesToLanguage() is case insensitive
62 //
63 // Sort order: Most used first.
64 //
65 // The default entry for a LangID <-> ISO mapping has to be first. For
66 // conversion of legacy mappings one LangID can map to multiple ISO codes, and
67 // one ISO code combination can map to multiple LangIDs. For compatibility with
68 // already existing calls it can also be a sequence as follows:
69
70 // LANGUAGE_ENGLISH, "en", ""
71 // LANGUAGE_ENGLISH_US, "en", "US"
72
73 // Here, in a convertIsoNamesToLanguage() call "en-US" is converted to
74 // LANGUAGE_ENGLISH_US and "en" is converted to LANGUAGE_ENGLISH. A call with
75 // "en-ZZ" (not in table) would result in LANGUAGE_ENGLISH because the first
76 // entry matching the language and not having a country is returned, regardless
77 // of whether being sorted before or after other entries of the same language
78 // with some country. To obtain a _locale_ (not language only) in the order
79 // given, convertLocaleToLanguageWithFallback() must be called.
80
81 // If the sequence instead was
82
83 // LANGUAGE_ENGLISH_US, "en", "US"
84 // LANGUAGE_ENGLISH, "en", ""
85
86 // in a convertIsoNamesToLanguage() call "en-US" is still converted to
87 // LANGUAGE_ENGLISH_US, but "en" is _also_ converted to LANGUAGE_ENGLISH_US
88 // because no country was passed and it is the first entry to match the
89 // language, see code. A call with "en-ZZ" (not in table) would still result in
90 // LANGUAGE_ENGLISH.
91
92 /* erAck: 2007-07-05T20:01+0200 TODO: The entire suite's "primary language
93 * only" usage and locale fall back should be cleaned up and made consistent. I
94 * strongly doubt that most callers exactly expect the behavior described.
95 * Currently these primary LangIDs are used literally in OOo code:
96 * LANGUAGE_ENGLISH LANGUAGE_CHINESE LANGUAGE_MALAY
97 * LANGUAGE_AZERI LANGUAGE_URDU LANGUAGE_KASHMIRI
98 */
99
100 static MsLangId::IsoLangEntry const aImplIsoLangEntries[] =
101 {
102 // MS-LANGID codes ISO639-1/2/3 ISO3166
103 { LANGUAGE_ENGLISH, "en", "" },
104 { LANGUAGE_ENGLISH_US, "en", "US" },
105 { LANGUAGE_ENGLISH_UK, "en", "GB" },
106 { LANGUAGE_ENGLISH_AUS, "en", "AU" },
107 { LANGUAGE_ENGLISH_CAN, "en", "CA" },
108 { LANGUAGE_FRENCH, "fr", "FR" },
109 { LANGUAGE_FRENCH, "fr", "" },
110 { LANGUAGE_GERMAN, "de", "DE" },
111 { LANGUAGE_ITALIAN, "it", "IT" },
112 { LANGUAGE_DUTCH, "nl", "NL" },
113 { LANGUAGE_SPANISH_MODERN, "es", "ES" },
114 { LANGUAGE_SPANISH_DATED, "es", "ES" },
115 { LANGUAGE_PORTUGUESE, "pt", "PT" },
116 { LANGUAGE_PORTUGUESE_BRAZILIAN, "pt", "BR" },
117 { LANGUAGE_DANISH, "da", "DK" },
118 { LANGUAGE_GREEK, "el", "GR" },
119 { LANGUAGE_CHINESE, "zh", "" },
120 { LANGUAGE_CHINESE_SIMPLIFIED, "zh", "CN" },
121 { LANGUAGE_CHINESE_TRADITIONAL, "zh", "TW" },
122 { LANGUAGE_CHINESE_HONGKONG, "zh", "HK" },
123 { LANGUAGE_CHINESE_SINGAPORE, "zh", "SG" },
124 { LANGUAGE_CHINESE_MACAU, "zh", "MO" },
125 { LANGUAGE_ENGLISH_HONG_KONG_SAR, "en", "HK" },
126 { LANGUAGE_JAPANESE, "ja", "JP" },
127 { LANGUAGE_KOREAN, "ko", "KR" },
128 { LANGUAGE_KOREAN_JOHAB, "ko", "KR" },
129 { LANGUAGE_USER_KOREAN_NORTH, "ko", "KP" },
130 { LANGUAGE_SWEDISH, "sv", "SE" },
131 { LANGUAGE_SWEDISH_FINLAND, "sv", "FI" },
132 { LANGUAGE_FINNISH, "fi", "FI" },
133 { LANGUAGE_RUSSIAN, "ru", "RU" },
134 { LANGUAGE_TATAR, "tt", "RU" },
135 { LANGUAGE_ENGLISH_NZ, "en", "NZ" },
136 { LANGUAGE_ENGLISH_EIRE, "en", "IE" },
137 { LANGUAGE_DUTCH_BELGIAN, "nl", "BE" },
138 { LANGUAGE_FRENCH_BELGIAN, "fr", "BE" },
139 { LANGUAGE_FRENCH_CANADIAN, "fr", "CA" },
140 { LANGUAGE_FRENCH_SWISS, "fr", "CH" },
141 { LANGUAGE_GERMAN_SWISS, "de", "CH" },
142 { LANGUAGE_GERMAN_AUSTRIAN, "de", "AT" },
143 { LANGUAGE_ITALIAN_SWISS, "it", "CH" },
144 { LANGUAGE_ALBANIAN, "sq", "AL" },
145 { LANGUAGE_ARABIC_SAUDI_ARABIA, "ar", "SA" },
146 { LANGUAGE_ARABIC_EGYPT, "ar", "EG" },
147 { LANGUAGE_ARABIC_UAE, "ar", "AE" },
148 { LANGUAGE_ARABIC_IRAQ, "ar", "IQ" },
149 { LANGUAGE_ARABIC_LIBYA, "ar", "LY" },
150 { LANGUAGE_ARABIC_ALGERIA, "ar", "DZ" },
151 { LANGUAGE_ARABIC_MOROCCO, "ar", "MA" },
152 { LANGUAGE_ARABIC_TUNISIA, "ar", "TN" },
153 { LANGUAGE_ARABIC_OMAN, "ar", "OM" },
154 { LANGUAGE_ARABIC_YEMEN, "ar", "YE" },
155 { LANGUAGE_ARABIC_SYRIA, "ar", "SY" },
156 { LANGUAGE_ARABIC_JORDAN, "ar", "JO" },
157 { LANGUAGE_ARABIC_LEBANON, "ar", "LB" },
158 { LANGUAGE_ARABIC_KUWAIT, "ar", "KW" },
159 { LANGUAGE_ARABIC_BAHRAIN, "ar", "BH" },
160 { LANGUAGE_ARABIC_QATAR, "ar", "QA" },
161 { LANGUAGE_USER_ARABIC_CHAD, "ar", "TD" },
162 { LANGUAGE_USER_ARABIC_COMOROS, "ar", "KM" },
163 { LANGUAGE_USER_ARABIC_DJIBOUTI, "ar", "DJ" },
164 { LANGUAGE_USER_ARABIC_ERITREA, "ar", "ER" },
165 { LANGUAGE_USER_ARABIC_ISRAEL, "ar", "IL" },
166 { LANGUAGE_USER_ARABIC_MAURITANIA, "ar", "MR" },
167 { LANGUAGE_USER_ARABIC_PALESTINE, "ar", "PS" },
168 { LANGUAGE_USER_ARABIC_SOMALIA, "ar", "SO" },
169 { LANGUAGE_USER_ARABIC_SUDAN, "ar", "SD" },
170 { LANGUAGE_ARABIC_PRIMARY_ONLY, "ar", "" },
171 { LANGUAGE_BASQUE, "eu", "" },
172 { LANGUAGE_BULGARIAN, "bg", "BG" },
173 { LANGUAGE_CZECH, "cs", "CZ" },
174 { LANGUAGE_CZECH, "cz", "" },
175 { LANGUAGE_ENGLISH_JAMAICA, "en", "JM" },
176 { LANGUAGE_ENGLISH_CARRIBEAN, "en", "BS" }, // not 100%, because AG is Bahamas
177 { LANGUAGE_ENGLISH_BELIZE, "en", "BZ" },
178 { LANGUAGE_ENGLISH_TRINIDAD, "en", "TT" },
179 { LANGUAGE_ENGLISH_ZIMBABWE, "en", "ZW" },
180 { LANGUAGE_ENGLISH_INDONESIA, "en", "ID" },
181 { LANGUAGE_ESTONIAN, "et", "EE" },
182 { LANGUAGE_FAEROESE, "fo", "FO" },
183 { LANGUAGE_FARSI, "fa", "IR" },
184 { LANGUAGE_FRENCH_LUXEMBOURG, "fr", "LU" },
185 { LANGUAGE_FRENCH_MONACO, "fr", "MC" },
186 { LANGUAGE_GERMAN_LUXEMBOURG, "de", "LU" },
187 { LANGUAGE_GERMAN_LIECHTENSTEIN, "de", "LI" },
188 { LANGUAGE_HEBREW, "he", "IL" }, // new: old was "iw"
