Line data Source code
1 : /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
2 : /*
3 : * This file is part of the LibreOffice project.
4 : *
5 : * This Source Code Form is subject to the terms of the Mozilla Public
6 : * License, v. 2.0. If a copy of the MPL was not distributed with this
7 : * file, You can obtain one at http://mozilla.org/MPL/2.0/.
8 : *
9 : * This file incorporates work covered by the following license notice:
10 : *
11 : * Licensed to the Apache Software Foundation (ASF) under one or more
12 : * contributor license agreements. See the NOTICE file distributed
13 : * with this work for additional information regarding copyright
14 : * ownership. The ASF licenses this file to you under the Apache
15 : * License, Version 2.0 (the "License"); you may not use this file
16 : * except in compliance with the License. You may obtain a copy of
17 : * the License at http://www.apache.org/licenses/LICENSE-2.0 .
18 : */
19 :
20 : #include <rtl/ustring.hxx>
21 : #include <rtl/string.hxx>
22 : #include <rtl/ustrbuf.hxx>
23 : #include <rtl/strbuf.hxx>
24 :
25 : #include "i18nlangtag/mslangid.hxx"
26 : #include "i18nlangtag/languagetag.hxx"
27 :
28 : using namespace com::sun::star;
29 :
30 :
31 :
32 : static const LanguageType kSAME = 0xffff;
33 :
34 : namespace {
35 292245 : inline LanguageType getOverrideLang( LanguageType nLang, LanguageType nOverride )
36 : {
37 292245 : return nOverride ? ((nOverride == kSAME) ? nLang : nOverride) : nLang;
38 : }
39 : }
40 :
41 : /* Usage of override mechanism:
42 : * If a table entry's mnOverride is not 0, an override entry with an mnLang
43 : * value of (mnOverride==kSAME ? mnLang : mnOverride) exists that should be
44 : * used instead. There MUST exist one such entry that does not have an
45 : * mnOverride value and within one table it MUST be located before any entry
46 : * with that mnLang and an mnOverride value of not 0. Usually kSAME is used as
47 : * override value, with rare exceptions, see tables below.
48 : *
49 : * The override serves these purposes:
50 : * - With getOverride() it indicates that there is a different language tag
51 : * (locale) that the requested language tag should be "canonicalized" to.
52 : * - With lookupFallbackLocale() a locale may be returned where the language
53 : * tag differs.
54 : * - With convertLanguageToLocaleImpl() and bIgnoreOverride=false the override
55 : * is followed and the override locale returned.
56 : * - With convertLocaleToLanguageImpl() a different LangID may be returned in
57 : * rare cases where the actual mapped ID differs.
58 : */
59 :
60 : struct IsoLanguageCountryEntry
61 : {
62 : LanguageType mnLang;
63 : sal_Char maLanguage[4];
64 : sal_Char maCountry[3];
65 : LanguageType mnOverride;
66 :
67 : /** Obtain a language tag string with '-' separator. */
68 : OUString getTagString() const;
69 :
70 : /** Obtain a locale. */
71 : ::com::sun::star::lang::Locale getLocale() const;
72 : };
73 :
74 : struct IsoLanguageScriptCountryEntry
75 : {
76 : LanguageType mnLang;
77 : sal_Char maLanguageScript[9]; ///< "ll-Ssss" or "lll-Ssss"
78 : sal_Char maCountry[3];
79 : LanguageType mnOverride;
80 :
81 : /** Obtain a language tag string with '-' separator. */
82 : OUString getTagString() const;
83 :
84 : /** Obtain a locale. */
85 : ::com::sun::star::lang::Locale getLocale() const;
86 :
87 : /** If rStr starts with maLanguageScript ignoring case.
88 :
89 : We don't have OUString::startsWithIgnoreAsciiCaseAscii()
90 : */
91 : bool startsInIgnoreAsciiCase( const OUString & rStr ) const;
92 : };
93 :
94 : struct Bcp47CountryEntry
95 : {
96 : LanguageType mnLang;
97 : const sal_Char* mpBcp47;
98 : sal_Char maCountry[3];
99 : const sal_Char* mpFallback;
100 :
101 : /** Obtain a language tag string with '-' separator. */
102 : OUString getTagString() const;
103 :
104 : /** Obtain a locale. */
105 : ::com::sun::star::lang::Locale getLocale() const;
106 : };
107 :
108 : struct IsoLangEngEntry
109 : {
110 : LanguageType mnLang;
111 : sal_Char maCountry[3];
112 : };
113 :
114 : struct IsoLangNoneStdEntry
115 : {
116 : LanguageType mnLang;
117 : sal_Char maLanguage[4];
118 : sal_Char maCountry[9];
119 : };
120 :
121 : struct IsoLangOtherEntry
122 : {
123 : LanguageType mnLang;
124 : const sal_Char* mpLanguage;
125 : };
126 :
127 :
128 :
129 : // Entries for languages are lower case, for countries upper case, as
130 : // recommended by rfc5646 (obsoletes rfc4646 (obsoletes rfc3066 (obsoletes
131 : // rfc1766))). convertIsoNamesToLanguage(), convertLocaleToLanguageImpl()
132 : // and lookupFallbackLocale() are case insensitive.
133 : //
134 : // Sort order: Most used first and within one language the default fallback
135 : // locale of that language first.
136 : //
137 : // The default entry for a LangID <-> ISO mapping has to be first. For
138 : // conversion of legacy mappings one LangID can map to multiple ISO codes
139 : // except if the LangID is primary-only, and one ISO code combination can map
140 : // to multiple LangIDs. For compatibility with already existing calls it can
141 : // also be a sequence as follows:
142 :
143 : // LANGUAGE_ENGLISH, "en", ""
144 : // LANGUAGE_ENGLISH_US, "en", "US"
145 :
146 : // Here, in a convertIsoNamesToLanguage() call "en-US" is converted to
147 : // LANGUAGE_ENGLISH_US and "en" is converted to LANGUAGE_ENGLISH. A call with
148 : // "en-ZZ" (not in table) would result in LANGUAGE_ENGLISH because the first
149 : // entry matching the language and not having a country is returned, regardless
150 : // of whether being sorted before or after other entries of the same language
151 : // with some country. To obtain a _locale_ (not language only) in the order
152 : // given, lookupFallbackLocale() must be called.
153 :
154 : // If the sequence instead was
155 :
156 : // LANGUAGE_ENGLISH_US, "en", "US"
157 : // LANGUAGE_ENGLISH, "en", ""
158 :
159 : // in a convertIsoNamesToLanguage() call "en-US" would still be converted to
160 : // LANGUAGE_ENGLISH_US, but "en" would _also_ be converted to
161 : // LANGUAGE_ENGLISH_US because no country was passed and it is the first entry
162 : // to match the language, see code. A call with "en-ZZ" (not in table) would
163 : // still result in LANGUAGE_ENGLISH.
164 :
165 : /* Currently (2013-08-29) only these primary LangID are still used literally in
166 : * code:
167 : * LANGUAGE_ENGLISH LANGUAGE_ARABIC_PRIMARY_ONLY
168 : */
169 :
170 : static IsoLanguageCountryEntry const aImplIsoLangEntries[] =
171 : {
172 : // MS-LANGID codes, ISO639-1/2/3, ISO3166, override
173 : { LANGUAGE_ENGLISH, "en", "" , 0 },
174 : { LANGUAGE_ENGLISH_US, "en", "US", 0 },
175 : { LANGUAGE_ENGLISH_UK, "en", "GB", 0 },
176 : { LANGUAGE_ENGLISH_AUS, "en", "AU", 0 },
177 : { LANGUAGE_ENGLISH_CAN, "en", "CA", 0 },
178 : { LANGUAGE_FRENCH, "fr", "FR", 0 },
179 : { LANGUAGE_GERMAN, "de", "DE", 0 },
180 : { LANGUAGE_ITALIAN, "it", "IT", 0 },
181 : { LANGUAGE_DUTCH, "nl", "NL", 0 },
182 : { LANGUAGE_SPANISH_MODERN, "es", "ES", 0 },
183 : { LANGUAGE_SPANISH_DATED, "es", "ES", 0 },
184 : { LANGUAGE_PORTUGUESE, "pt", "PT", 0 },
185 : { LANGUAGE_PORTUGUESE_BRAZILIAN, "pt", "BR", 0 },
186 : { LANGUAGE_DANISH, "da", "DK", 0 },
187 : { LANGUAGE_GREEK, "el", "GR", 0 },
188 : { LANGUAGE_CHINESE_SIMPLIFIED, "zh", "CN", 0 },
189 : { LANGUAGE_CHINESE_SIMPLIFIED_LEGACY, "zh", "CN", 0 },
190 : { LANGUAGE_CHINESE_TRADITIONAL, "zh", "TW", 0 },
191 : { LANGUAGE_CHINESE_HONGKONG, "zh", "HK", 0 },
192 : { LANGUAGE_CHINESE_SINGAPORE, "zh", "SG", 0 },
193 : { LANGUAGE_CHINESE_MACAU, "zh", "MO", 0 },
194 : { LANGUAGE_CHINESE_LSO, "zh", "" , 0 },
195 : { LANGUAGE_YUE_CHINESE_HONGKONG, "yue", "HK", 0 },
196 : { LANGUAGE_ENGLISH_HONG_KONG_SAR, "en", "HK", 0 },
197 : { LANGUAGE_JAPANESE, "ja", "JP", 0 },
198 : { LANGUAGE_KOREAN, "ko", "KR", 0 },
199 : { LANGUAGE_KOREAN_JOHAB, "ko", "KR", 0 },
200 : { LANGUAGE_USER_KOREAN_NORTH, "ko", "KP", 0 },
201 : { LANGUAGE_SWEDISH, "sv", "SE", 0 },
202 : { LANGUAGE_SWEDISH_FINLAND, "sv", "FI", 0 },
203 : { LANGUAGE_FINNISH, "fi", "FI", 0 },
204 : { LANGUAGE_RUSSIAN, "ru", "RU", 0 },
205 : { LANGUAGE_TATAR, "tt", "RU", 0 },
206 : { LANGUAGE_ENGLISH_NZ, "en", "NZ", 0 },
207 : { LANGUAGE_ENGLISH_EIRE, "en", "IE", 0 },
208 : { LANGUAGE_DUTCH_BELGIAN, "nl", "BE", 0 },
209 : { LANGUAGE_FRENCH_BELGIAN, "fr", "BE", 0 },
210 : { LANGUAGE_FRENCH_CANADIAN, "fr", "CA", 0 },
211 : { LANGUAGE_FRENCH_SWISS, "fr", "CH", 0 },
212 : { LANGUAGE_GERMAN_SWISS, "de", "CH", 0 },
213 : { LANGUAGE_GERMAN_AUSTRIAN, "de", "AT", 0 },
214 : { LANGUAGE_ITALIAN_SWISS, "it", "CH", 0 },
215 : { LANGUAGE_ALBANIAN, "sq", "AL", 0 },
216 : { LANGUAGE_ARABIC_SAUDI_ARABIA, "ar", "SA", 0 },
217 : { LANGUAGE_ARABIC_EGYPT, "ar", "EG", 0 },
218 : { LANGUAGE_ARABIC_UAE, "ar", "AE", 0 },
219 : { LANGUAGE_ARABIC_IRAQ, "ar", "IQ", 0 },
220 : { LANGUAGE_ARABIC_LIBYA, "ar", "LY", 0 },
221 : { LANGUAGE_ARABIC_ALGERIA, "ar", "DZ", 0 },
222 : { LANGUAGE_ARABIC_MOROCCO, "ar", "MA", 0 },
223 : { LANGUAGE_ARABIC_TUNISIA, "ar", "TN", 0 },
224 : { LANGUAGE_ARABIC_OMAN, "ar", "OM", 0 },
225 : { LANGUAGE_ARABIC_YEMEN, "ar", "YE", 0 },
226 : { LANGUAGE_ARABIC_SYRIA, "ar", "SY", 0 },
