diff options
Diffstat (limited to 'i18nlangtag/source/isolang/isolang.cxx')
-rw-r--r-- | i18nlangtag/source/isolang/isolang.cxx | 1075 |
1 files changed, 537 insertions, 538 deletions
diff --git a/i18nlangtag/source/isolang/isolang.cxx b/i18nlangtag/source/isolang/isolang.cxx index 303b399e130b..3c2d0219f7e0 100644 --- a/i18nlangtag/source/isolang/isolang.cxx +++ b/i18nlangtag/source/isolang/isolang.cxx @@ -28,7 +28,7 @@ using namespace com::sun::star; -static const LanguageType kSAME = 0xffff; +static const LanguageType kSAME(0xffff); namespace { inline LanguageType getOverrideLang( LanguageType nLang, LanguageType nOverride ) @@ -165,157 +165,158 @@ struct IsoLangOtherEntry * code: * LANGUAGE_ENGLISH LANGUAGE_ARABIC_PRIMARY_ONLY */ +constexpr LanguageType k0(0); static IsoLanguageCountryEntry const aImplIsoLangEntries[] = { // MS-LANGID codes, ISO639-1/2/3, ISO3166, override - { LANGUAGE_ENGLISH, "en", "" , 0 }, - { LANGUAGE_ENGLISH_US, "en", "US", 0 }, - { LANGUAGE_ENGLISH_UK, "en", "GB", 0 }, - { LANGUAGE_ENGLISH_AUS, "en", "AU", 0 }, - { LANGUAGE_ENGLISH_CAN, "en", "CA", 0 }, - { LANGUAGE_FRENCH, "fr", "FR", 0 }, - { LANGUAGE_GERMAN, "de", "DE", 0 }, - { LANGUAGE_ITALIAN, "it", "IT", 0 }, - { LANGUAGE_DUTCH, "nl", "NL", 0 }, - { LANGUAGE_SPANISH_MODERN, "es", "ES", 0 }, - { LANGUAGE_SPANISH_DATED, "es", "ES", 0 }, - { LANGUAGE_PORTUGUESE, "pt", "PT", 0 }, - { LANGUAGE_PORTUGUESE_BRAZILIAN, "pt", "BR", 0 }, - { LANGUAGE_DANISH, "da", "DK", 0 }, - { LANGUAGE_GREEK, "el", "GR", 0 }, - { LANGUAGE_CHINESE_SIMPLIFIED, "zh", "CN", 0 }, - { LANGUAGE_CHINESE_SIMPLIFIED_LEGACY, "zh", "CN", 0 }, - { LANGUAGE_CHINESE_TRADITIONAL, "zh", "TW", 0 }, - { LANGUAGE_CHINESE_HONGKONG, "zh", "HK", 0 }, - { LANGUAGE_CHINESE_SINGAPORE, "zh", "SG", 0 }, - { LANGUAGE_CHINESE_MACAU, "zh", "MO", 0 }, - { LANGUAGE_CHINESE_LSO, "zh", "" , 0 }, - { LANGUAGE_YUE_CHINESE_HONGKONG, "yue", "HK", 0 }, - { LANGUAGE_ENGLISH_HONG_KONG_SAR, "en", "HK", 0 }, - { LANGUAGE_JAPANESE, "ja", "JP", 0 }, - { LANGUAGE_KOREAN, "ko", "KR", 0 }, - { LANGUAGE_KOREAN_JOHAB, "ko", "KR", 0 }, - { LANGUAGE_USER_KOREAN_NORTH, "ko", "KP", 0 }, - { LANGUAGE_SWEDISH, "sv", "SE", 0 }, - { LANGUAGE_SWEDISH_FINLAND, "sv", "FI", 0 }, - { LANGUAGE_FINNISH, "fi", "FI", 0 }, - { LANGUAGE_RUSSIAN, "ru", "RU", 0 }, - { LANGUAGE_TATAR, "tt", "RU", 0 }, - { LANGUAGE_ENGLISH_NZ, "en", "NZ", 0 }, - { LANGUAGE_ENGLISH_EIRE, "en", "IE", 0 }, - { LANGUAGE_DUTCH_BELGIAN, "nl", "BE", 0 }, - { LANGUAGE_FRENCH_BELGIAN, "fr", "BE", 0 }, - { LANGUAGE_FRENCH_CANADIAN, "fr", "CA", 0 }, - { LANGUAGE_FRENCH_SWISS, "fr", "CH", 0 }, - { LANGUAGE_GERMAN_SWISS, "de", "CH", 0 }, - { LANGUAGE_GERMAN_AUSTRIAN, "de", "AT", 0 }, - { LANGUAGE_ITALIAN_SWISS, "it", "CH", 0 }, - { LANGUAGE_ALBANIAN, "sq", "AL", 0 }, - { LANGUAGE_ARABIC_SAUDI_ARABIA, "ar", "SA", 0 }, - { LANGUAGE_ARABIC_EGYPT, "ar", "EG", 0 }, - { LANGUAGE_ARABIC_UAE, "ar", "AE", 0 }, - { LANGUAGE_ARABIC_IRAQ, "ar", "IQ", 0 }, - { LANGUAGE_ARABIC_LIBYA, "ar", "LY", 0 }, - { LANGUAGE_ARABIC_ALGERIA, "ar", "DZ", 0 }, - { LANGUAGE_ARABIC_MOROCCO, "ar", "MA", 0 }, - { LANGUAGE_ARABIC_TUNISIA, "ar", "TN", 0 }, - { LANGUAGE_ARABIC_OMAN, "ar", "OM", 0 }, - { LANGUAGE_ARABIC_YEMEN, "ar", "YE", 0 }, - { LANGUAGE_ARABIC_SYRIA, "ar", "SY", 0 }, - { LANGUAGE_ARABIC_JORDAN, "ar", "JO", 0 }, - { LANGUAGE_ARABIC_LEBANON, "ar", "LB", 0 }, - { LANGUAGE_ARABIC_KUWAIT, "ar", "KW", 0 }, - { LANGUAGE_ARABIC_BAHRAIN, "ar", "BH", 0 }, - { LANGUAGE_ARABIC_QATAR, "ar", "QA", 0 }, - { LANGUAGE_USER_ARABIC_CHAD, "ar", "TD", 0 }, - { LANGUAGE_USER_ARABIC_COMOROS, "ar", "KM", 0 }, - { LANGUAGE_USER_ARABIC_DJIBOUTI, "ar", "DJ", 0 }, - { LANGUAGE_USER_ARABIC_ERITREA, "ar", "ER", 0 }, - { LANGUAGE_USER_ARABIC_ISRAEL, "ar", "IL", 0 }, - { LANGUAGE_USER_ARABIC_MAURITANIA, "ar", "MR", 0 }, - { LANGUAGE_USER_ARABIC_PALESTINE, "ar", "PS", 0 }, - { LANGUAGE_USER_ARABIC_SOMALIA, "ar", "SO", 0 }, - { LANGUAGE_USER_ARABIC_SUDAN, "ar", "SD", 0 }, - { LANGUAGE_ARABIC_PRIMARY_ONLY, "ar", "" , 0 }, - { LANGUAGE_BASQUE, "eu", "ES", 0 }, + { LANGUAGE_ENGLISH, "en", "" , k0 }, + { LANGUAGE_ENGLISH_US, "en", "US", k0 }, + { LANGUAGE_ENGLISH_UK, "en", "GB", k0 }, + { LANGUAGE_ENGLISH_AUS, "en", "AU", k0 }, + { LANGUAGE_ENGLISH_CAN, "en", "CA", k0 }, + { LANGUAGE_FRENCH, "fr", "FR", k0 }, + { LANGUAGE_GERMAN, "de", "DE", k0 }, + { LANGUAGE_ITALIAN, "it", "IT", k0 }, + { LANGUAGE_DUTCH, "nl", "NL", k0 }, + { LANGUAGE_SPANISH_MODERN, "es", "ES", k0 }, + { LANGUAGE_SPANISH_DATED, "es", "ES", k0 }, + { LANGUAGE_PORTUGUESE, "pt", "PT", k0 }, + { LANGUAGE_PORTUGUESE_BRAZILIAN, "pt", "BR", k0 }, + { LANGUAGE_DANISH, "da", "DK", k0 }, + { LANGUAGE_GREEK, "el", "GR", k0 }, + { LANGUAGE_CHINESE_SIMPLIFIED, "zh", "CN", k0 }, + { LANGUAGE_CHINESE_SIMPLIFIED_LEGACY, "zh", "CN", k0 }, + { LANGUAGE_CHINESE_TRADITIONAL, "zh", "TW", k0 }, + { LANGUAGE_CHINESE_HONGKONG, "zh", "HK", k0 }, + { LANGUAGE_CHINESE_SINGAPORE, "zh", "SG", k0 }, + { LANGUAGE_CHINESE_MACAU, "zh", "MO", k0 }, + { LANGUAGE_CHINESE_LSO, "zh", "" , k0 }, + { LANGUAGE_YUE_CHINESE_HONGKONG, "yue", "HK", k0 }, + { LANGUAGE_ENGLISH_HONG_KONG_SAR, "en", "HK", k0 }, + { LANGUAGE_JAPANESE, "ja", "JP", k0 }, + { LANGUAGE_KOREAN, "ko", "KR", k0 }, + { LANGUAGE_KOREAN_JOHAB, "ko", "KR", k0 }, + { LANGUAGE_USER_KOREAN_NORTH, "ko", "KP", k0 }, + { LANGUAGE_SWEDISH, "sv", "SE", k0 }, + { LANGUAGE_SWEDISH_FINLAND, "sv", "FI", k0 }, + { LANGUAGE_FINNISH, "fi", "FI", k0 }, + { LANGUAGE_RUSSIAN, "ru", "RU", k0 }, + { LANGUAGE_TATAR, "tt", "RU", k0 }, + { LANGUAGE_ENGLISH_NZ, "en", "NZ", k0 }, + { LANGUAGE_ENGLISH_EIRE, "en", "IE", k0 }, + { LANGUAGE_DUTCH_BELGIAN, "nl", "BE", k0 }, + { LANGUAGE_FRENCH_BELGIAN, "fr", "BE", k0 }, + { LANGUAGE_FRENCH_CANADIAN, "fr", "CA", k0 }, + { LANGUAGE_FRENCH_SWISS, "fr", "CH", k0 }, + { LANGUAGE_GERMAN_SWISS, "de", "CH", k0 }, + { LANGUAGE_GERMAN_AUSTRIAN, "de", "AT", k0 }, + { LANGUAGE_ITALIAN_SWISS, "it", "CH", k0 }, + { LANGUAGE_ALBANIAN, "sq", "AL", k0 }, + { LANGUAGE_ARABIC_SAUDI_ARABIA, "ar", "SA", k0 }, + { LANGUAGE_ARABIC_EGYPT, "ar", "EG", k0 }, + { LANGUAGE_ARABIC_UAE, "ar", "AE", k0 }, + { LANGUAGE_ARABIC_IRAQ, "ar", "IQ", k0 }, + { LANGUAGE_ARABIC_LIBYA, "ar", "LY", k0 }, + { LANGUAGE_ARABIC_ALGERIA, "ar", "DZ", k0 }, + { LANGUAGE_ARABIC_MOROCCO, "ar", "MA", k0 }, + { LANGUAGE_ARABIC_TUNISIA, "ar", "TN", k0 }, + { LANGUAGE_ARABIC_OMAN, "ar", "OM", k0 }, + { LANGUAGE_ARABIC_YEMEN, "ar", "YE", k0 }, + { LANGUAGE_ARABIC_SYRIA, "ar", "SY", k0 }, + { LANGUAGE_ARABIC_JORDAN, "ar", "JO", k0 }, + { LANGUAGE_ARABIC_LEBANON, "ar", "LB", k0 }, + { LANGUAGE_ARABIC_KUWAIT, "ar", "KW", k0 }, + { LANGUAGE_ARABIC_BAHRAIN, "ar", "BH", k0 }, + { LANGUAGE_ARABIC_QATAR, "ar", "QA", k0 }, + { LANGUAGE_USER_ARABIC_CHAD, "ar", "TD", k0 }, + { LANGUAGE_USER_ARABIC_COMOROS, "ar", "KM", k0 }, + { LANGUAGE_USER_ARABIC_DJIBOUTI, "ar", "DJ", k0 }, + { LANGUAGE_USER_ARABIC_ERITREA, "ar", "ER", k0 }, + { LANGUAGE_USER_ARABIC_ISRAEL, "ar", "IL", k0 }, + { LANGUAGE_USER_ARABIC_MAURITANIA, "ar", "MR", k0 }, + { LANGUAGE_USER_ARABIC_PALESTINE, "ar", "PS", k0 }, + { LANGUAGE_USER_ARABIC_SOMALIA, "ar", "SO", k0 }, + { LANGUAGE_USER_ARABIC_SUDAN, "ar", "SD", k0 }, + { LANGUAGE_ARABIC_PRIMARY_ONLY, "ar", "" , k0 }, + { LANGUAGE_BASQUE, "eu", "ES", k0 }, { LANGUAGE_BASQUE, "eu", "" , kSAME }, // our earlier definition - { LANGUAGE_BULGARIAN, "bg", "BG", 0 }, - { LANGUAGE_CZECH, "cs", "CZ", 0 }, + { LANGUAGE_BULGARIAN, "bg", "BG", k0 }, + { LANGUAGE_CZECH, "cs", "CZ", k0 }, { LANGUAGE_CZECH, "cz", "" , kSAME }, - { LANGUAGE_ENGLISH_JAMAICA, "en", "JM", 0 }, - { LANGUAGE_ENGLISH_CARRIBEAN, "en", "BS", 0 }, // not 100%, because AG is Bahamas - { LANGUAGE_ENGLISH_BELIZE, "en", "BZ", 0 }, - { LANGUAGE_ENGLISH_TRINIDAD, "en", "TT", 0 }, - { LANGUAGE_ENGLISH_ZIMBABWE, "en", "ZW", 0 }, - { LANGUAGE_ENGLISH_INDONESIA, "en", "ID", 0 }, - { LANGUAGE_ESTONIAN, "et", "EE", 0 }, - { LANGUAGE_FAEROESE, "fo", "FO", 0 }, - { LANGUAGE_FARSI, "fa", "IR", 0 }, - { LANGUAGE_FRENCH_LUXEMBOURG, "fr", "LU", 0 }, - { LANGUAGE_FRENCH_MONACO, "fr", "MC", 0 }, - { LANGUAGE_GERMAN_LUXEMBOURG, "de", "LU", 0 }, - { LANGUAGE_GERMAN_LIECHTENSTEIN, "de", "LI", 0 }, - { LANGUAGE_HEBREW, "he", "IL", 0 }, // new: old was "iw" + { LANGUAGE_ENGLISH_JAMAICA, "en", "JM", k0 }, + { LANGUAGE_ENGLISH_CARRIBEAN, "en", "BS", k0 }, // not 100%, because AG is Bahamas + { LANGUAGE_ENGLISH_BELIZE, "en", "BZ", k0 }, + { LANGUAGE_ENGLISH_TRINIDAD, "en", "TT", k0 }, + { LANGUAGE_ENGLISH_ZIMBABWE, "en", "ZW", k0 }, + { LANGUAGE_ENGLISH_INDONESIA, "en", "ID", k0 }, + { LANGUAGE_ESTONIAN, "et", "EE", k0 }, + { LANGUAGE_FAEROESE, "fo", "FO", k0 }, + { LANGUAGE_FARSI, "fa", "IR", k0 }, + { LANGUAGE_FRENCH_LUXEMBOURG, "fr", "LU", k0 }, + { LANGUAGE_FRENCH_MONACO, "fr", "MC", k0 }, + { LANGUAGE_GERMAN_LUXEMBOURG, "de", "LU", k0 }, + { LANGUAGE_GERMAN_LIECHTENSTEIN, "de", "LI", k0 }, + { LANGUAGE_HEBREW, "he", "IL", k0 }, // new: old was "iw" { LANGUAGE_HEBREW, "iw", "IL", kSAME }, // old: new is "he" - { LANGUAGE_HUNGARIAN, "hu", "HU", 0 }, - { LANGUAGE_ICELANDIC, "is", "IS", 0 }, - { LANGUAGE_INDONESIAN, "id", "ID", 0 }, // new: old was "in" + { LANGUAGE_HUNGARIAN, "hu", "HU", k0 }, + { LANGUAGE_ICELANDIC, "is", "IS", k0 }, + { LANGUAGE_INDONESIAN, "id", "ID", k0 }, // new: old was "in" { LANGUAGE_INDONESIAN, "in", "ID", kSAME }, // old: new is "id" - { LANGUAGE_NORWEGIAN, "no", "NO", 0 }, - { LANGUAGE_NORWEGIAN_BOKMAL, "nb", "NO", 0 }, - { LANGUAGE_NORWEGIAN_BOKMAL_LSO, "nb", "" , 0 }, - { LANGUAGE_NORWEGIAN_NYNORSK, "nn", "NO", 0 }, - { LANGUAGE_NORWEGIAN_NYNORSK_LSO, "nn", "" , 0 }, - { LANGUAGE_POLISH, "pl", "PL", 0 }, - { LANGUAGE_RHAETO_ROMAN, "rm", "CH", 0 }, - { LANGUAGE_ROMANIAN, "ro", "RO", 0 }, - { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD", 0 }, - { LANGUAGE_SLOVAK, "sk", "SK", 0 }, - { LANGUAGE_SLOVENIAN, "sl", "SI", 0 }, - { LANGUAGE_SPANISH_MEXICAN, "es", "MX", 0 }, - { LANGUAGE_SPANISH_GUATEMALA, "es", "GT", 0 }, - { LANGUAGE_SPANISH_COSTARICA, "es", "CR", 0 }, - { LANGUAGE_SPANISH_PANAMA, "es", "PA", 0 }, - { LANGUAGE_SPANISH_DOMINICAN_REPUBLIC, "es", "DO", 0 }, - { LANGUAGE_SPANISH_VENEZUELA, "es", "VE", 0 }, - { LANGUAGE_SPANISH_COLOMBIA, "es", "CO", 0 }, - { LANGUAGE_SPANISH_PERU, "es", "PE", 0 }, - { LANGUAGE_SPANISH_ARGENTINA, "es", "AR", 0 }, - { LANGUAGE_SPANISH_ECUADOR, "es", "EC", 0 }, - { LANGUAGE_SPANISH_CHILE, "es", "CL", 0 }, - { LANGUAGE_SPANISH_URUGUAY, "es", "UY", 0 }, - { LANGUAGE_SPANISH_PARAGUAY, "es", "PY", 0 }, - { LANGUAGE_SPANISH_BOLIVIA, "es", "BO", 0 }, - { LANGUAGE_SPANISH_EL_SALVADOR, "es", "SV", 0 }, - { LANGUAGE_SPANISH_HONDURAS, "es", "HN", 0 }, - { LANGUAGE_SPANISH_NICARAGUA, "es", "NI", 0 }, - { LANGUAGE_SPANISH_PUERTO_RICO, "es", "PR", 0 }, - { LANGUAGE_SPANISH_UNITED_STATES, "es", "US", 0 }, - { LANGUAGE_SPANISH_LATIN_AMERICA, "es", "" , 0 }, - { LANGUAGE_TURKISH, "tr", "TR", 0 }, - { LANGUAGE_UKRAINIAN, "uk", "UA", 0 }, - { LANGUAGE_VIETNAMESE, "vi", "VN", 0 }, - { LANGUAGE_LATVIAN, "lv", "LV", 0 }, - { LANGUAGE_MACEDONIAN, "mk", "MK", 0 }, - { LANGUAGE_MALAY_MALAYSIA, "ms", "MY", 0 }, - { LANGUAGE_MALAY_BRUNEI_DARUSSALAM, "ms", "BN", 0 }, - { LANGUAGE_ENGLISH_MALAYSIA, "en", "MY", 0 }, - { LANGUAGE_THAI, "th", "TH", 0 }, - { LANGUAGE_LITHUANIAN, "lt", "LT", 0 }, - { LANGUAGE_LITHUANIAN_CLASSIC, "lt", "LT", 0 }, - { LANGUAGE_CROATIAN, "hr", "HR", 0 }, // Croatian in Croatia - { LANGUAGE_CROATIAN_BOSNIA_HERZEGOVINA, "hr", "BA", 0 }, - { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA, "bs", "BA", 0 }, - { LANGUAGE_BOSNIAN_LSO, "bs", "" , 0 }, // so what is 'bs' vs 'bs-Latn'? - { LANGUAGE_SERBIAN_CYRILLIC_SERBIA, "sr", "RS", 0 }, // Serbian Cyrillic in Serbia - { LANGUAGE_OBSOLETE_USER_SERBIAN_CYRILLIC_SERBIA, "sr", "RS", 0 }, - { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr", "CS", 0 }, // Serbian Cyrillic in Serbia and Montenegro + { LANGUAGE_NORWEGIAN, "no", "NO", k0 }, + { LANGUAGE_NORWEGIAN_BOKMAL, "nb", "NO", k0 }, + { LANGUAGE_NORWEGIAN_BOKMAL_LSO, "nb", "" , k0 }, + { LANGUAGE_NORWEGIAN_NYNORSK, "nn", "NO", k0 }, + { LANGUAGE_NORWEGIAN_NYNORSK_LSO, "nn", "" , k0 }, + { LANGUAGE_POLISH, "pl", "PL", k0 }, + { LANGUAGE_RHAETO_ROMAN, "rm", "CH", k0 }, + { LANGUAGE_ROMANIAN, "ro", "RO", k0 }, + { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD", k0 }, + { LANGUAGE_SLOVAK, "sk", "SK", k0 }, + { LANGUAGE_SLOVENIAN, "sl", "SI", k0 }, + { LANGUAGE_SPANISH_MEXICAN, "es", "MX", k0 }, + { LANGUAGE_SPANISH_GUATEMALA, "es", "GT", k0 }, + { LANGUAGE_SPANISH_COSTARICA, "es", "CR", k0 }, + { LANGUAGE_SPANISH_PANAMA, "es", "PA", k0 }, + { LANGUAGE_SPANISH_DOMINICAN_REPUBLIC, "es", "DO", k0 }, + { LANGUAGE_SPANISH_VENEZUELA, "es", "VE", k0 }, + { LANGUAGE_SPANISH_COLOMBIA, "es", "CO", k0 }, + { LANGUAGE_SPANISH_PERU, "es", "PE", k0 }, + { LANGUAGE_SPANISH_ARGENTINA, "es", "AR", k0 }, + { LANGUAGE_SPANISH_ECUADOR, "es", "EC", k0 }, + { LANGUAGE_SPANISH_CHILE, "es", "CL", k0 }, + { LANGUAGE_SPANISH_URUGUAY, "es", "UY", k0 }, + { LANGUAGE_SPANISH_PARAGUAY, "es", "PY", k0 }, + { LANGUAGE_SPANISH_BOLIVIA, "es", "BO", k0 }, + { LANGUAGE_SPANISH_EL_SALVADOR, "es", "SV", k0 }, + { LANGUAGE_SPANISH_HONDURAS, "es", "HN", k0 }, + { LANGUAGE_SPANISH_NICARAGUA, "es", "NI", k0 }, + { LANGUAGE_SPANISH_PUERTO_RICO, "es", "PR", k0 }, + { LANGUAGE_SPANISH_UNITED_STATES, "es", "US", k0 }, + { LANGUAGE_SPANISH_LATIN_AMERICA, "es", "" , k0 }, + { LANGUAGE_TURKISH, "tr", "TR", k0 }, + { LANGUAGE_UKRAINIAN, "uk", "UA", k0 }, + { LANGUAGE_VIETNAMESE, "vi", "VN", k0 }, + { LANGUAGE_LATVIAN, "lv", "LV", k0 }, + { LANGUAGE_MACEDONIAN, "mk", "MK", k0 }, + { LANGUAGE_MALAY_MALAYSIA, "ms", "MY", k0 }, + { LANGUAGE_MALAY_BRUNEI_DARUSSALAM, "ms", "BN", k0 }, + { LANGUAGE_ENGLISH_MALAYSIA, "en", "MY", k0 }, + { LANGUAGE_THAI, "th", "TH", k0 }, + { LANGUAGE_LITHUANIAN, "lt", "LT", k0 }, + { LANGUAGE_LITHUANIAN_CLASSIC, "lt", "LT", k0 }, + { LANGUAGE_CROATIAN, "hr", "HR", k0 }, // Croatian in Croatia + { LANGUAGE_CROATIAN_BOSNIA_HERZEGOVINA, "hr", "BA", k0 }, + { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA, "bs", "BA", k0 }, + { LANGUAGE_BOSNIAN_LSO, "bs", "" , k0 }, // so what is 'bs' vs 'bs-Latn'? + { LANGUAGE_SERBIAN_CYRILLIC_SERBIA, "sr", "RS", k0 }, // Serbian Cyrillic in Serbia + { LANGUAGE_OBSOLETE_USER_SERBIAN_CYRILLIC_SERBIA, "sr", "RS", k0 }, + { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr", "CS", k0 }, // Serbian Cyrillic in Serbia and Montenegro { 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) - { LANGUAGE_SERBIAN_CYRILLIC_MONTENEGRO, "sr", "ME", 0 }, - { LANGUAGE_OBSOLETE_USER_SERBIAN_CYRILLIC_MONTENEGRO, "sr", "ME", 0 }, - { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr", "BA", 0 }, - { LANGUAGE_SERBIAN_CYRILLIC_LSO, "sr", "" , 0 }, + { LANGUAGE_SERBIAN_CYRILLIC_MONTENEGRO, "sr", "ME", k0 }, + { LANGUAGE_OBSOLETE_USER_SERBIAN_CYRILLIC_MONTENEGRO, "sr", "ME", k0 }, + { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr", "BA", k0 }, + { LANGUAGE_SERBIAN_CYRILLIC_LSO, "sr", "" , k0 }, { LANGUAGE_SERBIAN_LATIN_SERBIA, "sh", "RS", kSAME }, // legacy kludge, is sr-Latn-RS now { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_SERBIA, "sh", "RS", kSAME }, // legacy kludge, is sr-Latn-RS now { LANGUAGE_SERBIAN_LATIN_SAM, "sh", "CS", kSAME }, // legacy kludge, is sr-Latn-CS now @@ -324,449 +325,449 @@ static IsoLanguageCountryEntry const aImplIsoLangEntries[] = { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_MONTENEGRO, "sh", "ME", kSAME }, // legacy kludge, is sr-Latn-ME now { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA, "sh", "BA", kSAME }, // legacy kludge, is sr-Latn-BA now { LANGUAGE_SERBIAN_LATIN_LSO, "sh", "" , kSAME }, // legacy kludge, is sr-Latn now - { LANGUAGE_ARMENIAN, "hy", "AM", 0 }, - { LANGUAGE_AZERI_LATIN, "az", "AZ", 0 }, // macrolanguage code - { LANGUAGE_UZBEK_LATIN, "uz", "UZ", 0 }, // macrolanguage code - { LANGUAGE_UZBEK_LATIN_LSO, "uz", "" , 0 }, // macrolanguage code - { LANGUAGE_BENGALI_BANGLADESH, "bn", "BD", 0 }, - { LANGUAGE_BENGALI, "bn", "IN", 0 }, - { LANGUAGE_BURMESE, "my", "MM", 0 }, - { LANGUAGE_KAZAKH, "kk", "KZ", 0 }, - { LANGUAGE_ENGLISH_INDIA, "en", "IN", 0 }, - { LANGUAGE_URDU_INDIA, "ur", "IN", 0 }, - { LANGUAGE_URDU_PAKISTAN, "ur", "PK", 0 }, - { LANGUAGE_HINDI, "hi", "IN", 0 }, - { LANGUAGE_GUJARATI, "gu", "IN", 0 }, - { LANGUAGE_KANNADA, "kn", "IN", 0 }, - { LANGUAGE_ASSAMESE, "as", "IN", 0 }, - { LANGUAGE_KASHMIRI_INDIA, "ks", "IN", 0 }, + { LANGUAGE_ARMENIAN, "hy", "AM", k0 }, + { LANGUAGE_AZERI_LATIN, "az", "AZ", k0 }, // macrolanguage code + { LANGUAGE_UZBEK_LATIN, "uz", "UZ", k0 }, // macrolanguage code + { LANGUAGE_UZBEK_LATIN_LSO, "uz", "" , k0 }, // macrolanguage code + { LANGUAGE_BENGALI_BANGLADESH, "bn", "BD", k0 }, + { LANGUAGE_BENGALI, "bn", "IN", k0 }, + { LANGUAGE_BURMESE, "my", "MM", k0 }, + { LANGUAGE_KAZAKH, "kk", "KZ", k0 }, + { LANGUAGE_ENGLISH_INDIA, "en", "IN", k0 }, + { LANGUAGE_URDU_INDIA, "ur", "IN", k0 }, + { LANGUAGE_URDU_PAKISTAN, "ur", "PK", k0 }, + { LANGUAGE_HINDI, "hi", "IN", k0 }, + { LANGUAGE_GUJARATI, "gu", "IN", k0 }, + { LANGUAGE_KANNADA, "kn", "IN", k0 }, + { LANGUAGE_ASSAMESE, "as", "IN", k0 }, + { LANGUAGE_KASHMIRI_INDIA, "ks", "IN", k0 }, { LANGUAGE_KASHMIRI, "ks", "" , kSAME }, // Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that - { LANGUAGE_MALAYALAM, "ml", "IN", 0 }, - { LANGUAGE_MANIPURI, "mni", "IN", 0 }, - { LANGUAGE_MARATHI, "mr", "IN", 0 }, - { LANGUAGE_KONKANI, "kok", "IN", 0 }, - { LANGUAGE_NEPALI, "ne", "NP", 0 }, - { LANGUAGE_NEPALI_INDIA, "ne", "IN", 0 }, - { LANGUAGE_ODIA, "or", "IN", 0 }, - { LANGUAGE_PUNJABI, "pa", "IN", 0 }, - { LANGUAGE_SANSKRIT, "sa", "IN", 0 }, - { LANGUAGE_TAMIL, "ta", "IN", 0 }, - { LANGUAGE_TAMIL_SRI_LANKA, "ta", "LK", 0 }, - { LANGUAGE_TELUGU, "te", "IN", 0 }, - { LANGUAGE_PUNJABI_PAKISTAN, "pnb", "PK", 0 }, - { LANGUAGE_PUNJABI_ARABIC_LSO, "pnb", "" , 0 }, + { LANGUAGE_MALAYALAM, "ml", "IN", k0 }, + { LANGUAGE_MANIPURI, "mni", "IN", k0 }, + { LANGUAGE_MARATHI, "mr", "IN", k0 }, + { LANGUAGE_KONKANI, "kok", "IN", k0 }, + { LANGUAGE_NEPALI, "ne", "NP", k0 }, + { LANGUAGE_NEPALI_INDIA, "ne", "IN", k0 }, + { LANGUAGE_ODIA, "or", "IN", k0 }, + { LANGUAGE_PUNJABI, "pa", "IN", k0 }, + { LANGUAGE_SANSKRIT, "sa", "IN", k0 }, + { LANGUAGE_TAMIL, "ta", "IN", k0 }, + { LANGUAGE_TAMIL_SRI_LANKA, "ta", "LK", k0 }, + { LANGUAGE_TELUGU, "te", "IN", k0 }, + { LANGUAGE_PUNJABI_PAKISTAN, "pnb", "PK", k0 }, + { LANGUAGE_PUNJABI_ARABIC_LSO, "pnb", "" , k0 }, { LANGUAGE_PUNJABI_PAKISTAN, "lah", "PK", kSAME }, // macrolanguage code, earlier preferred 'lah' over 'pa' for Western Panjabi, now there is 'pnb' { 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 { LANGUAGE_SINDHI_PAKISTAN, "sd", "PK", kSAME }, // Arabic script - { LANGUAGE_SINDHI, "sd", "IN", 0 }, // TODO: there's Deva(nagari) and Arab(ic) script, MS maps this to 'sd-Deva-IN' - { LANGUAGE_BELARUSIAN, "be", "BY", 0 }, - { LANGUAGE_CATALAN, "ca", "ES", 0 }, // Spain (default) - { LANGUAGE_CATALAN, "ca", "AD", 0 }, // Andorra + { LANGUAGE_SINDHI, "sd", "IN", k0 }, // TODO: there's Deva(nagari) and Arab(ic) script, MS maps this to 'sd-Deva-IN' + { LANGUAGE_BELARUSIAN, "be", "BY", k0 }, + { LANGUAGE_CATALAN, "ca", "ES", k0 }, // Spain (default) + { LANGUAGE_CATALAN, "ca", "AD", k0 }, // Andorra //LANGUAGE_CATALAN_VALENCIAN ca-ES-valencia Bcp47CountryEntry takes precedence { LANGUAGE_CATALAN_VALENCIAN, "ca", "XV", kSAME }, // XV: ISO 3166 user-assigned; old workaround for UI localization only, in case it escaped to document content { 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 - { LANGUAGE_FRENCH_CAMEROON, "fr", "CM", 0 }, - { LANGUAGE_FRENCH_COTE_D_IVOIRE, "fr", "CI", 0 }, - { LANGUAGE_FRENCH_MALI, "fr", "ML", 0 }, - { LANGUAGE_FRENCH_SENEGAL, "fr", "SN", 0 }, - { LANGUAGE_FRENCH_ZAIRE, "fr", "CD", 0 }, // Democratic Republic Of Congo - { LANGUAGE_FRENCH_MOROCCO, "fr", "MA", 0 }, - { LANGUAGE_FRENCH_REUNION, "fr", "RE", 0 }, - { LANGUAGE_FRENCH, "fr", "" , 0 }, // needed as a catcher before other "fr" entries! - { LANGUAGE_FRENCH_NORTH_AFRICA, "fr", "" , 0 }, - { LANGUAGE_FRENCH_WEST_INDIES, "fr", "" , 0 }, // no ISO country code; MS "Neither defined nor reserved" - { LANGUAGE_FRISIAN_NETHERLANDS, "fy", "NL", 0 }, - { LANGUAGE_GAELIC_IRELAND, "ga", "IE", 0 }, - { LANGUAGE_GAELIC_SCOTLAND, "gd", "GB", 0 }, - { LANGUAGE_GAELIC_SCOTLAND_LEGACY, "gd", "GB", 0 }, - { LANGUAGE_GALICIAN, "gl", "ES", 0 }, - { LANGUAGE_GEORGIAN, "ka", "GE", 0 }, - { LANGUAGE_KHMER, "km", "KH", 0 }, - { LANGUAGE_KIRGHIZ, "ky", "KG", 0 }, - { LANGUAGE_LAO, "lo", "LA", 0 }, - { LANGUAGE_MALTESE, "mt", "MT", 0 }, - { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA, "mn", "MN", 0 }, // macrolanguage code; should be khk-MN; Cyrillic script - { LANGUAGE_MONGOLIAN_CYRILLIC_LSO, "mn", "" , 0 }, // macrolanguage code; should be khk; Cyrillic script - { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD", 0 }, - { LANGUAGE_ROMANIAN_MOLDOVA, "mo", "MD", 0 }, // 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 - { LANGUAGE_RUSSIAN_MOLDOVA, "ru", "MD", 0 }, // as per [MS-LCID] rev. 7.0 2015-06-30 - { LANGUAGE_SWAHILI, "sw", "KE", 0 }, - { LANGUAGE_USER_SWAHILI_TANZANIA, "sw", "TZ", 0 }, - { LANGUAGE_TAJIK, "tg", "TJ", 0 }, - { LANGUAGE_TAJIK_LSO, "tg", "" , 0 }, - { LANGUAGE_TIBETAN, "bo", "CN", 0 }, // CN politically correct? - { LANGUAGE_USER_TIBETAN_INDIA, "bo", "IN", 0 }, - { LANGUAGE_USER_TIBETAN_BHUTAN, "bo", "BT", 0 }, - { LANGUAGE_DZONGKHA_BHUTAN, "dz", "BT", 0 }, - { LANGUAGE_TIBETAN_BHUTAN, "dz", "BT", 0 }, // MS reserved for bo-BT, but LCID was used as Dzongkha, see #i53497# - { LANGUAGE_USER_DZONGKHA_MAP_LONLY, "dz", "" , 0 }, // because of the MS error, see lang.h - { LANGUAGE_TURKMEN, "tk", "TM", 0 }, - { LANGUAGE_WELSH, "cy", "GB", 0 }, - { LANGUAGE_SESOTHO, "st", "ZA", 0 }, - { LANGUAGE_SEPEDI, "nso", "ZA", 0 }, + { LANGUAGE_FRENCH_CAMEROON, "fr", "CM", k0 }, + { LANGUAGE_FRENCH_COTE_D_IVOIRE, "fr", "CI", k0 }, + { LANGUAGE_FRENCH_MALI, "fr", "ML", k0 }, + { LANGUAGE_FRENCH_SENEGAL, "fr", "SN", k0 }, + { LANGUAGE_FRENCH_ZAIRE, "fr", "CD", k0 }, // Democratic Republic Of Congo + { LANGUAGE_FRENCH_MOROCCO, "fr", "MA", k0 }, + { LANGUAGE_FRENCH_REUNION, "fr", "RE", k0 }, + { LANGUAGE_FRENCH, "fr", "" , k0 }, // needed as a catcher before other "fr" entries! + { LANGUAGE_FRENCH_NORTH_AFRICA, "fr", "" , k0 }, + { LANGUAGE_FRENCH_WEST_INDIES, "fr", "" , k0 }, // no ISO country code; MS "Neither defined nor reserved" + { LANGUAGE_FRISIAN_NETHERLANDS, "fy", "NL", k0 }, + { LANGUAGE_GAELIC_IRELAND, "ga", "IE", k0 }, + { LANGUAGE_GAELIC_SCOTLAND, "gd", "GB", k0 }, + { LANGUAGE_GAELIC_SCOTLAND_LEGACY, "gd", "GB", k0 }, + { LANGUAGE_GALICIAN, "gl", "ES", k0 }, + { LANGUAGE_GEORGIAN, "ka", "GE", k0 }, + { LANGUAGE_KHMER, "km", "KH", k0 }, + { LANGUAGE_KIRGHIZ, "ky", "KG", k0 }, + { LANGUAGE_LAO, "lo", "LA", k0 }, + { LANGUAGE_MALTESE, "mt", "MT", k0 }, + { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA, "mn", "MN", k0 }, // macrolanguage code; should be khk-MN; Cyrillic script + { LANGUAGE_MONGOLIAN_CYRILLIC_LSO, "mn", "" , k0 }, // macrolanguage code; should be khk; Cyrillic script + { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD", k0 }, + { 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 + { LANGUAGE_RUSSIAN_MOLDOVA, "ru", "MD", k0 }, // as per [MS-LCID] rev. 7.0 2015-06-30 + { LANGUAGE_SWAHILI, "sw", "KE", k0 }, + { LANGUAGE_USER_SWAHILI_TANZANIA, "sw", "TZ", k0 }, + { LANGUAGE_TAJIK, "tg", "TJ", k0 }, + { LANGUAGE_TAJIK_LSO, "tg", "" , k0 }, + { LANGUAGE_TIBETAN, "bo", "CN", k0 }, // CN politically correct? + { LANGUAGE_USER_TIBETAN_INDIA, "bo", "IN", k0 }, + { LANGUAGE_USER_TIBETAN_BHUTAN, "bo", "BT", k0 }, + { LANGUAGE_DZONGKHA_BHUTAN, "dz", "BT", k0 }, + { LANGUAGE_TIBETAN_BHUTAN, "dz", "BT", k0 }, // MS reserved for bo-BT, but LCID was used as Dzongkha, see #i53497# + { LANGUAGE_USER_DZONGKHA_MAP_LONLY, "dz", "" , k0 }, // because of the MS error, see lang.h + { LANGUAGE_TURKMEN, "tk", "TM", k0 }, + { LANGUAGE_WELSH, "cy", "GB", k0 }, + { LANGUAGE_SESOTHO, "st", "ZA", k0 }, + { LANGUAGE_SEPEDI, "nso", "ZA", k0 }, { LANGUAGE_SEPEDI, "ns", "ZA", kSAME }, // fake "ns" for compatibility with existing OOo1.1.x localization to be able to read those documents - { LANGUAGE_TSONGA, "ts", "ZA", 0 }, - { LANGUAGE_TSWANA, "tn", "ZA", 0 }, - { LANGUAGE_ENGLISH_SAFRICA, "en", "ZA", 0 }, - { LANGUAGE_AFRIKAANS, "af", "ZA", 0 }, - { LANGUAGE_VENDA, "ve", "ZA", 0 }, // default 639-1 + { LANGUAGE_TSONGA, "ts", "ZA", k0 }, + { LANGUAGE_TSWANA, "tn", "ZA", k0 }, + { LANGUAGE_ENGLISH_SAFRICA, "en", "ZA", k0 }, + { LANGUAGE_AFRIKAANS, "af", "ZA", k0 }, + { LANGUAGE_VENDA, "ve", "ZA", k0 }, // default 639-1 { LANGUAGE_VENDA, "ven", "ZA", kSAME }, // 639-2 may have been used temporarily since 2004-07-23 - { LANGUAGE_XHOSA, "xh", "ZA", 0 }, - { LANGUAGE_ZULU, "zu", "ZA", 0 }, -// { LANGUAGE_QUECHUA_COLOMBIA, "quc", "CO", 0 }, // MS reserved, and looks wrong, quc would be in Guatemala, not Colombia - { LANGUAGE_QUECHUA_ECUADOR, "quz", "EC", 0 }, // MS + { LANGUAGE_XHOSA, "xh", "ZA", k0 }, + { LANGUAGE_ZULU, "zu", "ZA", k0 }, +// { LANGUAGE_QUECHUA_COLOMBIA, "quc", "CO", k0 }, // MS reserved, and looks wrong, quc would be in Guatemala, not Colombia + { LANGUAGE_QUECHUA_ECUADOR, "quz", "EC", k0 }, // MS { LANGUAGE_QUECHUA_ECUADOR, "qu", "EC", kSAME }, // macrolanguage code - { LANGUAGE_QUECHUA_PERU, "quz", "PE", 0 }, // MS + { LANGUAGE_QUECHUA_PERU, "quz", "PE", k0 }, // MS { LANGUAGE_QUECHUA_PERU, "qu", "PE", kSAME }, // macrolanguage code - { LANGUAGE_QUECHUA_BOLIVIA, "qu", "BO", 0 }, // macrolanguage code, TODO instead: quh-BO or qul-BO; MS says quz-BO which is wrong - { LANGUAGE_PASHTO, "ps", "AF", 0 }, - { LANGUAGE_OROMO, "om", "ET", 0 }, - { LANGUAGE_DHIVEHI, "dv", "MV", 0 }, - { LANGUAGE_UIGHUR_CHINA, "ug", "CN", 