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
23 #include <i18nlangtag/mslangid.hxx>
24 #include <i18nlangtag/languagetag.hxx>
25
26 using namespace com::sun::star;
27
28
29 constexpr LanguageType k0(0);
30 constexpr LanguageType kSAME(0xffff);
31
32 namespace {
getOverrideLang(LanguageType nLang,LanguageType nOverride)33 LanguageType getOverrideLang( LanguageType nLang, LanguageType nOverride )
34 {
35 return nOverride ? ((nOverride == kSAME) ? nLang : nOverride) : nLang;
36 }
37 }
38
39 /* Usage of override mechanism:
40 * If a table entry's mnOverride is not 0, an override entry with an mnLang
41 * value of (mnOverride==kSAME ? mnLang : mnOverride) exists that should be
42 * used instead. There MUST exist one such entry that does not have an
43 * mnOverride value and within one table it MUST be located before any entry
44 * with that mnLang and an mnOverride value of not 0. Usually kSAME is used as
45 * override value, with rare exceptions, see tables below.
46 *
47 * The override serves these purposes:
48 * - With getOverride() it indicates that there is a different language tag
49 * (locale) that the requested language tag should be "canonicalized" to.
50 * - With lookupFallbackLocale() a locale may be returned where the language
51 * tag differs.
52 * - With convertLanguageToLocaleImpl() and bIgnoreOverride=false the override
53 * is followed and the override locale returned.
54 * - With convertLocaleToLanguageImpl() a different LangID may be returned in
55 * rare cases where the actual mapped ID differs.
56 */
57
58 struct IsoLanguageCountryEntry
59 {
60 LanguageType mnLang;
61 char maLanguage[4];
62 char maCountry[3];
63 LanguageType mnOverride;
64
65 /** Obtain a language tag string with '-' separator. */
66 OUString getTagString() const;
67
68 /** Obtain a locale. */
69 css::lang::Locale getLocale() const;
70 };
71
72 struct IsoLanguageScriptCountryEntry
73 {
74 LanguageType mnLang;
75 char maLanguageScript[9]; ///< "ll-Ssss" or "lll-Ssss"
76 char maCountry[3];
77 LanguageType mnOverride;
78
79 /** Obtain a language tag string with '-' separator. */
80 OUString getTagString() const;
81
82 /** Obtain a locale. */
83 css::lang::Locale getLocale() const;
84
85 /** If rStr starts with maLanguageScript ignoring case.
86
87 We don't have OUString::startsWithIgnoreAsciiCaseAscii()
88 */
89 bool startsInIgnoreAsciiCase( const OUString & rStr ) const;
90 };
91
92 struct Bcp47CountryEntry
93 {
94 LanguageType mnLang;
95 const char* mpBcp47;
96 char maCountry[3];
97 const char* mpFallback;
98 LanguageType mnOverride;
99
100 /** Obtain a language tag string with '-' separator. */
101 OUString getTagString() const;
102
103 /** Obtain a locale. */
104 css::lang::Locale getLocale() const;
105 };
106
107 namespace {
108
109 struct IsoLangEngEntry
110 {
111 LanguageType mnLang;
112 char maCountry[3];
113 };
114
115 struct IsoLangNoneStdEntry
116 {
117 LanguageType mnLang;
118 char maLanguage[4];
119 char maCountry[9];
120 };
121
122 struct IsoLangOtherEntry
123 {
124 LanguageType mnLang;
125 const char* mpLanguage;
126 };
127
128 }
129
130 // Entries for languages are lower case, for countries upper case, as
131 // recommended by rfc5646 (obsoletes rfc4646 (obsoletes rfc3066 (obsoletes
132 // rfc1766))). convertIsoNamesToLanguage(), convertLocaleToLanguageImpl()
133 // and lookupFallbackLocale() are case insensitive.
134 //
135 // Sort order: Most used first and within one language the default fallback
136 // locale of that language first.
137 //
138 // The default entry for a LangID <-> ISO mapping has to be first. For
139 // conversion of legacy mappings one LangID can map to multiple ISO codes
140 // except if the LangID is primary-only, and one ISO code combination can map
141 // to multiple LangIDs. For compatibility with already existing calls it can
142 // also be a sequence as follows:
143
144 // LANGUAGE_ENGLISH, "en", ""
145 // LANGUAGE_ENGLISH_US, "en", "US"
146
147 // Here, in a convertIsoNamesToLanguage() call "en-US" is converted to
148 // LANGUAGE_ENGLISH_US and "en" is converted to LANGUAGE_ENGLISH. A call with
149 // "en-ZZ" (not in table) would result in LANGUAGE_ENGLISH because the first
150 // entry matching the language and not having a country is returned, regardless
151 // of whether being sorted before or after other entries of the same language
152 // with some country. To obtain a _locale_ (not language only) in the order
153 // given, lookupFallbackLocale() must be called.
154
155 // If the sequence instead was
156
157 // LANGUAGE_ENGLISH_US, "en", "US"
158 // LANGUAGE_ENGLISH, "en", ""
159
160 // in a convertIsoNamesToLanguage() call "en-US" would still be converted to
161 // LANGUAGE_ENGLISH_US, but "en" would _also_ be converted to
162 // LANGUAGE_ENGLISH_US because no country was passed and it is the first entry
163 // to match the language, see code. A call with "en-ZZ" (not in table) would
164 // still result in LANGUAGE_ENGLISH.
165
166 /* Currently (2013-08-29) only these primary LangID are still used literally in
167 * code:
168 * LANGUAGE_ENGLISH LANGUAGE_ARABIC_PRIMARY_ONLY
169 */
170
171 IsoLanguageCountryEntry const aImplIsoLangEntries[] =
172 {
173 // MS-LANGID codes, ISO639-1/2/3, ISO3166, override
174 { LANGUAGE_ENGLISH, "en", "" , k0 },
175 { LANGUAGE_ENGLISH_US, "en", "US", k0 },
176 { LANGUAGE_ENGLISH_UK, "en", "GB", k0 },
177 { LANGUAGE_ENGLISH_AUS, "en", "AU", k0 },
178 { LANGUAGE_ENGLISH_CAN, "en", "CA", k0 },
179 { LANGUAGE_FRENCH, "fr", "FR", k0 },
180 { LANGUAGE_GERMAN, "de", "DE", k0 },
181 { LANGUAGE_ITALIAN, "it", "IT", k0 },
182 { LANGUAGE_DUTCH, "nl", "NL", k0 },
183 { LANGUAGE_SPANISH_MODERN, "es", "ES", k0 },
184 { LANGUAGE_PORTUGUESE, "pt", "PT", k0 },
185 { LANGUAGE_PORTUGUESE_BRAZILIAN, "pt", "BR", k0 },
186 { LANGUAGE_DANISH, "da", "DK", k0 },
187 { LANGUAGE_GREEK, "el", "GR", k0 },
188 { LANGUAGE_CHINESE_SIMPLIFIED, "zh", "CN", k0 },
189 { LANGUAGE_CHINESE_SIMPLIFIED_LEGACY, "zh", "CN", k0 },
190 { LANGUAGE_CHINESE_SIMPLIFIED, "cmn", "CN", kSAME },
191 { LANGUAGE_CHINESE_TRADITIONAL, "zh", "TW", k0 },
192 { LANGUAGE_CHINESE_TRADITIONAL, "cmn", "TW", kSAME },
193 { LANGUAGE_CHINESE_HONGKONG, "zh", "HK", k0 },
194 { LANGUAGE_CHINESE_SINGAPORE, "zh", "SG", k0 },
195 { LANGUAGE_CHINESE_MACAU, "zh", "MO", k0 },
196 { LANGUAGE_CHINESE_LSO, "zh", "" , k0 },
197 { LANGUAGE_YUE_CHINESE_HONGKONG, "yue", "HK", k0 },
198 { LANGUAGE_ENGLISH_HONG_KONG_SAR, "en", "HK", k0 },
199 { LANGUAGE_JAPANESE, "ja", "JP", k0 },
200 { LANGUAGE_KOREAN, "ko", "KR", k0 },
201 { LANGUAGE_KOREAN_JOHAB, "ko", "KR", k0 },
202 { LANGUAGE_USER_KOREAN_NORTH, "ko", "KP", k0 },
203 { LANGUAGE_SWEDISH, "sv", "SE", k0 },
204 { LANGUAGE_SWEDISH_FINLAND, "sv", "FI", k0 },
205 { LANGUAGE_FINNISH, "fi", "FI", k0 },
206 { LANGUAGE_RUSSIAN, "ru", "RU", k0 },
207 { LANGUAGE_TATAR, "tt", "RU", k0 },
208 { LANGUAGE_ENGLISH_NZ, "en", "NZ", k0 },
209 { LANGUAGE_ENGLISH_EIRE, "en", "IE", k0 },
210 { LANGUAGE_DUTCH_BELGIAN, "nl", "BE", k0 },
211 { LANGUAGE_FRENCH_BELGIAN, "fr", "BE", k0 },
212 { LANGUAGE_FRENCH_CANADIAN, "fr", "CA", k0 },
213 { LANGUAGE_FRENCH_SWISS, "fr", "CH", k0 },
214 { LANGUAGE_GERMAN_SWISS, "de", "CH", k0 },
215 { LANGUAGE_GERMAN_AUSTRIAN, "de", "AT", k0 },
216 { LANGUAGE_ITALIAN_SWISS, "it", "CH", k0 },
217 { LANGUAGE_ALBANIAN, "sq", "AL", k0 },
218 { LANGUAGE_ARABIC_SAUDI_ARABIA, "ar", "SA", k0 },
219 { LANGUAGE_ARABIC_EGYPT, "ar", "EG", k0 },
220 { LANGUAGE_ARABIC_UAE, "ar", "AE", k0 },
221 { LANGUAGE_ARABIC_IRAQ, "ar", "IQ", k0 },
222 { LANGUAGE_ARABIC_LIBYA, "ar", "LY", k0 },
223 { LANGUAGE_ARABIC_ALGERIA, "ar", "DZ", k0 },
224 { LANGUAGE_ARABIC_MOROCCO, "ar", "MA", k0 },
225 { LANGUAGE_ARABIC_TUNISIA, "ar", "TN", k0 },
226 { LANGUAGE_ARABIC_OMAN, "ar", "OM", k0 },
227 { LANGUAGE_ARABIC_YEMEN, "ar", "YE", k0 },
228 { LANGUAGE_ARABIC_SYRIA, "ar", "SY", k0 },
229 { LANGUAGE_ARABIC_JORDAN, "ar", "JO", k0 },
230 { LANGUAGE_ARABIC_LEBANON, "ar", "LB", k0 },
231 { LANGUAGE_ARABIC_KUWAIT, "ar", "KW", k0 },
232 { LANGUAGE_ARABIC_BAHRAIN, "ar", "BH", k0 },
233 { LANGUAGE_ARABIC_QATAR, "ar", "QA", k0 },
234 { LANGUAGE_USER_ARABIC_CHAD, "ar", "TD", k0 },
235 { LANGUAGE_USER_ARABIC_COMOROS, "ar", "KM", k0 },
236 { LANGUAGE_USER_ARABIC_DJIBOUTI, "ar", "DJ", k0 },
237 { LANGUAGE_USER_ARABIC_ERITREA, "ar", "ER", k0 },