189 { LANGUAGE_HEBREW, "iw", "IL" }, // old: new is "he"
190 { LANGUAGE_HUNGARIAN, "hu", "HU" },
191 { LANGUAGE_ICELANDIC, "is", "IS" },
192 { LANGUAGE_INDONESIAN, "id", "ID" }, // new: old was "in"
193 { LANGUAGE_INDONESIAN, "in", "ID" }, // old: new is "id"
194 { LANGUAGE_NORWEGIAN, "no", "NO" },
195 { LANGUAGE_NORWEGIAN_BOKMAL, "nb", "NO" },
196 { LANGUAGE_NORWEGIAN_NYNORSK, "nn", "NO" },
197 { LANGUAGE_POLISH, "pl", "PL" },
198 { LANGUAGE_RHAETO_ROMAN, "rm", "CH" },
199 { LANGUAGE_ROMANIAN, "ro", "RO" },
200 { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD" },
201 { LANGUAGE_SLOVAK, "sk", "SK" },
202 { LANGUAGE_SLOVENIAN, "sl", "SI" },
203 { LANGUAGE_SPANISH_MEXICAN, "es", "MX" },
204 { LANGUAGE_SPANISH_GUATEMALA, "es", "GT" },
205 { LANGUAGE_SPANISH_COSTARICA, "es", "CR" },
206 { LANGUAGE_SPANISH_PANAMA, "es", "PA" },
207 { LANGUAGE_SPANISH_DOMINICAN_REPUBLIC, "es", "DO" },
208 { LANGUAGE_SPANISH_VENEZUELA, "es", "VE" },
209 { LANGUAGE_SPANISH_COLOMBIA, "es", "CO" },
210 { LANGUAGE_SPANISH_PERU, "es", "PE" },
211 { LANGUAGE_SPANISH_ARGENTINA, "es", "AR" },
212 { LANGUAGE_SPANISH_ECUADOR, "es", "EC" },
213 { LANGUAGE_SPANISH_CHILE, "es", "CL" },
214 { LANGUAGE_SPANISH_URUGUAY, "es", "UY" },
215 { LANGUAGE_SPANISH_PARAGUAY, "es", "PY" },
216 { LANGUAGE_SPANISH_BOLIVIA, "es", "BO" },
217 { LANGUAGE_SPANISH_EL_SALVADOR, "es", "SV" },
218 { LANGUAGE_SPANISH_HONDURAS, "es", "HN" },
219 { LANGUAGE_SPANISH_NICARAGUA, "es", "NI" },
220 { LANGUAGE_SPANISH_PUERTO_RICO, "es", "PR" },
221 { LANGUAGE_SPANISH_UNITED_STATES, "es", "US" },
222 { LANGUAGE_SPANISH_LATIN_AMERICA, "es", "" },
223 { LANGUAGE_TURKISH, "tr", "TR" },
224 { LANGUAGE_UKRAINIAN, "uk", "UA" },
225 { LANGUAGE_VIETNAMESE, "vi", "VN" },
226 { LANGUAGE_LATVIAN, "lv", "LV" },
227 { LANGUAGE_MACEDONIAN, "mk", "MK" },
228 { LANGUAGE_MALAY, "ms", "" },
229 { LANGUAGE_MALAY_MALAYSIA, "ms", "MY" },
230 { LANGUAGE_MALAY_BRUNEI_DARUSSALAM, "ms", "BN" },
231 { LANGUAGE_ENGLISH_MALAYSIA, "en", "MY" },
232 { LANGUAGE_THAI, "th", "TH" },
233 { LANGUAGE_LITHUANIAN, "lt", "LT" },
234 { LANGUAGE_LITHUANIAN_CLASSIC, "lt", "LT" },
235 { LANGUAGE_CROATIAN, "hr", "HR" }, // Croatian in Croatia
236 { LANGUAGE_CROATIAN_BOSNIA_HERZEGOVINA, "hr", "BA" },
237 { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA, "bs", "BA" },
238 // { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_AND_HERZEGOVINA, "bs", "BA" }, // script codes not supported yet
239 { LANGUAGE_USER_SERBIAN_CYRILLIC_SERBIA, "sr", "RS" }, // Serbian Cyrillic in Serbia
240 { LANGUAGE_SERBIAN_CYRILLIC, "sr", "YU" }, // legacy Serbian Cyrillic in Serbia and Montenegro (former Yugoslavia); kludge, needed to be sr_CS instead, sr_CS not supported by ICU 2.6 (3.4 does)
241 { LANGUAGE_SERBIAN_CYRILLIC, "sr", "CS" }, // alias to be able to integrate localizations, rsc needs it
242 { LANGUAGE_USER_SERBIAN_CYRILLIC_MONTENEGRO, "sr", "ME" },
243 { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr", "BA" },
244 { LANGUAGE_SERBIAN, "sr", "" }, // SERBIAN is only LID, MS-LCID not defined (was dupe of CROATIAN)
245 { LANGUAGE_USER_SERBIAN_LATIN_SERBIA, "sh", "RS" }, // Serbian Latin in Serbia; kludge, needed to be sr_Latn_RS instead, script codes not supported yet
246 { LANGUAGE_SERBIAN_LATIN, "sh", "YU" }, // legacy Serbian Latin in Serbia and Montenegro (former Yugoslavia); kludge, needed to be sr_Latn_CS instead, script codes not supported yet
247 { LANGUAGE_SERBIAN_LATIN, "sh", "CS" }, // Serbian Latin in Serbia and Montenegro; kludge, needed to be sr_Latn_CS instead, script codes not supported yet
248 { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO, "sh", "ME" }, // Serbian Latin in Montenegro; kludge, needed to be sr_Latn_ME instead, script codes not supported yet
249 { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA, "sh", "BA" },
250 { LANGUAGE_SERBIAN_LATIN_NEUTRAL, "sh", "" }, // kludge, needed to be sr_Latn instead, script codes not supported yet
251 { LANGUAGE_ARMENIAN, "hy", "AM" },
252 { LANGUAGE_AZERI, "az", "" },
253 { LANGUAGE_AZERI_LATIN, "az", "AZ" },
254 // { LANGUAGE_AZERI_CYRILLIC, "az", "AZ" }, // script codes not supported yet
255 { LANGUAGE_UZBEK_LATIN, "uz", "UZ" },
256 // { LANGUAGE_UZBEK_CYRILLIC, "uz", "UZ" }, // script codes not supported yet
257 { LANGUAGE_BENGALI_BANGLADESH, "bn", "BD" },
258 { LANGUAGE_BENGALI, "bn", "IN" },
259 { LANGUAGE_BURMESE, "my", "MM" },
260 { LANGUAGE_KAZAK, "kk", "KZ" },
261 { LANGUAGE_ENGLISH_INDIA, "en", "IN" },
262 { LANGUAGE_URDU, "ur", "" },
263 { LANGUAGE_URDU_INDIA, "ur", "IN" },
264 { LANGUAGE_URDU_PAKISTAN, "ur", "PK" },
265 { LANGUAGE_HINDI, "hi", "IN" },
266 { LANGUAGE_GUJARATI, "gu", "IN" },
267 { LANGUAGE_KANNADA, "kn", "IN" },
268 { LANGUAGE_ASSAMESE, "as", "IN" },
269 { LANGUAGE_KASHMIRI, "ks", "" },
270 { LANGUAGE_KASHMIRI_INDIA, "ks", "IN" },
271 { LANGUAGE_MALAYALAM, "ml", "IN" },
272 { LANGUAGE_MANIPURI, "mni", "IN" },
273 { LANGUAGE_MARATHI, "mr", "IN" },
274 { LANGUAGE_KONKANI, "kok", "IN" },
275 { LANGUAGE_NEPALI, "ne", "NP" },
276 { LANGUAGE_NEPALI_INDIA, "ne", "IN" },
277 { LANGUAGE_ORIYA, "or", "IN" },
278 { LANGUAGE_PUNJABI, "pa", "IN" },
279 { LANGUAGE_SANSKRIT, "sa", "IN" },
280 { LANGUAGE_SINDHI, "sd", "IN" },
281 { LANGUAGE_TAMIL, "ta", "IN" },
282 { LANGUAGE_TELUGU, "te", "IN" },
283 { LANGUAGE_PUNJABI_PAKISTAN, "lah", "PK" }, // preferring "lah" over "pa" for Western Punjabi, see http://www.ethnologue.com/show_language.asp?code=PNB
284 { LANGUAGE_PUNJABI_PAKISTAN, "pa", "PK" },
285 { LANGUAGE_SINDHI_PAKISTAN, "sd", "PK" },
286 { LANGUAGE_BELARUSIAN, "be", "BY" },
287 { LANGUAGE_CATALAN, "ca", "ES" }, // Spain (default)
288 { LANGUAGE_CATALAN, "ca", "AD" }, // Andorra
289 { LANGUAGE_USER_CATALAN_VALENCIAN, "ca", "XV" }, // XV: ISO 3166 user-assigned; workaround for UI localization only, do not use in document content!