0 }, - { LANGUAGE_TIGRIGNA_ETHIOPIA, "ti", "ET", 0 }, - { LANGUAGE_TIGRIGNA_ERITREA, "ti", "ER", 0 }, - { LANGUAGE_AMHARIC_ETHIOPIA, "am", "ET", 0 }, - { LANGUAGE_GUARANI_PARAGUAY, "gug", "PY", 0 }, - { LANGUAGE_HAWAIIAN_UNITED_STATES, "haw", "US", 0 }, - { LANGUAGE_EDO, "bin", "NG", 0 }, - { LANGUAGE_FULFULDE_NIGERIA, "fuv", "NG", 0 }, + { LANGUAGE_QUECHUA_BOLIVIA, "qu", "BO", k0 }, // macrolanguage code, TODO instead: quh-BO or qul-BO; MS says quz-BO which is wrong + { LANGUAGE_PASHTO, "ps", "AF", k0 }, + { LANGUAGE_OROMO, "om", "ET", k0 }, + { LANGUAGE_DHIVEHI, "dv", "MV", k0 }, + { LANGUAGE_UIGHUR_CHINA, "ug", "CN", k0 }, + { LANGUAGE_TIGRIGNA_ETHIOPIA, "ti", "ET", k0 }, + { LANGUAGE_TIGRIGNA_ERITREA, "ti", "ER", k0 }, + { LANGUAGE_AMHARIC_ETHIOPIA, "am", "ET", k0 }, + { LANGUAGE_GUARANI_PARAGUAY, "gug", "PY", k0 }, + { LANGUAGE_HAWAIIAN_UNITED_STATES, "haw", "US", k0 }, + { LANGUAGE_EDO, "bin", "NG", k0 }, + { LANGUAGE_FULFULDE_NIGERIA, "fuv", "NG", k0 }, { LANGUAGE_FULFULDE_NIGERIA, "ff", "NG", kSAME }, // macrolanguage code - { LANGUAGE_FULFULDE_SENEGAL, "ff", "SN", 0 }, // macrolanguage code + { LANGUAGE_FULFULDE_SENEGAL, "ff", "SN", k0 }, // macrolanguage code { LANGUAGE_HAUSA_NIGERIA, "ha", "NG", kSAME }, { LANGUAGE_USER_HAUSA_GHANA, "ha", "GH", kSAME }, - { LANGUAGE_IGBO_NIGERIA, "ig", "NG", 0 }, - { LANGUAGE_KANURI_NIGERIA, "kr", "NG", 0 }, - { LANGUAGE_YORUBA, "yo", "NG", 0 }, - { LANGUAGE_SOMALI, "so", "SO", 0 }, - { LANGUAGE_PAPIAMENTU, "pap", "AN", 0 }, - { LANGUAGE_USER_PAPIAMENTU_ARUBA, "pap", "AW", 0 }, - { LANGUAGE_USER_PAPIAMENTU_CURACAO, "pap", "CW", 0 }, - { LANGUAGE_USER_PAPIAMENTU_BONAIRE, "pap", "BQ", 0 }, - { LANGUAGE_ENGLISH_SINGAPORE, "en", "SG", 0 }, - { LANGUAGE_USER_YIDDISH_US, "yi", "US", 0 }, - { LANGUAGE_YIDDISH, "yi", "IL", 0 }, // new: old was "ji" + { LANGUAGE_IGBO_NIGERIA, "ig", "NG", k0 }, + { LANGUAGE_KANURI_NIGERIA, "kr", "NG", k0 }, + { LANGUAGE_YORUBA, "yo", "NG", k0 }, + { LANGUAGE_SOMALI, "so", "SO", k0 }, + { LANGUAGE_PAPIAMENTU, "pap", "AN", k0 }, + { LANGUAGE_USER_PAPIAMENTU_ARUBA, "pap", "AW", k0 }, + { LANGUAGE_USER_PAPIAMENTU_CURACAO, "pap", "CW", k0 }, + { LANGUAGE_USER_PAPIAMENTU_BONAIRE, "pap", "BQ", k0 }, + { LANGUAGE_ENGLISH_SINGAPORE, "en", "SG", k0 }, + { LANGUAGE_USER_YIDDISH_US, "yi", "US", k0 }, + { LANGUAGE_YIDDISH, "yi", "IL", k0 }, // new: old was "ji" { LANGUAGE_YIDDISH, "ji", "IL", kSAME }, // old: new is "yi" - { LANGUAGE_SYRIAC, "syr", "TR", 0 }, // "TR" according to http://www.ethnologue.com/show_language.asp?code=SYC - { LANGUAGE_SINHALESE_SRI_LANKA, "si", "LK", 0 }, + { LANGUAGE_SYRIAC, "syr", "TR", k0 }, // "TR" according to http://www.ethnologue.com/show_language.asp?code=SYC + { LANGUAGE_SINHALESE_SRI_LANKA, "si", "LK", k0 }, { LANGUAGE_CHEROKEE_UNITED_STATES, "chr", "US", kSAME }, { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu", "CA", kSAME }, // macrolanguage code { LANGUAGE_INUKTITUT_LATIN_LSO, "iu", "" , kSAME }, // macrolanguage code - { LANGUAGE_SAMI_NORTHERN_NORWAY, "se", "NO", 0 }, - { LANGUAGE_SAMI_INARI, "smn", "FI", 0 }, - { LANGUAGE_SAMI_INARI_LSO, "smn", "" , 0 }, - { LANGUAGE_SAMI_LULE_NORWAY, "smj", "NO", 0 }, - { LANGUAGE_SAMI_LULE_SWEDEN, "smj", "SE", 0 }, - { LANGUAGE_SAMI_LULE_LSO, "smj", "" , 0 }, - { LANGUAGE_SAMI_NORTHERN_FINLAND, "se", "FI", 0 }, - { LANGUAGE_SAMI_NORTHERN_SWEDEN, "se", "SE", 0 }, - { LANGUAGE_SAMI_SKOLT, "sms", "FI", 0 }, - { LANGUAGE_SAMI_SKOLT_LSO, "sms", "" , 0 }, - { LANGUAGE_SAMI_SOUTHERN_NORWAY, "sma", "NO", 0 }, - { LANGUAGE_SAMI_SOUTHERN_SWEDEN, "sma", "SE", 0 }, - { LANGUAGE_SAMI_SOUTHERN_LSO, "sma", "" , 0 }, - { LANGUAGE_USER_SAMI_KILDIN_RUSSIA, "sjd", "RU", 0 }, - { LANGUAGE_MAPUDUNGUN_CHILE, "arn", "CL", 0 }, - { LANGUAGE_CORSICAN_FRANCE, "co", "FR", 0 }, - { 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. - { LANGUAGE_YAKUT_RUSSIA, "sah", "RU", 0 }, - { LANGUAGE_MOHAWK_CANADA, "moh", "CA", 0 }, - { LANGUAGE_BASHKIR_RUSSIA, "ba", "RU", 0 }, - { LANGUAGE_KICHE_GUATEMALA, "qut", "GT", 0 }, - { LANGUAGE_DARI_AFGHANISTAN, "prs", "AF", 0 }, + { LANGUAGE_SAMI_NORTHERN_NORWAY, "se", "NO", k0 }, + { LANGUAGE_SAMI_INARI, "smn", "FI", k0 }, + { LANGUAGE_SAMI_INARI_LSO, "smn", "" , k0 }, + { LANGUAGE_SAMI_LULE_NORWAY, "smj", "NO", k0 }, + { LANGUAGE_SAMI_LULE_SWEDEN, "smj", "SE", k0 }, + { LANGUAGE_SAMI_LULE_LSO, "smj", "" , k0 }, + { LANGUAGE_SAMI_NORTHERN_FINLAND, "se", "FI", k0 }, + { LANGUAGE_SAMI_NORTHERN_SWEDEN, "se", "SE", k0 }, + { LANGUAGE_SAMI_SKOLT, "sms", "FI", k0 }, + { LANGUAGE_SAMI_SKOLT_LSO, "sms", "" , k0 }, + { LANGUAGE_SAMI_SOUTHERN_NORWAY, "sma", "NO", k0 }, + { LANGUAGE_SAMI_SOUTHERN_SWEDEN, "sma", "SE", k0 }, + { LANGUAGE_SAMI_SOUTHERN_LSO, "sma", "" , k0 }, + { LANGUAGE_USER_SAMI_KILDIN_RUSSIA, "sjd", "RU", k0 }, + { LANGUAGE_MAPUDUNGUN_CHILE, "arn", "CL", k0 }, + { LANGUAGE_CORSICAN_FRANCE, "co", "FR", k0 }, + { 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. + { LANGUAGE_YAKUT_RUSSIA, "sah", "RU", k0 }, + { LANGUAGE_MOHAWK_CANADA, "moh", "CA", k0 }, + { LANGUAGE_BASHKIR_RUSSIA, "ba", "RU", k0 }, + { LANGUAGE_KICHE_GUATEMALA, "qut", "GT", k0 }, + { LANGUAGE_DARI_AFGHANISTAN, "prs", "AF", k0 }, { LANGUAGE_DARI_AFGHANISTAN, "gbz", "AF", kSAME }, // was an error - { LANGUAGE_WOLOF_SENEGAL, "wo", "SN", 0 }, - { LANGUAGE_FILIPINO, "fil", "PH", 0 }, - { LANGUAGE_USER_TAGALOG, "tl", "PH", 0 }, - { LANGUAGE_ENGLISH_PHILIPPINES, "en", "PH", 0 }, - { LANGUAGE_IBIBIO_NIGERIA, "ibb", "NG", 0 }, - { LANGUAGE_YI, "ii", "CN", 0 }, - { LANGUAGE_ENGLISH_ARAB_EMIRATES, "en", "AE", 0 }, // MS reserved - { LANGUAGE_ENGLISH_BAHRAIN, "en", "BH", 0 }, // MS reserved - { LANGUAGE_ENGLISH_EGYPT, "en", "EG", 0 }, // MS reserved - { LANGUAGE_ENGLISH_JORDAN, "en", "JO", 0 }, // MS reserved - { LANGUAGE_ENGLISH_KUWAIT, "en", "KW", 0 }, // MS reserved - { LANGUAGE_ENGLISH_TURKEY, "en", "TR", 0 }, // MS reserved - { LANGUAGE_ENGLISH_YEMEN, "en", "YE", 0 }, // MS reserved - { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "kab", "DZ", 0 }, // In practice Kabyle is the language used for this - { LANGUAGE_OBSOLETE_USER_KABYLE, "kab", "DZ", 0 }, + { LANGUAGE_WOLOF_SENEGAL, "wo", "SN", k0 }, + { LANGUAGE_FILIPINO, "fil", "PH", k0 }, + { LANGUAGE_USER_TAGALOG, "tl", "PH", k0 }, + { LANGUAGE_ENGLISH_PHILIPPINES, "en", "PH", k0 }, + { LANGUAGE_IBIBIO_NIGERIA, "ibb", "NG", k0 }, + { LANGUAGE_YI, "ii", "CN", k0 }, + { LANGUAGE_ENGLISH_ARAB_EMIRATES, "en", "AE", k0 }, // MS