227 : { LANGUAGE_ARABIC_JORDAN, "ar", "JO", 0 },
228 : { LANGUAGE_ARABIC_LEBANON, "ar", "LB", 0 },
229 : { LANGUAGE_ARABIC_KUWAIT, "ar", "KW", 0 },
230 : { LANGUAGE_ARABIC_BAHRAIN, "ar", "BH", 0 },
231 : { LANGUAGE_ARABIC_QATAR, "ar", "QA", 0 },
232 : { LANGUAGE_USER_ARABIC_CHAD, "ar", "TD", 0 },
233 : { LANGUAGE_USER_ARABIC_COMOROS, "ar", "KM", 0 },
234 : { LANGUAGE_USER_ARABIC_DJIBOUTI, "ar", "DJ", 0 },
235 : { LANGUAGE_USER_ARABIC_ERITREA, "ar", "ER", 0 },
236 : { LANGUAGE_USER_ARABIC_ISRAEL, "ar", "IL", 0 },
237 : { LANGUAGE_USER_ARABIC_MAURITANIA, "ar", "MR", 0 },
238 : { LANGUAGE_USER_ARABIC_PALESTINE, "ar", "PS", 0 },
239 : { LANGUAGE_USER_ARABIC_SOMALIA, "ar", "SO", 0 },
240 : { LANGUAGE_USER_ARABIC_SUDAN, "ar", "SD", 0 },
241 : { LANGUAGE_ARABIC_PRIMARY_ONLY, "ar", "" , 0 },
242 : { LANGUAGE_BASQUE, "eu", "" , 0 },
243 : { LANGUAGE_BULGARIAN, "bg", "BG", 0 },
244 : { LANGUAGE_CZECH, "cs", "CZ", 0 },
245 : { LANGUAGE_CZECH, "cz", "" , kSAME },
246 : { LANGUAGE_ENGLISH_JAMAICA, "en", "JM", 0 },
247 : { LANGUAGE_ENGLISH_CARRIBEAN, "en", "BS", 0 }, // not 100%, because AG is Bahamas
248 : { LANGUAGE_ENGLISH_BELIZE, "en", "BZ", 0 },
249 : { LANGUAGE_ENGLISH_TRINIDAD, "en", "TT", 0 },
250 : { LANGUAGE_ENGLISH_ZIMBABWE, "en", "ZW", 0 },
251 : { LANGUAGE_ENGLISH_INDONESIA, "en", "ID", 0 },
252 : { LANGUAGE_ESTONIAN, "et", "EE", 0 },
253 : { LANGUAGE_FAEROESE, "fo", "FO", 0 },
254 : { LANGUAGE_FARSI, "fa", "IR", 0 },
255 : { LANGUAGE_FRENCH_LUXEMBOURG, "fr", "LU", 0 },
256 : { LANGUAGE_FRENCH_MONACO, "fr", "MC", 0 },
257 : { LANGUAGE_GERMAN_LUXEMBOURG, "de", "LU", 0 },
258 : { LANGUAGE_GERMAN_LIECHTENSTEIN, "de", "LI", 0 },
259 : { LANGUAGE_HEBREW, "he", "IL", 0 }, // new: old was "iw"
260 : { LANGUAGE_HEBREW, "iw", "IL", kSAME }, // old: new is "he"
261 : { LANGUAGE_HUNGARIAN, "hu", "HU", 0 },
262 : { LANGUAGE_ICELANDIC, "is", "IS", 0 },
263 : { LANGUAGE_INDONESIAN, "id", "ID", 0 }, // new: old was "in"
264 : { LANGUAGE_INDONESIAN, "in", "ID", kSAME }, // old: new is "id"
265 : { LANGUAGE_NORWEGIAN, "no", "NO", 0 },
266 : { LANGUAGE_NORWEGIAN_BOKMAL, "nb", "NO", 0 },
267 : { LANGUAGE_NORWEGIAN_BOKMAL_LSO, "nb", "" , 0 },
268 : { LANGUAGE_NORWEGIAN_NYNORSK, "nn", "NO", 0 },
269 : { LANGUAGE_NORWEGIAN_NYNORSK_LSO, "nn", "" , 0 },
270 : { LANGUAGE_POLISH, "pl", "PL", 0 },
271 : { LANGUAGE_RHAETO_ROMAN, "rm", "CH", 0 },
272 : { LANGUAGE_ROMANIAN, "ro", "RO", 0 },
273 : { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD", 0 },
274 : { LANGUAGE_SLOVAK, "sk", "SK", 0 },
275 : { LANGUAGE_SLOVENIAN, "sl", "SI", 0 },
276 : { LANGUAGE_SPANISH_MEXICAN, "es", "MX", 0 },
277 : { LANGUAGE_SPANISH_GUATEMALA, "es", "GT", 0 },
278 : { LANGUAGE_SPANISH_COSTARICA, "es", "CR", 0 },
279 : { LANGUAGE_SPANISH_PANAMA, "es", "PA", 0 },
280 : { LANGUAGE_SPANISH_DOMINICAN_REPUBLIC, "es", "DO", 0 },
281 : { LANGUAGE_SPANISH_VENEZUELA, "es", "VE", 0 },
282 : { LANGUAGE_SPANISH_COLOMBIA, "es", "CO", 0 },
283 : { LANGUAGE_SPANISH_PERU, "es", "PE", 0 },
284 : { LANGUAGE_SPANISH_ARGENTINA, "es", "AR", 0 },
285 : { LANGUAGE_SPANISH_ECUADOR, "es", "EC", 0 },
286 : { LANGUAGE_SPANISH_CHILE, "es", "CL", 0 },
287 : { LANGUAGE_SPANISH_URUGUAY, "es", "UY", 0 },
288 : { LANGUAGE_SPANISH_PARAGUAY, "es", "PY", 0 },
289 : { LANGUAGE_SPANISH_BOLIVIA, "es", "BO", 0 },
290 : { LANGUAGE_SPANISH_EL_SALVADOR, "es", "SV", 0 },
291 : { LANGUAGE_SPANISH_HONDURAS, "es", "HN", 0 },
292 : { LANGUAGE_SPANISH_NICARAGUA, "es", "NI", 0 },
293 : { LANGUAGE_SPANISH_PUERTO_RICO, "es", "PR", 0 },
294 : { LANGUAGE_SPANISH_UNITED_STATES, "es", "US", 0 },
295 : { LANGUAGE_SPANISH_LATIN_AMERICA, "es", "" , 0 },
296 : { LANGUAGE_TURKISH, "tr", "TR", 0 },
297 : { LANGUAGE_UKRAINIAN, "uk", "UA", 0 },
298 : { LANGUAGE_VIETNAMESE, "vi", "VN", 0 },
299 : { LANGUAGE_LATVIAN, "lv", "LV", 0 },
300 : { LANGUAGE_MACEDONIAN, "mk", "MK", 0 },
301 : { LANGUAGE_MALAY_MALAYSIA, "ms", "MY", 0 },
302 : { LANGUAGE_MALAY_BRUNEI_DARUSSALAM, "ms", "BN", 0 },
303 : { LANGUAGE_ENGLISH_MALAYSIA, "en", "MY", 0 },
304 : { LANGUAGE_THAI, "th", "TH", 0 },
305 : { LANGUAGE_LITHUANIAN, "lt", "LT", 0 },
306 : { LANGUAGE_LITHUANIAN_CLASSIC, "lt", "LT", 0 },
307 : { LANGUAGE_CROATIAN, "hr", "HR", 0 }, // Croatian in Croatia
308 : { LANGUAGE_CROATIAN_BOSNIA_HERZEGOVINA, "hr", "BA", 0 },
309 : { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA, "bs", "BA", 0 },
310 : { LANGUAGE_BOSNIAN_LSO, "bs", "" , 0 }, // so what is 'bs' vs 'bs-Latn'?
311 : { LANGUAGE_SERBIAN_CYRILLIC_SERBIA, "sr", "RS", 0 }, // Serbian Cyrillic in Serbia
312 : { LANGUAGE_OBSOLETE_USER_SERBIAN_CYRILLIC_SERBIA, "sr", "RS", 0 },
313 : { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr", "CS", 0 }, // Serbian Cyrillic in Serbia and Montenegro
314 : { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr", "YU", kSAME }, // legacy Serbian Cyrillic in Serbia and Montenegro (former Yugoslavia); kludge, sr_CS not supported by ICU 2.6 (3.4 does)
315 : { LANGUAGE_SERBIAN_CYRILLIC_MONTENEGRO, "sr", "ME", 0 },
316 : { LANGUAGE_OBSOLETE_USER_SERBIAN_CYRILLIC_MONTENEGRO, "sr", "ME", 0 },
317 : { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr", "BA", 0 },
318 : { LANGUAGE_SERBIAN_CYRILLIC_LSO, "sr", "" , 0 },
319 : { LANGUAGE_SERBIAN_LATIN_SERBIA, "sh", "RS", kSAME }, // legacy kludge, is sr-Latn-RS now
320 : { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_SERBIA, "sh", "RS", kSAME }, // legacy kludge, is sr-Latn-RS now
321 : { LANGUAGE_SERBIAN_LATIN_SAM, "sh", "CS", kSAME }, // legacy kludge, is sr-Latn-CS now
322 : { LANGUAGE_SERBIAN_LATIN_SAM, "sh", "YU", kSAME }, // legacy kludge, is sr-Latn-YU now
323 : { LANGUAGE_SERBIAN_LATIN_MONTENEGRO, "sh", "ME", kSAME }, // legacy kludge, is sr-Latn-ME now
324 : { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_MONTENEGRO, "sh", "ME", kSAME }, // legacy kludge, is sr-Latn-ME now
325 : { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA, "sh", "BA", kSAME }, // legacy kludge, is sr-Latn-BA now
326 : { LANGUAGE_SERBIAN_LATIN_LSO, "sh", "" , kSAME }, // legacy kludge, is sr-Latn now
327 : { LANGUAGE_ARMENIAN, "hy", "AM", 0 },
328 : { LANGUAGE_AZERI_LATIN, "az", "AZ", 0 }, // macrolanguage code
329 : { LANGUAGE_UZBEK_LATIN, "uz", "UZ", 0 }, // macrolanguage code
330 : { LANGUAGE_UZBEK_LATIN_LSO, "uz", "" , 0 }, // macrolanguage code
331 : { LANGUAGE_BENGALI_BANGLADESH, "bn", "BD", 0 },
332 : { LANGUAGE_BENGALI, "bn", "IN", 0 },
333 : { LANGUAGE_BURMESE, "my", "MM", 0 },
334 : { LANGUAGE_KAZAKH, "kk", "KZ", 0 },
335 : { LANGUAGE_ENGLISH_INDIA, "en", "IN", 0 },
336 : { LANGUAGE_URDU_INDIA, "ur", "IN", 0 },
337 : { LANGUAGE_URDU_PAKISTAN, "ur", "PK", 0 },
338 : { LANGUAGE_HINDI, "hi", "IN", 0 },
339 : { LANGUAGE_GUJARATI, "gu", "IN", 0 },
340 : { LANGUAGE_KANNADA, "kn", "IN", 0 },
341 : { LANGUAGE_ASSAMESE, "as", "IN", 0 },
342 : { LANGUAGE_KASHMIRI_INDIA, "ks", "IN", 0 },
343 : { LANGUAGE_KASHMIRI, "ks", "" , kSAME }, // Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that
344 : { LANGUAGE_MALAYALAM, "ml", "IN", 0 },
345 : { LANGUAGE_MANIPURI, "mni", "IN", 0 },
346 : { LANGUAGE_MARATHI, "mr", "IN", 0 },
347 : { LANGUAGE_KONKANI, "kok", "IN", 0 },
348 : { LANGUAGE_NEPALI, "ne", "NP", 0 },
349 : { LANGUAGE_NEPALI_INDIA, "ne", "IN", 0 },
350 : { LANGUAGE_ODIA, "or", "IN", 0 },
351 : { LANGUAGE_PUNJABI, "pa", "IN", 0 },
352 : { LANGUAGE_SANSKRIT, "sa", "IN", 0 },
353 : { LANGUAGE_TAMIL, "ta", "IN", 0 },
354 : { LANGUAGE_TAMIL_SRI_LANKA, "ta", "LK", 0 },
355 : { LANGUAGE_TELUGU, "te", "IN", 0 },
356 : { LANGUAGE_PUNJABI_PAKISTAN, "pnb", "PK", 0 },
357 : { LANGUAGE_PUNJABI_ARABIC_LSO, "pnb", "" , 0 },
358 : { LANGUAGE_PUNJABI_PAKISTAN, "lah", "PK", kSAME }, // macrolanguage code, earlier preferred 'lah' over 'pa' for Western Panjabi, now there is 'pnb'
359 : { LANGUAGE_PUNJABI_PAKISTAN, "pa", "PK", kSAME }, // MS maps this to 'pa-Arab-PK', but 'pa'='pan' Eastern Panjabi is not used in PK, only in IN
360 : { LANGUAGE_SINDHI_PAKISTAN, "sd", "PK", kSAME }, // Arabic script
361 : { LANGUAGE_SINDHI, "sd", "IN", 0 }, // TODO: there's Deva(nagari) and Arab(ic) script, MS maps this to 'sd-Deva-IN'
362 : { LANGUAGE_BELARUSIAN, "be", "BY", 0 },
363 : { LANGUAGE_CATALAN, "ca", "ES", 0 }, // Spain (default)
364 : { LANGUAGE_CATALAN, "ca", "AD", 0 }, // Andorra
365 : //LANGUAGE_CATALAN_VALENCIAN ca-ES-valencia Bcp47CountryEntry takes precedence
366 : { LANGUAGE_CATALAN_VALENCIAN, "ca", "XV", kSAME }, // XV: ISO 3166 user-assigned; old workaround for UI localization only, in case it escaped to document content
367 : { LANGUAGE_CATALAN_VALENCIAN, "qcv", "ES", kSAME }, // qcv: ISO 639-3 reserved-for-local-use; old UI localization quirk only, in case it escaped to document content
368 : { LANGUAGE_FRENCH_CAMEROON, "fr", "CM", 0 },
369 : { LANGUAGE_FRENCH_COTE_D_IVOIRE, "fr", "CI", 0 },
370 : { LANGUAGE_FRENCH_MALI, "fr", "ML", 0 },
371 : { LANGUAGE_FRENCH_SENEGAL, "fr", "SN", 0 },
372 : { LANGUAGE_FRENCH_ZAIRE, "fr", "CD", 0 }, // Democratic Republic Of Congo
373 : { LANGUAGE_FRENCH_MOROCCO, "fr", "MA", 0 },
374 : { LANGUAGE_FRENCH_REUNION, "fr", "RE", 0 },
375 : { LANGUAGE_FRENCH, "fr", "" , 0 }, // needed as a catcher before other "fr" entries!