290 { LANGUAGE_CATALAN, "qcv", "ES" }, // qcv: ISO 639-3 reserved-for-local-use; UI localization quirk only, do not use in document content!
291 // { LANGUAGE_USER_CATALAN_VALENCIAN, "ca", "ES" }, // In case MS format files escaped into the wild, map them back.
292 { LANGUAGE_FRENCH_CAMEROON, "fr", "CM" },
293 { LANGUAGE_FRENCH_COTE_D_IVOIRE, "fr", "CI" },
294 { LANGUAGE_FRENCH_MALI, "fr", "ML" },
295 { LANGUAGE_FRENCH_SENEGAL, "fr", "SN" },
296 { LANGUAGE_FRENCH_ZAIRE, "fr", "CD" }, // Democratic Republic Of Congo
297 { LANGUAGE_FRENCH_MOROCCO, "fr", "MA" },
298 { LANGUAGE_FRENCH_REUNION, "fr", "RE" },
299 { LANGUAGE_FRENCH_NORTH_AFRICA, "fr", "" },
300 { LANGUAGE_FRENCH_WEST_INDIES, "fr", "" }, // unknown ISO country code
301 { LANGUAGE_FRISIAN_NETHERLANDS, "fy", "NL" },
302 { LANGUAGE_GAELIC_IRELAND, "ga", "IE" },
303 { LANGUAGE_GAELIC_SCOTLAND, "gd", "GB" },
304 { LANGUAGE_GALICIAN, "gl", "ES" },
305 { LANGUAGE_GEORGIAN, "ka", "GE" },
306 { LANGUAGE_KHMER, "km", "KH" },
307 { LANGUAGE_KIRGHIZ, "ky", "KG" },
308 { LANGUAGE_LAO, "lo", "LA" },
309 { LANGUAGE_MALTESE, "mt", "MT" },
310 { LANGUAGE_MONGOLIAN, "mn", "MN" }, // Cyrillic script
311 { LANGUAGE_MONGOLIAN_MONGOLIAN, "mn", "MN" },
312 { LANGUAGE_RUSSIAN_MOLDOVA, "mo", "MD" },
313 { LANGUAGE_SWAHILI, "sw", "KE" },
314 { LANGUAGE_USER_SWAHILI_TANZANIA, "sw", "TZ" },
315 { LANGUAGE_TAJIK, "tg", "TJ" },
316 { LANGUAGE_TIBETAN, "bo", "CN" }, // CN politically correct?
317 { LANGUAGE_DZONGKHA, "dz", "BT" },
318 { LANGUAGE_TURKMEN, "tk", "TM" },
319 { LANGUAGE_WELSH, "cy", "GB" },
320 { LANGUAGE_SESOTHO, "st", "ZA" },
321 { LANGUAGE_SEPEDI, "nso", "ZA" },
322 { LANGUAGE_SEPEDI, "ns", "ZA" }, // fake "ns" for compatibility with existing OOo1.1.x localization to be able to read those documents
323 { LANGUAGE_TSONGA, "ts", "ZA" },
324 { LANGUAGE_TSWANA, "tn", "ZA" },
325 { LANGUAGE_ENGLISH_SAFRICA, "en", "ZA" },
326 { LANGUAGE_AFRIKAANS, "af", "ZA" },
327 { LANGUAGE_VENDA, "ve", "ZA" }, // default 639-1
328 { LANGUAGE_VENDA, "ven", "ZA" }, // 639-2 may have been used temporarily since 2004-07-23
329 { LANGUAGE_XHOSA, "xh", "ZA" },
330 { LANGUAGE_ZULU, "zu", "ZA" },
331 { LANGUAGE_QUECHUA_ECUADOR, "qu", "EC" },
332 { LANGUAGE_QUECHUA_PERU, "qu", "PE" },
333 { LANGUAGE_QUECHUA_BOLIVIA, "qu", "BO" }, // macro: quh-BO, qul-BO
334 { LANGUAGE_PASHTO, "ps", "AF" },
335 { LANGUAGE_OROMO, "om", "ET" },
336 { LANGUAGE_DHIVEHI, "dv", "MV" },
337 { LANGUAGE_UIGHUR_CHINA, "ug", "CN" },
338 { LANGUAGE_TIGRIGNA_ETHIOPIA, "ti", "ET" },
339 { LANGUAGE_TIGRIGNA_ERITREA, "ti", "ER" },
340 { LANGUAGE_AMHARIC_ETHIOPIA, "am", "ET" },
341 { LANGUAGE_GUARANI_PARAGUAY, "gug", "PY" },
342 { LANGUAGE_HAWAIIAN_UNITED_STATES, "haw", "US" },
343 { LANGUAGE_EDO, "bin", "NG" },
344 { LANGUAGE_FULFULDE_NIGERIA, "ff", "NG" },
345 { LANGUAGE_HAUSA_NIGERIA, "ha", "NG" },
346 { LANGUAGE_USER_HAUSA_GHANA, "ha", "GH" },
347 { LANGUAGE_IGBO_NIGERIA, "ig", "NG" },
348 { LANGUAGE_KANURI_NIGERIA, "kr", "NG" },
349 { LANGUAGE_YORUBA, "yo", "NG" },
350 { LANGUAGE_SOMALI, "so", "SO" },
351 { LANGUAGE_PAPIAMENTU, "pap", "AN" },
352 { LANGUAGE_USER_PAPIAMENTU_ARUBA, "pap", "AW" },
353 { LANGUAGE_ENGLISH_SINGAPORE, "en", "SG" },
354 { LANGUAGE_USER_YIDDISH_US, "yi", "US" },
355 { LANGUAGE_YIDDISH, "yi", "IL" }, // new: old was "ji"
356 { LANGUAGE_YIDDISH, "ji", "IL" }, // old: new is "yi"
357 { LANGUAGE_SYRIAC, "syr", "TR" }, // "TR" according to http://www.ethnologue.com/show_language.asp?code=SYC
358 { LANGUAGE_SINHALESE_SRI_LANKA, "si", "LK" },
359 { LANGUAGE_CHEROKEE_UNITED_STATES, "chr", "US" },
360 { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu", "CA" },
361 // { LANGUAGE_INUKTITUT_SYLLABICS_CANADA, "iu", "CA" }, // script codes not supported yet
362 { LANGUAGE_SAMI_NORTHERN_NORWAY, "se", "NO" },
363 { LANGUAGE_SAMI_INARI, "smn", "FI" },
364 { LANGUAGE_SAMI_LULE_NORWAY, "smj", "NO" },
365 { LANGUAGE_SAMI_LULE_SWEDEN, "smj", "SE" },
366 { LANGUAGE_SAMI_NORTHERN_FINLAND, "se", "FI" },
367 { LANGUAGE_SAMI_NORTHERN_SWEDEN, "se", "SE" },
368 { LANGUAGE_SAMI_SKOLT, "sms", "FI" },
369 { LANGUAGE_SAMI_SOUTHERN_NORWAY, "sma", "NO" },
370 { LANGUAGE_SAMI_SOUTHERN_SWEDEN, "sma", "SE" },
371 { LANGUAGE_USER_SAMI_KILDIN_RUSSIA, "sjd", "RU" },
372 { LANGUAGE_MAPUDUNGUN_CHILE, "arn", "CL" },
373 { LANGUAGE_CORSICAN_FRANCE, "co", "FR" },
374 { LANGUAGE_ALSATIAN_FRANCE, "gsw", "FR" }, // in fact 'gsw' is Schwyzerduetsch (Swiss German), which is a dialect of Alemannic German, as is Alsatian. They aren't distinct languages and share this code.