238 { LANGUAGE_USER_ARABIC_ISRAEL, "ar", "IL", k0 },
239 { LANGUAGE_USER_ARABIC_MAURITANIA, "ar", "MR", k0 },
240 { LANGUAGE_USER_ARABIC_PALESTINE, "ar", "PS", k0 },
241 { LANGUAGE_USER_ARABIC_SOMALIA, "ar", "SO", k0 },
242 { LANGUAGE_USER_ARABIC_SUDAN, "ar", "SD", k0 },
243 { LANGUAGE_ARABIC_PRIMARY_ONLY, "ar", "" , k0 },
244 { LANGUAGE_BASQUE, "eu", "ES", k0 },
245 { LANGUAGE_BASQUE, "eu", "" , kSAME }, // our earlier definition
246 { LANGUAGE_BULGARIAN, "bg", "BG", k0 },
247 { LANGUAGE_CZECH, "cs", "CZ", k0 },
248 { LANGUAGE_CZECH, "cz", "" , kSAME },
249 { LANGUAGE_ENGLISH_JAMAICA, "en", "JM", k0 },
250 { LANGUAGE_ENGLISH_CARIBBEAN, "en", "BS", k0 }, // not 100%, because AG is Bahamas
251 { LANGUAGE_ENGLISH_BELIZE, "en", "BZ", k0 },
252 { LANGUAGE_ENGLISH_TRINIDAD, "en", "TT", k0 },
253 { LANGUAGE_ENGLISH_ZIMBABWE, "en", "ZW", k0 },
254 { LANGUAGE_ENGLISH_INDONESIA, "en", "ID", k0 },
255 { LANGUAGE_ESTONIAN, "et", "EE", k0 },
256 { LANGUAGE_FAEROESE, "fo", "FO", k0 },
257 { LANGUAGE_FARSI, "fa", "IR", k0 },
258 { LANGUAGE_FRENCH_LUXEMBOURG, "fr", "LU", k0 },
259 { LANGUAGE_FRENCH_MONACO, "fr", "MC", k0 },
260 { LANGUAGE_GERMAN_LUXEMBOURG, "de", "LU", k0 },
261 { LANGUAGE_GERMAN_LIECHTENSTEIN, "de", "LI", k0 },
262 { LANGUAGE_HEBREW, "he", "IL", k0 }, // new: old was "iw"
263 { LANGUAGE_HEBREW, "iw", "IL", kSAME }, // old: new is "he"
264 { LANGUAGE_HUNGARIAN, "hu", "HU", k0 },
265 { LANGUAGE_ICELANDIC, "is", "IS", k0 },
266 { LANGUAGE_INDONESIAN, "id", "ID", k0 }, // new: old was "in"
267 { LANGUAGE_INDONESIAN, "in", "ID", kSAME }, // old: new is "id"
268 { LANGUAGE_NORWEGIAN, "no", "NO", k0 },
269 { LANGUAGE_NORWEGIAN_BOKMAL, "nb", "NO", k0 },
270 { LANGUAGE_NORWEGIAN_BOKMAL_LSO, "nb", "" , k0 },
271 { LANGUAGE_NORWEGIAN_NYNORSK, "nn", "NO", k0 },
272 { LANGUAGE_NORWEGIAN_NYNORSK_LSO, "nn", "" , k0 },
273 { LANGUAGE_POLISH, "pl", "PL", k0 },
274 { LANGUAGE_RHAETO_ROMAN, "rm", "CH", k0 },
275 { LANGUAGE_ROMANIAN, "ro", "RO", k0 },
276 { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD", k0 },
277 { LANGUAGE_SLOVAK, "sk", "SK", k0 },
278 { LANGUAGE_SLOVENIAN, "sl", "SI", k0 },
279 { LANGUAGE_SPANISH_MEXICAN, "es", "MX", k0 },
280 { LANGUAGE_SPANISH_GUATEMALA, "es", "GT", k0 },
281 { LANGUAGE_SPANISH_COSTARICA, "es", "CR", k0 },
282 { LANGUAGE_SPANISH_PANAMA, "es", "PA", k0 },
283 { LANGUAGE_SPANISH_DOMINICAN_REPUBLIC, "es", "DO", k0 },
284 { LANGUAGE_SPANISH_VENEZUELA, "es", "VE", k0 },
285 { LANGUAGE_SPANISH_COLOMBIA, "es", "CO", k0 },
286 { LANGUAGE_SPANISH_PERU, "es", "PE", k0 },
287 { LANGUAGE_SPANISH_ARGENTINA, "es", "AR", k0 },
288 { LANGUAGE_SPANISH_ECUADOR, "es", "EC", k0 },
289 { LANGUAGE_SPANISH_CHILE, "es", "CL", k0 },
290 { LANGUAGE_SPANISH_URUGUAY, "es", "UY", k0 },
291 { LANGUAGE_SPANISH_PARAGUAY, "es", "PY", k0 },
292 { LANGUAGE_SPANISH_BOLIVIA, "es", "BO", k0 },
293 { LANGUAGE_SPANISH_EL_SALVADOR, "es", "SV", k0 },
294 { LANGUAGE_SPANISH_HONDURAS, "es", "HN", k0 },
295 { LANGUAGE_SPANISH_NICARAGUA, "es", "NI", k0 },
296 { LANGUAGE_SPANISH_PUERTO_RICO, "es", "PR", k0 },
297 { LANGUAGE_SPANISH_UNITED_STATES, "es", "US", k0 },
298 { LANGUAGE_SPANISH_LATIN_AMERICA, "es", "" , k0 },
299 { LANGUAGE_TURKISH, "tr", "TR", k0 },
300 { LANGUAGE_UKRAINIAN, "uk", "UA", k0 },
301 { LANGUAGE_VIETNAMESE, "vi", "VN", k0 },
302 { LANGUAGE_LATVIAN, "lv", "LV", k0 },
303 { LANGUAGE_MACEDONIAN, "mk", "MK", k0 },
304 { LANGUAGE_MALAY_MALAYSIA, "ms", "MY", k0 },
305 { LANGUAGE_MALAY_BRUNEI_DARUSSALAM, "ms", "BN", k0 },
306 { LANGUAGE_ENGLISH_MALAYSIA, "en", "MY", k0 },
307 { LANGUAGE_THAI, "th", "TH", k0 },
308 { LANGUAGE_LITHUANIAN, "lt", "LT", k0 },
309 { LANGUAGE_LITHUANIAN_CLASSIC, "lt", "LT", k0 },
310 { LANGUAGE_CROATIAN, "hr", "HR", k0 }, // Croatian in Croatia
311 { LANGUAGE_CROATIAN_BOSNIA_HERZEGOVINA, "hr", "BA", k0 },
312 { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA, "bs", "BA", k0 },
313 { LANGUAGE_BOSNIAN_LSO, "bs", "" , k0 }, // so what is 'bs' vs 'bs-Latn'?
314 { LANGUAGE_SERBIAN_CYRILLIC_SERBIA, "sr", "RS", k0 }, // Serbian Cyrillic in Serbia
315 { LANGUAGE_OBSOLETE_USER_SERBIAN_CYRILLIC_SERBIA, "sr", "RS", k0 },
316 { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr", "CS", k0 }, // Serbian Cyrillic in Serbia and Montenegro
317 { 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)
318 { LANGUAGE_SERBIAN_CYRILLIC_MONTENEGRO, "sr", "ME", k0 },
319 { LANGUAGE_OBSOLETE_USER_SERBIAN_CYRILLIC_MONTENEGRO, "sr", "ME", k0 },
320 { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr", "BA", k0 },
321 { LANGUAGE_SERBIAN_CYRILLIC_LSO, "sr", "" , k0 },
322 { LANGUAGE_SERBIAN_LATIN_SERBIA, "sh", "RS", kSAME }, // legacy kludge, is sr-Latn-RS now
323 { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_SERBIA, "sh", "RS", kSAME }, // legacy kludge, is sr-Latn-RS now
324 { LANGUAGE_SERBIAN_LATIN_SAM, "sh", "CS", kSAME }, // legacy kludge, is sr-Latn-CS now
325 { LANGUAGE_SERBIAN_LATIN_SAM, "sh", "YU", kSAME }, // legacy kludge, is sr-Latn-YU now
326 { LANGUAGE_SERBIAN_LATIN_MONTENEGRO, "sh", "ME", kSAME }, // legacy kludge, is sr-Latn-ME now
327 { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_MONTENEGRO, "sh", "ME", kSAME }, // legacy kludge, is sr-Latn-ME now
328 { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA, "sh", "BA", kSAME }, // legacy kludge, is sr-Latn-BA now
329 { LANGUAGE_SERBIAN_LATIN_LSO, "sh", "" , kSAME }, // legacy kludge, is sr-Latn now
330 { LANGUAGE_ARMENIAN, "hy", "AM", k0 },
331 { LANGUAGE_USER_ARMENIAN_RUSSIA, "hy", "RU", k0 },
332 { LANGUAGE_USER_ARMENIAN_IRAN, "hy", "IR", k0 },
333 { LANGUAGE_AZERI_LATIN, "az", "AZ", k0 }, // macrolanguage code
334 { LANGUAGE_UZBEK_LATIN, "uz", "UZ", k0 }, // macrolanguage code
335 { LANGUAGE_UZBEK_LATIN_LSO, "uz", "" , k0 }, // macrolanguage code
336 { LANGUAGE_BENGALI_BANGLADESH, "bn", "BD", k0 },
337 { LANGUAGE_BENGALI, "bn", "IN", k0 },
338 { LANGUAGE_BURMESE, "my", "MM", k0 },
339 { LANGUAGE_KAZAKH, "kk", "KZ", k0 },
340 { LANGUAGE_ENGLISH_INDIA, "en", "IN", k0 },
341 { LANGUAGE_URDU_INDIA, "ur", "IN", k0 },
342 { LANGUAGE_URDU_PAKISTAN, "ur", "PK", k0 },
343 { LANGUAGE_HINDI, "hi", "IN", k0 },
344 { LANGUAGE_GUJARATI, "gu", "IN", k0 },
345 { LANGUAGE_KANNADA, "kn", "IN", k0 },
346 { LANGUAGE_ASSAMESE, "as", "IN", k0 },
347 { LANGUAGE_KASHMIRI_INDIA, "ks", "IN", k0 },
348 { LANGUAGE_KASHMIRI, "ks", "" , kSAME }, // Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that
349 { LANGUAGE_MALAYALAM, "ml", "IN", k0 },
350 { LANGUAGE_MANIPURI, "mni", "IN", k0 },
351 { LANGUAGE_MARATHI, "mr", "IN", k0 },
352 { LANGUAGE_KONKANI, "kok", "IN", k0 },
353 { LANGUAGE_NEPALI, "ne", "NP", k0 },
354 { LANGUAGE_NEPALI_INDIA, "ne", "IN", k0 },
355 { LANGUAGE_ODIA, "or", "IN", k0 },
356 { LANGUAGE_PUNJABI, "pa", "IN", k0 },
357 { LANGUAGE_SANSKRIT, "sa", "IN", k0 },
358 { LANGUAGE_TAMIL, "ta", "IN", k0 },
359 { LANGUAGE_TAMIL_SRI_LANKA, "ta", "LK", k0 },
360 { LANGUAGE_TELUGU, "te", "IN", k0 },
361 { LANGUAGE_PUNJABI_PAKISTAN, "pnb", "PK", k0 },
362 { LANGUAGE_PUNJABI_ARABIC_LSO, "pnb", "" , k0 },
363 { LANGUAGE_PUNJABI_PAKISTAN, "lah", "PK", kSAME }, // macrolanguage code, earlier preferred 'lah' over 'pa' for Western Panjabi, now there is 'pnb'
364 { 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
365 { LANGUAGE_SINDHI_PAKISTAN, "sd", "PK", kSAME }, // Arabic script
366 { LANGUAGE_SINDHI, "sd", "IN", kSAME }, // Devanagari script
367 { LANGUAGE_BELARUSIAN, "be", "BY", k0 },
368 { LANGUAGE_CATALAN, "ca", "ES", k0 }, // Spain (default)
369 { LANGUAGE_CATALAN, "ca", "AD", k0 }, // Andorra
370 //LANGUAGE_CATALAN_VALENCIAN ca-ES-valencia Bcp47CountryEntry takes precedence
371 { LANGUAGE_CATALAN_VALENCIAN, "ca", "XV", kSAME }, // XV: ISO 3166 user-assigned; old workaround for UI localization only, in case it escaped to document content
372 { 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
373 { LANGUAGE_FRENCH_CAMEROON, "fr", "CM", k0 },
374 { LANGUAGE_FRENCH_COTE_D_IVOIRE, "fr", "CI", k0 },
375 { LANGUAGE_FRENCH_MALI, "fr", "ML", k0 },
376 { LANGUAGE_FRENCH_SENEGAL, "fr", "SN", k0 },
377 { LANGUAGE_FRENCH_ZAIRE, "fr", "CD", k0 }, // Democratic Republic Of Congo
378 { LANGUAGE_FRENCH_MOROCCO, "fr", "MA", k0 },
379 { LANGUAGE_FRENCH_REUNION, "fr", "RE", k0 },
380 { LANGUAGE_FRENCH, "fr", "" , k0 }, // needed as a catcher before other "fr" entries!