376 : { LANGUAGE_FRENCH_NORTH_AFRICA, "fr", "" , 0 },
377 : { LANGUAGE_FRENCH_WEST_INDIES, "fr", "" , 0 }, // no ISO country code; MS "Neither defined nor reserved"
378 : { LANGUAGE_FRISIAN_NETHERLANDS, "fy", "NL", 0 },
379 : { LANGUAGE_GAELIC_IRELAND, "ga", "IE", 0 },
380 : { LANGUAGE_GAELIC_SCOTLAND, "gd", "GB", 0 },
381 : { LANGUAGE_GAELIC_SCOTLAND_LEGACY, "gd", "GB", 0 },
382 : { LANGUAGE_GALICIAN, "gl", "ES", 0 },
383 : { LANGUAGE_GEORGIAN, "ka", "GE", 0 },
384 : { LANGUAGE_KHMER, "km", "KH", 0 },
385 : { LANGUAGE_KIRGHIZ, "ky", "KG", 0 },
386 : { LANGUAGE_LAO, "lo", "LA", 0 },
387 : { LANGUAGE_MALTESE, "mt", "MT", 0 },
388 : { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA, "mn", "MN", 0 }, // macrolanguage code; should be khk-MN; Cyrillic script
389 : { LANGUAGE_MONGOLIAN_CYRILLIC_LSO, "mn", "" , 0 }, // macrolanguage code; should be khk; Cyrillic script
390 : { LANGUAGE_RUSSIAN_MOLDOVA, "mo", "MD", 0 },
391 : { LANGUAGE_SWAHILI, "sw", "KE", 0 },
392 : { LANGUAGE_USER_SWAHILI_TANZANIA, "sw", "TZ", 0 },
393 : { LANGUAGE_TAJIK, "tg", "TJ", 0 },
394 : { LANGUAGE_TAJIK_LSO, "tg", "" , 0 },
395 : { LANGUAGE_TIBETAN, "bo", "CN", 0 }, // CN politically correct?
396 : { LANGUAGE_USER_TIBETAN_INDIA, "bo", "IN", 0 },
397 : { LANGUAGE_USER_TIBETAN_BHUTAN, "bo", "BT", 0 }, // MS reserved, but with the ID error instead
398 : { LANGUAGE_DZONGKHA, "dz", "BT", 0 },
399 : { LANGUAGE_USER_DZONGKHA_MAP_LONLY, "dz", "" , 0 }, // because of the MS error, see lang.h
400 : { LANGUAGE_TURKMEN, "tk", "TM", 0 },
401 : { LANGUAGE_WELSH, "cy", "GB", 0 },
402 : { LANGUAGE_SESOTHO, "st", "ZA", 0 },
403 : { LANGUAGE_SEPEDI, "nso", "ZA", 0 },
404 : { LANGUAGE_SEPEDI, "ns", "ZA", kSAME }, // fake "ns" for compatibility with existing OOo1.1.x localization to be able to read those documents
405 : { LANGUAGE_TSONGA, "ts", "ZA", 0 },
406 : { LANGUAGE_TSWANA, "tn", "ZA", 0 },
407 : { LANGUAGE_ENGLISH_SAFRICA, "en", "ZA", 0 },
408 : { LANGUAGE_AFRIKAANS, "af", "ZA", 0 },
409 : { LANGUAGE_VENDA, "ve", "ZA", 0 }, // default 639-1
410 : { LANGUAGE_VENDA, "ven", "ZA", kSAME }, // 639-2 may have been used temporarily since 2004-07-23
411 : { LANGUAGE_XHOSA, "xh", "ZA", 0 },
412 : { LANGUAGE_ZULU, "zu", "ZA", 0 },
413 : // { LANGUAGE_QUECHUA_COLOMBIA, "quc", "CO", 0 }, // MS reserved, and looks wrong, quc would be in Guatemala, not Colombia
414 : { LANGUAGE_QUECHUA_ECUADOR, "quz", "EC", 0 }, // MS
415 : { LANGUAGE_QUECHUA_ECUADOR, "qu", "EC", kSAME }, // macrolanguage code
416 : { LANGUAGE_QUECHUA_PERU, "quz", "PE", 0 }, // MS
417 : { LANGUAGE_QUECHUA_PERU, "qu", "PE", kSAME }, // macrolanguage code
418 : { LANGUAGE_QUECHUA_BOLIVIA, "qu", "BO", 0 }, // macrolanguage code, TODO instead: quh-BO or qul-BO; MS says quz-BO which is wrong
419 : { LANGUAGE_PASHTO, "ps", "AF", 0 },
420 : { LANGUAGE_OROMO, "om", "ET", 0 },
421 : { LANGUAGE_DHIVEHI, "dv", "MV", 0 },
422 : { LANGUAGE_UIGHUR_CHINA, "ug", "CN", 0 },
423 : { LANGUAGE_TIGRIGNA_ETHIOPIA, "ti", "ET", 0 },
424 : { LANGUAGE_TIGRIGNA_ERITREA, "ti", "ER", 0 },
425 : { LANGUAGE_AMHARIC_ETHIOPIA, "am", "ET", 0 },
426 : { LANGUAGE_GUARANI_PARAGUAY, "gug", "PY", 0 },
427 : { LANGUAGE_HAWAIIAN_UNITED_STATES, "haw", "US", 0 },
428 : { LANGUAGE_EDO, "bin", "NG", 0 },
429 : { LANGUAGE_FULFULDE_NIGERIA, "fuv", "NG", 0 },
430 : { LANGUAGE_FULFULDE_NIGERIA, "ff", "NG", kSAME }, // macrolanguage code
431 : { LANGUAGE_FULFULDE_SENEGAL, "ff", "SN", 0 }, // macrolanguage code
432 : { LANGUAGE_HAUSA_NIGERIA, "ha", "NG", kSAME },
433 : { LANGUAGE_USER_HAUSA_GHANA, "ha", "GH", kSAME },
434 : { LANGUAGE_IGBO_NIGERIA, "ig", "NG", 0 },
435 : { LANGUAGE_KANURI_NIGERIA, "kr", "NG", 0 },
436 : { LANGUAGE_YORUBA, "yo", "NG", 0 },
437 : { LANGUAGE_SOMALI, "so", "SO", 0 },
438 : { LANGUAGE_PAPIAMENTU, "pap", "AN", 0 },
439 : { LANGUAGE_USER_PAPIAMENTU_ARUBA, "pap", "AW", 0 },
440 : { LANGUAGE_USER_PAPIAMENTU_CURACAO, "pap", "CW", 0 },
441 : { LANGUAGE_USER_PAPIAMENTU_BONAIRE, "pap", "BQ", 0 },
442 : { LANGUAGE_ENGLISH_SINGAPORE, "en", "SG", 0 },
443 : { LANGUAGE_USER_YIDDISH_US, "yi", "US", 0 },
444 : { LANGUAGE_YIDDISH, "yi", "IL", 0 }, // new: old was "ji"
445 : { LANGUAGE_YIDDISH, "ji", "IL", kSAME }, // old: new is "yi"
446 : { LANGUAGE_SYRIAC, "syr", "TR", 0 }, // "TR" according to http://www.ethnologue.com/show_language.asp?code=SYC
447 : { LANGUAGE_SINHALESE_SRI_LANKA, "si", "LK", 0 },
448 : { LANGUAGE_CHEROKEE_UNITED_STATES, "chr", "US", kSAME },
449 : { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu", "CA", kSAME }, // macrolanguage code
450 : { LANGUAGE_INUKTITUT_LATIN_LSO, "iu", "" , kSAME }, // macrolanguage code
451 : { LANGUAGE_SAMI_NORTHERN_NORWAY, "se", "NO", 0 },
452 : { LANGUAGE_SAMI_INARI, "smn", "FI", 0 },
453 : { LANGUAGE_SAMI_INARI_LSO, "smn", "" , 0 },
454 : { LANGUAGE_SAMI_LULE_NORWAY, "smj", "NO", 0 },
455 : { LANGUAGE_SAMI_LULE_SWEDEN, "smj", "SE", 0 },
456 : { LANGUAGE_SAMI_LULE_LSO, "smj", "" , 0 },
457 : { LANGUAGE_SAMI_NORTHERN_FINLAND, "se", "FI", 0 },
458 : { LANGUAGE_SAMI_NORTHERN_SWEDEN, "se", "SE", 0 },
459 : { LANGUAGE_SAMI_SKOLT, "sms", "FI", 0 },
460 : { LANGUAGE_SAMI_SKOLT_LSO, "sms", "" , 0 },
461 : { LANGUAGE_SAMI_SOUTHERN_NORWAY, "sma", "NO", 0 },
462 : { LANGUAGE_SAMI_SOUTHERN_SWEDEN, "sma", "SE", 0 },
463 : { LANGUAGE_SAMI_SOUTHERN_LSO, "sma", "" , 0 },
464 : { LANGUAGE_USER_SAMI_KILDIN_RUSSIA, "sjd", "RU", 0 },
465 : { LANGUAGE_MAPUDUNGUN_CHILE, "arn", "CL", 0 },
466 : { LANGUAGE_CORSICAN_FRANCE, "co", "FR", 0 },
467 : { LANGUAGE_ALSATIAN_FRANCE, "gsw", "FR", 0 }, // 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.
468 : { LANGUAGE_YAKUT_RUSSIA, "sah", "RU", 0 },
469 : { LANGUAGE_MOHAWK_CANADA, "moh", "CA", 0 },
470 : { LANGUAGE_BASHKIR_RUSSIA, "ba", "RU", 0 },
471 : { LANGUAGE_KICHE_GUATEMALA, "qut", "GT", 0 },
472 : { LANGUAGE_DARI_AFGHANISTAN, "prs", "AF", 0 },
473 : { LANGUAGE_DARI_AFGHANISTAN, "gbz", "AF", kSAME }, // was an error
474 : { LANGUAGE_WOLOF_SENEGAL, "wo", "SN", 0 },
475 : { LANGUAGE_FILIPINO, "fil", "PH", 0 },
476 : { LANGUAGE_USER_TAGALOG, "tl", "PH", 0 },
477 : { LANGUAGE_ENGLISH_PHILIPPINES, "en", "PH", 0 },
478 : { LANGUAGE_IBIBIO_NIGERIA, "ibb", "NG", 0 },
479 : { LANGUAGE_YI, "ii", "CN", 0 },
480 : { LANGUAGE_ENGLISH_ARAB_EMIRATES, "en", "AE", 0 }, // MS reserved
481 : { LANGUAGE_ENGLISH_BAHRAIN, "en", "BH", 0 }, // MS reserved
482 : { LANGUAGE_ENGLISH_EGYPT, "en", "EG", 0 }, // MS reserved
483 : { LANGUAGE_ENGLISH_JORDAN, "en", "JO", 0 }, // MS reserved
484 : { LANGUAGE_ENGLISH_KUWAIT, "en", "KW", 0 }, // MS reserved
485 : { LANGUAGE_ENGLISH_TURKEY, "en", "TR", 0 }, // MS reserved
486 : { LANGUAGE_ENGLISH_YEMEN, "en", "YE", 0 }, // MS reserved
487 : { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "kab", "DZ", 0 }, // In practice Kabyle is the language used for this
488 : { LANGUAGE_OBSOLETE_USER_KABYLE, "kab", "DZ", 0 },
489 : { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "ber", "DZ", kSAME }, // In practice Algeria has standardized on Kabyle as the member of the "ber" collective which gets used there.