375 { LANGUAGE_YAKUT_RUSSIA, "sah", "RU" },
376 { LANGUAGE_MOHAWK_CANADA, "moh", "CA" },
377 { LANGUAGE_BASHKIR_RUSSIA, "ba", "RU" },
378 { LANGUAGE_KICHE_GUATEMALA, "qut", "GT" },
379 { LANGUAGE_DARI_AFGHANISTAN, "gbz", "AF" },
380 { LANGUAGE_WOLOF_SENEGAL, "wo", "SN" },
381 { LANGUAGE_FILIPINO, "fil", "PH" },
382 { LANGUAGE_USER_TAGALOG, "tl", "PH" },
383 { LANGUAGE_ENGLISH_PHILIPPINES, "en", "PH" },
384 // { LANGUAGE_IBIBIO_NIGERIA, "nic", "NG" }, // ISO "nic" is only a collective language code
385 { LANGUAGE_YI, "ii", "CN" },
386 { LANGUAGE_TAMAZIGHT_LATIN, "kab", "DZ" }, // In practice Kabyle is the language used for this
387 { LANGUAGE_OBSOLETE_USER_KABYLE, "kab", "DZ" },
388 { LANGUAGE_TAMAZIGHT_LATIN, "ber", "DZ" }, // In practice Algeria has standardized on Kabyle as the member of the "ber" collective which gets used there.
389 { LANGUAGE_TAMAZIGHT_TIFINAGH, "ber", "MA" }, // Morocco is officially using Tifinagh for its Berber languages so store it to distinguish explicitly from LANGUAGE_TAMAZIGHT_LATIN, even though as a collective language its not of much use
390 // { LANGUAGE_TAMAZIGHT_ARABIC, "ber", "" }, // ISO "ber" only collective!
391 { LANGUAGE_LATIN, "la", "VA" },
392 { LANGUAGE_OBSOLETE_USER_LATIN, "la", "VA" },
393 { LANGUAGE_USER_ESPERANTO, "eo", "" },
394 { LANGUAGE_USER_INTERLINGUA, "ia", "" },
395 { LANGUAGE_MAORI_NEW_ZEALAND, "mi", "NZ" },
396 { LANGUAGE_OBSOLETE_USER_MAORI, "mi", "NZ" },
397 { LANGUAGE_KINYARWANDA_RWANDA, "rw", "RW" },
398 { LANGUAGE_OBSOLETE_USER_KINYARWANDA, "rw", "RW" },
399 { LANGUAGE_UPPER_SORBIAN_GERMANY, "hsb", "DE" }, // MS maps this to 'wen-DE', which is nonsense. 'wen' is a collective language code, 'WEN' is a SIL code, see http://www.ethnologue.com/14/show_iso639.asp?code=wen and http://www.ethnologue.com/14/show_language.asp?code=WEN
400 { LANGUAGE_OBSOLETE_USER_UPPER_SORBIAN,"hsb", "DE" },
401 { LANGUAGE_LOWER_SORBIAN_GERMANY, "dsb", "DE" }, // MS maps this to 'wee-DE', which is nonsense. 'WEE' is a SIL code, see http://www.ethnologue.com/14/show_language.asp?code=WEE
402 { LANGUAGE_OBSOLETE_USER_LOWER_SORBIAN,"dsb", "DE" },
403 { LANGUAGE_OCCITAN_FRANCE, "oc", "FR" },
404 { LANGUAGE_OBSOLETE_USER_OCCITAN, "oc", "FR" },
405 { LANGUAGE_USER_KURDISH_TURKEY, "ku", "TR" },
406 { LANGUAGE_USER_KURDISH_SYRIA, "ku", "SY" },
407 { LANGUAGE_USER_KURDISH_IRAQ, "ku", "IQ" },
408 { LANGUAGE_USER_KURDISH_IRAN, "ku", "IR" },
409 { LANGUAGE_USER_SARDINIAN, "sc", "IT" }, // macrolanguage code
410 { LANGUAGE_USER_SARDINIAN_CAMPIDANESE, "sro", "IT" },
411 { LANGUAGE_USER_SARDINIAN_GALLURESE, "sdn", "IT" },
412 { LANGUAGE_USER_SARDINIAN_LOGUDORESE, "src", "IT" },
413 { LANGUAGE_USER_SARDINIAN_SASSARESE, "sdc", "IT" },
414 { LANGUAGE_BRETON_FRANCE, "br", "FR" },
415 { LANGUAGE_OBSOLETE_USER_BRETON, "br", "FR" },
416 { LANGUAGE_KALAALLISUT_GREENLAND, "kl", "GL" },
417 { LANGUAGE_OBSOLETE_USER_KALAALLISUT, "kl", "GL" },
418 { LANGUAGE_USER_SWAZI, "ss", "ZA" },
419 { LANGUAGE_USER_NDEBELE_SOUTH, "nr", "ZA" },
420 { LANGUAGE_USER_TSWANA_BOTSWANA, "tn", "BW" },
421 { LANGUAGE_USER_MOORE, "mos", "BF" },
422 { LANGUAGE_USER_BAMBARA, "bm", "ML" },
423 { LANGUAGE_USER_AKAN, "ak", "GH" },
424 { LANGUAGE_LUXEMBOURGISH_LUXEMBOURG, "lb", "LU" },
425 { LANGUAGE_OBSOLETE_USER_LUXEMBOURGISH, "lb", "LU" },
426 { LANGUAGE_USER_FRIULIAN, "fur", "IT" },
427 { LANGUAGE_USER_FIJIAN, "fj", "FJ" },
428 { LANGUAGE_USER_AFRIKAANS_NAMIBIA, "af", "NA" },
429 { LANGUAGE_USER_ENGLISH_NAMIBIA, "en", "NA" },
430 { LANGUAGE_USER_WALLOON, "wa", "BE" },
431 { LANGUAGE_USER_COPTIC, "cop", "EG" },
432 { LANGUAGE_USER_GASCON, "gsc", "FR" },
433 { LANGUAGE_USER_GERMAN_BELGIUM, "de", "BE" },
434 { LANGUAGE_USER_CHUVASH, "cv", "RU" },
435 { LANGUAGE_USER_EWE_GHANA, "ee", "GH" },
436 { LANGUAGE_USER_ENGLISH_GHANA, "en", "GH" },
437 { LANGUAGE_USER_SANGO, "sg", "CF" },
438 { LANGUAGE_USER_GANDA, "lg", "UG" },
439 { LANGUAGE_USER_LINGALA_DRCONGO, "ln", "CD" },
440 { LANGUAGE_USER_LOW_GERMAN, "nds", "DE" },
441 { LANGUAGE_USER_HILIGAYNON, "hil", "PH" },
442 { LANGUAGE_USER_ENGLISH_MALAWI, "en", "MW" }, /* en default for MW */
443 { LANGUAGE_USER_NYANJA, "ny", "MW" },
444 { LANGUAGE_USER_KASHUBIAN, "csb", "PL" },
445 { LANGUAGE_USER_SPANISH_CUBA, "es", "CU" },
446 { LANGUAGE_USER_QUECHUA_NORTH_BOLIVIA, "qul", "BO" },
447 { LANGUAGE_USER_QUECHUA_SOUTH_BOLIVIA, "quh", "BO" },
448 { LANGUAGE_USER_BODO_INDIA, "brx", "IN" },
449 { LANGUAGE_USER_DOGRI_INDIA, "dgo", "IN" },
450 { LANGUAGE_USER_MAITHILI_INDIA, "mai", "IN" },
451 { LANGUAGE_USER_SANTALI_INDIA, "sat", "IN" },
452 { LANGUAGE_USER_TETUN, "tet", "ID" },
453 { LANGUAGE_USER_TETUN_TIMOR_LESTE, "tet", "TL" },
454 { LANGUAGE_USER_TOK_PISIN, "tpi", "PG" },
455 { LANGUAGE_USER_SHUSWAP, "shs", "CA" },
456 { LANGUAGE_USER_ANCIENT_GREEK, "grc", "GR" },
457 { LANGUAGE_USER_ASTURIAN, "ast", "ES" },
458 { LANGUAGE_USER_LATGALIAN, "ltg", "LV" },
459 { LANGUAGE_USER_MAORE, "swb", "YT" },
460 { LANGUAGE_USER_BUSHI, "buc", "YT" },