reserved + { LANGUAGE_ENGLISH_BAHRAIN, "en", "BH", k0 }, // MS reserved + { LANGUAGE_ENGLISH_EGYPT, "en", "EG", k0 }, // MS reserved + { LANGUAGE_ENGLISH_JORDAN, "en", "JO", k0 }, // MS reserved + { LANGUAGE_ENGLISH_KUWAIT, "en", "KW", k0 }, // MS reserved + { LANGUAGE_ENGLISH_TURKEY, "en", "TR", k0 }, // MS reserved + { LANGUAGE_ENGLISH_YEMEN, "en", "YE", k0 }, // MS reserved + { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "kab", "DZ", k0 }, // In practice Kabyle is the language used for this + { LANGUAGE_OBSOLETE_USER_KABYLE, "kab", "DZ", k0 }, { 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. { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "tmz", "MA", kSAME }, - { LANGUAGE_TAMAZIGHT_MOROCCO, "tmz", "MA", 0 }, // MS reserved + { LANGUAGE_TAMAZIGHT_MOROCCO, "tmz", "MA", k0 }, // MS reserved { 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 - { LANGUAGE_USER_LATIN_VATICAN, "la", "VA", 0 }, - { LANGUAGE_OBSOLETE_USER_LATIN, "la", "VA", 0 }, - { LANGUAGE_LATIN_LSO, "la", "" , 0 }, - { LANGUAGE_USER_ESPERANTO, "eo", "" , 0 }, - { LANGUAGE_USER_INTERLINGUA, "ia", "" , 0 }, - { LANGUAGE_USER_INTERLINGUE, "ie", "" , 0 }, - { LANGUAGE_MAORI_NEW_ZEALAND, "mi", "NZ", 0 }, - { LANGUAGE_OBSOLETE_USER_MAORI, "mi", "NZ", 0 }, - { LANGUAGE_KINYARWANDA_RWANDA, "rw", "RW", 0 }, - { LANGUAGE_OBSOLETE_USER_KINYARWANDA, "rw", "RW", 0 }, - { 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 - { LANGUAGE_OBSOLETE_USER_UPPER_SORBIAN,"hsb", "DE", 0 }, - { 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 - { LANGUAGE_LOWER_SORBIAN_LSO, "dsb", "" , 0 }, - { LANGUAGE_OBSOLETE_USER_LOWER_SORBIAN,"dsb", "DE", 0 }, - { LANGUAGE_OCCITAN_FRANCE, "oc", "FR", 0 }, - { LANGUAGE_OBSOLETE_USER_OCCITAN, "oc", "FR", 0 }, + { LANGUAGE_USER_LATIN_VATICAN, "la", "VA", k0 }, + { LANGUAGE_OBSOLETE_USER_LATIN, "la", "VA", k0 }, + { LANGUAGE_LATIN_LSO, "la", "" , k0 }, + { LANGUAGE_USER_ESPERANTO, "eo", "" , k0 }, + { LANGUAGE_USER_INTERLINGUA, "ia", "" , k0 }, + { LANGUAGE_USER_INTERLINGUE, "ie", "" , k0 }, + { LANGUAGE_MAORI_NEW_ZEALAND, "mi", "NZ", k0 }, + { LANGUAGE_OBSOLETE_USER_MAORI, "mi", "NZ", k0 }, + { LANGUAGE_KINYARWANDA_RWANDA, "rw", "RW", k0 }, + { LANGUAGE_OBSOLETE_USER_KINYARWANDA, "rw", "RW", k0 }, + { 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 + { LANGUAGE_OBSOLETE_USER_UPPER_SORBIAN,"hsb", "DE", k0 }, + { 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 + { LANGUAGE_LOWER_SORBIAN_LSO, "dsb", "" , k0 }, + { LANGUAGE_OBSOLETE_USER_LOWER_SORBIAN,"dsb", "DE", k0 }, + { LANGUAGE_OCCITAN_FRANCE, "oc", "FR", k0 }, + { LANGUAGE_OBSOLETE_USER_OCCITAN, "oc", "FR", k0 }, { LANGUAGE_USER_KURDISH_TURKEY, "kmr", "TR", kSAME }, { LANGUAGE_USER_KURDISH_TURKEY, "ku", "TR", kSAME }, { LANGUAGE_USER_KURDISH_SYRIA, "kmr", "SY", kSAME }, { LANGUAGE_USER_KURDISH_SYRIA, "ku", "SY", kSAME }, - { LANGUAGE_KURDISH_ARABIC_IRAQ, "ckb", "IQ", 0 }, + { LANGUAGE_KURDISH_ARABIC_IRAQ, "ckb", "IQ", k0 }, { LANGUAGE_KURDISH_ARABIC_IRAQ, "ku", "IQ", kSAME }, { LANGUAGE_OBSOLETE_USER_KURDISH_IRAQ, "ku", "IQ", LANGUAGE_KURDISH_ARABIC_IRAQ }, - { LANGUAGE_USER_KURDISH_SOUTHERN_IRAN, "sdh", "IR", 0 }, - { LANGUAGE_USER_KURDISH_SOUTHERN_IRAQ, "sdh", "IQ", 0 }, - { LANGUAGE_USER_KURDISH_IRAN, "ckb", "IR", 0 }, + { LANGUAGE_USER_KURDISH_SOUTHERN_IRAN, "sdh", "IR", k0 }, + { LANGUAGE_USER_KURDISH_SOUTHERN_IRAQ, "sdh", "IQ", k0 }, + { LANGUAGE_USER_KURDISH_IRAN, "ckb", "IR", k0 }, { LANGUAGE_USER_KURDISH_IRAN, "ku", "IR", kSAME }, - { LANGUAGE_KURDISH_ARABIC_LSO, "ckb", "" , 0 }, - { LANGUAGE_USER_SARDINIAN, "sc", "IT", 0 }, // macrolanguage code - { LANGUAGE_USER_SARDINIAN_CAMPIDANESE, "sro", "IT", 0 }, - { LANGUAGE_USER_SARDINIAN_GALLURESE, "sdn", "IT", 0 }, - { LANGUAGE_USER_SARDINIAN_LOGUDORESE, "src", "IT", 0 }, - { LANGUAGE_USER_SARDINIAN_SASSARESE, "sdc", "IT", 0 }, - { LANGUAGE_BRETON_FRANCE, "br", "FR", 0 }, - { LANGUAGE_OBSOLETE_USER_BRETON, "br", "FR", 0 }, - { LANGUAGE_KALAALLISUT_GREENLAND, "kl", "GL", 0 }, - { LANGUAGE_OBSOLETE_USER_KALAALLISUT, "kl", "GL", 0 }, - { LANGUAGE_USER_SWAZI, "ss", "ZA", 0 }, - { LANGUAGE_USER_NDEBELE_SOUTH, "nr", "ZA", 0 }, - { LANGUAGE_TSWANA_BOTSWANA, "tn", "BW", 0 }, - { LANGUAGE_OBSOLETE_USER_TSWANA_BOTSWANA, "tn", "BW", 0 }, - { LANGUAGE_USER_ENGLISH_BOTSWANA, "en", "BW", 0 }, - { LANGUAGE_USER_MOORE, "mos", "BF", 0 }, - { LANGUAGE_USER_BAMBARA, "bm", "ML", 0 }, - { LANGUAGE_USER_AKAN, "ak", "GH", 0 }, - { LANGUAGE_LUXEMBOURGISH_LUXEMBOURG, "lb", "LU", 0 }, - { LANGUAGE_OBSOLETE_USER_LUXEMBOURGISH, "lb", "LU", 0 }, - { LANGUAGE_USER_FRIULIAN, "fur", "IT", 0 }, - { LANGUAGE_USER_FIJIAN, "fj", "FJ", 0 }, - { LANGUAGE_USER_AFRIKAANS_NAMIBIA, "af", "NA", 0 }, - { LANGUAGE_USER_ENGLISH_NAMIBIA, "en", "NA", 0 }, - { LANGUAGE_USER_WALLOON, "wa", "BE", 0 }, - { LANGUAGE_USER_COPTIC, "cop", "EG", 0 }, - { LANGUAGE_USER_GASCON, "gsc", "FR", 0 }, - { LANGUAGE_USER_GERMAN_BELGIUM, "de", "BE", 0 }, - { LANGUAGE_USER_CHUVASH, "cv", "RU", 0 }, - { LANGUAGE_USER_EWE_GHANA, "ee", "GH", 0 }, - { LANGUAGE_USER_ENGLISH_GHANA, "en", "GH", 0 }, - { LANGUAGE_USER_SANGO, "sg", "CF", 0 }, - { LANGUAGE_USER_GANDA, "lg", "UG", 0 }, - { LANGUAGE_USER_LINGALA_DRCONGO, "ln", "CD", 0 }, - { LANGUAGE_USER_LOW_GERMAN, "nds", "DE", 0 }, - { LANGUAGE_USER_HILIGAYNON, "hil", "PH", 0 }, - { LANGUAGE_USER_ENGLISH_MALAWI, "en", "MW", 0 }, /* en default for MW */ - { LANGUAGE_USER_NYANJA, "ny", "MW", 0 }, - { LANGUAGE_USER_KASHUBIAN, "csb", "PL", 0 }, - { LANGUAGE_SPANISH_CUBA, "es", "CU", 0 }, - { LANGUAGE_OBSOLETE_USER_SPANISH_CUBA, "es", "CU", 0 }, - { LANGUAGE_USER_QUECHUA_NORTH_BOLIVIA, "qul", "BO", 0 }, - { LANGUAGE_USER_QUECHUA_SOUTH_BOLIVIA, "quh", "BO", 0 }, - { LANGUAGE_USER_BODO_INDIA, "brx", "IN", 0 }, - { LANGUAGE_USER_DOGRI_INDIA, "dgo", "IN", 0 }, - { LANGUAGE_USER_MAITHILI_INDIA, "mai", "IN", 0 }, - { LANGUAGE_USER_SANTALI_INDIA, "sat", "IN", 0 }, - { LANGUAGE_USER_TETUN, "tet", "ID", 0 }, - { LANGUAGE_USER_TETUN_TIMOR_LESTE, "tet", "TL", 0 }, - { LANGUAGE_USER_TOK_PISIN, "tpi", "PG", 0 }, - { LANGUAGE_USER_SHUSWAP, "shs", "CA", 0 }, - { LANGUAGE_USER_ANCIENT_GREEK, "grc", "GR", 0 }, - { LANGUAGE_USER_ASTURIAN, "ast", "ES", 0 }, - { LANGUAGE_USER_LATGALIAN, "ltg", "LV", 0 }, - { LANGUAGE_USER_MAORE, "swb", "YT", 0 }, - { LANGUAGE_USER_BUSHI, "buc", "YT", 0 }, - { LANGUAGE_USER_TAHITIAN, "ty", "PF", 0 }, - { LANGUAGE_MALAGASY_PLATEAU, "plt", "MG", 0 }, + { LANGUAGE_KURDISH_ARABIC_LSO, "ckb", "" , k0 }, + { LANGUAGE_USER_SARDINIAN, "sc", "IT", k0 }, // macrolanguage code + { LANGUAGE_USER_SARDINIAN_CAMPIDANESE, "sro", "IT", k0 }, + { LANGUAGE_USER_SARDINIAN_GALLURESE, "sdn", "IT", k0 }, + { LANGUAGE_USER_SARDINIAN_LOGUDORESE, "src", "IT", k0 }, + { LANGUAGE_USER_SARDINIAN_SASSARESE, "sdc", "IT", k0 }, + { LANGUAGE_BRETON_FRANCE, "br", "FR", k0 }, + { LANGUAGE_OBSOLETE_USER_BRETON, "br", "FR", k0 }, + { LANGUAGE_KALAALLISUT_GREENLAND, "kl", "GL", k0 }, + { LANGUAGE_OBSOLETE_USER_KALAALLISUT, "kl", "GL", k0 }, + { LANGUAGE_USER_SWAZI, "ss", "ZA", k0 }, + { LANGUAGE_USER_NDEBELE_SOUTH, "nr", "ZA", k0 }, + { LANGUAGE_TSWANA_BOTSWANA, "tn", "BW", k0 }, + { LANGUAGE_OBSOLETE_USER_TSWANA_BOTSWANA, "tn", "BW", k0 }, + { LANGUAGE_USER_ENGLISH_BOTSWANA, "en", "BW", k0 }, + { LANGUAGE_USER_MOORE, "mos", "BF", k0 }, + { LANGUAGE_USER_BAMBARA, "bm", "ML", k0 }, + { LANGUAGE_USER_AKAN, "ak", "GH", k0 }, + { LANGUAGE_LUXEMBOURGISH_LUXEMBOURG, "lb", "LU", k0 }, + { LANGUAGE_OBSOLETE_USER_LUXEMBOURGISH, "lb", "LU", k0 }, + { LANGUAGE_USER_FRIULIAN, "fur", "IT", k0 }, + { LANGUAGE_USER_FIJIAN, "fj", "FJ", k0 }, + { LANGUAGE_USER_AFRIKAANS_NAMIBIA, "af", "NA", k0 }, + { LANGUAGE_USER_ENGLISH_NAMIBIA, "en", "NA", k0 }, + { LANGUAGE_USER_WALLOON, "wa", "BE", k0 }, + { LANGUAGE_USER_COPTIC, "cop", "EG", k0 }, + { LANGUAGE_USER_GASCON, "gsc", "FR", k0 }, + { LANGUAGE_USER_GERMAN_BELGIUM, "de", "BE", k0 }, + { LANGUAGE_USER_CHUVASH, "cv", "RU", k0 }, + { LANGUAGE_USER_EWE_GHANA, "ee", "GH", k0 }, + { LANGUAGE_USER_ENGLISH_GHANA, "en", "GH", k0 }, + { LANGUAGE_USER_SANGO, "sg", "CF", k0 }, + { LANGUAGE_USER_GANDA, "lg", "UG", k0 }, + { LANGUAGE_USER_LINGALA_DRCONGO, "ln", "CD", k0 }, + { LANGUAGE_USER_LOW_GERMAN, "nds", "DE", k0 }, + { LANGUAGE_USER_HILIGAYNON, "hil", "PH", k0 }, + { LANGUAGE_USER_ENGLISH_MALAWI, "en", "MW", k0 }, /* en default for MW */ + { LANGUAGE_USER_NYANJA, "ny", "MW", k0 }, + { LANGUAGE_USER_KASHUBIAN, "csb", "PL", k0 }, + { LANGUAGE_SPANISH_CUBA, "es", "CU", k0 }, + { LANGUAGE_OBSOLETE_USER_SPANISH_CUBA, "es", "CU", k0 }, + { LANGUAGE_USER_QUECHUA_NORTH_BOLIVIA, "qul", "BO", k0 }, + { LANGUAGE_USER_QUECHUA_SOUTH_BOLIVIA, "quh", "BO", k0 }, + { LANGUAGE_USER_BODO_INDIA, "brx", "IN", k0 }, + { LANGUAGE_USER_DOGRI_INDIA, "dgo", "IN", k0 }, + { LANGUAGE_USER_MAITHILI_INDIA, "mai", "IN", k0 }, + { LANGUAGE_USER_SANTALI_INDIA, "sat", "IN", k0 }, + { LANGUAGE_USER_TETUN, "tet", "ID", k0 }, + { LANGUAGE_USER_TETUN_TIMOR_LESTE, "tet", "TL", k0 }, + { LANGUAGE_USER_TOK_PISIN, "tpi", "PG", k0 }, + { LANGUAGE_USER_SHUSWAP, "shs", "CA", k0 }, + { LANGUAGE_USER_ANCIENT_GREEK, "grc", "GR", k0 }, + { LANGUAGE_USER_ASTURIAN, "ast", "ES", k0 }, + { LANGUAGE_USER_LATGALIAN, "ltg", "LV", k0 }, + { LANGUAGE_USER_MAORE, "swb", "YT", k0 }, + { LANGUAGE_USER_BUSHI, "buc", "YT", k0 }, + { LANGUAGE_USER_TAHITIAN, "ty", "PF", k0 }, + { LANGUAGE_MALAGASY_PLATEAU, "plt", "MG", k0 }, { LANGUAGE_MALAGASY_PLATEAU, "mg", "MG", kSAME }, - { LANGUAGE_OBSOLETE_USER_MALAGASY_PLATEAU, "plt", "MG", 0 }, - { LANGUAGE_USER_BAFIA, "ksf", "CM", 0 }, - { LANGUAGE_USER_GIKUYU, "ki", "KE", 0 }, - { LANGUAGE_USER_RUSYN_UKRAINE, "rue", "UA", 0 }, - { LANGUAGE_USER_RUSYN_SLOVAKIA, "rue", "SK", 0 }, - { LANGUAGE_USER_LIMBU, "lif", "NP", 0 }, - { LANGUAGE_USER_LOJBAN, "jbo", "" , 0 }, - { LANGUAGE_USER_HAITIAN, "ht", "HT", 0 }, - { LANGUAGE_FRENCH_HAITI, "fr", "HT", 0 }, - { LANGUAGE_USER_BEEMBE, "beq", "CG", 0 }, - { LANGUAGE_USER_BEKWEL, "bkw", "CG", 0 }, - { LANGUAGE_USER_KITUBA, "mkw", "CG", 0 }, - { LANGUAGE_USER_LARI, "ldi", "CG", 0 }, - { LANGUAGE_USER_MBOCHI, "mdw", "CG", 0 }, - { LANGUAGE_USER_TEKE_EBOO, "ebo", "CG", 0 }, - { LANGUAGE_USER_TEKE_IBALI, "tek", "CG", 0 }, - { LANGUAGE_USER_TEKE_TYEE, "tyx", "CG", 0 }, - { LANGUAGE_USER_VILI, "vif", "CG", 0 }, - { LANGUAGE_USER_PORTUGUESE_ANGOLA, "pt", "AO", 0 }, - { LANGUAGE_USER_MANX, "gv", "GB", 0 }, - { LANGUAGE_USER_ARAGONESE, "an", "ES", 0 }, - { LANGUAGE_USER_KEYID, "qtz", "" , 0 }, // key id pseudolanguage used for UI testing + { LANGUAGE_OBSOLETE_USER_MALAGASY_PLATEAU, "plt", "MG", k0 }, + { LANGUAGE_USER_BAFIA, "ksf", "CM", k0 }, + { LANGUAGE_USER_GIKUYU, "ki", "KE", k0 }, + { LANGUAGE_USER_RUSYN_UKRAINE, "rue", "UA", k0 }, + { LANGUAGE_USER_RUSYN_SLOVAKIA, "rue", "SK", k0 }, + { LANGUAGE_USER_LIMBU, "lif", "NP", k0 }, + { LANGUAGE_USER_LOJBAN, "jbo", "" , k0 }, + { LANGUAGE_USER_HAITIAN, "ht", "HT", k0 }, + { LANGUAGE_FRENCH_HAITI, "fr", "HT", k0 }, + { LANGUAGE_USER_BEEMBE, "beq", "CG", k0 }, + { LANGUAGE_USER_BEKWEL, "bkw", "CG", k0 }, + { LANGUAGE_USER_KITUBA, "mkw", "CG", k0 }, + { LANGUAGE_USER_LARI, "ldi", "CG", k0 }, + { LANGUAGE_USER_MBOCHI, "mdw", "CG", k0 }, + { LANGUAGE_USER_TEKE_EBOO, "ebo", "CG", k0 }, + { LANGUAGE_USER_TEKE_IBALI, "tek", "CG", k0 }, + { LANGUAGE_USER_TEKE_TYEE, "tyx", "CG", k0 }, + { LANGUAGE_USER_VILI, "vif", "CG", k0 }, + { LANGUAGE_USER_PORTUGUESE_ANGOLA, "pt", "AO", k0 }, + { LANGUAGE_USER_MANX, "gv", "GB", k0 }, + { LANGUAGE_USER_ARAGONESE, "an", "ES", k0 }, + { LANGUAGE_USER_KEYID, "qtz", "" , k0 }, // key id pseudolanguage used for UI testing { LANGUAGE_USER_PALI_LATIN, "pli", "" , kSAME }, // Pali with Latin script, ISO 639-3 (sigh..) back-compat, Latin is not a default script though.. - { LANGUAGE_USER_KYRGYZ_CHINA, "ky", "CN", 0 }, - { LANGUAGE_USER_KOMI_ZYRIAN, "kpv", "RU", 0 }, - { LANGUAGE_USER_KOMI_PERMYAK, "koi", "RU", 0 }, - { LANGUAGE_USER_PITJANTJATJARA, "pjt", "AU", 0 }, - { LANGUAGE_USER_ERZYA, "myv", "RU", 0 }, - { LANGUAGE_USER_MARI_MEADOW, "mhr", "RU", 0 }, - { LANGUAGE_USER_KHANTY, "kca", "RU", 0 }, - { LANGUAGE_USER_LIVONIAN, "liv", "RU", 0 }, - { LANGUAGE_USER_MOKSHA, "mdf", "RU", 0 }, - { LANGUAGE_USER_MARI_HILL, "mrj", "RU", 0 }, - { LANGUAGE_USER_NGANASAN, "nio", "RU", 0 }, - { LANGUAGE_USER_OLONETS, "olo", "RU", 0 }, - { LANGUAGE_USER_VEPS, "vep", "RU", 0 }, - { LANGUAGE_USER_VORO, "vro", "EE", 0 }, - { LANGUAGE_USER_NENETS, "yrk", "RU", 0 }, - { LANGUAGE_USER_AKA, "axk", "CF", 0 }, - { LANGUAGE_USER_AKA_CONGO, "axk", "CG", 0 }, - { LANGUAGE_USER_DIBOLE, "bvx", "CG", 0 }, - { LANGUAGE_USER_DOONDO, "dde", "CG", 0 }, - { LANGUAGE_USER_KAAMBA, "xku", "CG", 0 }, - { LANGUAGE_USER_KOONGO, "kng", "CD", 0 }, - { LANGUAGE_USER_KOONGO_CONGO, "kng", "CG", 0 }, - { LANGUAGE_USER_KUNYI, "njx", "CG", 0 }, - { LANGUAGE_USER_NGUNGWEL, "ngz", "CG", 0 }, - { LANGUAGE_USER_NJYEM, "njy", "CM", 0 }, - { LANGUAGE_USER_NJYEM_CONGO, "njy", "CG", 0 }, - { LANGUAGE_USER_PUNU, "puu", "GA", 