490 : { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "tmz", "MA", kSAME },
491 : { LANGUAGE_TAMAZIGHT_MOROCCO, "tmz", "MA", 0 }, // MS reserved
492 : { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "ber", "MA", kSAME }, // Morocco is officially using Tifinagh for its Berber languages, old kludge to distinguish from LANGUAGE_TAMAZIGHT_LATIN_ALGERIA
493 : { LANGUAGE_USER_LATIN_VATICAN, "la", "VA", 0 },
494 : { LANGUAGE_OBSOLETE_USER_LATIN, "la", "VA", 0 },
495 : { LANGUAGE_LATIN_LSO, "la", "" , 0 },
496 : { LANGUAGE_USER_ESPERANTO, "eo", "" , 0 },
497 : { LANGUAGE_USER_INTERLINGUA, "ia", "" , 0 },
498 : { LANGUAGE_MAORI_NEW_ZEALAND, "mi", "NZ", 0 },
499 : { LANGUAGE_OBSOLETE_USER_MAORI, "mi", "NZ", 0 },
500 : { LANGUAGE_KINYARWANDA_RWANDA, "rw", "RW", 0 },
501 : { LANGUAGE_OBSOLETE_USER_KINYARWANDA, "rw", "RW", 0 },
502 : { LANGUAGE_UPPER_SORBIAN_GERMANY, "hsb", "DE", 0 }, // 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
503 : { LANGUAGE_OBSOLETE_USER_UPPER_SORBIAN,"hsb", "DE", 0 },
504 : { LANGUAGE_LOWER_SORBIAN_GERMANY, "dsb", "DE", 0 }, // 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
505 : { LANGUAGE_LOWER_SORBIAN_LSO, "dsb", "" , 0 },
506 : { LANGUAGE_OBSOLETE_USER_LOWER_SORBIAN,"dsb", "DE", 0 },
507 : { LANGUAGE_OCCITAN_FRANCE, "oc", "FR", 0 },
508 : { LANGUAGE_OBSOLETE_USER_OCCITAN, "oc", "FR", 0 },
509 : { LANGUAGE_USER_KURDISH_TURKEY, "kmr", "TR", kSAME },
510 : { LANGUAGE_USER_KURDISH_TURKEY, "ku", "TR", kSAME },
511 : { LANGUAGE_USER_KURDISH_SYRIA, "kmr", "SY", kSAME },
512 : { LANGUAGE_USER_KURDISH_SYRIA, "ku", "SY", kSAME },
513 : { LANGUAGE_KURDISH_ARABIC_IRAQ, "ckb", "IQ", 0 },
514 : { LANGUAGE_KURDISH_ARABIC_IRAQ, "ku", "IQ", kSAME },
515 : { LANGUAGE_OBSOLETE_USER_KURDISH_IRAQ, "ku", "IQ", LANGUAGE_KURDISH_ARABIC_IRAQ },
516 : { LANGUAGE_USER_KURDISH_SOUTHERN_IRAN, "sdh", "IR", 0 },
517 : { LANGUAGE_USER_KURDISH_SOUTHERN_IRAQ, "sdh", "IQ", 0 },
518 : { LANGUAGE_USER_KURDISH_IRAN, "ckb", "IR", 0 },
519 : { LANGUAGE_USER_KURDISH_IRAN, "ku", "IR", kSAME },
520 : { LANGUAGE_KURDISH_ARABIC_LSO, "ckb", "" , 0 },
521 : { LANGUAGE_USER_SARDINIAN, "sc", "IT", 0 }, // macrolanguage code
522 : { LANGUAGE_USER_SARDINIAN_CAMPIDANESE, "sro", "IT", 0 },
523 : { LANGUAGE_USER_SARDINIAN_GALLURESE, "sdn", "IT", 0 },
524 : { LANGUAGE_USER_SARDINIAN_LOGUDORESE, "src", "IT", 0 },
525 : { LANGUAGE_USER_SARDINIAN_SASSARESE, "sdc", "IT", 0 },
526 : { LANGUAGE_BRETON_FRANCE, "br", "FR", 0 },
527 : { LANGUAGE_OBSOLETE_USER_BRETON, "br", "FR", 0 },
528 : { LANGUAGE_KALAALLISUT_GREENLAND, "kl", "GL", 0 },
529 : { LANGUAGE_OBSOLETE_USER_KALAALLISUT, "kl", "GL", 0 },
530 : { LANGUAGE_USER_SWAZI, "ss", "ZA", 0 },
531 : { LANGUAGE_USER_NDEBELE_SOUTH, "nr", "ZA", 0 },
532 : { LANGUAGE_TSWANA_BOTSWANA, "tn", "BW", 0 },
533 : { LANGUAGE_OBSOLETE_USER_TSWANA_BOTSWANA, "tn", "BW", 0 },
534 : { LANGUAGE_USER_MOORE, "mos", "BF", 0 },
535 : { LANGUAGE_USER_BAMBARA, "bm", "ML", 0 },
536 : { LANGUAGE_USER_AKAN, "ak", "GH", 0 },
537 : { LANGUAGE_LUXEMBOURGISH_LUXEMBOURG, "lb", "LU", 0 },
538 : { LANGUAGE_OBSOLETE_USER_LUXEMBOURGISH, "lb", "LU", 0 },
539 : { LANGUAGE_USER_FRIULIAN, "fur", "IT", 0 },
540 : { LANGUAGE_USER_FIJIAN, "fj", "FJ", 0 },
541 : { LANGUAGE_USER_AFRIKAANS_NAMIBIA, "af", "NA", 0 },
542 : { LANGUAGE_USER_ENGLISH_NAMIBIA, "en", "NA", 0 },
543 : { LANGUAGE_USER_WALLOON, "wa", "BE", 0 },
544 : { LANGUAGE_USER_COPTIC, "cop", "EG", 0 },
545 : { LANGUAGE_USER_GASCON, "gsc", "FR", 0 },
546 : { LANGUAGE_USER_GERMAN_BELGIUM, "de", "BE", 0 },
547 : { LANGUAGE_USER_CHUVASH, "cv", "RU", 0 },
548 : { LANGUAGE_USER_EWE_GHANA, "ee", "GH", 0 },
549 : { LANGUAGE_USER_ENGLISH_GHANA, "en", "GH", 0 },
550 : { LANGUAGE_USER_SANGO, "sg", "CF", 0 },
551 : { LANGUAGE_USER_GANDA, "lg", "UG", 0 },
552 : { LANGUAGE_USER_LINGALA_DRCONGO, "ln", "CD", 0 },
553 : { LANGUAGE_USER_LOW_GERMAN, "nds", "DE", 0 },
554 : { LANGUAGE_USER_HILIGAYNON, "hil", "PH", 0 },
555 : { LANGUAGE_USER_ENGLISH_MALAWI, "en", "MW", 0 }, /* en default for MW */
556 : { LANGUAGE_USER_NYANJA, "ny", "MW", 0 },
557 : { LANGUAGE_USER_KASHUBIAN, "csb", "PL", 0 },
558 : { LANGUAGE_USER_SPANISH_CUBA, "es", "CU", 0 },
559 : { LANGUAGE_USER_QUECHUA_NORTH_BOLIVIA, "qul", "BO", 0 },
560 : { LANGUAGE_USER_QUECHUA_SOUTH_BOLIVIA, "quh", "BO", 0 },
561 : { LANGUAGE_USER_BODO_INDIA, "brx", "IN", 0 },
562 : { LANGUAGE_USER_DOGRI_INDIA, "dgo", "IN", 0 },
563 : { LANGUAGE_USER_MAITHILI_INDIA, "mai", "IN", 0 },
564 : { LANGUAGE_USER_SANTALI_INDIA, "sat", "IN", 0 },
565 : { LANGUAGE_USER_TETUN, "tet", "ID", 0 },
566 : { LANGUAGE_USER_TETUN_TIMOR_LESTE, "tet", "TL", 0 },
567 : { LANGUAGE_USER_TOK_PISIN, "tpi", "PG", 0 },
568 : { LANGUAGE_USER_SHUSWAP, "shs", "CA", 0 },
569 : { LANGUAGE_USER_ANCIENT_GREEK, "grc", "GR", 0 },
570 : { LANGUAGE_USER_ASTURIAN, "ast", "ES", 0 },
571 : { LANGUAGE_USER_LATGALIAN, "ltg", "LV", 0 },
572 : { LANGUAGE_USER_MAORE, "swb", "YT", 0 },
573 : { LANGUAGE_USER_BUSHI, "buc", "YT", 0 },
574 : { LANGUAGE_USER_TAHITIAN, "ty", "PF", 0 },
575 : { LANGUAGE_MALAGASY_PLATEAU, "plt", "MG", 0 },
576 : { LANGUAGE_MALAGASY_PLATEAU, "mg", "MG", kSAME },
577 : { LANGUAGE_OBSOLETE_USER_MALAGASY_PLATEAU, "plt", "MG", 0 },
578 : { LANGUAGE_USER_BAFIA, "ksf", "CM", 0 },
579 : { LANGUAGE_USER_GIKUYU, "ki", "KE", 0 },
580 : { LANGUAGE_USER_RUSYN_UKRAINE, "rue", "UA", 0 },
581 : { LANGUAGE_USER_RUSYN_SLOVAKIA, "rue", "SK", 0 },
582 : { LANGUAGE_USER_LIMBU, "lif", "NP", 0 },
583 : { LANGUAGE_USER_LOJBAN, "jbo", "" , 0 },
584 : { LANGUAGE_USER_HAITIAN, "ht", "HT", 0 },
585 : { LANGUAGE_FRENCH_HAITI, "fr", "HT", 0 },
586 : { LANGUAGE_USER_BEEMBE, "beq", "CG", 0 },
587 : { LANGUAGE_USER_BEKWEL, "bkw", "CG", 0 },
588 : { LANGUAGE_USER_KITUBA, "mkw", "CG", 0 },
589 : { LANGUAGE_USER_LARI, "ldi", "CG", 0 },
590 : { LANGUAGE_USER_MBOCHI, "mdw", "CG", 0 },
591 : { LANGUAGE_USER_TEKE_EBOO, "ebo", "CG", 0 },
592 : { LANGUAGE_USER_TEKE_IBALI, "tek", "CG", 0 },
593 : { LANGUAGE_USER_TEKE_TYEE, "tyx", "CG", 0 },
594 : { LANGUAGE_USER_VILI, "vif", "CG", 0 },
595 : { LANGUAGE_USER_PORTUGUESE_ANGOLA, "pt", "AO", 0 },
596 : { LANGUAGE_USER_MANX, "gv", "GB", 0 },
597 : { LANGUAGE_USER_ARAGONESE, "an", "ES", 0 },
598 : { LANGUAGE_USER_KEYID, "qtz", "" , 0 }, // key id pseudolanguage used for UI testing
599 : { LANGUAGE_USER_PALI_LATIN, "pli", "" , kSAME }, // Pali with Latin script, ISO 639-3 (sigh..) back-compat, Latin is not a default script though..