461 { LANGUAGE_USER_TAHITIAN, "ty", "PF" },
462 { LANGUAGE_USER_MALAGASY_PLATEAU, "plt", "MG" },
463 { LANGUAGE_USER_MALAGASY_PLATEAU, "mg", "MG" },
464 { LANGUAGE_USER_BAFIA, "ksf", "CM" },
465 { LANGUAGE_USER_GIKUYU, "ki", "KE" },
466 { LANGUAGE_USER_RUSYN_UKRAINE, "rue", "UA" },
467 { LANGUAGE_USER_RUSYN_SLOVAKIA, "rue", "SK" },
468 { LANGUAGE_USER_LIMBU, "lif", "NP" },
469 { LANGUAGE_USER_LOJBAN, "jbo", "" },
470 { LANGUAGE_USER_HAITIAN, "ht", "HT" },
471 { LANGUAGE_FRENCH_HAITI, "fr", "HT" },
472 { LANGUAGE_USER_BEEMBE, "beq", "CG" },
473 { LANGUAGE_USER_BEKWEL, "bkw", "CG" },
474 { LANGUAGE_USER_KITUBA, "mkw", "CG" },
475 { LANGUAGE_USER_LARI, "ldi", "CG" },
476 { LANGUAGE_USER_MBOCHI, "mdw", "CG" },
477 { LANGUAGE_USER_TEKE_EBOO, "ebo", "CG" },
478 { LANGUAGE_USER_TEKE_IBALI, "tek", "CG" },
479 { LANGUAGE_USER_TEKE_TYEE, "tyx", "CG" },
480 { LANGUAGE_USER_VILI, "vif", "CG" },
481 { LANGUAGE_USER_PORTUGUESE_ANGOLA, "pt", "AO" },
482 { LANGUAGE_USER_MANX, "gv", "GB" },
483 { LANGUAGE_USER_ARAGONESE, "an", "ES" },
484 { LANGUAGE_USER_KEYID, "qtz", "" }, // key id pseudolanguage used for UI testing
485 { LANGUAGE_USER_PALI_LATIN, "pli", "" }, // Pali with Latin script
486 { LANGUAGE_USER_KYRGYZ_CHINA, "ky", "CN" },
487 { LANGUAGE_USER_KOMI_ZYRIAN, "kpv", "RU" },
488 { LANGUAGE_USER_KOMI_PERMYAK, "koi", "RU" },
489 { LANGUAGE_USER_PITJANTJATJARA, "pjt", "AU" },
490 { LANGUAGE_USER_ERZYA, "myv", "RU" },
491 { LANGUAGE_USER_MARI_MEADOW, "mhr", "RU" },
492 { LANGUAGE_NONE, "zxx", "" }, // added to ISO 639-2 on 2006-01-11: Used to declare the absence of linguistic information
493 { LANGUAGE_DONTKNOW, "", "" } // marks end of table
494 };
495
496 static MsLangId::IsoLangEntry aLastResortFallbackEntry =
497 { LANGUAGE_ENGLISH_US, "en", "US" };
498
499 // -----------------------------------------------------------------------
500
501 // In this table are the countries which should mapped to a specific
502 // english language
503 static IsoLangEngEntry const aImplIsoLangEngEntries[] =
504 {
505 { LANGUAGE_ENGLISH_UK, "AO" }, // Angola
506 { LANGUAGE_ENGLISH_UK, "BJ" }, // Benin
507 { LANGUAGE_ENGLISH_UK, "BW" }, // Botswana
508 { LANGUAGE_ENGLISH_UK, "BI" }, // Burundi
509 { LANGUAGE_ENGLISH_UK, "CM" }, // Cameroon
510 { LANGUAGE_ENGLISH_UK, "GA" }, // Gabon
511 { LANGUAGE_ENGLISH_UK, "GM" }, // Gambia
512 { LANGUAGE_ENGLISH_UK, "GH" }, // Ghana
513 { LANGUAGE_ENGLISH_UK, "GN" }, // Guinea
514 { LANGUAGE_ENGLISH_UK, "LS" }, // Lesotho
515 { LANGUAGE_ENGLISH_UK, "MW" }, // Malawi
516 { LANGUAGE_ENGLISH_UK, "MT" }, // Malta
517 { LANGUAGE_ENGLISH_UK, "NA" }, // Namibia
518 { LANGUAGE_ENGLISH_UK, "NG" }, // Nigeria
519 { LANGUAGE_ENGLISH_UK, "UG" }, // Uganda
520 { LANGUAGE_ENGLISH_UK, "ZM" }, // Zambia
521 { LANGUAGE_ENGLISH_UK, "ZW" }, // Zimbabwe
522 { LANGUAGE_ENGLISH_UK, "SZ" }, // Swaziland
523 { LANGUAGE_ENGLISH_UK, "NG" }, // Sierra Leone
524 { LANGUAGE_ENGLISH_UK, "KN" }, // Saint Kitts and Nevis
525 { LANGUAGE_ENGLISH_UK, "SH" }, // St. Helena
526 { LANGUAGE_ENGLISH_UK, "IO" }, // British Indian Oceanic Territory
527 { LANGUAGE_ENGLISH_UK, "FK" }, // Falkland Islands
528 { LANGUAGE_ENGLISH_UK, "GI" }, // Gibraltar
529 { LANGUAGE_ENGLISH_UK, "KI" }, // Kiribati
530 { LANGUAGE_ENGLISH_UK, "VG" }, // Virgin Islands
531 { LANGUAGE_ENGLISH_UK, "MU" }, // Mauritius
532 { LANGUAGE_ENGLISH_UK, "FJ" }, // Fiji
533 { LANGUAGE_ENGLISH_US, "KI" }, // Kiribati
534 { LANGUAGE_ENGLISH_US, "LR" }, // Liberia
535 { LANGUAGE_ENGLISH_US, "GU" }, // Guam
536 { LANGUAGE_ENGLISH_US, "MH" }, // Marshall Islands
537 { LANGUAGE_ENGLISH_US, "PW" }, // Palau
538 { LANGUAGE_ENGLISH_CARRIBEAN, "AI" }, // Anguilla
539 { LANGUAGE_ENGLISH_CARRIBEAN, "AG" }, // Antigua and Barbuda
540 { LANGUAGE_ENGLISH_CARRIBEAN, "BS" }, // Bahamas
541 { LANGUAGE_ENGLISH_CARRIBEAN, "BB" }, // Barbedos
542 { LANGUAGE_ENGLISH_CARRIBEAN, "BM" }, // Bermuda
543 { LANGUAGE_ENGLISH_CARRIBEAN, "KY" }, // Cayman Islands
544 { LANGUAGE_ENGLISH_CARRIBEAN, "GD" }, // Grenada
545 { LANGUAGE_ENGLISH_CARRIBEAN, "DM" }, // Dominica
546 { LANGUAGE_ENGLISH_CARRIBEAN, "HT" }, // Haiti
547 { LANGUAGE_ENGLISH_CARRIBEAN, "MS" }, // Montserrat
548 { LANGUAGE_ENGLISH_CARRIBEAN, "FM" }, // Micronesia
549 { LANGUAGE_ENGLISH_CARRIBEAN, "VC" }, // St. Vincent / Grenadines
550 { LANGUAGE_ENGLISH_CARRIBEAN, "LC" }, // Saint Lucia
551 { LANGUAGE_ENGLISH_CARRIBEAN, "TC" }, // Turks & Caicos Islands
552 { LANGUAGE_ENGLISH_CARRIBEAN, "GY" }, // Guyana
553 { LANGUAGE_ENGLISH_CARRIBEAN, "TT" }, // Trinidad and Tobago
554 { LANGUAGE_ENGLISH_AUS, "CX" }, // Christmas Islands
555 { LANGUAGE_ENGLISH_AUS, "CC" }, // Cocos (Keeling) Islands
556 { LANGUAGE_ENGLISH_AUS, "NF" }, // Norfolk Island
557 { LANGUAGE_ENGLISH_AUS, "PG" }, // Papua New Guinea
558 { LANGUAGE_ENGLISH_AUS, "SB" }, // Solomon Islands
559 { LANGUAGE_ENGLISH_AUS, "TV" }, // Tuvalu
560 { LANGUAGE_ENGLISH_AUS, "NR" }, // Nauru
561 { LANGUAGE_ENGLISH_NZ, "CK" }, // Cook Islands
562 { LANGUAGE_ENGLISH_NZ, "NU" }, // Niue