381 { LANGUAGE_FRENCH_NORTH_AFRICA, "fr", "" , k0 }, // MS reserved, "fr-015"
382 { LANGUAGE_FRENCH_WEST_INDIES, "fr", "" , k0 }, // no ISO country code; MS "Neither defined nor reserved"
383 { LANGUAGE_FRISIAN_NETHERLANDS, "fy", "NL", k0 },
384 { LANGUAGE_GAELIC_IRELAND, "ga", "IE", k0 },
385 { LANGUAGE_GAELIC_SCOTLAND, "gd", "GB", k0 },
386 { LANGUAGE_GAELIC_SCOTLAND_LEGACY, "gd", "GB", k0 },
387 { LANGUAGE_GALICIAN, "gl", "ES", k0 },
388 { LANGUAGE_GEORGIAN, "ka", "GE", k0 },
389 { LANGUAGE_KHMER, "km", "KH", k0 },
390 { LANGUAGE_KIRGHIZ, "ky", "KG", k0 },
391 { LANGUAGE_LAO, "lo", "LA", k0 },
392 { LANGUAGE_MALTESE, "mt", "MT", k0 },
393 { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA, "mn", "MN", k0 }, // macrolanguage code; should be khk-MN; Cyrillic script
394 { LANGUAGE_MONGOLIAN_CYRILLIC_LSO, "mn", "" , k0 }, // macrolanguage code; should be khk; Cyrillic script
395 { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD", k0 },
396 { LANGUAGE_ROMANIAN_MOLDOVA, "mo", "MD", k0 }, // mo-MD was associated with Russian Moldova LCID, apparently an error; 'mo' is retired, merged with 'ro', see http://www-01.sil.org/iso639-3/documentation.asp?id=mol
397 { LANGUAGE_RUSSIAN_MOLDOVA, "ru", "MD", k0 }, // as per [MS-LCID] rev. 7.0 2015-06-30
398 { LANGUAGE_SWAHILI, "sw", "KE", k0 },
399 { LANGUAGE_USER_SWAHILI_TANZANIA, "sw", "TZ", k0 },
400 { LANGUAGE_TAJIK, "tg", "TJ", k0 },
401 { LANGUAGE_TAJIK_LSO, "tg", "" , k0 },
402 { LANGUAGE_TIBETAN, "bo", "CN", k0 }, // CN politically correct?
403 { LANGUAGE_USER_TIBETAN_INDIA, "bo", "IN", k0 },
404 { LANGUAGE_USER_TIBETAN_BHUTAN, "bo", "BT", k0 },
405 { LANGUAGE_DZONGKHA_BHUTAN, "dz", "BT", k0 },
406 { LANGUAGE_TIBETAN_BHUTAN, "dz", "BT", k0 }, // MS reserved for bo-BT, but LCID was used as Dzongkha, see #i53497#
407 { LANGUAGE_USER_DZONGKHA_MAP_LONLY, "dz", "" , k0 }, // because of the MS error, see lang.h
408 { LANGUAGE_TURKMEN, "tk", "TM", k0 },
409 { LANGUAGE_WELSH, "cy", "GB", k0 },
410 { LANGUAGE_SESOTHO, "st", "ZA", k0 },
411 { LANGUAGE_SEPEDI, "nso", "ZA", k0 },
412 { LANGUAGE_SEPEDI, "ns", "ZA", kSAME }, // fake "ns" for compatibility with existing OOo1.1.x localization to be able to read those documents
413 { LANGUAGE_TSONGA, "ts", "ZA", k0 },
414 { LANGUAGE_TSWANA, "tn", "ZA", k0 },
415 { LANGUAGE_ENGLISH_SAFRICA, "en", "ZA", k0 },
416 { LANGUAGE_AFRIKAANS, "af", "ZA", k0 },
417 { LANGUAGE_VENDA, "ve", "ZA", k0 }, // default 639-1
418 { LANGUAGE_VENDA, "ven", "ZA", kSAME }, // 639-2 may have been used temporarily since 2004-07-23
419 { LANGUAGE_XHOSA, "xh", "ZA", k0 },
420 { LANGUAGE_ZULU, "zu", "ZA", k0 },
421 // { LANGUAGE_QUECHUA_COLOMBIA, "quc", "CO", k0 }, // MS reserved, and looks wrong, quc would be in Guatemala, not Colombia
422 { LANGUAGE_QUECHUA_ECUADOR, "quz", "EC", k0 }, // MS
423 { LANGUAGE_QUECHUA_ECUADOR, "qu", "EC", kSAME }, // macrolanguage code
424 { LANGUAGE_QUECHUA_PERU, "quz", "PE", k0 }, // MS
425 { LANGUAGE_QUECHUA_PERU, "qu", "PE", kSAME }, // macrolanguage code
426 { LANGUAGE_QUECHUA_BOLIVIA, "qu", "BO", k0 }, // macrolanguage code, TODO instead: quh-BO or qul-BO; MS says quz-BO which is wrong
427 { LANGUAGE_PASHTO, "ps", "AF", k0 },
428 { LANGUAGE_OROMO, "om", "ET", k0 },
429 { LANGUAGE_DHIVEHI, "dv", "MV", k0 },
430 { LANGUAGE_UIGHUR_CHINA, "ug", "CN", k0 },
431 { LANGUAGE_TIGRIGNA_ETHIOPIA, "ti", "ET", k0 },
432 { LANGUAGE_TIGRIGNA_ERITREA, "ti", "ER", k0 },
433 { LANGUAGE_AMHARIC_ETHIOPIA, "am", "ET", k0 },
434 { LANGUAGE_GUARANI_PARAGUAY, "gug", "PY", k0 },
435 { LANGUAGE_HAWAIIAN_UNITED_STATES, "haw", "US", k0 },
436 { LANGUAGE_EDO, "bin", "NG", k0 },
437 { LANGUAGE_FULFULDE_NIGERIA, "fuv", "NG", k0 },
438 { LANGUAGE_FULFULDE_NIGERIA, "ff", "NG", kSAME }, // macrolanguage code
439 { LANGUAGE_FULFULDE_SENEGAL, "ff", "SN", k0 }, // macrolanguage code
440 { LANGUAGE_HAUSA_NIGERIA, "ha", "NG", kSAME },
441 { LANGUAGE_USER_HAUSA_GHANA, "ha", "GH", kSAME },
442 { LANGUAGE_IGBO_NIGERIA, "ig", "NG", k0 },
443 { LANGUAGE_KANURI_NIGERIA, "kr", "NG", k0 },
444 { LANGUAGE_YORUBA, "yo", "NG", k0 },
445 { LANGUAGE_SOMALI, "so", "SO", k0 },
446 { LANGUAGE_PAPIAMENTU, "pap", "AN", k0 },
447 { LANGUAGE_USER_PAPIAMENTU_ARUBA, "pap", "AW", k0 },
448 { LANGUAGE_USER_PAPIAMENTU_CURACAO, "pap", "CW", k0 },
449 { LANGUAGE_USER_PAPIAMENTU_BONAIRE, "pap", "BQ", k0 },
450 { LANGUAGE_ENGLISH_SINGAPORE, "en", "SG", k0 },
451 { LANGUAGE_USER_YIDDISH_US, "yi", "US", k0 },
452 { LANGUAGE_YIDDISH, "yi", "IL", k0 }, // new: old was "ji"
453 { LANGUAGE_YIDDISH, "ji", "IL", kSAME }, // old: new is "yi"
454 { LANGUAGE_SYRIAC, "syr", "TR", k0 }, // "TR" according to http://www.ethnologue.com/show_language.asp?code=SYC
455 { LANGUAGE_SINHALESE_SRI_LANKA, "si", "LK", k0 },
456 { LANGUAGE_CHEROKEE_UNITED_STATES, "chr", "US", kSAME },
457 { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu", "CA", kSAME }, // macrolanguage code
458 { LANGUAGE_INUKTITUT_LATIN_LSO, "iu", "" , kSAME }, // macrolanguage code
459 { LANGUAGE_SAMI_NORTHERN_NORWAY, "se", "NO", k0 },
460 { LANGUAGE_SAMI_INARI, "smn", "FI", k0 },
461 { LANGUAGE_SAMI_INARI_LSO, "smn", "" , k0 },
462 { LANGUAGE_SAMI_LULE_NORWAY, "smj", "NO", k0 },
463 { LANGUAGE_SAMI_LULE_SWEDEN, "smj", "SE", k0 },
464 { LANGUAGE_SAMI_LULE_LSO, "smj", "" , k0 },
465 { LANGUAGE_SAMI_NORTHERN_FINLAND, "se", "FI", k0 },
466 { LANGUAGE_SAMI_NORTHERN_SWEDEN, "se", "SE", k0 },
467 { LANGUAGE_SAMI_SKOLT, "sms", "FI", k0 },
468 { LANGUAGE_SAMI_SKOLT_LSO, "sms", "" , k0 },
469 { LANGUAGE_SAMI_SOUTHERN_NORWAY, "sma", "NO", k0 },
470 { LANGUAGE_SAMI_SOUTHERN_SWEDEN, "sma", "SE", k0 },
471 { LANGUAGE_SAMI_SOUTHERN_LSO, "sma", "" , k0 },
472 { LANGUAGE_USER_SAMI_KILDIN_RUSSIA, "sjd", "RU", k0 },
473 { LANGUAGE_MAPUDUNGUN_CHILE, "arn", "CL", k0 },
474 { LANGUAGE_CORSICAN_FRANCE, "co", "FR", k0 },
475 { LANGUAGE_ALSATIAN_FRANCE, "gsw", "FR", k0 }, // 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.
476 { LANGUAGE_YAKUT_RUSSIA, "sah", "RU", k0 },
477 { LANGUAGE_MOHAWK_CANADA, "moh", "CA", k0 },
478 { LANGUAGE_BASHKIR_RUSSIA, "ba", "RU", k0 },
479 { LANGUAGE_KICHE_GUATEMALA, "qut", "GT", k0 },
480 { LANGUAGE_DARI_AFGHANISTAN, "prs", "AF", k0 },
481 { LANGUAGE_DARI_AFGHANISTAN, "gbz", "AF", kSAME }, // was an error
482 { LANGUAGE_WOLOF_SENEGAL, "wo", "SN", k0 },
483 { LANGUAGE_FILIPINO, "fil", "PH", k0 },
484 { LANGUAGE_USER_TAGALOG, "tl", "PH", k0 },
485 { LANGUAGE_ENGLISH_PHILIPPINES, "en", "PH", k0 },
486 { LANGUAGE_IBIBIO_NIGERIA, "ibb", "NG", k0 },
487 { LANGUAGE_YI, "ii", "CN", k0 },
488 { LANGUAGE_ENGLISH_ARAB_EMIRATES, "en", "AE", k0 },
489 { LANGUAGE_ENGLISH_BAHRAIN, "en", "BH", k0 }, // MS reserved
490 { LANGUAGE_ENGLISH_EGYPT, "en", "EG", k0 }, // MS reserved
491 { LANGUAGE_ENGLISH_JORDAN, "en", "JO", k0 }, // MS reserved
492 { LANGUAGE_ENGLISH_KUWAIT, "en", "KW", k0 }, // MS reserved
493 { LANGUAGE_ENGLISH_TURKEY, "en", "TR", k0 }, // MS reserved
494 { LANGUAGE_ENGLISH_YEMEN, "en", "YE", k0 }, // MS reserved
495 { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "kab", "DZ", k0 }, // In practice Kabyle is the language used for this
496 { LANGUAGE_OBSOLETE_USER_KABYLE, "kab", "DZ", k0 },
497 { 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.