600 : { LANGUAGE_USER_KYRGYZ_CHINA, "ky", "CN", 0 },
601 : { LANGUAGE_USER_KOMI_ZYRIAN, "kpv", "RU", 0 },
602 : { LANGUAGE_USER_KOMI_PERMYAK, "koi", "RU", 0 },
603 : { LANGUAGE_USER_PITJANTJATJARA, "pjt", "AU", 0 },
604 : { LANGUAGE_USER_ERZYA, "myv", "RU", 0 },
605 : { LANGUAGE_USER_MARI_MEADOW, "mhr", "RU", 0 },
606 : { LANGUAGE_USER_KHANTY, "kca", "RU", 0 },
607 : { LANGUAGE_USER_LIVONIAN, "liv", "RU", 0 },
608 : { LANGUAGE_USER_MOKSHA, "mdf", "RU", 0 },
609 : { LANGUAGE_USER_MARI_HILL, "mrj", "RU", 0 },
610 : { LANGUAGE_USER_NGANASAN, "nio", "RU", 0 },
611 : { LANGUAGE_USER_OLONETS, "olo", "RU", 0 },
612 : { LANGUAGE_USER_VEPS, "vep", "RU", 0 },
613 : { LANGUAGE_USER_VORO, "vro", "EE", 0 },
614 : { LANGUAGE_USER_NENETS, "yrk", "RU", 0 },
615 : { LANGUAGE_USER_AKA, "axk", "CF", 0 },
616 : { LANGUAGE_USER_AKA_CONGO, "axk", "CG", 0 },
617 : { LANGUAGE_USER_DIBOLE, "bvx", "CG", 0 },
618 : { LANGUAGE_USER_DOONDO, "dde", "CG", 0 },
619 : { LANGUAGE_USER_KAAMBA, "xku", "CG", 0 },
620 : { LANGUAGE_USER_KOONGO, "kng", "CD", 0 },
621 : { LANGUAGE_USER_KOONGO_CONGO, "kng", "CG", 0 },
622 : { LANGUAGE_USER_KUNYI, "njx", "CG", 0 },
623 : { LANGUAGE_USER_NGUNGWEL, "ngz", "CG", 0 },
624 : { LANGUAGE_USER_NJYEM, "njy", "CM", 0 },
625 : { LANGUAGE_USER_NJYEM_CONGO, "njy", "CG", 0 },
626 : { LANGUAGE_USER_PUNU, "puu", "GA", 0 },
627 : { LANGUAGE_USER_PUNU_CONGO, "puu", "CG", 0 },
628 : { LANGUAGE_USER_SUUNDI, "sdj", "CG", 0 },
629 : { LANGUAGE_USER_TEKE_KUKUYA, "kkw", "CG", 0 },
630 : { LANGUAGE_USER_TSAANGI, "tsa", "CG", 0 },
631 : { LANGUAGE_USER_YAKA, "iyx", "CG", 0 },
632 : { LANGUAGE_USER_YOMBE, "yom", "CD", 0 },
633 : { LANGUAGE_USER_YOMBE_CONGO, "yom", "CG", 0 },
634 : { LANGUAGE_USER_SIDAMA, "sid", "ET", 0 },
635 : { LANGUAGE_USER_NKO, "nqo", "GN", 0 },
636 : { LANGUAGE_USER_UDMURT, "udm", "RU", 0 },
637 : { LANGUAGE_USER_CORNISH, "kw", "UK", 0 },
638 : { LANGUAGE_USER_SAMI_PITE_SWEDEN, "sje", "SE", 0 },
639 : { LANGUAGE_USER_NGAEBERE, "gym", "PA", 0 },
640 : { LANGUAGE_USER_KUMYK, "kum", "RU", 0 },
641 : { LANGUAGE_USER_NOGAI, "nog", "RU", 0 },
642 : { LANGUAGE_USER_LADIN, "lld", "IT", 0 },
643 : { LANGUAGE_USER_FRENCH_BURKINA_FASO, "fr", "BF", 0 },
644 : { LANGUAGE_USER_PUINAVE, "pui", "CO", 0 },
645 : { LANGUAGE_USER_AVAR, "av", "RU", 0 },
646 : { LANGUAGE_USER_LENGO, "lgr", "SB", 0 },
647 : { LANGUAGE_USER_FRENCH_BENIN, "fr", "BJ", 0 },
648 : { LANGUAGE_USER_FRENCH_NIGER, "fr", "NE", 0 },
649 : { LANGUAGE_USER_FRENCH_TOGO, "fr", "TG", 0 },
650 : { LANGUAGE_USER_KVEN_FINNISH, "fkv", "NO", 0 },
651 : { LANGUAGE_MULTIPLE, "mul", "" , 0 }, // multiple languages, many languages are used
652 : { LANGUAGE_UNDETERMINED, "und", "" , 0 }, // undetermined language, language cannot be identified
653 : { LANGUAGE_NONE, "zxx", "" , 0 }, // added to ISO 639-2 on 2006-01-11: Used to declare the absence of linguistic information
654 : { LANGUAGE_DONTKNOW, "", "" , 0 } // marks end of table
655 : };
656 :
657 : static IsoLanguageScriptCountryEntry const aImplIsoLangScriptEntries[] =
658 : {
659 : // MS-LangID, ISO639-ISO15924, ISO3166, override
660 : { LANGUAGE_SERBIAN_LATIN_SERBIA, "sr-Latn", "RS", 0 },
661 : { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_SERBIA, "sr-Latn", "RS", 0 },
662 : { LANGUAGE_SERBIAN_LATIN_MONTENEGRO, "sr-Latn", "ME", 0 },
663 : { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_MONTENEGRO,"sr-Latn", "ME", 0 },
664 : { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA, "sr-Latn", "BA", 0 },
665 : { LANGUAGE_SERBIAN_LATIN_SAM, "sr-Latn", "CS", 0 }, // Serbian Latin in Serbia and Montenegro; note that not all applications may know about the 'CS' reusage mess, see https://en.wikipedia.org/wiki/ISO_3166-2:CS
666 : { LANGUAGE_SERBIAN_LATIN_SAM, "sr-Latn", "YU", 0 }, // legacy Serbian Latin in Yugoslavia
667 : { LANGUAGE_SERBIAN_LATIN_LSO, "sr-Latn", "" , 0 },
668 : { LANGUAGE_SERBIAN_LATIN_NEUTRAL, "sr-Latn", "" , LANGUAGE_SERBIAN_LATIN_LSO }, // MS lists this as 'sr' only, what a mess
669 : { LANGUAGE_SERBIAN_CYRILLIC_SERBIA, "sr-Cyrl", "RS", kSAME }, // MS
670 : { LANGUAGE_SERBIAN_CYRILLIC_MONTENEGRO, "sr-Cyrl", "ME", kSAME }, // MS
671 : { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr-Cyrl", "BA", kSAME }, // MS
672 : { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr-Cyrl", "CS", kSAME }, // MS
673 : { LANGUAGE_SERBIAN_CYRILLIC_LSO, "sr-Cyrl", "" , kSAME }, // MS
674 : { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs-Cyrl", "BA", 0 },
675 : { LANGUAGE_BOSNIAN_CYRILLIC_LSO, "bs-Cyrl", "" , 0 },
676 : { LANGUAGE_AZERI_CYRILLIC, "az-Cyrl", "AZ", 0 }, // macrolanguage code
677 : { LANGUAGE_AZERI_CYRILLIC_LSO, "az-Cyrl", "" , 0 }, // macrolanguage code
678 : { LANGUAGE_UZBEK_CYRILLIC, "uz-Cyrl", "UZ", 0 }, // macrolanguage code
679 : { LANGUAGE_UZBEK_CYRILLIC_LSO, "uz-Cyrl", "" , 0 }, // macrolanguage code
680 : { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA, "mn-Cyrl", "MN", 0 }, // macrolanguage code; should be khk-MN or khk-Cyrl-MN
681 : { LANGUAGE_MONGOLIAN_CYRILLIC_LSO, "mn-Cyrl", "" , 0 }, // macrolanguage code; MS, should be khk or khk-Cyrl
682 : { LANGUAGE_MONGOLIAN_MONGOLIAN_MONGOLIA, "mn-Mong", "MN", 0 }, // macrolanguage code; MS, should be khk-Mong-MN
683 : { LANGUAGE_MONGOLIAN_MONGOLIAN_CHINA, "mn-Mong", "CN", 0 }, // macrolanguage code; MS, should actually be mvf-CN
684 : { LANGUAGE_MONGOLIAN_MONGOLIAN_LSO, "mn-Mong", "" , 0 }, // macrolanguage code
685 : { LANGUAGE_USER_PALI_LATIN, "pi-Latn", "" , 0 },
686 : { LANGUAGE_USER_KARAKALPAK_LATIN, "kaa-Latn", "UZ", 0 },
687 : { LANGUAGE_TAJIK, "tg-Cyrl", "TJ", 0 }, // MS
688 : { LANGUAGE_TAJIK_LSO, "tg-Cyrl", "" , 0 }, // MS
689 : { LANGUAGE_AZERI_LATIN, "az-Latn", "AZ", 0 }, // macrolanguage code; MS
690 : { LANGUAGE_AZERI_LATIN_LSO, "az-Latn", "" , 0 }, // macrolanguage code; MS
691 : { LANGUAGE_USER_YIDDISH_US, "yi-Hebr", "US", kSAME }, // macrolanguage code; MS, Hebr is suppress-script
692 : { LANGUAGE_YIDDISH, "yi-Hebr", "IL", kSAME }, // macrolanguage code; MS, Hebr is suppress-script
693 : { LANGUAGE_UZBEK_LATIN, "uz-Latn", "UZ", 0 }, // macrolanguage code
694 : { LANGUAGE_UZBEK_LATIN_LSO, "uz-Latn", "" , 0 },
695 : // { LANGUAGE_SINDHI, "sd-Deva", "IN", 0 }, // MS, TODO: see comment above in aImplIsoLangEntries
696 : { LANGUAGE_SINDHI_PAKISTAN, "sd-Arab", "PK", 0 }, // MS
697 : { LANGUAGE_SINDHI_ARABIC_LSO, "sd-Arab", "" , 0 },
698 : { LANGUAGE_CHEROKEE_UNITED_STATES, "chr-Cher", "US", 0 }, // MS
699 : { LANGUAGE_CHEROKEE_CHEROKEE_LSO, "chr-Cher", "" , 0 },
700 : { LANGUAGE_INUKTITUT_SYLLABICS_CANADA, "iu-Cans", "CA", 0 }, // macrolanguage code, MS
701 : { LANGUAGE_INUKTITUT_SYLLABICS_LSO, "iu-Cans", "" , 0 }, // macrolanguage code, MS
702 : { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu-Latn", "CA", 0 }, // macrolanguage code, MS
703 : { LANGUAGE_INUKTITUT_LATIN_LSO, "iu-Latn", "" , 0 }, // macrolanguage code, MS
704 : { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "tzm-Tfng", "MA", 0 },
705 : { LANGUAGE_TAMAZIGHT_TIFINAGH_LSO, "tzm-Tfng", "" , 0 },
706 : { LANGUAGE_KASHMIRI_INDIA, "ks-Deva", "IN", 0 }, // MS
707 : { LANGUAGE_KASHMIRI, "ks-Arab", "" , 0 }, // MS, Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that
708 : { LANGUAGE_HAUSA_NIGERIA, "ha-Latn", "NG", 0 }, // MS
709 : { LANGUAGE_USER_HAUSA_GHANA, "ha-Latn", "GH", 0 },
710 : { LANGUAGE_HAUSA_LATIN_LSO, "ha-Latn", "" , 0 },
711 : { LANGUAGE_LATIN_LSO, "la-Latn", "" , kSAME }, // MS, though Latn is suppress-script
712 : { LANGUAGE_TAI_NUA_CHINA, "tdd-Tale", "CN", 0 }, // MS reserved
713 : { LANGUAGE_LU_CHINA, "khb-Talu", "CN", 0 }, // MS reserved
714 : { LANGUAGE_KURDISH_ARABIC_IRAQ, "ku-Arab", "IQ", kSAME }, // macrolanguage code, MS
715 : { LANGUAGE_KURDISH_ARABIC_LSO, "ku-Arab", "" , kSAME }, // macrolanguage code, MS
716 : { LANGUAGE_USER_KURDISH_TURKEY, "kmr-Latn", "TR", 0 },
717 : { LANGUAGE_USER_KURDISH_SYRIA, "kmr-Latn", "SY", 0 },
718 : { LANGUAGE_PUNJABI_PAKISTAN, "pnb-Arab", "PK", 0 },
719 : { LANGUAGE_PUNJABI_ARABIC_LSO, "pnb-Arab", "" , 0 },
720 : { LANGUAGE_PUNJABI_PAKISTAN, "pa-Arab", "PK", 0 }, // MS, incorrect
721 : { LANGUAGE_PUNJABI_ARABIC_LSO, "pa-Arab", "" , 0 }, // MS, incorrect
722 : { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "tzm-Latn", "DZ", kSAME }, // MS
723 : { LANGUAGE_TAMAZIGHT_LATIN_LSO, "tzm-Latn", "" , 0 }, // MS
724 : { LANGUAGE_FULFULDE_SENEGAL, "ff-Latn", "SN", 0 }, // macrolanguage code, MS
725 : { LANGUAGE_FULFULDE_LATIN_LSO, "ff-Latn", "" , 0 }, // macrolanguage code
726 : { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA, "bs-Latn", "BA", kSAME }, // MS, though Latn is suppress-script
727 : { LANGUAGE_BOSNIAN_LATIN_LSO, "bs-Latn", "" , LANGUAGE_BOSNIAN_LSO }, // MS, though Latn is suppress-script
728 : { LANGUAGE_CHINESE_TRADITIONAL_LSO, "zh-Hant", "" , 0 },
729 : { LANGUAGE_USER_MANINKAKAN_EASTERN_LATIN, "emk-Latn", "GN", 0 },
730 : { LANGUAGE_USER_CREE_PLAINS_LATIN, "crk-Latn", "CN", 0 },
731 : { LANGUAGE_USER_CREE_PLAINS_SYLLABICS, "crk-Cans", "CN", 0 },
732 : { LANGUAGE_DONTKNOW, "", "" , 0 } // marks end of table
733 : };
734 :
735 : static Bcp47CountryEntry const aImplBcp47CountryEntries[] =
736 : {
737 : // MS-LangID full BCP47, ISO3166, ISO639-Variant or other fallback
738 : { LANGUAGE_CATALAN_VALENCIAN, "ca-ES-valencia", "ES", "ca-valencia" },
739 : { LANGUAGE_OBSOLETE_USER_CATALAN_VALENCIAN, "ca-ES-valencia", "ES", "" }, // In case MS format files using the old value escaped into the wild, map them back.