563 { LANGUAGE_ENGLISH_NZ, "TK" }, // Tokelau
564 { LANGUAGE_ENGLISH_NZ, "TO" }, // Tonga
565 { LANGUAGE_DONTKNOW, "" } // marks end of table
566 };
567
568 // -----------------------------------------------------------------------
569
570 static IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries[] =
571 {
572 { LANGUAGE_NORWEGIAN_BOKMAL, "no", "BOK" }, // registered subtags for "no" in rfc1766
573 { LANGUAGE_NORWEGIAN_NYNORSK, "no", "NYN" }, // registered subtags for "no" in rfc1766
574 { LANGUAGE_SERBIAN_LATIN, "sr", "latin" },
575 { LANGUAGE_SERBIAN_CYRILLIC, "sr", "cyrillic" },
576 { LANGUAGE_AZERI_LATIN, "az", "latin" },
577 { LANGUAGE_AZERI_CYRILLIC, "az", "cyrillic" },
578 { LANGUAGE_DONTKNOW, "", "" } // marks end of table
579 };
580
581 // -----------------------------------------------------------------------
582
583 // in this table are only names to find the best language
584 static IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries2[] =
585 {
586 { LANGUAGE_NORWEGIAN_BOKMAL, "no", "bokmaal" },
587 { LANGUAGE_NORWEGIAN_BOKMAL, "no", "bokmal" },
588 { LANGUAGE_NORWEGIAN_NYNORSK, "no", "nynorsk" },
589 { LANGUAGE_DONTKNOW, "", "" } // marks end of table
590 };
591
592 // -----------------------------------------------------------------------
593
594 // in this table are only names to find the best language
595 static IsoLangOtherEntry const aImplOtherEntries[] =
596 {
597 { LANGUAGE_ENGLISH_US, "c" },
598 { LANGUAGE_CHINESE, "chinese" },
599 { LANGUAGE_GERMAN, "german" },
600 { LANGUAGE_JAPANESE, "japanese" },
601 { LANGUAGE_KOREAN, "korean" },
602 { LANGUAGE_ENGLISH_US, "posix" },
603 { LANGUAGE_CHINESE_TRADITIONAL, "tchinese" },
604 { LANGUAGE_DONTKNOW, NULL } // marks end of table
605 };
606
607 // =======================================================================
608
609 // static
610 void MsLangId::convertLanguageToIsoNames( LanguageType nLang,
611 rtl::OUString& rLangStr, rtl::OUString& rCountry )
612 {
613 if ( nLang == LANGUAGE_SYSTEM )
614 nLang = MsLangId::getSystemLanguage();
615
616 // Search for LangID (in this table we find only defined ISO combinations)
617 const IsoLangEntry* pEntry = aImplIsoLangEntries;
618 do
619 {
620 if ( pEntry->mnLang == nLang )
621 {
622 rLangStr = rtl::OUString::createFromAscii( pEntry->maLangStr );
623 rCountry = rtl::OUString::createFromAscii( pEntry->maCountry );
624 return;
625 }
626 ++pEntry;
627 }
628 while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
629
630 // Search for LangID if we didn't find a specific ISO combination.
631 // All entries in this table are allowed for mime specifications,
632 // but not defined ISO combinations.
633 const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries;
634 do
635 {
636 if ( pNoneStdEntry->mnLang == nLang )
637 {
638 rLangStr = rtl::OUString::createFromAscii( pNoneStdEntry->maLangStr );
639 rCountry = rtl::OUString::createFromAscii( pNoneStdEntry->maCountry );
640 return;
641 }
642 ++pNoneStdEntry;
643 }
644 while ( pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW );
645
646 // not found
647 rLangStr = rtl::OUString();
648 rCountry = rtl::OUString();
649 }
650
651 // -----------------------------------------------------------------------
652
653 // static
654 void MsLangId::convertLanguageToIsoNames( LanguageType nLang,
655 rtl::OString& rLangStr, rtl::OString& rCountry )
656 {
657 if ( nLang == LANGUAGE_SYSTEM )
658 nLang = MsLangId::getSystemLanguage();
659
660 // Search for LangID (in this table we find only defined ISO combinations)
661 const IsoLangEntry* pEntry = aImplIsoLangEntries;
662 do
663 {
664 if ( pEntry->mnLang == nLang )
665 { // avoid embedded \0 warning
666 rLangStr = rtl::OString( static_cast< const char* >( pEntry->maLangStr ));
667 rCountry = rtl::OString( static_cast< const char* >( pEntry->maCountry ));
668 return;
669 }
670 ++pEntry;
671 }
672 while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
673
674 // Search for LangID if we didn't find a specific ISO combination.
675 // All entries in this table are allowed for mime specifications,
676 // but not defined ISO combinations.
677 const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries;
678 do
679 {
680 if ( pNoneStdEntry->mnLang == nLang )
681 { // avoid embedded \0 warning
682 rLangStr = rtl::OString( static_cast< const char* >( pNoneStdEntry->maLangStr ));
683 rCountry = rtl::OString( static_cast< const char* >( pNoneStdEntry->maCountry ));
684 return;
685 }
686 ++pNoneStdEntry;
687 }
688 while ( pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW );
689
690 // not found
691 rLangStr = rtl::OString();
692 rCountry = rtl::OString();
693 }
694
695 // -----------------------------------------------------------------------
696
697 static const MsLangId::IsoLangEntry & lcl_lookupFallbackEntry( LanguageType nLang )
698 {
699 LanguageType nPrimary = MsLangId::getPrimaryLanguage( nLang);
700
701 // Search for LangID and remember first lang-only.