498 { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "tmz", "MA", kSAME },
499 { LANGUAGE_TAMAZIGHT_MOROCCO, "tmz", "MA", k0 }, // MS reserved
500 { 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
501 { LANGUAGE_USER_LATIN_VATICAN, "la", "VA", k0 },
502 { LANGUAGE_OBSOLETE_USER_LATIN, "la", "VA", k0 },
503 { LANGUAGE_LATIN_LSO, "la", "" , k0 },
504 { LANGUAGE_USER_ESPERANTO, "eo", "" , k0 },
505 { LANGUAGE_USER_INTERLINGUA, "ia", "" , k0 },
506 { LANGUAGE_USER_INTERLINGUE, "ie", "" , k0 },
507 { LANGUAGE_MAORI_NEW_ZEALAND, "mi", "NZ", k0 },
508 { LANGUAGE_OBSOLETE_USER_MAORI, "mi", "NZ", k0 },
509 { LANGUAGE_KINYARWANDA_RWANDA, "rw", "RW", k0 },
510 { LANGUAGE_OBSOLETE_USER_KINYARWANDA, "rw", "RW", k0 },
511 { LANGUAGE_UPPER_SORBIAN_GERMANY, "hsb", "DE", k0 }, // 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
512 { LANGUAGE_OBSOLETE_USER_UPPER_SORBIAN,"hsb", "DE", k0 },
513 { LANGUAGE_LOWER_SORBIAN_GERMANY, "dsb", "DE", k0 }, // 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
514 { LANGUAGE_LOWER_SORBIAN_LSO, "dsb", "" , k0 },
515 { LANGUAGE_OBSOLETE_USER_LOWER_SORBIAN,"dsb", "DE", k0 },
516 { LANGUAGE_OCCITAN_FRANCE, "oc", "FR", k0 },
517 { LANGUAGE_OBSOLETE_USER_OCCITAN, "oc", "FR", k0 },
518 { LANGUAGE_USER_KURDISH_TURKEY, "kmr", "TR", kSAME },
519 { LANGUAGE_USER_KURDISH_TURKEY, "ku", "TR", kSAME },
520 { LANGUAGE_USER_KURDISH_SYRIA, "kmr", "SY", kSAME },
521 { LANGUAGE_USER_KURDISH_SYRIA, "ku", "SY", kSAME },
522 { LANGUAGE_KURDISH_ARABIC_IRAQ, "ckb", "IQ", k0 },
523 { LANGUAGE_KURDISH_ARABIC_IRAQ, "ku", "IQ", kSAME },
524 { LANGUAGE_OBSOLETE_USER_KURDISH_IRAQ, "ku", "IQ", LANGUAGE_KURDISH_ARABIC_IRAQ },
525 { LANGUAGE_USER_KURDISH_SOUTHERN_IRAN, "sdh", "IR", k0 },
526 { LANGUAGE_USER_KURDISH_SOUTHERN_IRAQ, "sdh", "IQ", k0 },
527 { LANGUAGE_USER_KURDISH_IRAN, "ckb", "IR", k0 },
528 { LANGUAGE_USER_KURDISH_IRAN, "ku", "IR", kSAME },
529 { LANGUAGE_KURDISH_ARABIC_LSO, "ckb", "" , k0 },
530 { LANGUAGE_USER_SARDINIAN, "sc", "IT", k0 }, // macrolanguage code
531 { LANGUAGE_USER_SARDINIAN_CAMPIDANESE, "sro", "IT", k0 },
532 { LANGUAGE_USER_SARDINIAN_GALLURESE, "sdn", "IT", k0 },
533 { LANGUAGE_USER_SARDINIAN_LOGUDORESE, "src", "IT", k0 },
534 { LANGUAGE_USER_SARDINIAN_SASSARESE, "sdc", "IT", k0 },
535 { LANGUAGE_BRETON_FRANCE, "br", "FR", k0 },
536 { LANGUAGE_OBSOLETE_USER_BRETON, "br", "FR", k0 },
537 { LANGUAGE_KALAALLISUT_GREENLAND, "kl", "GL", k0 },
538 { LANGUAGE_OBSOLETE_USER_KALAALLISUT, "kl", "GL", k0 },
539 { LANGUAGE_USER_SWAZI, "ss", "ZA", k0 },
540 { LANGUAGE_USER_NDEBELE_SOUTH, "nr", "ZA", k0 },
541 { LANGUAGE_TSWANA_BOTSWANA, "tn", "BW", k0 },
542 { LANGUAGE_OBSOLETE_USER_TSWANA_BOTSWANA, "tn", "BW", k0 },
543 { LANGUAGE_USER_ENGLISH_BOTSWANA, "en", "BW", k0 },
544 { LANGUAGE_USER_MOORE, "mos", "BF", k0 },
545 { LANGUAGE_USER_BAMBARA, "bm", "ML", k0 },
546 { LANGUAGE_USER_AKAN, "ak", "GH", k0 },
547 { LANGUAGE_LUXEMBOURGISH_LUXEMBOURG, "lb", "LU", k0 },
548 { LANGUAGE_OBSOLETE_USER_LUXEMBOURGISH, "lb", "LU", k0 },
549 { LANGUAGE_USER_FRIULIAN, "fur", "IT", k0 },
550 { LANGUAGE_USER_FIJIAN, "fj", "FJ", k0 },
551 { LANGUAGE_USER_AFRIKAANS_NAMIBIA, "af", "NA", k0 },
552 { LANGUAGE_USER_ENGLISH_NAMIBIA, "en", "NA", k0 },
553 { LANGUAGE_USER_WALLOON, "wa", "BE", k0 },
554 { LANGUAGE_USER_COPTIC, "cop", "EG", k0 },
555 { LANGUAGE_USER_GASCON, "gsc", "FR", k0 },
556 { LANGUAGE_USER_GERMAN_BELGIUM, "de", "BE", k0 },
557 { LANGUAGE_USER_CHUVASH, "cv", "RU", k0 },
558 { LANGUAGE_USER_EWE_GHANA, "ee", "GH", k0 },
559 { LANGUAGE_USER_ENGLISH_GHANA, "en", "GH", k0 },
560 { LANGUAGE_USER_SANGO, "sg", "CF", k0 },
561 { LANGUAGE_USER_GANDA, "lg", "UG", k0 },
562 { LANGUAGE_USER_LINGALA_DRCONGO, "ln", "CD", k0 },
563 { LANGUAGE_USER_LOW_GERMAN, "nds", "DE", k0 },
564 { LANGUAGE_USER_HILIGAYNON, "hil", "PH", k0 },
565 { LANGUAGE_USER_ENGLISH_MALAWI, "en", "MW", k0 }, /* en default for MW */
566 { LANGUAGE_USER_NYANJA, "ny", "MW", k0 },
567 { LANGUAGE_USER_KASHUBIAN, "csb", "PL", k0 },
568 { LANGUAGE_SPANISH_CUBA, "es", "CU", k0 },
569 { LANGUAGE_OBSOLETE_USER_SPANISH_CUBA, "es", "CU", k0 },
570 { LANGUAGE_USER_QUECHUA_NORTH_BOLIVIA, "qul", "BO", k0 },
571 { LANGUAGE_USER_QUECHUA_SOUTH_BOLIVIA, "quh", "BO", k0 },
572 { LANGUAGE_USER_BODO_INDIA, "brx", "IN", k0 },
573 { LANGUAGE_USER_DOGRI_INDIA, "dgo", "IN", k0 },
574 { LANGUAGE_USER_MAITHILI_INDIA, "mai", "IN", k0 },
575 { LANGUAGE_USER_SANTALI_INDIA, "sat", "IN", k0 },
576 { LANGUAGE_USER_TETUN, "tet", "ID", k0 },
577 { LANGUAGE_USER_TETUN_TIMOR_LESTE, "tet", "TL", k0 },
578 { LANGUAGE_USER_TOK_PISIN, "tpi", "PG", k0 },
579 { LANGUAGE_USER_SHUSWAP, "shs", "CA", k0 },
580 { LANGUAGE_USER_ANCIENT_GREEK, "grc", "GR", k0 },
581 { LANGUAGE_USER_ASTURIAN, "ast", "ES", k0 },
582 { LANGUAGE_USER_LATGALIAN, "ltg", "LV", k0 },
583 { LANGUAGE_USER_MAORE, "swb", "YT", k0 },
584 { LANGUAGE_USER_BUSHI, "buc", "YT", k0 },
585 { LANGUAGE_USER_TAHITIAN, "ty", "PF", k0 },
586 { LANGUAGE_MALAGASY_PLATEAU, "plt", "MG", k0 },
587 { LANGUAGE_MALAGASY_PLATEAU, "mg", "MG", kSAME },
588 { LANGUAGE_OBSOLETE_USER_MALAGASY_PLATEAU, "plt", "MG", k0 },
589 { LANGUAGE_USER_BAFIA, "ksf", "CM", k0 },
590 { LANGUAGE_USER_GIKUYU, "ki", "KE", k0 },
591 { LANGUAGE_USER_RUSYN_UKRAINE, "rue", "UA", k0 },
592 { LANGUAGE_USER_RUSYN_SLOVAKIA, "rue", "SK", k0 },
593 { LANGUAGE_USER_LIMBU, "lif", "NP", k0 },
594 { LANGUAGE_USER_LOJBAN, "jbo", "" , k0 },
595 { LANGUAGE_USER_HAITIAN, "ht", "HT", k0 },
596 { LANGUAGE_FRENCH_HAITI, "fr", "HT", k0 },
597 { LANGUAGE_USER_BEEMBE, "beq", "CG", k0 },
598 { LANGUAGE_USER_BEKWEL, "bkw", "CG", k0 },
599 { LANGUAGE_USER_KITUBA, "mkw", "CG", k0 },
600 { LANGUAGE_USER_LARI, "ldi", "CG", k0 },
601 { LANGUAGE_USER_MBOCHI, "mdw", "CG", k0 },
602 { LANGUAGE_USER_TEKE_EBOO, "ebo", "CG", k0 },
603 { LANGUAGE_USER_TEKE_IBALI, "tek", "CG", k0 },
604 { LANGUAGE_USER_TEKE_TYEE, "tyx", "CG", k0 },
605 { LANGUAGE_USER_VILI, "vif", "CG", k0 },
606 { LANGUAGE_USER_PORTUGUESE_ANGOLA, "pt", "AO", k0 },
607 { LANGUAGE_USER_MANX, "gv", "GB", k0 },
608 { LANGUAGE_USER_ARAGONESE, "an", "ES", k0 },
609 { LANGUAGE_USER_KEYID, "qtz", "" , k0 }, // key id pseudolanguage used for UI testing
610 { LANGUAGE_USER_PALI_LATIN, "pli", "" , kSAME }, // Pali with Latin script, ISO 639-3 (sigh..) back-compat, Latin is not a default script though...
611 { LANGUAGE_USER_KYRGYZ_CHINA, "ky", "CN", k0 },
612 { LANGUAGE_USER_KOMI_ZYRIAN, "kpv", "RU", k0 },
613 { LANGUAGE_USER_KOMI_PERMYAK, "koi", "RU", k0 },
614 { LANGUAGE_USER_PITJANTJATJARA, "pjt", "AU", k0 },
615 { LANGUAGE_USER_ERZYA, "myv", "RU", k0 },
616 { LANGUAGE_USER_MARI_MEADOW, "mhr", "RU", k0 },
617 { LANGUAGE_USER_KHANTY, "kca", "RU", k0 },
618 { LANGUAGE_USER_LIVONIAN, "liv", "RU", k0 },
619 { LANGUAGE_USER_MOKSHA, "mdf", "RU", k0 },
620 { LANGUAGE_USER_MARI_HILL, "mrj", "RU", k0 },
621 { LANGUAGE_USER_NGANASAN, "nio", "RU", k0 },
622 { LANGUAGE_USER_OLONETS, "olo", "RU", k0 },
623 { LANGUAGE_USER_VEPS, "vep", "RU", k0 },
624 { LANGUAGE_USER_VORO, "vro", "EE", k0 },
625 { LANGUAGE_USER_NENETS, "yrk", "RU", k0 },
626 { LANGUAGE_USER_AKA, "axk", "CF", k0 },
627 { LANGUAGE_USER_AKA_CONGO, "axk", "CG", k0 },
628 { LANGUAGE_USER_DIBOLE, "bvx", "CG", k0 },
629 { LANGUAGE_USER_DOONDO, "dde", "CG", k0 },
630 { LANGUAGE_USER_KAAMBA, "xku", "CG", k0 },
631 { LANGUAGE_USER_KOONGO, "kng", "CD", k0 },
632 { LANGUAGE_USER_KOONGO_CONGO, "kng", "CG", k0 },
633 { LANGUAGE_USER_KUNYI, "njx", "CG", k0 },
634 { LANGUAGE_USER_NGUNGWEL, "ngz", "CG", k0 },
635 { LANGUAGE_USER_NJYEM, "njy", "CM", k0 },
636 { LANGUAGE_USER_NJYEM_CONGO, "njy", "CG", k0 },
637 { LANGUAGE_USER_PUNU, "puu", "GA", k0 },
638 { LANGUAGE_USER_PUNU_CONGO, "puu", "CG", k0 },
639 { LANGUAGE_USER_SUUNDI, "sdj", "CG", k0 },
640 { LANGUAGE_USER_TEKE_KUKUYA, "kkw", "CG", k0 },
641 { LANGUAGE_USER_TSAANGI, "tsa", "CG", k0 },
642 { LANGUAGE_USER_YAKA, "iyx", "CG", k0 },
643 { LANGUAGE_USER_YOMBE, "yom", "CD", k0 },
644 { LANGUAGE_USER_YOMBE_CONGO, "yom", "CG", k0 },
645 { LANGUAGE_USER_SIDAMA, "sid", "ET", k0 },
646 { LANGUAGE_USER_NKO, "nqo", "GN", k0 },
647 { LANGUAGE_USER_UDMURT, "udm", "RU", k0 },
648 { LANGUAGE_USER_CORNISH, "kw", "UK", k0 },
649 { LANGUAGE_USER_SAMI_PITE_SWEDEN, "sje", "SE", k0 },
650 { LANGUAGE_USER_NGAEBERE, "gym", "PA", k0 },
651 { LANGUAGE_USER_KUMYK, "kum", "RU", k0 },
652 { LANGUAGE_USER_NOGAI, "nog", "RU", k0 },
653 { LANGUAGE_USER_LADIN, "lld", "IT", k0 },
654 { LANGUAGE_USER_FRENCH_BURKINA_FASO, "fr", "BF", k0 },
655 { LANGUAGE_USER_PUINAVE, "pui", "CO", k0 },
656 { LANGUAGE_USER_AVAR, "av", "RU", k0 },
657 { LANGUAGE_USER_LENGO, "lgr", "SB", k0 },
658 { LANGUAGE_USER_FRENCH_BENIN, "fr", "BJ", k0 },
659 { LANGUAGE_USER_FRENCH_NIGER, "fr", "NE", k0 },
660 { LANGUAGE_USER_FRENCH_TOGO, "fr", "TG", k0 },
661 { LANGUAGE_USER_KVEN_FINNISH, "fkv", "NO", k0 },
662 { LANGUAGE_USER_CHURCH_SLAVIC, "cu", "RU", k0 },
663 { LANGUAGE_USER_VENETIAN, "vec", "IT", k0 },
664 { LANGUAGE_USER_ENGLISH_GAMBIA, "en", "GM", k0 },