740 : { LANGUAGE_USER_ENGLISH_UK_OED, "en-GB-oed", "GB", "" }, // grandfathered
741 : // { LANGUAGE_YUE_CHINESE_HONGKONG, "zh-yue-HK", "HK", "" }, // MS reserved, prefer yue-HK; do not add unless LanguageTag::simpleExtract() can handle it to not call liblangtag for rsc!
742 : { LANGUAGE_DONTKNOW, "", "", "" } // marks end of table
743 : };
744 :
745 : static IsoLanguageCountryEntry aLastResortFallbackEntry =
746 : { LANGUAGE_ENGLISH_US, "en", "US", 0 };
747 :
748 212197 : OUString IsoLanguageCountryEntry::getTagString() const
749 : {
750 212197 : if (maCountry[0])
751 196249 : return OUString( OUString::createFromAscii( maLanguage) + "-" + OUString::createFromAscii( maCountry));
752 : else
753 15948 : return OUString::createFromAscii( maLanguage);
754 : }
755 :
756 210145 : ::com::sun::star::lang::Locale IsoLanguageCountryEntry::getLocale() const
757 : {
758 210145 : return lang::Locale( OUString::createFromAscii( maLanguage), OUString::createFromAscii( maCountry), OUString());
759 : }
760 :
761 258884 : OUString IsoLanguageScriptCountryEntry::getTagString() const
762 : {
763 258884 : if (maCountry[0])
764 190636 : return OUString( OUString::createFromAscii( maLanguageScript) + "-" + OUString::createFromAscii( maCountry));
765 : else
766 68248 : return OUString::createFromAscii( maLanguageScript);
767 : }
768 :
769 24625 : ::com::sun::star::lang::Locale IsoLanguageScriptCountryEntry::getLocale() const
770 : {
771 24625 : return lang::Locale( I18NLANGTAG_QLT, OUString::createFromAscii( maCountry), getTagString());
772 : }
773 :
774 3128233 : bool IsoLanguageScriptCountryEntry::startsInIgnoreAsciiCase( const OUString & rStr ) const
775 : {
776 3128233 : return rStr.matchIgnoreAsciiCaseAsciiL( maLanguageScript, strlen( maLanguageScript), 0);
777 : }
778 :
779 261138 : OUString Bcp47CountryEntry::getTagString() const
780 : {
781 261138 : return OUString::createFromAscii( mpBcp47);
782 : }
783 :
784 6 : ::com::sun::star::lang::Locale Bcp47CountryEntry::getLocale() const
785 : {
786 6 : return lang::Locale( I18NLANGTAG_QLT, OUString::createFromAscii( maCountry), getTagString());
787 : }
788 :
789 :
790 :
791 : // In this table are the countries which should mapped to a specific
792 : // english language
793 : static IsoLangEngEntry const aImplIsoLangEngEntries[] =
794 : {
795 : { LANGUAGE_ENGLISH_UK, "AO" }, // Angola
796 : { LANGUAGE_ENGLISH_UK, "BJ" }, // Benin
797 : { LANGUAGE_ENGLISH_UK, "BW" }, // Botswana
798 : { LANGUAGE_ENGLISH_UK, "BI" }, // Burundi
799 : { LANGUAGE_ENGLISH_UK, "CM" }, // Cameroon
800 : { LANGUAGE_ENGLISH_UK, "GA" }, // Gabon
801 : { LANGUAGE_ENGLISH_UK, "GM" }, // Gambia
802 : { LANGUAGE_ENGLISH_UK, "GH" }, // Ghana
803 : { LANGUAGE_ENGLISH_UK, "GN" }, // Guinea
804 : { LANGUAGE_ENGLISH_UK, "LS" }, // Lesotho
805 : { LANGUAGE_ENGLISH_UK, "MW" }, // Malawi
806 : { LANGUAGE_ENGLISH_UK, "MT" }, // Malta
807 : { LANGUAGE_ENGLISH_UK, "NA" }, // Namibia
808 : { LANGUAGE_ENGLISH_UK, "NG" }, // Nigeria
809 : { LANGUAGE_ENGLISH_UK, "UG" }, // Uganda
810 : { LANGUAGE_ENGLISH_UK, "ZM" }, // Zambia
811 : { LANGUAGE_ENGLISH_UK, "ZW" }, // Zimbabwe
812 : { LANGUAGE_ENGLISH_UK, "SZ" }, // Swaziland
813 : { LANGUAGE_ENGLISH_UK, "NG" }, // Sierra Leone
814 : { LANGUAGE_ENGLISH_UK, "KN" }, // Saint Kitts and Nevis
815 : { LANGUAGE_ENGLISH_UK, "SH" }, // St. Helena
816 : { LANGUAGE_ENGLISH_UK, "IO" }, // British Indian Oceanic Territory
817 : { LANGUAGE_ENGLISH_UK, "FK" }, // Falkland Islands
818 : { LANGUAGE_ENGLISH_UK, "GI" }, // Gibraltar
819 : { LANGUAGE_ENGLISH_UK, "KI" }, // Kiribati
820 : { LANGUAGE_ENGLISH_UK, "VG" }, // Virgin Islands
821 : { LANGUAGE_ENGLISH_UK, "MU" }, // Mauritius
822 : { LANGUAGE_ENGLISH_UK, "FJ" }, // Fiji
823 : { LANGUAGE_ENGLISH_US, "KI" }, // Kiribati
824 : { LANGUAGE_ENGLISH_US, "LR" }, // Liberia
825 : { LANGUAGE_ENGLISH_US, "GU" }, // Guam
826 : { LANGUAGE_ENGLISH_US, "MH" }, // Marshall Islands
827 : { LANGUAGE_ENGLISH_US, "PW" }, // Palau
828 : { LANGUAGE_ENGLISH_CARRIBEAN, "AI" }, // Anguilla
829 : { LANGUAGE_ENGLISH_CARRIBEAN, "AG" }, // Antigua and Barbuda
830 : { LANGUAGE_ENGLISH_CARRIBEAN, "BS" }, // Bahamas
831 : { LANGUAGE_ENGLISH_CARRIBEAN, "BB" }, // Barbedos
832 : { LANGUAGE_ENGLISH_CARRIBEAN, "BM" }, // Bermuda
833 : { LANGUAGE_ENGLISH_CARRIBEAN, "KY" }, // Cayman Islands
834 : { LANGUAGE_ENGLISH_CARRIBEAN, "GD" }, // Grenada
835 : { LANGUAGE_ENGLISH_CARRIBEAN, "DM" }, // Dominica
836 : { LANGUAGE_ENGLISH_CARRIBEAN, "HT" }, // Haiti
837 : { LANGUAGE_ENGLISH_CARRIBEAN, "MS" }, // Montserrat
838 : { LANGUAGE_ENGLISH_CARRIBEAN, "FM" }, // Micronesia
839 : { LANGUAGE_ENGLISH_CARRIBEAN, "VC" }, // St. Vincent / Grenadines
840 : { LANGUAGE_ENGLISH_CARRIBEAN, "LC" }, // Saint Lucia
841 : { LANGUAGE_ENGLISH_CARRIBEAN, "TC" }, // Turks & Caicos Islands
842 : { LANGUAGE_ENGLISH_CARRIBEAN, "GY" }, // Guyana
843 : { LANGUAGE_ENGLISH_CARRIBEAN, "TT" }, // Trinidad and Tobago
844 : { LANGUAGE_ENGLISH_AUS, "CX" }, // Christmas Islands
845 : { LANGUAGE_ENGLISH_AUS, "CC" }, // Cocos (Keeling) Islands
846 : { LANGUAGE_ENGLISH_AUS, "NF" }, // Norfolk Island
847 : { LANGUAGE_ENGLISH_AUS, "PG" }, // Papua New Guinea
848 : { LANGUAGE_ENGLISH_AUS, "SB" }, // Solomon Islands
849 : { LANGUAGE_ENGLISH_AUS, "TV" }, // Tuvalu
850 : { LANGUAGE_ENGLISH_AUS, "NR" }, // Nauru
851 : { LANGUAGE_ENGLISH_NZ, "CK" }, // Cook Islands
852 : { LANGUAGE_ENGLISH_NZ, "NU" }, // Niue
853 : { LANGUAGE_ENGLISH_NZ, "TK" }, // Tokelau
854 : { LANGUAGE_ENGLISH_NZ, "TO" }, // Tonga
855 : { LANGUAGE_DONTKNOW, "" } // marks end of table
856 : };
857 :
858 :
859 :
860 : static IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries[] =
861 : {
862 : { LANGUAGE_NORWEGIAN_BOKMAL, "no", "BOK" }, // registered subtags for "no" in rfc1766
863 : { LANGUAGE_NORWEGIAN_NYNORSK, "no", "NYN" }, // registered subtags for "no" in rfc1766
864 : { LANGUAGE_SERBIAN_LATIN_SAM, "sr", "latin" },
865 : { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr", "cyrillic" },
866 : { LANGUAGE_AZERI_LATIN, "az", "latin" },
867 : { LANGUAGE_AZERI_CYRILLIC, "az", "cyrillic" },
868 : { LANGUAGE_DONTKNOW, "", "" } // marks end of table
869 : };
870 :
871 :
872 :
873 : // in this table are only names to find the best language
874 : static IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries2[] =
875 : {
876 : { LANGUAGE_NORWEGIAN_BOKMAL, "no", "bokmaal" },
877 : { LANGUAGE_NORWEGIAN_BOKMAL, "no", "bokmal" },
878 : { LANGUAGE_NORWEGIAN_NYNORSK, "no", "nynorsk" },
879 : { LANGUAGE_DONTKNOW, "", "" } // marks end of table
880 : };
881 :
882 :
883 :
884 : // in this table are only names to find the best language
885 : static IsoLangOtherEntry const aImplOtherEntries[] =
886 : {
887 : { LANGUAGE_ENGLISH_US, "c" },
888 : { LANGUAGE_CHINESE, "chinese" },
889 : { LANGUAGE_GERMAN, "german" },
890 : { LANGUAGE_JAPANESE, "japanese" },
891 : { LANGUAGE_KOREAN, "korean" },
892 : { LANGUAGE_ENGLISH_US, "posix" },
893 : { LANGUAGE_CHINESE_TRADITIONAL, "tchinese" },
894 : { LANGUAGE_DONTKNOW, NULL } // marks end of table
895 : };
896 :
897 :
898 : // in this table are only privateuse names
899 : static IsoLangOtherEntry const aImplPrivateUseEntries[] =
900 : {
901 : { LANGUAGE_USER_PRIV_NOTRANSLATE, "x-no-translate" }, //! not BCP47 but legacy in .xcu configmgr
902 : { LANGUAGE_USER_PRIV_DEFAULT, "x-default" },
903 : { LANGUAGE_USER_PRIV_COMMENT, "x-comment" },
904 : { LANGUAGE_USER_PRIV_JOKER, "*" }, //! not BCP47 but transferable in configmgr
905 : { LANGUAGE_DONTKNOW, NULL } // marks end of table
906 : };
907 :
908 :
909 :
910 : // static
911 247593 : void MsLangId::Conversion::convertLanguageToLocaleImpl( LanguageType nLang,
912 : ::com::sun::star::lang::Locale & rLocale, bool bIgnoreOverride )
913 : {
914 247593 : const IsoLanguageScriptCountryEntry* pScriptEntryOverride = NULL;
915 247593 : const IsoLanguageCountryEntry* pEntryOverride = NULL;
916 :
917 : Label_Override_Lang_Locale:
918 :
919 : // Search for LangID in BCP47
920 2027700 : for (const Bcp47CountryEntry* pBcp47Entry = aImplBcp47CountryEntries;
921 1013850 : pBcp47Entry->mnLang != LANGUAGE_DONTKNOW; ++pBcp47Entry)
922 : {
923 761065 : if (pBcp47Entry->mnLang == nLang)
924 : {
925 1806 : rLocale.Language = I18NLANGTAG_QLT;
926 1806 : rLocale.Country = OUString::createFromAscii( pBcp47Entry->maCountry);
927 1806 : rLocale.Variant = pBcp47Entry->getTagString();
928 1806 : return;
929 : }
930 : }
931 :
932 : // Search for LangID in ISO lll-Ssss-CC
933 32752072 : for (const IsoLanguageScriptCountryEntry* pScriptEntry = aImplIsoLangScriptEntries;
934 16376036 : pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry)
935 : {
936 16174681 : if (pScriptEntry->mnLang == nLang)
937 : {
938 58428 : if (bIgnoreOverride || !pScriptEntry->mnOverride)
939 : {
940 44432 : rLocale.Language = I18NLANGTAG_QLT;
941 44432 : rLocale.Country = OUString::createFromAscii( pScriptEntry->maCountry);
942 44432 : rLocale.Variant = pScriptEntry->getTagString();
943 44432 : return;
944 : }
945 13996 : else if (pScriptEntry->mnOverride && pScriptEntryOverride != pScriptEntry)
946 : {
947 6998 : pScriptEntryOverride = pScriptEntry;
948 6998 : nLang = getOverrideLang( pScriptEntry->mnLang, pScriptEntry->mnOverride);
949 6998 : goto Label_Override_Lang_Locale;
950 : }
951 : }
952 : }
953 :
954 : // Search for LangID in ISO lll-CC
955 95148234 : for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries;
956 47574117 : pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
957 : {
958 47574033 : if (pEntry->mnLang == nLang)
959 : {
960 201271 : if (bIgnoreOverride || !pEntry->mnOverride)
961 : {
962 201271 : rLocale.Language = OUString::createFromAscii( pEntry->maLanguage );
963 201271 : rLocale.Country = OUString::createFromAscii( pEntry->maCountry );
964 201271 : rLocale.Variant = OUString();
965 201271 : return;
966 : }
967 0 : else if (pEntry->mnOverride && pEntryOverride != pEntry)
968 : {
969 0 : pEntryOverride = pEntry;
970 0 : nLang = getOverrideLang( pEntry->mnLang, pEntry->mnOverride);
971 0 : goto Label_Override_Lang_Locale;
972 : }
973 : }
974 : }
975 :
976 : // Look for privateuse definitions.