702 const MsLangId::IsoLangEntry* pFirstPrimary = NULL;
703 const MsLangId::IsoLangEntry* pEntry = aImplIsoLangEntries;
704 do
705 {
706 if (pEntry->mnLang == nLang)
707 {
708 if (*pEntry->maCountry)
709 return *pEntry;
710 switch (nLang)
711 {
712 // These are known to have no country assigned.
713 case LANGUAGE_BASQUE:
714 case LANGUAGE_USER_ESPERANTO:
715 case LANGUAGE_USER_INTERLINGUA:
716 case LANGUAGE_USER_LOJBAN:
717 return *pEntry;
718 default:
719 ; // nothing
720 }
721 }
722 if (!pFirstPrimary &&
723 MsLangId::getPrimaryLanguage( pEntry->mnLang) == nPrimary)
724 pFirstPrimary = pEntry;
725 ++pEntry;
726 }
727 while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
728
729 // Language not found at all => use default.
730 if (!pFirstPrimary)
731 return aLastResortFallbackEntry;
732
733 // Search for first entry of primary language with any country.
734 pEntry = pFirstPrimary;
735 do
736 {
737 if (MsLangId::getPrimaryLanguage( pEntry->mnLang) == nLang)
738 {
739 if (*pEntry->maCountry)
740 return *pEntry;
741 }
742 ++pEntry;
743 }
744 while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
745
746 return aLastResortFallbackEntry;
747 }
748
749 // static
750 LanguageType MsLangId::lookupFallbackLanguage( LanguageType nLang )
751 {
752 return lcl_lookupFallbackEntry( nLang).mnLang;
753 }
754
755
756 // static
757 ::com::sun::star::lang::Locale MsLangId::lookupFallbackLocale( LanguageType nLang )
758 {
759 const MsLangId::IsoLangEntry& rEntry = lcl_lookupFallbackEntry( nLang);
760 return ::com::sun::star::lang::Locale(
761 rtl::OUString::createFromAscii( rEntry.maLangStr),
762 rtl::OUString::createFromAscii( rEntry.maCountry),
763 rtl::OUString());
764 }
765
766 // -----------------------------------------------------------------------
767
768 static const MsLangId::IsoLangEntry & lcl_lookupFallbackEntry(
769 const ::com::sun::star::lang::Locale & rLocale )
770 {
771 // language is lower case in table
772 rtl::OUString aLowerLang = rLocale.Language.toAsciiLowerCase();
773 // country is upper case in table
774 rtl::OUString aUpperCountry = rLocale.Country.toAsciiUpperCase();
775 sal_Int32 nCountryLen = aUpperCountry.getLength();
776
777 // Search for locale and remember first lang-only.
778 const MsLangId::IsoLangEntry* pFirstLang = NULL;
779 const MsLangId::IsoLangEntry* pEntry = aImplIsoLangEntries;
780 do
781 {
782 if (aLowerLang.equalsAscii( pEntry->maLangStr))
783 {
784 if (*pEntry->maCountry)
785 {
786 if (nCountryLen && aUpperCountry.equalsAscii( pEntry->maCountry))
787 return *pEntry;
788 }
789 else
790 {
791 switch (pEntry->mnLang)
792 {
793 // These are known to have no country assigned.
794 case LANGUAGE_BASQUE:
795 case LANGUAGE_USER_ESPERANTO:
796 case LANGUAGE_USER_INTERLINGUA:
797 case LANGUAGE_USER_LOJBAN:
798 return *pEntry;
799 default:
800 ; // nothing
801 }
802 }
803 if (!pFirstLang)
804 pFirstLang = pEntry;
805 }
806 ++pEntry;
807 }
808 while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
809
810 // Language not found at all => use default.
811 if (!pFirstLang)
812 return aLastResortFallbackEntry;
813
814 // Search for first entry of language with any country.
815 pEntry = pFirstLang;
816 do
817 {
818 if (aLowerLang.equalsAscii( pEntry->maLangStr))
819 {
820 if (*pEntry->maCountry)
821 return *pEntry;
822 }
823 ++pEntry;
824 }
825 while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
826
827 return aLastResortFallbackEntry;
828 }
829
830 // static
831 LanguageType MsLangId::lookupFallbackLanguage(
832 const ::com::sun::star::lang::Locale & rLocale )
833 {
834 return lcl_lookupFallbackEntry( rLocale).mnLang;
835 }
836
837
838 // static
839 ::com::sun::star::lang::Locale MsLangId::lookupFallbackLocale(
840 const ::com::sun::star::lang::Locale & rLocale )
841 {
842 const MsLangId::IsoLangEntry& rEntry = lcl_lookupFallbackEntry( rLocale);
843 return ::com::sun::star::lang::Locale(
844 rtl::OUString::createFromAscii( rEntry.maLangStr),
845 rtl::OUString::createFromAscii( rEntry.maCountry),
846 rtl::OUString());
847 }
848
849 // -----------------------------------------------------------------------
850
851 // static
852 rtl::OUString MsLangId::convertLanguageToIsoString( LanguageType nLang,
853 sal_Unicode cSep )
854 {
855 rtl::OUString aLangStr;
856 rtl::OUString aCountry;
857 convertLanguageToIsoNames( nLang, aLangStr, aCountry );
858 if ( !aCountry.isEmpty() )
859 {
860 rtl::OUStringBuffer aBuf( aLangStr);
861 aBuf.append( cSep );
862 aBuf.append( aCountry );
863 return aBuf.makeStringAndClear();
864 }
865 else
866 return aLangStr;
867 }
868
869 // -----------------------------------------------------------------------
870
871 // static
872 rtl::OString MsLangId::convertLanguageToIsoByteString( LanguageType nLang,
873 sal_Char cSep )
874 {
875 rtl::OString aLangStr;
876 rtl::OString aCountry;
877 convertLanguageToIsoNames( nLang, aLangStr, aCountry );
878 if ( !aCountry.isEmpty() )
879 {
880 rtl::OStringBuffer aBuf( aLangStr);
881 aBuf.append( cSep );
882 aBuf.append( aCountry );
883 return aBuf.makeStringAndClear();
884 }
885 return aLangStr;
886 }
887
888 // =======================================================================
889
890 // static
891 LanguageType MsLangId::convertIsoNamesToLanguage( const rtl::OUString& rLang,
892 const rtl::OUString& rCountry )
893 {
894 // language is lower case in table
895 rtl::OUString aLowerLang = rLang.toAsciiLowerCase();
896 // country is upper case in table
897 rtl::OUString aUpperCountry = rCountry.toAsciiUpperCase();
898
899 // first look for exact match
900 const IsoLangEntry* pFirstLang = NULL;
901 const IsoLangEntry* pEntry = aImplIsoLangEntries;
902 do
903 {
904 if ( aLowerLang.equalsAscii( pEntry->maLangStr ) )
905 {
906 if ( aUpperCountry.isEmpty() ||
907 aUpperCountry.equalsAscii( pEntry->maCountry ) )
908 return pEntry->mnLang;
909 if ( !pFirstLang )
910 pFirstLang = pEntry;
911 else if ( !*pEntry->maCountry )
912 pFirstLang = pEntry;
913 }
914 ++pEntry;
915 }
916 while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
917
918 // some eng countries should be mapped to a specific english language
919 if ( aLowerLang == "en" )
920 {
921 const IsoLangEngEntry* pEngEntry = aImplIsoLangEngEntries;
922 do
923 {
924 if ( aUpperCountry.equalsAscii( pEngEntry->maCountry ) )
925 return pEngEntry->mnLang;
926 ++pEngEntry;
927 }
928 while ( pEngEntry->mnLang != LANGUAGE_DONTKNOW );
929 }
930
931 // test for specific languages which are not used standard ISO 3166 codes