665 { LANGUAGE_USER_OCCITAN_ARANESE, "oc", "ES", k0 },
666 { LANGUAGE_USER_ARPITAN_FRANCE, "frp", "FR", k0 },
667 { LANGUAGE_USER_ARPITAN_ITALY, "frp", "IT", k0 },
668 { LANGUAGE_USER_ARPITAN_SWITZERLAND, "frp", "CH", k0 },
669 { LANGUAGE_USER_APATANI, "apt", "IN", k0 },
670 { LANGUAGE_USER_ENGLISH_MAURITIUS, "en", "MU", k0 },
671 { LANGUAGE_USER_FRENCH_MAURITIUS, "fr", "MU", k0 },
672 { LANGUAGE_USER_SILESIAN, "szl", "PL", k0 },
673 { LANGUAGE_USER_MANCHU, "mnc", "CN", k0 },
674 { LANGUAGE_USER_XIBE, "sjo", "CN", k0 },
675 { LANGUAGE_USER_KITUBA_DRCONGO, "ktu", "CD", k0 },
676 { LANGUAGE_USER_FON, "fon", "BJ", k0 },
677 { LANGUAGE_USER_PLAUTDIETSCH, "pdt", "CA", k0 },
678 { LANGUAGE_USER_ARMENIAN_WESTERN, "hyw", "AM", k0 },
679 { LANGUAGE_USER_ARMENIAN_CLASSICAL, "xcl", "AM", k0 },
680 { LANGUAGE_USER_JUHOAN, "ktz", "NA", k0 },
681 { LANGUAGE_USER_NARO, "nhr", "BW", k0 },
682 { LANGUAGE_USER_ILOKO, "ilo", "PH", k0 },
683 { LANGUAGE_USER_ENGLISH_ZAMBIA, "en", "ZM", k0 },
684 { LANGUAGE_USER_ENGLISH_SRI_LANKA, "en", "LK", k0 },
685 { LANGUAGE_USER_ENGLISH_NIGERIA, "en", "NG", k0 },
686 { LANGUAGE_USER_KABARDIAN, "kbd", "RU", k0 }, // Cyrillic script
687 { LANGUAGE_USER_GUADELOUPEAN_CREOLE_FRENCH, "gcf", "GP", k0 },
688 { LANGUAGE_USER_LIGURIAN, "lij", "IT", k0 },
689 { LANGUAGE_USER_MINANGKABAU, "min", "ID", k0 },
690 { LANGUAGE_USER_SUNDANESE, "sun", "ID", k0 },
691 { LANGUAGE_USER_YAKA_DRCONGO, "yaf", "CD", k0 },
692 { LANGUAGE_USER_ENGLISH_KENYA, "en", "KE", k0 },
693 { LANGUAGE_USER_CABECAR, "cjp", "CR", k0 },
694 { LANGUAGE_USER_BRIBRI, "bzd", "CR", k0 },
695 { LANGUAGE_USER_ENGLISH_DENMARK, "en", "DK", k0 },
696 { LANGUAGE_USER_SESOTHO_LESOTHO, "st", "LS", k0 },
697 { LANGUAGE_MULTIPLE, "mul", "" , k0 }, // multiple languages, many languages are used
698 { LANGUAGE_UNDETERMINED, "und", "" , k0 }, // undetermined language, language cannot be identified
699 { LANGUAGE_NONE, "zxx", "" , k0 }, // added to ISO 639-2 on 2006-01-11: Used to declare the absence of linguistic information
700 { LANGUAGE_DONTKNOW, "", "" , k0 } // marks end of table
701 };
702
703 IsoLanguageScriptCountryEntry const aImplIsoLangScriptEntries[] =
704 {
705 // MS-LangID, ISO639-ISO15924, ISO3166, override
706 { LANGUAGE_SERBIAN_LATIN_SERBIA, "sr-Latn", "RS", k0 },
707 { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_SERBIA, "sr-Latn", "RS", k0 },
708 { LANGUAGE_SERBIAN_LATIN_MONTENEGRO, "sr-Latn", "ME", k0 },
709 { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_MONTENEGRO,"sr-Latn", "ME", k0 },
710 { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA, "sr-Latn", "BA", k0 },
711 { LANGUAGE_SERBIAN_LATIN_SAM, "sr-Latn", "CS", k0 }, // 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
712 { LANGUAGE_SERBIAN_LATIN_SAM, "sr-Latn", "YU", k0 }, // legacy Serbian Latin in Yugoslavia
713 { LANGUAGE_SERBIAN_LATIN_LSO, "sr-Latn", "" , k0 },
714 { LANGUAGE_SERBIAN_LATIN_NEUTRAL, "sr-Latn", "" , LANGUAGE_SERBIAN_LATIN_LSO }, // MS lists this as 'sr' only, what a mess
715 { LANGUAGE_SERBIAN_CYRILLIC_SERBIA, "sr-Cyrl", "RS", kSAME }, // MS
716 { LANGUAGE_SERBIAN_CYRILLIC_MONTENEGRO, "sr-Cyrl", "ME", kSAME }, // MS
717 { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr-Cyrl", "BA", kSAME }, // MS
718 { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr-Cyrl", "CS", kSAME }, // MS
719 { LANGUAGE_SERBIAN_CYRILLIC_LSO, "sr-Cyrl", "" , kSAME }, // MS
720 { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs-Cyrl", "BA", k0 },
721 { LANGUAGE_BOSNIAN_CYRILLIC_LSO, "bs-Cyrl", "" , k0 },
722 { LANGUAGE_AZERI_CYRILLIC, "az-Cyrl", "AZ", k0 }, // macrolanguage code
723 { LANGUAGE_AZERI_CYRILLIC_LSO, "az-Cyrl", "" , k0 }, // macrolanguage code
724 { LANGUAGE_UZBEK_CYRILLIC, "uz-Cyrl", "UZ", k0 }, // macrolanguage code
725 { LANGUAGE_UZBEK_CYRILLIC_LSO, "uz-Cyrl", "" , k0 }, // macrolanguage code
726 { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA, "mn-Cyrl", "MN", k0 }, // macrolanguage code; should be khk-MN or khk-Cyrl-MN
727 { LANGUAGE_MONGOLIAN_CYRILLIC_LSO, "mn-Cyrl", "" , k0 }, // macrolanguage code; MS, should be khk or khk-Cyrl
728 { LANGUAGE_MONGOLIAN_MONGOLIAN_MONGOLIA, "mn-Mong", "MN", k0 }, // macrolanguage code; MS, should be khk-Mong-MN
729 { LANGUAGE_MONGOLIAN_MONGOLIAN_CHINA, "mn-Mong", "CN", k0 }, // macrolanguage code; MS, should actually be mvf-CN
730 { LANGUAGE_MONGOLIAN_MONGOLIAN_LSO, "mn-Mong", "" , k0 }, // macrolanguage code
731 { LANGUAGE_USER_PALI_LATIN, "pi-Latn", "" , k0 },
732 { LANGUAGE_USER_PALI_THAI, "pi-Thai", "" , k0 },
733 { LANGUAGE_USER_KARAKALPAK_LATIN, "kaa-Latn", "UZ", k0 },
734 { LANGUAGE_TAJIK, "tg-Cyrl", "TJ", k0 }, // MS
735 { LANGUAGE_TAJIK_LSO, "tg-Cyrl", "" , k0 }, // MS
736 { LANGUAGE_AZERI_LATIN, "az-Latn", "AZ", k0 }, // macrolanguage code; MS
737 { LANGUAGE_AZERI_LATIN_LSO, "az-Latn", "" , k0 }, // macrolanguage code; MS
738 { LANGUAGE_USER_YIDDISH_US, "yi-Hebr", "US", kSAME }, // macrolanguage code; MS, Hebr is suppress-script
739 { LANGUAGE_YIDDISH, "yi-Hebr", "IL", kSAME }, // macrolanguage code; MS, Hebr is suppress-script
740 { LANGUAGE_UZBEK_LATIN, "uz-Latn", "UZ", k0 }, // macrolanguage code
741 { LANGUAGE_UZBEK_LATIN_LSO, "uz-Latn", "" , k0 },
742 { LANGUAGE_SINDHI, "sd-Deva", "IN", k0 }, // MS
743 { LANGUAGE_SINDHI_PAKISTAN, "sd-Arab", "PK", k0 }, // MS
744 { LANGUAGE_SINDHI_ARABIC_LSO, "sd-Arab", "" , k0 },
745 { LANGUAGE_CHEROKEE_UNITED_STATES, "chr-Cher", "US", k0 }, // MS
746 { LANGUAGE_CHEROKEE_CHEROKEE_LSO, "chr-Cher", "" , k0 },
747 { LANGUAGE_INUKTITUT_SYLLABICS_CANADA, "iu-Cans", "CA", k0 }, // macrolanguage code, MS
748 { LANGUAGE_INUKTITUT_SYLLABICS_LSO, "iu-Cans", "" , k0 }, // macrolanguage code, MS
749 { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu-Latn", "CA", k0 }, // macrolanguage code, MS
750 { LANGUAGE_INUKTITUT_LATIN_LSO, "iu-Latn", "" , k0 }, // macrolanguage code, MS
751 { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "tzm-Tfng", "MA", k0 },
752 { LANGUAGE_TAMAZIGHT_TIFINAGH_LSO, "tzm-Tfng", "" , k0 },
753 { LANGUAGE_KASHMIRI_INDIA, "ks-Deva", "IN", k0 }, // MS
754 { LANGUAGE_KASHMIRI, "ks-Arab", "" , k0 }, // MS, Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that
755 { LANGUAGE_HAUSA_NIGERIA, "ha-Latn", "NG", k0 }, // MS
756 { LANGUAGE_USER_HAUSA_GHANA, "ha-Latn", "GH", k0 },
757 { LANGUAGE_HAUSA_LATIN_LSO, "ha-Latn", "" , k0 },
758 { LANGUAGE_LATIN_LSO, "la-Latn", "" , kSAME }, // MS, though Latn is suppress-script
759 { LANGUAGE_TAI_NUA_CHINA, "tdd-Tale", "CN", k0 }, // MS reserved
760 { LANGUAGE_LU_CHINA, "khb-Talu", "CN", k0 }, // MS reserved
761 { LANGUAGE_KURDISH_ARABIC_IRAQ, "ku-Arab", "IQ", kSAME }, // macrolanguage code, MS
762 { LANGUAGE_KURDISH_ARABIC_LSO, "ku-Arab", "" , kSAME }, // macrolanguage code, MS
763 { LANGUAGE_USER_KURDISH_TURKEY, "kmr-Latn", "TR", k0 },
764 { LANGUAGE_USER_KURDISH_SYRIA, "kmr-Latn", "SY", k0 },
765 { LANGUAGE_PUNJABI_PAKISTAN, "pnb-Arab", "PK", k0 },
766 { LANGUAGE_PUNJABI_ARABIC_LSO, "pnb-Arab", "" , k0 },
767 { LANGUAGE_PUNJABI_PAKISTAN, "pa-Arab", "PK", k0 }, // MS, incorrect
768 { LANGUAGE_PUNJABI_ARABIC_LSO, "pa-Arab", "" , k0 }, // MS, incorrect
769 { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "tzm-Latn", "DZ", kSAME }, // MS
770 { LANGUAGE_TAMAZIGHT_LATIN_LSO, "tzm-Latn", "" , k0 }, // MS
771 { LANGUAGE_FULFULDE_SENEGAL, "ff-Latn", "SN", k0 }, // macrolanguage code, MS
772 { LANGUAGE_FULFULDE_LATIN_LSO, "ff-Latn", "" , k0 }, // macrolanguage code
773 { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA, "bs-Latn", "BA", kSAME }, // MS, though Latn is suppress-script
774 { LANGUAGE_BOSNIAN_LATIN_LSO, "bs-Latn", "" , LANGUAGE_BOSNIAN_LSO }, // MS, though Latn is suppress-script
775 { LANGUAGE_CHINESE_TRADITIONAL_LSO, "zh-Hant", "" , k0 },
776 { LANGUAGE_USER_MANINKAKAN_EASTERN_LATIN, "emk-Latn", "GN", k0 },
777 { LANGUAGE_USER_CREE_PLAINS_LATIN, "crk-Latn", "CA", k0 },
778 { LANGUAGE_USER_CREE_PLAINS_SYLLABICS, "crk-Cans", "CA", k0 },
779 { LANGUAGE_USER_CREE_PLAINS_LATIN, "crk-Latn", "CN", kSAME }, // erroneous tdf#73973
780 { LANGUAGE_USER_CREE_PLAINS_SYLLABICS, "crk-Cans", "CN", kSAME }, // erroneous tdf#73973
781 { LANGUAGE_USER_HUNGARIAN_ROVAS, "hu-Hung", "HU", k0 },
782 { LANGUAGE_USER_MALAY_ARABIC_MALAYSIA, "ms-Arab", "MY", k0 },
783 { LANGUAGE_USER_MALAY_ARABIC_BRUNEI, "ms-Arab", "BN", k0 },
784 { LANGUAGE_KAZAKH_LATIN, "kk-Latn", "KZ", k0 }, // MS reserved
785 { LANGUAGE_KAZAKH_LATIN_LSO, "kk-Latn", "" , k0 }, // MS reserved
786 { LANGUAGE_KAZAKH_CYRILLIC_LSO, "kk-Cyrl", "" , k0 }, // MS reserved
787 { LANGUAGE_DONTKNOW, "", "" , k0 } // marks end of table
788 };
789
790 Bcp47CountryEntry const aImplBcp47CountryEntries[] =
791 {
792 // MS-LangID full BCP47, ISO3166, ISO639-Variant or other fallback
793 { LANGUAGE_CATALAN_VALENCIAN, "ca-ES-valencia", "ES", "ca-valencia", k0 },
794 { LANGUAGE_OBSOLETE_USER_CATALAN_VALENCIAN, "ca-ES-valencia", "ES", "", k0 }, // In case MS format files using the old value escaped into the wild, map them back.