977 200 : for (const IsoLangOtherEntry* pPrivateEntry = aImplPrivateUseEntries;
978 100 : pPrivateEntry->mnLang != LANGUAGE_DONTKNOW; ++pPrivateEntry)
979 : {
980 100 : if (pPrivateEntry->mnLang == nLang)
981 : {
982 84 : rLocale.Language = I18NLANGTAG_QLT;
983 84 : rLocale.Country = OUString();
984 84 : rLocale.Variant = OUString::createFromAscii( pPrivateEntry->mpLanguage );
985 84 : return;
986 : }
987 : }
988 :
989 : // Not found. Passed rLocale argument remains unchanged.
990 : }
991 :
992 :
993 :
994 : // static
995 226604 : com::sun::star::lang::Locale MsLangId::Conversion::getLocale( const IsoLanguageCountryEntry * pEntry )
996 : {
997 226604 : if (pEntry->mnOverride)
998 : {
999 16463 : lang::Locale aLocale;
1000 16463 : convertLanguageToLocaleImpl( getOverrideLang( pEntry->mnLang, pEntry->mnOverride), aLocale, false);
1001 16463 : return aLocale;
1002 : }
1003 : else
1004 210141 : return pEntry->getLocale();
1005 : }
1006 :
1007 : // static
1008 30360 : com::sun::star::lang::Locale MsLangId::Conversion::getLocale( const IsoLanguageScriptCountryEntry * pEntry )
1009 : {
1010 30360 : if (pEntry->mnOverride)
1011 : {
1012 5735 : lang::Locale aLocale;
1013 5735 : convertLanguageToLocaleImpl( getOverrideLang( pEntry->mnLang, pEntry->mnOverride), aLocale, false);
1014 5735 : return aLocale;
1015 : }
1016 : else
1017 24625 : return pEntry->getLocale();
1018 : }
1019 :
1020 : // static
1021 13991 : ::com::sun::star::lang::Locale MsLangId::Conversion::lookupFallbackLocale(
1022 : const ::com::sun::star::lang::Locale & rLocale )
1023 : {
1024 : // language is lower case in table
1025 13991 : OUString aLowerLang = rLocale.Language.toAsciiLowerCase();
1026 : // country is upper case in table
1027 27982 : OUString aUpperCountry = rLocale.Country.toAsciiUpperCase();
1028 13991 : sal_Int32 nCountryLen = aUpperCountry.getLength();
1029 :
1030 13991 : if (rLocale.Language == I18NLANGTAG_QLT)
1031 : {
1032 : // Search in BCP47, only full match and one fallback, for other
1033 : // fallbacks only LanguageTag can decide.
1034 44 : for (const Bcp47CountryEntry* pBcp47Entry = aImplBcp47CountryEntries;
1035 22 : pBcp47Entry->mnLang != LANGUAGE_DONTKNOW; ++pBcp47Entry)
1036 : {
1037 32 : if ( rLocale.Variant.equalsIgnoreAsciiCase( pBcp47Entry->getTagString()) ||
1038 14 : rLocale.Variant.equalsIgnoreAsciiCaseAscii( pBcp47Entry->mpFallback))
1039 16 : return pBcp47Entry->getLocale();
1040 : }
1041 :
1042 : // Search in ISO lll-Ssss-CC
1043 4 : const IsoLanguageScriptCountryEntry* pFirstScript = NULL;
1044 28 : for (const IsoLanguageScriptCountryEntry* pScriptEntry = aImplIsoLangScriptEntries;
1045 14 : pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry)
1046 : {
1047 14 : if (pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant))
1048 : {
1049 14 : if (rLocale.Variant.equalsIgnoreAsciiCase( pScriptEntry->getTagString()))
1050 4 : return getLocale( pScriptEntry); // may override
1051 10 : if (!pFirstScript)
1052 2 : pFirstScript = pScriptEntry;
1053 : }
1054 : }
1055 : // If at least a lll-Ssss matched, try that with country or use it as
1056 : // fallback.
1057 0 : if (pFirstScript)
1058 : {
1059 : // Check for country only if there is more than lll-Ssss-CC in tag
1060 : // string, else we would had matched it already.
1061 0 : if (!aUpperCountry.isEmpty() && rLocale.Variant.getLength() > 11)
1062 : {
1063 0 : for (const IsoLanguageScriptCountryEntry* pScriptEntry = pFirstScript;
1064 0 : pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry)
1065 : {
1066 0 : if (aUpperCountry.equalsAscii( pScriptEntry->maCountry) &&
1067 0 : pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant))
1068 0 : return getLocale( pScriptEntry); // may override
1069 : }
1070 : }
1071 0 : return getLocale( pFirstScript); // may override
1072 : }
1073 :
1074 : // Extract language from tag string, country is used as present in
1075 : // Locale because in the tables that follow we have only ISO 3166
1076 : // countries and if that is in the tag string we also have it in the
1077 : // Locale.
1078 0 : sal_Int32 nIndex = 0;
1079 0 : aLowerLang = rLocale.Variant.getToken( 0, '-', nIndex).toAsciiLowerCase();
1080 : // Nothing with "x-..." or "i-..." or any 1 letter in lll-CC table that
1081 : // follows.
1082 0 : if (aLowerLang.getLength() == 1)
1083 0 : return aLastResortFallbackEntry.getLocale();
1084 : }
1085 :
1086 : // Search for locale and remember first lang-only.
1087 13981 : const IsoLanguageCountryEntry* pFirstLang = NULL;
1088 13981 : const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries;
1089 4489022 : for ( ; pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1090 : {
1091 4480864 : if (aLowerLang.equalsAscii( pEntry->maLanguage))
1092 : {
1093 65810 : if (*pEntry->maCountry)
1094 : {
1095 59761 : if (nCountryLen && aUpperCountry.equalsAscii( pEntry->maCountry))
1096 5043 : return getLocale( pEntry); // may override
1097 : }
1098 : else
1099 : {
1100 6049 : switch (pEntry->mnLang)
1101 : {
1102 : // These are known to have no country assigned.
1103 : case LANGUAGE_BASQUE:
1104 : case LANGUAGE_USER_ESPERANTO:
1105 : case LANGUAGE_USER_INTERLINGUA:
1106 : case LANGUAGE_USER_LOJBAN:
1107 : case LANGUAGE_KASHMIRI:
1108 : case LANGUAGE_USER_KEYID:
1109 : // And the special codes without country.
1110 : case LANGUAGE_MULTIPLE:
1111 : case LANGUAGE_UNDETERMINED:
1112 : case LANGUAGE_NONE:
1113 780 : return getLocale( pEntry); // may override
1114 : default:
1115 : ; // nothing
1116 : }
1117 : }
1118 59987 : if (!pFirstLang)
1119 12781 : pFirstLang = pEntry;
1120 : }
1121 : }
1122 :
1123 : // Language not found at all => use default.
1124 8158 : if (!pFirstLang)
1125 4 : return aLastResortFallbackEntry.getLocale();
1126 :
1127 : // Search for first entry of language with any country.