932 const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries;
933 do
934 {
935 if ( aLowerLang.equalsAscii( pNoneStdEntry->maLangStr ) )
936 {
937 // The countries in this table are not all in upper case
938 if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry->maCountry ) )
939 return pNoneStdEntry->mnLang;
940 }
941 ++pNoneStdEntry;
942 }
943 while ( pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW );
944 pNoneStdEntry = aImplIsoNoneStdLangEntries2;
945 do
946 {
947 if ( aLowerLang.equalsAscii( pNoneStdEntry->maLangStr ) )
948 {
949 // The countries in this table are not all in upper case
950 if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry->maCountry ) )
951 return pNoneStdEntry->mnLang;
952 }
953 ++pNoneStdEntry;
954 }
955 while ( pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW );
956
957 // If the language is correct, than we return the default language
958 if ( pFirstLang )
959 return pFirstLang->mnLang;
960
961 // if only the country is set, look for any entry matching the country
962 // (to allow reading country and language in separate steps, in any order)
963 if ( !rCountry.isEmpty() && rLang.isEmpty() )
964 {
965 const IsoLangEntry* pEntry2 = aImplIsoLangEntries;
966 do
967 {
968 if ( aUpperCountry.equalsAscii( pEntry2->maCountry ) )
969 return pEntry2->mnLang;
970 ++pEntry2;
971 }
972 while ( pEntry2->mnLang != LANGUAGE_DONTKNOW );
973
974 aLowerLang = aUpperCountry.toAsciiLowerCase();
975 }
976
977 // Now look for all other definitions, which are not standard
978 const IsoLangOtherEntry* pOtherEntry = aImplOtherEntries;
979 do
980 {
981 if ( aLowerLang.equalsAscii( pOtherEntry->mpLangStr ) )
982 return pOtherEntry->mnLang;
983 ++pOtherEntry;
984 }
985 while ( pOtherEntry->mnLang != LANGUAGE_DONTKNOW );
986
987 return LANGUAGE_DONTKNOW;
988 }
989
990 // -----------------------------------------------------------------------
991
992 // static
993 LanguageType MsLangId::convertIsoNamesToLanguage( const rtl::OString& rLang,
994 const rtl::OString& rCountry )
995 {
996 rtl::OUString aLang = OStringToOUString( rLang, RTL_TEXTENCODING_ASCII_US);
997 rtl::OUString aCountry = OStringToOUString( rCountry, RTL_TEXTENCODING_ASCII_US);
998 return convertIsoNamesToLanguage( aLang, aCountry);
999 }
1000
1001 // -----------------------------------------------------------------------
1002
1003 // static
1004 LanguageType MsLangId::convertIsoStringToLanguage(
1005 const rtl::OUString& rString, sal_Unicode cSep )
1006 {
1007 rtl::OUString aLang;
1008 rtl::OUString aCountry;
1009 sal_Int32 nSepPos = rString.indexOf( cSep );
1010 if ( nSepPos >= 0 )
1011 {
1012 aLang = rString.copy( 0, nSepPos );
1013 aCountry = rString.copy( nSepPos+1 );
1014 }
1015 else
1016 aLang = rString;
1017
1018 return convertIsoNamesToLanguage( aLang, aCountry );
1019 }
1020
1021 // -----------------------------------------------------------------------
1022
1023 struct IsoLangGLIBCModifiersEntry
1024 {
1025 LanguageType mnLang;
1026 sal_Char maLangStr[4];
1027 sal_Char maCountry[3];
1028 sal_Char maAtString[9];
1029 };
1030
1031 static IsoLangGLIBCModifiersEntry const aImplIsoLangGLIBCModifiersEntries[] =
1032 {
1033 // MS-LANGID codes ISO639-1/2/3 ISO3166 glibc modifier
1034 { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs", "BA", "cyrillic" },
1035 { LANGUAGE_USER_SERBIAN_LATIN_SERBIA, "sr", "RS", "latin" }, // Serbian Latin in Serbia
1036 { LANGUAGE_SERBIAN_LATIN, "sr", "CS", "latin" }, // Serbian Latin in Serbia and Montenegro
1037 { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO, "sr", "ME", "latin" }, // Serbian Latin in Montenegro
1038 { LANGUAGE_SERBIAN_LATIN_NEUTRAL, "sr", "", "latin" },
1039 { LANGUAGE_AZERI_CYRILLIC, "az", "AZ", "cyrillic" },
1040 { LANGUAGE_UZBEK_CYRILLIC, "uz", "UZ", "cyrillic" },
1041 { LANGUAGE_DONTKNOW, "", "", "" } // marks end of table
1042 };
1043
1044 // convert a unix locale string into LanguageType
1045
1046 // static
1047 LanguageType MsLangId::convertUnxByteStringToLanguage(
1048 const rtl::OString& rString )
1049 {
1050 rtl::OString aLang;
1051 rtl::OString aCountry;
1052 rtl::OString aAtString;
1053
1054 sal_Int32 nLangSepPos = rString.indexOf( (sal_Char)'_' );
1055 sal_Int32 nCountrySepPos = rString.indexOf( (sal_Char)'.' );
1056 sal_Int32 nAtPos = rString.indexOf( (sal_Char)'@' );
1057
1058 if (nCountrySepPos < 0)
1059 nCountrySepPos = nAtPos;
1060 if (nCountrySepPos < 0)
1061 nCountrySepPos = rString.getLength();
1062
1063 if (nAtPos >= 0)
1064 aAtString = rString.copy( nAtPos+1 );
1065
1066 if ( ((nLangSepPos >= 0) && (nLangSepPos > nCountrySepPos))
1067 || ((nLangSepPos < 0)) )
1068 {
1069 // eg. "el.sun_eu_greek", "tchinese", "es.ISO8859-15"
1070 aLang = rString.copy( 0, nCountrySepPos );
1071 }
1072 else if ( nLangSepPos >= 0 )
1073 {
1074 // well formed iso names like "en_US.UTF-8", "sh_BA.ISO8859-2@bosnia"
1075 aLang = rString.copy( 0, nLangSepPos );
1076 aCountry = rString.copy( nLangSepPos+1, nCountrySepPos - nLangSepPos - 1);
1077 }
1078
1079 // if there is a glibc modifier, first look for exact match in modifier table
1080 if (!aAtString.isEmpty())
1081 {
1082 // language is lower case in table
1083 rtl::OString aLowerLang = aLang.toAsciiLowerCase();
1084 // country is upper case in table
1085 rtl::OString aUpperCountry = aCountry.toAsciiUpperCase();
1086 const IsoLangGLIBCModifiersEntry* pGLIBCModifiersEntry = aImplIsoLangGLIBCModifiersEntries;
1087 do
1088 { // avoid embedded \0 warning
1089 if (( aLowerLang.equals( static_cast< const char* >( pGLIBCModifiersEntry->maLangStr ))) &&
1090 ( aAtString.equals( static_cast< const char* >( pGLIBCModifiersEntry->maAtString ))))
1091 {
1092 if ( aUpperCountry.isEmpty() ||
1093 aUpperCountry.equals( static_cast< const char* >( pGLIBCModifiersEntry->maCountry )))
1094 {
1095 return pGLIBCModifiersEntry->mnLang;
1096 }
1097 }
1098 ++pGLIBCModifiersEntry;
1099 }
1100 while ( pGLIBCModifiersEntry->mnLang != LANGUAGE_DONTKNOW );
1101 }
1102
1103 return convertIsoNamesToLanguage( aLang, aCountry );
1104 }
1105
1106 // -----------------------------------------------------------------------
1107 // pass one IsoLangEntry to the outer world of the resource compiler
1108
1109 // static
1110 const MsLangId::IsoLangEntry* MsLangId::getIsoLangEntry( size_t nIndex )
1111 {
1112 if (nIndex < SAL_N_ELEMENTS(aImplIsoLangEntries))
1113 return &aImplIsoLangEntries[ nIndex];
1114 return 0;
1115 }
1116
1117 /* vim:set shiftwidth=4 softtabstop=4 expandtab: */
FREE OFFICE SUITE