795 { LANGUAGE_USER_ENGLISH_UK_OXENDICT, "en-GB-oxendict", "GB", "", k0 },
796 { LANGUAGE_USER_ENGLISH_UK_OED, "en-GB-oed", "GB", "", LANGUAGE_USER_ENGLISH_UK_OXENDICT }, // grandfathered, deprecated, prefer en-GB-oxendict
797 { LANGUAGE_SPANISH_DATED, "es-ES-u-co-trad", "ES", "es-u-co-trad", k0 }, // RFC6067/CLDR
798 { LANGUAGE_SPANISH_DATED, "es-ES_tradnl", "ES", "", kSAME }, // MS malformed
799 // { LANGUAGE_YUE_CHINESE_HONGKONG, "zh-yue-HK", "HK", "", 0 }, // MS reserved, prefer yue-HK; do not add unless LanguageTag::simpleExtract() can handle it to not call liblangtag for rsc!
800 { LANGUAGE_DONTKNOW, "", "", "", k0 } // marks end of table
801 };
802
803 const IsoLanguageCountryEntry aLastResortFallbackEntry =
804 { LANGUAGE_ENGLISH_US, "en", "US", k0 };
805
getTagString() const806 OUString IsoLanguageCountryEntry::getTagString() const
807 {
808 if (maCountry[0])
809 return OUString( OUString::createFromAscii( maLanguage) + "-" + OUString::createFromAscii( maCountry));
810 else
811 return OUString::createFromAscii( maLanguage);
812 }
813
getLocale() const814 css::lang::Locale IsoLanguageCountryEntry::getLocale() const
815 {
816 return lang::Locale( OUString::createFromAscii( maLanguage), OUString::createFromAscii( maCountry), OUString());
817 }
818
getTagString() const819 OUString IsoLanguageScriptCountryEntry::getTagString() const
820 {
821 if (maCountry[0])
822 return OUString( OUString::createFromAscii( maLanguageScript) + "-" + OUString::createFromAscii( maCountry));
823 else
824 return OUString::createFromAscii( maLanguageScript);
825 }
826
getLocale() const827 css::lang::Locale IsoLanguageScriptCountryEntry::getLocale() const
828 {
829 return lang::Locale( I18NLANGTAG_QLT, OUString::createFromAscii( maCountry), getTagString());
830 }
831
startsInIgnoreAsciiCase(const OUString & rStr) const832 bool IsoLanguageScriptCountryEntry::startsInIgnoreAsciiCase( const OUString & rStr ) const
833 {
834 return rStr.matchIgnoreAsciiCaseAsciiL( maLanguageScript, strlen( maLanguageScript) );
835 }
836
getTagString() const837 OUString Bcp47CountryEntry::getTagString() const
838 {
839 return OUString::createFromAscii( mpBcp47);
840 }
841
getLocale() const842 css::lang::Locale Bcp47CountryEntry::getLocale() const
843 {
844 return lang::Locale( I18NLANGTAG_QLT, OUString::createFromAscii( maCountry), getTagString());
845 }
846
847
848 // In this table are the countries which should mapped to a specific
849 // english language
850 IsoLangEngEntry const aImplIsoLangEngEntries[] =
851 {
852 { LANGUAGE_ENGLISH_UK, "AO" }, // Angola
853 { LANGUAGE_ENGLISH_UK, "BJ" }, // Benin
854 { LANGUAGE_ENGLISH_UK, "BW" }, // Botswana
855 { LANGUAGE_ENGLISH_UK, "BI" }, // Burundi
856 { LANGUAGE_ENGLISH_UK, "CM" }, // Cameroon
857 { LANGUAGE_ENGLISH_UK, "GA" }, // Gabon
858 { LANGUAGE_ENGLISH_UK, "GM" }, // Gambia
859 { LANGUAGE_ENGLISH_UK, "GH" }, // Ghana
860 { LANGUAGE_ENGLISH_UK, "GN" }, // Guinea
861 { LANGUAGE_ENGLISH_UK, "LS" }, // Lesotho
862 { LANGUAGE_ENGLISH_UK, "MW" }, // Malawi
863 { LANGUAGE_ENGLISH_UK, "MT" }, // Malta
864 { LANGUAGE_ENGLISH_UK, "NA" }, // Namibia
865 { LANGUAGE_ENGLISH_UK, "NG" }, // Nigeria
866 { LANGUAGE_ENGLISH_UK, "UG" }, // Uganda
867 { LANGUAGE_ENGLISH_UK, "ZM" }, // Zambia
868 { LANGUAGE_ENGLISH_UK, "ZW" }, // Zimbabwe
869 { LANGUAGE_ENGLISH_UK, "SZ" }, // Swaziland
870 { LANGUAGE_ENGLISH_UK, "NG" }, // Sierra Leone
871 { LANGUAGE_ENGLISH_UK, "KN" }, // Saint Kitts and Nevis
872 { LANGUAGE_ENGLISH_UK, "SH" }, // St. Helena
873 { LANGUAGE_ENGLISH_UK, "IO" }, // British Indian Oceanic Territory
874 { LANGUAGE_ENGLISH_UK, "FK" }, // Falkland Islands
875 { LANGUAGE_ENGLISH_UK, "GI" }, // Gibraltar
876 { LANGUAGE_ENGLISH_UK, "KI" }, // Kiribati
877 { LANGUAGE_ENGLISH_UK, "VG" }, // Virgin Islands
878 { LANGUAGE_ENGLISH_UK, "MU" }, // Mauritius
879 { LANGUAGE_ENGLISH_UK, "FJ" }, // Fiji
880 { LANGUAGE_ENGLISH_US, "KI" }, // Kiribati
881 { LANGUAGE_ENGLISH_US, "LR" }, // Liberia
882 { LANGUAGE_ENGLISH_US, "GU" }, // Guam
883 { LANGUAGE_ENGLISH_US, "MH" }, // Marshall Islands
884 { LANGUAGE_ENGLISH_US, "PW" }, // Palau
885 { LANGUAGE_ENGLISH_CARIBBEAN, "AI" }, // Anguilla
886 { LANGUAGE_ENGLISH_CARIBBEAN, "AG" }, // Antigua and Barbuda
887 { LANGUAGE_ENGLISH_CARIBBEAN, "BS" }, // Bahamas
888 { LANGUAGE_ENGLISH_CARIBBEAN, "BB" }, // Barbados
889 { LANGUAGE_ENGLISH_CARIBBEAN, "BM" }, // Bermuda
890 { LANGUAGE_ENGLISH_CARIBBEAN, "KY" }, // Cayman Islands
891 { LANGUAGE_ENGLISH_CARIBBEAN, "GD" }, // Grenada
892 { LANGUAGE_ENGLISH_CARIBBEAN, "DM" }, // Dominica
893 { LANGUAGE_ENGLISH_CARIBBEAN, "HT" }, // Haiti
894 { LANGUAGE_ENGLISH_CARIBBEAN, "MS" }, // Montserrat
895 { LANGUAGE_ENGLISH_CARIBBEAN, "FM" }, // Micronesia
896 { LANGUAGE_ENGLISH_CARIBBEAN, "VC" }, // St. Vincent / Grenadines
897 { LANGUAGE_ENGLISH_CARIBBEAN, "LC" }, // Saint Lucia
898 { LANGUAGE_ENGLISH_CARIBBEAN, "TC" }, // Turks & Caicos Islands
899 { LANGUAGE_ENGLISH_CARIBBEAN, "GY" }, // Guyana
900 { LANGUAGE_ENGLISH_CARIBBEAN, "TT" }, // Trinidad and Tobago
901 { LANGUAGE_ENGLISH_AUS, "CX" }, // Christmas Islands
902 { LANGUAGE_ENGLISH_AUS, "CC" }, // Cocos (Keeling) Islands
903 { LANGUAGE_ENGLISH_AUS, "NF" }, // Norfolk Island
904 { LANGUAGE_ENGLISH_AUS, "PG" }, // Papua New Guinea
905 { LANGUAGE_ENGLISH_AUS, "SB" }, // Solomon Islands
906 { LANGUAGE_ENGLISH_AUS, "TV" }, // Tuvalu
907 { LANGUAGE_ENGLISH_AUS, "NR" }, // Nauru
908 { LANGUAGE_ENGLISH_NZ, "CK" }, // Cook Islands
909 { LANGUAGE_ENGLISH_NZ, "NU" }, // Niue
910 { LANGUAGE_ENGLISH_NZ, "TK" }, // Tokelau
911 { LANGUAGE_ENGLISH_NZ, "TO" }, // Tonga
912 { LANGUAGE_DONTKNOW, "" } // marks end of table
913 };
914
915
916 IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries[] =
917 {
918 { LANGUAGE_NORWEGIAN_BOKMAL, "no", "BOK" }, // registered subtags for "no" in rfc1766
919 { LANGUAGE_NORWEGIAN_NYNORSK, "no", "NYN" }, // registered subtags for "no" in rfc1766
920 { LANGUAGE_SERBIAN_LATIN_SAM, "sr", "latin" },
921 { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr", "cyrillic" },
922 { LANGUAGE_AZERI_LATIN, "az", "latin" },
923 { LANGUAGE_AZERI_CYRILLIC, "az", "cyrillic" },
924 { LANGUAGE_DONTKNOW, "", "" } // marks end of table
925 };
926
927
928 // in this table are only names to find the best language
929 IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries2[] =
930 {
931 { LANGUAGE_NORWEGIAN_BOKMAL, "no", "bokmaal" },
932 { LANGUAGE_NORWEGIAN_BOKMAL, "no", "bokmal" },
933 { LANGUAGE_NORWEGIAN_NYNORSK, "no", "nynorsk" },
934 { LANGUAGE_DONTKNOW, "", "" } // marks end of table
935 };
936
937
938 // in this table are only names to find the best language
939 IsoLangOtherEntry const aImplOtherEntries[] =
940 {
941 { LANGUAGE_ENGLISH_US, "c" },
942 { LANGUAGE_CHINESE, "chinese" },
943 { LANGUAGE_GERMAN, "german" },
944 { LANGUAGE_JAPANESE, "japanese" },
945 { LANGUAGE_KOREAN, "korean" },
946 { LANGUAGE_ENGLISH_US, "posix" },
947 { LANGUAGE_CHINESE_TRADITIONAL, "tchinese" },
948 { LANGUAGE_DONTKNOW, nullptr } // marks end of table
949 };
950
951
952 // in this table are only privateuse names
953 IsoLangOtherEntry const aImplPrivateUseEntries[] =
954 {
955 { LANGUAGE_USER_PRIV_NOTRANSLATE, "x-no-translate" }, //! not BCP47 but legacy in .xcu configmgr
956 { LANGUAGE_USER_PRIV_DEFAULT, "x-default" },
957 { LANGUAGE_USER_PRIV_COMMENT, "x-comment" },
958 { LANGUAGE_USER_PRIV_NONE, "x-none" },
959 { LANGUAGE_USER_PRIV_JOKER, "*" }, //! not BCP47 but transferable in configmgr
960 { LANGUAGE_DONTKNOW, nullptr } // marks end of table
961 };
962
963
964 // static
convertLanguageToLocaleImpl(LanguageType nLang,css::lang::Locale & rLocale,bool bIgnoreOverride)965 void MsLangId::Conversion::convertLanguageToLocaleImpl( LanguageType nLang,
966 css::lang::Locale & rLocale, bool bIgnoreOverride )
967 {
968 const Bcp47CountryEntry* pBcp47EntryOverride = nullptr;
969 const IsoLanguageScriptCountryEntry* pScriptEntryOverride = nullptr;
970 const IsoLanguageCountryEntry* pEntryOverride = nullptr;
971
972 Label_Override_Lang_Locale:
973
974 // Search for LangID in BCP47
975 for (const Bcp47CountryEntry* pBcp47Entry = aImplBcp47CountryEntries;
976 pBcp47Entry->mnLang != LANGUAGE_DONTKNOW; ++pBcp47Entry)
977 {
978 if (pBcp47Entry->mnLang == nLang)
979 {
980 if (bIgnoreOverride || !pBcp47Entry->mnOverride)
981 {
982 rLocale.Language = I18NLANGTAG_QLT;
983 rLocale.Country = OUString::createFromAscii( pBcp47Entry->maCountry);
984 rLocale.Variant = pBcp47Entry->getTagString();
985 return;
986 }
987 else if (pBcp47Entry->mnOverride && pBcp47EntryOverride != pBcp47Entry)
988 {
989 pBcp47EntryOverride = pBcp47Entry;
990 nLang = getOverrideLang( pBcp47Entry->mnLang, pBcp47Entry->mnOverride);
991 goto Label_Override_Lang_Locale;
992 }
993 }
994 }
995
996 // Search for LangID in ISO lll-Ssss-CC
997 for (const IsoLanguageScriptCountryEntry* pScriptEntry = aImplIsoLangScriptEntries;
998 pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry)
999 {
1000 if (pScriptEntry->mnLang == nLang)
1001 {
1002 if (bIgnoreOverride || !pScriptEntry->mnOverride)
1003 {
1004 rLocale.Language = I18NLANGTAG_QLT;
1005 rLocale.Country = OUString::createFromAscii( pScriptEntry->maCountry);
1006 rLocale.Variant = pScriptEntry->getTagString();
1007 return;
1008 }
1009 else if (pScriptEntry->mnOverride && pScriptEntryOverride != pScriptEntry)
1010 {
1011 pScriptEntryOverride = pScriptEntry;
1012 nLang = getOverrideLang( pScriptEntry->mnLang, pScriptEntry->mnOverride);
1013 goto Label_Override_Lang_Locale;
1014 }
1015 }
1016 }
1017
1018 // Search for LangID in ISO lll-CC
1019 for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries;
1020 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1021 {
1022 if (pEntry->mnLang == nLang)
1023 {
1024 if (bIgnoreOverride || !pEntry->mnOverride)
1025 {
1026 rLocale.Language = OUString::createFromAscii( pEntry->maLanguage );
1027 rLocale.Country = OUString::createFromAscii( pEntry->maCountry );
1028 rLocale.Variant.clear();
1029 return;
1030 }
1031 else if (pEntry->mnOverride && pEntryOverride != pEntry)
1032 {
1033 pEntryOverride = pEntry;
1034 nLang = getOverrideLang( pEntry->mnLang, pEntry->mnOverride);
1035 goto Label_Override_Lang_Locale;
1036 }
1037 }
1038 }
1039
1040 // Look for privateuse definitions.