1128 8154 : pEntry = pFirstLang;
1129 8796 : for ( ; pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1130 : {
1131 8796 : if (aLowerLang.equalsAscii( pEntry->maLanguage))
1132 : {
1133 8796 : if (*pEntry->maCountry)
1134 8154 : return getLocale( pEntry); // may override
1135 : }
1136 : }
1137 :
1138 13991 : return aLastResortFallbackEntry.getLocale();
1139 : }
1140 :
1141 :
1142 :
1143 : // static
1144 134 : LanguageType MsLangId::Conversion::convertPrivateUseToLanguage( const OUString& rPriv )
1145 : {
1146 684 : for (const IsoLangOtherEntry* pPrivateEntry = aImplPrivateUseEntries;
1147 342 : pPrivateEntry->mnLang != LANGUAGE_DONTKNOW; ++pPrivateEntry)
1148 : {
1149 298 : if ( rPriv.equalsIgnoreAsciiCaseAscii( pPrivateEntry->mpLanguage ) )
1150 90 : return pPrivateEntry->mnLang;
1151 : }
1152 44 : return LANGUAGE_DONTKNOW;
1153 : }
1154 :
1155 :
1156 : // static
1157 272755 : LanguageType MsLangId::Conversion::convertLocaleToLanguageImpl(
1158 : const ::com::sun::star::lang::Locale& rLocale )
1159 : {
1160 272755 : if (rLocale.Language == I18NLANGTAG_QLT)
1161 : {
1162 : // "x-..." private use and the nasty "*" joker
1163 55819 : if (rLocale.Variant.startsWithIgnoreAsciiCase( "x-") || (rLocale.Variant == "*"))
1164 134 : return convertPrivateUseToLanguage( rLocale.Variant);
1165 :
1166 : // Search in BCP47
1167 437736 : for (const Bcp47CountryEntry* pBcp47Entry = aImplBcp47CountryEntries;
1168 218868 : pBcp47Entry->mnLang != LANGUAGE_DONTKNOW; ++pBcp47Entry)
1169 : {
1170 165047 : if (rLocale.Variant.equalsIgnoreAsciiCase( pBcp47Entry->getTagString()))
1171 1864 : return pBcp47Entry->mnLang;
1172 : }
1173 :
1174 : // Search in ISO lll-Ssss-CC
1175 4002468 : for (const IsoLanguageScriptCountryEntry* pScriptEntry = aImplIsoLangScriptEntries;
1176 2001234 : pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry)
1177 : {
1178 2001214 : if (pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant))
1179 : {
1180 101004 : if (rLocale.Variant.equalsIgnoreAsciiCase( pScriptEntry->getTagString()))
1181 53801 : return getOverrideLang( pScriptEntry->mnLang, pScriptEntry->mnOverride);
1182 : }
1183 : }
1184 : }
1185 : else
1186 : {
1187 : // language is lower case in table
1188 216936 : OUString aLowerLang = rLocale.Language.toAsciiLowerCase();
1189 : // country is upper case in table
1190 224624 : OUString aUpperCountry = rLocale.Country.toAsciiUpperCase();
1191 :
1192 : // Search in ISO lll-CC
1193 104856694 : for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries;
1194 52428347 : pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1195 : {
1196 52420659 : if (aLowerLang.equalsAscii( pEntry->maLanguage) && aUpperCountry.equalsAscii( pEntry->maCountry))
1197 209248 : return getOverrideLang( pEntry->mnLang, pEntry->mnOverride);
1198 7688 : }
1199 : }
1200 7708 : return LANGUAGE_DONTKNOW;
1201 : }
1202 :
1203 :
1204 : // static
1205 251667 : ::com::sun::star::lang::Locale MsLangId::Conversion::getOverride( const ::com::sun::star::lang::Locale& rLocale )
1206 : {
1207 251667 : if (rLocale.Language == I18NLANGTAG_QLT)
1208 : {
1209 : // "x-..." private use and the nasty "*" joker
1210 31354 : if (rLocale.Variant.startsWithIgnoreAsciiCase( "x-") || (rLocale.Variant == "*"))
1211 28 : return rLocale; // no overrides
1212 :
1213 : // Search in BCP47
1214 246588 : for (const Bcp47CountryEntry* pBcp47Entry = aImplBcp47CountryEntries;
1215 123294 : pBcp47Entry->mnLang != LANGUAGE_DONTKNOW; ++pBcp47Entry)
1216 : {
1217 92932 : if (rLocale.Variant.equalsIgnoreAsciiCase( pBcp47Entry->getTagString()))
1218 964 : return rLocale; // no overrides
1219 : }
1220 :
1221 : // Search in ISO lll-Ssss-CC
1222 2254022 : for (const IsoLanguageScriptCountryEntry* pScriptEntry = aImplIsoLangScriptEntries;
1223 1127011 : pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry)
1224 : {
1225 1127005 : if (pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant))
1226 : {
1227 57356 : if (rLocale.Variant.equalsIgnoreAsciiCase( pScriptEntry->getTagString()))
1228 30356 : return getLocale( pScriptEntry); // may override
1229 : }
1230 : }
1231 : }
1232 : else
1233 : {
1234 : // language is lower case in table
1235 220313 : OUString aLowerLang = rLocale.Language.toAsciiLowerCase();
1236 : // country is upper case in table
1237 227999 : OUString aUpperCountry = rLocale.Country.toAsciiUpperCase();
1238 :
1239 : // Search in ISO lll-CC
1240 107439598 : for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries;
1241 53719799 : pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1242 : {
1243 53712113 : if (aLowerLang.equalsAscii( pEntry->maLanguage) && aUpperCountry.equalsAscii( pEntry->maCountry))
1244 212627 : return getLocale( pEntry); // may override
1245 7686 : }
1246 : }
1247 7692 : return lang::Locale();
1248 : }
1249 :
1250 :
1251 : // static
1252 962 : LanguageType MsLangId::Conversion::convertIsoNamesToLanguage( const OUString& rLang,
1253 : const OUString& rCountry )
1254 : {
1255 : // language is lower case in table
1256 962 : OUString aLowerLang = rLang.toAsciiLowerCase();
1257 : // country is upper case in table
1258 1924 : OUString aUpperCountry = rCountry.toAsciiUpperCase();
1259 :
1260 : // first look for exact match
1261 962 : const IsoLanguageCountryEntry* pFirstLang = NULL;
1262 3848 : for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries;
1263 1924 : pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1264 : {
1265 1924 : if ( aLowerLang.equalsAscii( pEntry->maLanguage ) )
1266 : {
1267 3848 : if ( aUpperCountry.isEmpty() ||
1268 1924 : aUpperCountry.equalsAscii( pEntry->maCountry ) )
1269 962 : return pEntry->mnLang;
1270 962 : if ( !pFirstLang )
1271 962 : pFirstLang = pEntry;
1272 0 : else if ( !*pEntry->maCountry )
1273 0 : pFirstLang = pEntry;
1274 : }
1275 : }
1276 :
1277 : // some eng countries should be mapped to a specific english language
1278 0 : if ( aLowerLang == "en" )
1279 : {
1280 0 : for (const IsoLangEngEntry* pEngEntry = aImplIsoLangEngEntries;
1281 0 : pEngEntry->mnLang != LANGUAGE_DONTKNOW; ++pEngEntry)
1282 : {
1283 0 : if ( aUpperCountry.equalsAscii( pEngEntry->maCountry ) )
1284 0 : return pEngEntry->mnLang;
1285 : }
1286 : }
1287 :
1288 : // test for specific languages which are not used standard ISO 3166 codes
1289 0 : for (const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries;
1290 0 : pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW; ++pNoneStdEntry)
1291 : {
1292 0 : if ( aLowerLang.equalsAscii( pNoneStdEntry->maLanguage ) )
1293 : {
1294 : // The countries in this table are not all in upper case
1295 0 : if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry->maCountry ) )
1296 0 : return pNoneStdEntry->mnLang;
1297 : }
1298 : }
1299 0 : for (const IsoLangNoneStdEntry* pNoneStdEntry2 = aImplIsoNoneStdLangEntries2;
1300 0 : pNoneStdEntry2->mnLang != LANGUAGE_DONTKNOW; ++pNoneStdEntry2)
1301 : {
1302 0 : if ( aLowerLang.equalsAscii( pNoneStdEntry2->maLanguage ) )
1303 : {
1304 : // The countries in this table are not all in upper case
1305 0 : if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry2->maCountry ) )
1306 0 : return pNoneStdEntry2->mnLang;
1307 : }
1308 : }
1309 :
1310 : // If the language is correct, then we return the default language
1311 0 : if ( pFirstLang )
1312 0 : return pFirstLang->mnLang;
1313 :
1314 : // if only the country is set, look for any entry matching the country
1315 : // (to allow reading country and language in separate steps, in any order)
1316 0 : if ( !rCountry.isEmpty() && rLang.isEmpty() )
1317 : {
1318 0 : for (const IsoLanguageCountryEntry* pEntry2 = aImplIsoLangEntries;
1319 0 : pEntry2->mnLang != LANGUAGE_DONTKNOW; ++pEntry2)
1320 : {
1321 0 : if ( aUpperCountry.equalsAscii( pEntry2->maCountry ) )
1322 0 : return pEntry2->mnLang;
1323 : }
1324 :
1325 0 : aLowerLang = aUpperCountry.toAsciiLowerCase();
1326 : }
1327 :
1328 : // Look for privateuse definitions.
1329 0 : LanguageType nLang = convertPrivateUseToLanguage( aLowerLang);
1330 0 : if (nLang != LANGUAGE_DONTKNOW)
1331 0 : return nLang;
1332 :
1333 : // Now look for all other definitions, which are not standard
1334 0 : for (const IsoLangOtherEntry* pOtherEntry = aImplOtherEntries;
1335 0 : pOtherEntry->mnLang != LANGUAGE_DONTKNOW; ++pOtherEntry)
1336 : {
1337 0 : if ( aLowerLang.equalsAscii( pOtherEntry->mpLanguage ) )
1338 0 : return pOtherEntry->mnLang;
1339 : }
1340 :
1341 962 : return LANGUAGE_DONTKNOW;
1342 : }
1343 :
1344 :
1345 :
1346 : // static
1347 962 : LanguageType MsLangId::Conversion::convertIsoNamesToLanguage( const OString& rLang,
1348 : const OString& rCountry )
1349 : {
1350 962 : OUString aLang = OStringToOUString( rLang, RTL_TEXTENCODING_ASCII_US);
1351 1924 : OUString aCountry = OStringToOUString( rCountry, RTL_TEXTENCODING_ASCII_US);
1352 1924 : return convertIsoNamesToLanguage( aLang, aCountry);
1353 : }
1354 :
1355 :
1356 :
1357 : struct IsoLangGLIBCModifiersEntry
1358 : {
1359 : LanguageType mnLang;
1360 : sal_Char maLanguage[4];
1361 : sal_Char maCountry[3];
1362 : sal_Char maAtString[9];
1363 : };
1364 :
1365 : static IsoLangGLIBCModifiersEntry const aImplIsoLangGLIBCModifiersEntries[] =
1366 : {
1367 : // MS-LANGID codes ISO639-1/2/3 ISO3166 glibc modifier
1368 : { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs", "BA", "cyrillic" },
1369 : { LANGUAGE_USER_SERBIAN_LATIN_SERBIA, "sr", "RS", "latin" }, // Serbian Latin in Serbia
1370 : { LANGUAGE_SERBIAN_LATIN_SAM, "sr", "CS", "latin" }, // Serbian Latin in Serbia and Montenegro
1371 : { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO, "sr", "ME", "latin" }, // Serbian Latin in Montenegro
1372 : { LANGUAGE_SERBIAN_LATIN_LSO, "sr", "", "latin" },
1373 : { LANGUAGE_AZERI_CYRILLIC, "az", "AZ", "cyrillic" },
1374 : { LANGUAGE_UZBEK_CYRILLIC, "uz", "UZ", "cyrillic" },
1375 : { LANGUAGE_CATALAN_VALENCIAN, "ca", "ES", "valencia" },
1376 : { LANGUAGE_DONTKNOW, "", "", "" } // marks end of table
1377 : };
1378 :
1379 : // convert a unix locale string into LanguageType
1380 :
1381 : // static
1382 962 : LanguageType MsLangId::convertUnxByteStringToLanguage(
1383 : const OString& rString )
1384 : {
1385 962 : OString aLang;
1386 1924 : OString aCountry;
1387 1924 : OString aAtString;
1388 :
1389 962 : sal_Int32 nLangSepPos = rString.indexOf( (sal_Char)'_' );
1390 962 : sal_Int32 nCountrySepPos = rString.indexOf( (sal_Char)'.' );
1391 962 : sal_Int32 nAtPos = rString.indexOf( (sal_Char)'@' );
1392 :
1393 962 : if (nCountrySepPos < 0)
1394 0 : nCountrySepPos = nAtPos;
1395 962 : if (nCountrySepPos < 0)
1396 0 : nCountrySepPos = rString.getLength();
1397 :
1398 962 : if (nAtPos >= 0)
1399 0 : aAtString = rString.copy( nAtPos+1 );
1400 :
1401 962 : if (((nLangSepPos >= 0) && (nLangSepPos > nCountrySepPos)) || (nLangSepPos < 0))
1402 : {
1403 : // eg. "el.sun_eu_greek", "tchinese", "es.ISO8859-15"
1404 0 : aLang = rString.copy( 0, nCountrySepPos );
1405 : }
1406 962 : else if ( nLangSepPos >= 0 )
1407 : {
1408 : // well formed iso names like "en_US.UTF-8", "sh_BA.ISO8859-2@bosnia"
1409 962 : aLang = rString.copy( 0, nLangSepPos );
1410 962 : aCountry = rString.copy( nLangSepPos+1, nCountrySepPos - nLangSepPos - 1);
1411 : }
1412 :
1413 : // if there is a glibc modifier, first look for exact match in modifier table
1414 962 : if (!aAtString.isEmpty())
1415 : {
1416 : // language is lower case in table
1417 0 : OString aLowerLang = aLang.toAsciiLowerCase();
1418 : // country is upper case in table
1419 0 : OString aUpperCountry = aCountry.toAsciiUpperCase();
1420 0 : for (const IsoLangGLIBCModifiersEntry* pGLIBCModifiersEntry = aImplIsoLangGLIBCModifiersEntries;
1421 0 : pGLIBCModifiersEntry->mnLang != LANGUAGE_DONTKNOW; ++pGLIBCModifiersEntry)
1422 : { // avoid embedded \0 warning
1423 0 : if (aLowerLang.equals( static_cast< const char* >( pGLIBCModifiersEntry->maLanguage )) &&
1424 0 : aAtString.equals( static_cast< const char* >( pGLIBCModifiersEntry->maAtString )))
1425 : {
1426 0 : if (aUpperCountry.isEmpty() ||
1427 0 : aUpperCountry.equals( static_cast< const char* >( pGLIBCModifiersEntry->maCountry )))
1428 : {
1429 0 : return pGLIBCModifiersEntry->mnLang;
1430 : }
1431 : }
1432 0 : }
1433 : }
1434 :
1435 1924 : return Conversion::convertIsoNamesToLanguage( aLang, aCountry );
1436 : }
1437 :
1438 :
1439 : // static
1440 443 : ::std::vector< MsLangId::LanguagetagMapping > MsLangId::getDefinedLanguagetags()
1441 : {
1442 443 : ::std::vector< LanguagetagMapping > aVec;
1443 3544 : for (const Bcp47CountryEntry* pEntry = aImplBcp47CountryEntries;
1444 1772 : pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1445 : {
1446 1329 : aVec.push_back( LanguagetagMapping( pEntry->getTagString(), pEntry->mnLang));
1447 : }
1448 63792 : for (const IsoLanguageScriptCountryEntry* pEntry = aImplIsoLangScriptEntries;
1449 31896 : pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1450 : {
1451 31453 : aVec.push_back( LanguagetagMapping( pEntry->getTagString(), pEntry->mnLang));
1452 : }
1453 425280 : for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries;
1454 212640 : pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1455 : {
1456 212197 : aVec.push_back( LanguagetagMapping( pEntry->getTagString(), pEntry->mnLang));
1457 : }
1458 443 : return aVec;
1459 : }
1460 :
1461 : /* vim:set shiftwidth=4 softtabstop=4 expandtab: */
|