1041 for (const IsoLangOtherEntry* pPrivateEntry = aImplPrivateUseEntries;
1042 pPrivateEntry->mnLang != LANGUAGE_DONTKNOW; ++pPrivateEntry)
1043 {
1044 if (pPrivateEntry->mnLang == nLang)
1045 {
1046 rLocale.Language = I18NLANGTAG_QLT;
1047 rLocale.Country.clear();
1048 rLocale.Variant = OUString::createFromAscii( pPrivateEntry->mpLanguage );
1049 return;
1050 }
1051 }
1052
1053 // Not found. Passed rLocale argument remains unchanged.
1054 }
1055
1056
1057 // static
getLocale(const IsoLanguageCountryEntry * pEntry)1058 css::lang::Locale MsLangId::Conversion::getLocale( const IsoLanguageCountryEntry * pEntry )
1059 {
1060 if (pEntry->mnOverride)
1061 {
1062 lang::Locale aLocale;
1063 convertLanguageToLocaleImpl( getOverrideLang( pEntry->mnLang, pEntry->mnOverride), aLocale, false);
1064 return aLocale;
1065 }
1066 else
1067 return pEntry->getLocale();
1068 }
1069
1070 // static
getLocale(const IsoLanguageScriptCountryEntry * pEntry)1071 css::lang::Locale MsLangId::Conversion::getLocale( const IsoLanguageScriptCountryEntry * pEntry )
1072 {
1073 if (pEntry->mnOverride)
1074 {
1075 lang::Locale aLocale;
1076 convertLanguageToLocaleImpl( getOverrideLang( pEntry->mnLang, pEntry->mnOverride), aLocale, false);
1077 return aLocale;
1078 }
1079 else
1080 return pEntry->getLocale();
1081 }
1082
1083 // static
getLocale(const Bcp47CountryEntry * pEntry)1084 css::lang::Locale MsLangId::Conversion::getLocale( const Bcp47CountryEntry * pEntry )
1085 {
1086 if (pEntry->mnOverride)
1087 {
1088 lang::Locale aLocale;
1089 convertLanguageToLocaleImpl( getOverrideLang( pEntry->mnLang, pEntry->mnOverride), aLocale, false);
1090 return aLocale;
1091 }
1092 else
1093 return pEntry->getLocale();
1094 }
1095
1096 // static
lookupFallbackLocale(const css::lang::Locale & rLocale)1097 css::lang::Locale MsLangId::Conversion::lookupFallbackLocale(
1098 const css::lang::Locale & rLocale )
1099 {
1100 // language is lower case in table
1101 OUString aLowerLang = rLocale.Language.toAsciiLowerCase();
1102 // country is upper case in table
1103 OUString aUpperCountry = rLocale.Country.toAsciiUpperCase();
1104 sal_Int32 nCountryLen = aUpperCountry.getLength();
1105
1106 if (rLocale.Language == I18NLANGTAG_QLT)
1107 {
1108 // Search in BCP47, only full match and one fallback, for other
1109 // fallbacks only LanguageTag can decide.
1110 for (const Bcp47CountryEntry* pBcp47Entry = aImplBcp47CountryEntries;
1111 pBcp47Entry->mnLang != LANGUAGE_DONTKNOW; ++pBcp47Entry)
1112 {
1113 if ( rLocale.Variant.equalsIgnoreAsciiCase( pBcp47Entry->getTagString()) ||
1114 rLocale.Variant.equalsIgnoreAsciiCaseAscii( pBcp47Entry->mpFallback))
1115 return getLocale( pBcp47Entry); // may override
1116 }
1117
1118 // Search in ISO lll-Ssss-CC
1119 const IsoLanguageScriptCountryEntry* pFirstScript = nullptr;
1120 for (const IsoLanguageScriptCountryEntry* pScriptEntry = aImplIsoLangScriptEntries;
1121 pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry)
1122 {
1123 if (pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant))
1124 {
1125 if (rLocale.Variant.equalsIgnoreAsciiCase( pScriptEntry->getTagString()))
1126 return getLocale( pScriptEntry); // may override
1127 if (!pFirstScript)
1128 pFirstScript = pScriptEntry;
1129 }
1130 }
1131 // If at least a lll-Ssss matched, try that with country or use it as
1132 // fallback.
1133 if (pFirstScript)
1134 {
1135 // Check for country only if there is more than lll-Ssss-CC in tag
1136 // string, else we would had matched it already.
1137 if (!aUpperCountry.isEmpty() && rLocale.Variant.getLength() > 11)
1138 {
1139 for (const IsoLanguageScriptCountryEntry* pScriptEntry = pFirstScript;
1140 pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry)
1141 {
1142 if (aUpperCountry.equalsAscii( pScriptEntry->maCountry) &&
1143 pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant))
1144 return getLocale( pScriptEntry); // may override
1145 }
1146 }
1147 return getLocale( pFirstScript); // may override
1148 }
1149
1150 // Extract language from tag string, country is used as present in
1151 // Locale because in the tables that follow we have only ISO 3166
1152 // countries and if that is in the tag string we also have it in the
1153 // Locale.
1154 aLowerLang = rLocale.Variant.getToken(0, '-').toAsciiLowerCase();
1155 // Nothing with "x-..." or "i-..." or any 1 letter in lll-CC table that
1156 // follows.
1157 if (aLowerLang.getLength() == 1)
1158 return aLastResortFallbackEntry.getLocale();
1159 }
1160
1161 // Search for locale and remember first lang-only.
1162 const IsoLanguageCountryEntry* pFirstLang = nullptr;
1163 const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries;
1164 for ( ; pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1165 {
1166 if (aLowerLang.equalsAscii( pEntry->maLanguage))
1167 {
1168 if (*pEntry->maCountry)
1169 {
1170 if (nCountryLen && aUpperCountry.equalsAscii( pEntry->maCountry))
1171 return getLocale( pEntry); // may override
1172 }
1173 else
1174 {
1175 if (pEntry->mnLang.anyOf(
1176 // These are known to have no country assigned.
1177 LANGUAGE_USER_ESPERANTO,
1178 LANGUAGE_USER_INTERLINGUA,
1179 LANGUAGE_USER_INTERLINGUE,
1180 LANGUAGE_USER_LOJBAN,
1181 LANGUAGE_KASHMIRI,
1182 LANGUAGE_USER_KEYID,
1183 // And the special codes without country.
1184 LANGUAGE_MULTIPLE,
1185 LANGUAGE_UNDETERMINED,
1186 LANGUAGE_NONE))
1187 {
1188 return getLocale( pEntry); // may override
1189 }
1190 }
1191 if (!pFirstLang)
1192 pFirstLang = pEntry;
1193 }
1194 }
1195
1196 // Language not found at all => use default.
1197 if (!pFirstLang)
1198 return aLastResortFallbackEntry.getLocale();
1199
1200 // Search for first entry of language with any country.
1201 pEntry = pFirstLang;
1202 for ( ; pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1203 {
1204 if (aLowerLang.equalsAscii( pEntry->maLanguage))
1205 {
1206 if (*pEntry->maCountry)
1207 return getLocale( pEntry); // may override
1208 }
1209 }
1210
1211 return aLastResortFallbackEntry.getLocale();
1212 }
1213
1214
1215 // static
convertPrivateUseToLanguage(const OUString & rPriv)1216 LanguageType MsLangId::Conversion::convertPrivateUseToLanguage( const OUString& rPriv )
1217 {
1218 for (const IsoLangOtherEntry* pPrivateEntry = aImplPrivateUseEntries;
1219 pPrivateEntry->mnLang != LANGUAGE_DONTKNOW; ++pPrivateEntry)
1220 {
1221 if ( rPriv.equalsIgnoreAsciiCaseAscii( pPrivateEntry->mpLanguage ) )
1222 return pPrivateEntry->mnLang;
1223 }
1224 return LANGUAGE_DONTKNOW;
1225 }
1226
1227
1228 // static
convertLocaleToLanguageImpl(const css::lang::Locale & rLocale)1229 LanguageType MsLangId::Conversion::convertLocaleToLanguageImpl(
1230 const css::lang::Locale& rLocale )
1231 {
1232 if (rLocale.Language == I18NLANGTAG_QLT)
1233 {
1234 // "x-..." private use and the nasty "*" joker
1235 if (rLocale.Variant.startsWithIgnoreAsciiCase( "x-") || (rLocale.Variant == "*"))
1236 return convertPrivateUseToLanguage( rLocale.Variant);
1237
1238 // Search in BCP47
1239 for (const Bcp47CountryEntry* pBcp47Entry = aImplBcp47CountryEntries;
1240 pBcp47Entry->mnLang != LANGUAGE_DONTKNOW; ++pBcp47Entry)
1241 {
1242 if (rLocale.Variant.equalsIgnoreAsciiCase( pBcp47Entry->getTagString()))
1243 return getOverrideLang( pBcp47Entry->mnLang, pBcp47Entry->mnOverride);
1244 }
1245
1246 // Search in ISO lll-Ssss-CC
1247 for (const IsoLanguageScriptCountryEntry* pScriptEntry = aImplIsoLangScriptEntries;
1248 pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry)
1249 {
1250 if (pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant))
1251 {
1252 if (rLocale.Variant.equalsIgnoreAsciiCase( pScriptEntry->getTagString()))
1253 return getOverrideLang( pScriptEntry->mnLang, pScriptEntry->mnOverride);
1254 }
1255 }
1256 }
1257 else
1258 {
1259 // language is lower case in table
1260 OUString aLowerLang = rLocale.Language.toAsciiLowerCase();
1261 // country is upper case in table
1262 OUString aUpperCountry = rLocale.Country.toAsciiUpperCase();
1263
1264 // Search in ISO lll-CC
1265 for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries;
1266 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1267 {
1268 if (aLowerLang.equalsAscii( pEntry->maLanguage) && aUpperCountry.equalsAscii( pEntry->maCountry))
1269 return getOverrideLang( pEntry->mnLang, pEntry->mnOverride);
1270 }
1271 }
1272 return LANGUAGE_DONTKNOW;
1273 }
1274
1275
1276 // static
getOverride(const css::lang::Locale & rLocale)1277 css::lang::Locale MsLangId::Conversion::getOverride( const css::lang::Locale& rLocale )
1278 {
1279 if (rLocale.Language == I18NLANGTAG_QLT)
1280 {
1281 // "x-..." private use and the nasty "*" joker
1282 if (rLocale.Variant.startsWithIgnoreAsciiCase( "x-") || (rLocale.Variant == "*"))
1283 return rLocale; // no overrides
1284
1285 // Search in BCP47
1286 for (const Bcp47CountryEntry* pBcp47Entry = aImplBcp47CountryEntries;
1287 pBcp47Entry->mnLang != LANGUAGE_DONTKNOW; ++pBcp47Entry)
1288 {
1289 if (rLocale.Variant.equalsIgnoreAsciiCase( pBcp47Entry->getTagString()))
1290 return getLocale( pBcp47Entry); // may override
1291 }
1292
1293 // Search in ISO lll-Ssss-CC
1294 for (const IsoLanguageScriptCountryEntry* pScriptEntry = aImplIsoLangScriptEntries;
1295 pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry)
1296 {
1297 if (pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant))
1298 {
1299 if (rLocale.Variant.equalsIgnoreAsciiCase( pScriptEntry->getTagString()))
1300 return getLocale( pScriptEntry); // may override
1301 }
1302 }
1303 }
1304 else
1305 {
1306 // language is lower case in table
1307 OUString aLowerLang = rLocale.Language.toAsciiLowerCase();
1308 // country is upper case in table
1309 OUString aUpperCountry = rLocale.Country.toAsciiUpperCase();
1310
1311 // Search in ISO lll-CC
1312 for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries;
1313 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1314 {
1315 if (aLowerLang.equalsAscii( pEntry->maLanguage) && aUpperCountry.equalsAscii( pEntry->maCountry))
1316 return getLocale( pEntry); // may override
1317 }
1318 }
1319 return lang::Locale();
1320 }
1321
1322
1323 // static
convertIsoNamesToLanguage(const OUString & rLang,const OUString & rCountry,bool bSkipIsoTable)1324 LanguageType MsLangId::Conversion::convertIsoNamesToLanguage( const OUString& rLang,
1325 const OUString& rCountry, bool bSkipIsoTable )
1326 {
1327 // language is lower case in table
1328 OUString aLowerLang = rLang.toAsciiLowerCase();
1329 // country is upper case in table
1330 OUString aUpperCountry = rCountry.toAsciiUpperCase();
1331
1332 const IsoLanguageCountryEntry* pFirstLang = nullptr;
1333
1334 if (!bSkipIsoTable)
1335 {
1336 // first look for exact match
1337 for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries;
1338 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1339 {
1340 if ( aLowerLang.equalsAscii( pEntry->maLanguage ) )
1341 {
1342 if ( aUpperCountry.isEmpty() ||
1343 aUpperCountry.equalsAscii( pEntry->maCountry ) )
1344 return pEntry->mnLang;
1345 if ( !pFirstLang )
1346 pFirstLang = pEntry;
1347 else if ( !*pEntry->maCountry )
1348 pFirstLang = pEntry;
1349 }
1350 }
1351
1352 // some eng countries should be mapped to a specific english language
1353 if ( aLowerLang == "en" )
1354 {
1355 for (const IsoLangEngEntry* pEngEntry = aImplIsoLangEngEntries;
1356 pEngEntry->mnLang != LANGUAGE_DONTKNOW; ++pEngEntry)
1357 {
1358 if ( aUpperCountry.equalsAscii( pEngEntry->maCountry ) )
1359 return pEngEntry->mnLang;
1360 }
1361 }
1362 }
1363
1364 // test for specific languages which are not used standard ISO 3166 codes
1365 for (const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries;
1366 pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW; ++pNoneStdEntry)
1367 {
1368 if ( aLowerLang.equalsAscii( pNoneStdEntry->maLanguage ) )
1369 {
1370 // The countries in this table are not all in upper case
1371 if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry->maCountry ) )
1372 return pNoneStdEntry->mnLang;
1373 }
1374 }
1375 for (const IsoLangNoneStdEntry* pNoneStdEntry2 = aImplIsoNoneStdLangEntries2;
1376 pNoneStdEntry2->mnLang != LANGUAGE_DONTKNOW; ++pNoneStdEntry2)
1377 {
1378 if ( aLowerLang.equalsAscii( pNoneStdEntry2->maLanguage ) )
1379 {
1380 // The countries in this table are not all in upper case
1381 if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry2->maCountry ) )
1382 return pNoneStdEntry2->mnLang;
1383 }
1384 }
1385
1386 if (!bSkipIsoTable)
1387 {
1388 // If the language is correct, then we return the default language
1389 if ( pFirstLang )
1390 return pFirstLang->mnLang;
1391
1392 // if only the country is set, look for any entry matching the country
1393 // (to allow reading country and language in separate steps, in any order)
1394 if ( !rCountry.isEmpty() && rLang.isEmpty() )
1395 {
1396 for (const IsoLanguageCountryEntry* pEntry2 = aImplIsoLangEntries;
1397 pEntry2->mnLang != LANGUAGE_DONTKNOW; ++pEntry2)
1398 {
1399 if ( aUpperCountry.equalsAscii( pEntry2->maCountry ) )
1400 return pEntry2->mnLang;
1401 }
1402
1403 aLowerLang = aUpperCountry.toAsciiLowerCase();
1404 }
1405 }
1406
1407 // Look for privateuse definitions.
1408 LanguageType nLang = convertPrivateUseToLanguage( aLowerLang);
1409 if (nLang != LANGUAGE_DONTKNOW)
1410 return nLang;
1411
1412 // Now look for all other definitions, which are not standard
1413 for (const IsoLangOtherEntry* pOtherEntry = aImplOtherEntries;
1414 pOtherEntry->mnLang != LANGUAGE_DONTKNOW; ++pOtherEntry)
1415 {
1416 if ( aLowerLang.equalsAscii( pOtherEntry->mpLanguage ) )
1417 return pOtherEntry->mnLang;
1418 }
1419
1420 return LANGUAGE_DONTKNOW;
1421 }
1422
1423
1424 // static
convertIsoNamesToLanguage(std::string_view rLang,std::string_view rCountry)1425 LanguageType MsLangId::Conversion::convertIsoNamesToLanguage( std::string_view rLang,
1426 std::string_view rCountry )
1427 {
1428 OUString aLang = OStringToOUString( rLang, RTL_TEXTENCODING_ASCII_US);
1429 OUString aCountry = OStringToOUString( rCountry, RTL_TEXTENCODING_ASCII_US);
1430 return convertIsoNamesToLanguage( aLang, aCountry, false);
1431 }
1432
1433 namespace {
1434
1435 struct IsoLangGLIBCModifiersEntry
1436 {
1437 LanguageType mnLang;
1438 char maLanguage[4];
1439 char maCountry[3];
1440 char maAtString[9];
1441 };
1442
1443 }
1444
1445 IsoLangGLIBCModifiersEntry const aImplIsoLangGLIBCModifiersEntries[] =
1446 {
1447 // MS-LANGID codes ISO639-1/2/3 ISO3166 glibc modifier
1448 { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs", "BA", "cyrillic" },
1449 { LANGUAGE_USER_SERBIAN_LATIN_SERBIA, "sr", "RS", "latin" }, // Serbian Latin in Serbia
1450 { LANGUAGE_SERBIAN_LATIN_SAM, "sr", "CS", "latin" }, // Serbian Latin in Serbia and Montenegro
1451 { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO, "sr", "ME", "latin" }, // Serbian Latin in Montenegro
1452 { LANGUAGE_SERBIAN_LATIN_LSO, "sr", "", "latin" },
1453 { LANGUAGE_AZERI_CYRILLIC, "az", "AZ", "cyrillic" },
1454 { LANGUAGE_UZBEK_CYRILLIC, "uz", "UZ", "cyrillic" },
1455 { LANGUAGE_CATALAN_VALENCIAN, "ca", "ES", "valencia" },
1456 { LANGUAGE_DONTKNOW, "", "", "" } // marks end of table
1457 };
1458
1459 // convert a unix locale string into LanguageType
1460
1461 // static
convertUnxByteStringToLanguage(const OString & rString)1462 LanguageType MsLangId::convertUnxByteStringToLanguage(
1463 const OString& rString )
1464 {
1465 OString aLang;
1466 OString aCountry;
1467 OString aAtString;
1468
1469 sal_Int32 nLangSepPos = rString.indexOf( '_' );
1470 sal_Int32 nCountrySepPos = rString.indexOf( '.' );
1471 sal_Int32 nAtPos = rString.indexOf( '@' );
1472
1473 if (nCountrySepPos < 0)
1474 nCountrySepPos = nAtPos;
1475 if (nCountrySepPos < 0)
1476 nCountrySepPos = rString.getLength();
1477
1478 if (nAtPos >= 0)
1479 aAtString = rString.copy( nAtPos+1 );
1480
1481 if (((nLangSepPos >= 0) && (nLangSepPos > nCountrySepPos)) || (nLangSepPos < 0))
1482 {
1483 // eg. "el.sun_eu_greek", "tchinese", "es.ISO8859-15"
1484 aLang = rString.copy( 0, nCountrySepPos );
1485 }
1486 else if ( nLangSepPos >= 0 )
1487 {
1488 // well formed iso names like "en_US.UTF-8", "sh_BA.ISO8859-2@bosnia"
1489 aLang = rString.copy( 0, nLangSepPos );
1490 aCountry = rString.copy( nLangSepPos+1, nCountrySepPos - nLangSepPos - 1);
1491 }
1492
1493 // if there is a glibc modifier, first look for exact match in modifier table
1494 if (!aAtString.isEmpty())
1495 {
1496 // language is lower case in table
1497 OString aLowerLang = aLang.toAsciiLowerCase();
1498 // country is upper case in table
1499 OString aUpperCountry = aCountry.toAsciiUpperCase();
1500 for (const IsoLangGLIBCModifiersEntry* pGLIBCModifiersEntry = aImplIsoLangGLIBCModifiersEntries;
1501 pGLIBCModifiersEntry->mnLang != LANGUAGE_DONTKNOW; ++pGLIBCModifiersEntry)
1502 { // avoid embedded \0 warning
1503 if (aLowerLang == pGLIBCModifiersEntry->maLanguage &&
1504 aAtString == pGLIBCModifiersEntry->maAtString )
1505 {
1506 if (aUpperCountry.isEmpty() ||
1507 aUpperCountry == pGLIBCModifiersEntry->maCountry )
1508 {
1509 return pGLIBCModifiersEntry->mnLang;
1510 }
1511 }
1512 }
1513 }
1514
1515 return Conversion::convertIsoNamesToLanguage( aLang, aCountry );
1516 }
1517
1518
1519 // static
getDefinedLanguagetags()1520 ::std::vector< MsLangId::LanguagetagMapping > MsLangId::getDefinedLanguagetags()
1521 {
1522 ::std::vector< LanguagetagMapping > aVec;
1523 for (const Bcp47CountryEntry* pEntry = aImplBcp47CountryEntries;
1524 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1525 {
1526 aVec.emplace_back( pEntry->getTagString(), pEntry->mnLang);
1527 }
1528 for (const IsoLanguageScriptCountryEntry* pEntry = aImplIsoLangScriptEntries;
1529 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1530 {
1531 aVec.emplace_back( pEntry->getTagString(), pEntry->mnLang);
1532 }
1533 for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries;
1534 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry)
1535 {
1536 aVec.emplace_back( pEntry->getTagString(), pEntry->mnLang);
1537 }
1538 return aVec;
1539 }
1540
1541 /* vim:set shiftwidth=4 softtabstop=4 expandtab: */
1542