0 }, - { LANGUAGE_USER_PUNU_CONGO, "puu", "CG", 0 }, - { LANGUAGE_USER_SUUNDI, "sdj", "CG", 0 }, - { LANGUAGE_USER_TEKE_KUKUYA, "kkw", "CG", 0 }, - { LANGUAGE_USER_TSAANGI, "tsa", "CG", 0 }, - { LANGUAGE_USER_YAKA, "iyx", "CG", 0 }, - { LANGUAGE_USER_YOMBE, "yom", "CD", 0 }, - { LANGUAGE_USER_YOMBE_CONGO, "yom", "CG", 0 }, - { LANGUAGE_USER_SIDAMA, "sid", "ET", 0 }, - { LANGUAGE_USER_NKO, "nqo", "GN", 0 }, - { LANGUAGE_USER_UDMURT, "udm", "RU", 0 }, - { LANGUAGE_USER_CORNISH, "kw", "UK", 0 }, - { LANGUAGE_USER_SAMI_PITE_SWEDEN, "sje", "SE", 0 }, - { LANGUAGE_USER_NGAEBERE, "gym", "PA", 0 }, - { LANGUAGE_USER_KUMYK, "kum", "RU", 0 }, - { LANGUAGE_USER_NOGAI, "nog", "RU", 0 }, - { LANGUAGE_USER_LADIN, "lld", "IT", 0 }, - { LANGUAGE_USER_FRENCH_BURKINA_FASO, "fr", "BF", 0 }, - { LANGUAGE_USER_PUINAVE, "pui", "CO", 0 }, - { LANGUAGE_USER_AVAR, "av", "RU", 0 }, - { LANGUAGE_USER_LENGO, "lgr", "SB", 0 }, - { LANGUAGE_USER_FRENCH_BENIN, "fr", "BJ", 0 }, - { LANGUAGE_USER_FRENCH_NIGER, "fr", "NE", 0 }, - { LANGUAGE_USER_FRENCH_TOGO, "fr", "TG", 0 }, - { LANGUAGE_USER_KVEN_FINNISH, "fkv", "NO", 0 }, - { LANGUAGE_USER_CHURCH_SLAVIC, "cu", "RU", 0 }, - { LANGUAGE_USER_VENETIAN, "vec", "IT", 0 }, - { LANGUAGE_USER_ENGLISH_GAMBIA, "en", "GM", 0 }, - { LANGUAGE_USER_OCCITAN_ARANESE, "oc", "ES", 0 }, - { LANGUAGE_USER_ARPITAN_FRANCE, "frp", "FR", 0 }, - { LANGUAGE_USER_ARPITAN_ITALY, "frp", "IT", 0 }, - { LANGUAGE_USER_ARPITAN_SWITZERLAND, "frp", "CH", 0 }, - { LANGUAGE_USER_APATANI, "apt", "IN", 0 }, - { LANGUAGE_USER_ENGLISH_MAURITIUS, "en", "MU", 0 }, - { LANGUAGE_USER_FRENCH_MAURITIUS, "fr", "MU", 0 }, - { LANGUAGE_USER_SILESIAN, "szl", "PL", 0 }, - { LANGUAGE_USER_MANCHU, "mnc", "CN", 0 }, - { LANGUAGE_USER_XIBE, "sjo", "CN", 0 }, - { LANGUAGE_MULTIPLE, "mul", "" , 0 }, // multiple languages, many languages are used - { LANGUAGE_UNDETERMINED, "und", "" , 0 }, // undetermined language, language cannot be identified - { LANGUAGE_NONE, "zxx", "" , 0 }, // added to ISO 639-2 on 2006-01-11: Used to declare the absence of linguistic information - { LANGUAGE_DONTKNOW, "", "" , 0 } // marks end of table + { LANGUAGE_USER_KYRGYZ_CHINA, "ky", "CN", k0 }, + { LANGUAGE_USER_KOMI_ZYRIAN, "kpv", "RU", k0 }, + { LANGUAGE_USER_KOMI_PERMYAK, "koi", "RU", k0 }, + { LANGUAGE_USER_PITJANTJATJARA, "pjt", "AU", k0 }, + { LANGUAGE_USER_ERZYA, "myv", "RU", k0 }, + { LANGUAGE_USER_MARI_MEADOW, "mhr", "RU", k0 }, + { LANGUAGE_USER_KHANTY, "kca", "RU", k0 }, + { LANGUAGE_USER_LIVONIAN, "liv", "RU", k0 }, + { LANGUAGE_USER_MOKSHA, "mdf", "RU", k0 }, + { LANGUAGE_USER_MARI_HILL, "mrj", "RU", k0 }, + { LANGUAGE_USER_NGANASAN, "nio", "RU", k0 }, + { LANGUAGE_USER_OLONETS, "olo", "RU", k0 }, + { LANGUAGE_USER_VEPS, "vep", "RU", k0 }, + { LANGUAGE_USER_VORO, "vro", "EE", k0 }, + { LANGUAGE_USER_NENETS, "yrk", "RU", k0 }, + { LANGUAGE_USER_AKA, "axk", "CF", k0 }, + { LANGUAGE_USER_AKA_CONGO, "axk", "CG", k0 }, + { LANGUAGE_USER_DIBOLE, "bvx", "CG", k0 }, + { LANGUAGE_USER_DOONDO, "dde", "CG", k0 }, + { LANGUAGE_USER_KAAMBA, "xku", "CG", k0 }, + { LANGUAGE_USER_KOONGO, "kng", "CD", k0 }, + { LANGUAGE_USER_KOONGO_CONGO, "kng", "CG", k0 }, + { LANGUAGE_USER_KUNYI, "njx", "CG", k0 }, + { LANGUAGE_USER_NGUNGWEL, "ngz", "CG", k0 }, + { LANGUAGE_USER_NJYEM, "njy", "CM", k0 }, + { LANGUAGE_USER_NJYEM_CONGO, "njy", "CG", k0 }, + { LANGUAGE_USER_PUNU, "puu", "GA", k0 }, + { LANGUAGE_USER_PUNU_CONGO, "puu", "CG", k0 }, + { LANGUAGE_USER_SUUNDI, "sdj", "CG", k0 }, + { LANGUAGE_USER_TEKE_KUKUYA, "kkw", "CG", k0 }, + { LANGUAGE_USER_TSAANGI, "tsa", "CG", k0 }, + { LANGUAGE_USER_YAKA, "iyx", "CG", k0 }, + { LANGUAGE_USER_YOMBE, "yom", "CD", k0 }, + { LANGUAGE_USER_YOMBE_CONGO, "yom", "CG", k0 }, + { LANGUAGE_USER_SIDAMA, "sid", "ET", k0 }, + { LANGUAGE_USER_NKO, "nqo", "GN", k0 }, + { LANGUAGE_USER_UDMURT, "udm", "RU", k0 }, + { LANGUAGE_USER_CORNISH, "kw", "UK", k0 }, + { LANGUAGE_USER_SAMI_PITE_SWEDEN, "sje", "SE", k0 }, + { LANGUAGE_USER_NGAEBERE, "gym", "PA", k0 }, + { LANGUAGE_USER_KUMYK, "kum", "RU", k0 }, + { LANGUAGE_USER_NOGAI, "nog", "RU", k0 }, + { LANGUAGE_USER_LADIN, "lld", "IT", k0 }, + { LANGUAGE_USER_FRENCH_BURKINA_FASO, "fr", "BF", k0 }, + { LANGUAGE_USER_PUINAVE, "pui", "CO", k0 }, + { LANGUAGE_USER_AVAR, "av", "RU", k0 }, + { LANGUAGE_USER_LENGO, "lgr", "SB", k0 }, + { LANGUAGE_USER_FRENCH_BENIN, "fr", "BJ", k0 }, + { LANGUAGE_USER_FRENCH_NIGER, "fr", "NE", k0 }, + { LANGUAGE_USER_FRENCH_TOGO, "fr", "TG", k0 }, + { LANGUAGE_USER_KVEN_FINNISH, "fkv", "NO", k0 }, + { LANGUAGE_USER_CHURCH_SLAVIC, "cu", "RU", k0 }, + { LANGUAGE_USER_VENETIAN, "vec", "IT", k0 }, + { LANGUAGE_USER_ENGLISH_GAMBIA, "en", "GM", k0 }, + { LANGUAGE_USER_OCCITAN_ARANESE, "oc", "ES", k0 }, + { LANGUAGE_USER_ARPITAN_FRANCE, "frp", "FR", k0 }, + { LANGUAGE_USER_ARPITAN_ITALY, "frp", "IT", k0 }, + { LANGUAGE_USER_ARPITAN_SWITZERLAND, "frp", "CH", k0 }, + { LANGUAGE_USER_APATANI, "apt", "IN", k0 }, + { LANGUAGE_USER_ENGLISH_MAURITIUS, "en", "MU", k0 }, + { LANGUAGE_USER_FRENCH_MAURITIUS, "fr", "MU", k0 }, + { LANGUAGE_USER_SILESIAN, "szl", "PL", k0 }, + { LANGUAGE_USER_MANCHU, "mnc", "CN", k0 }, + { LANGUAGE_USER_XIBE, "sjo", "CN", k0 }, + { LANGUAGE_MULTIPLE, "mul", "" , k0 }, // multiple languages, many languages are used + { LANGUAGE_UNDETERMINED, "und", "" , k0 }, // undetermined language, language cannot be identified + { LANGUAGE_NONE, "zxx", "" , k0 }, // added to ISO 639-2 on 2006-01-11: Used to declare the absence of linguistic information + { LANGUAGE_DONTKNOW, "", "" , k0 } // marks end of table }; static IsoLanguageScriptCountryEntry const aImplIsoLangScriptEntries[] = { // MS-LangID, ISO639-ISO15924, ISO3166, override - { LANGUAGE_SERBIAN_LATIN_SERBIA, "sr-Latn", "RS", 0 }, - { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_SERBIA, "sr-Latn", "RS", 0 }, - { LANGUAGE_SERBIAN_LATIN_MONTENEGRO, "sr-Latn", "ME", 0 }, - { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_MONTENEGRO,"sr-Latn", "ME", 0 }, - { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA, "sr-Latn", "BA", 0 }, - { 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 - { LANGUAGE_SERBIAN_LATIN_SAM, "sr-Latn", "YU", 0 }, // legacy Serbian Latin in Yugoslavia - { LANGUAGE_SERBIAN_LATIN_LSO, "sr-Latn", "" , 0 }, + { LANGUAGE_SERBIAN_LATIN_SERBIA, "sr-Latn", "RS", k0 }, + { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_SERBIA, "sr-Latn", "RS", k0 }, + { LANGUAGE_SERBIAN_LATIN_MONTENEGRO, "sr-Latn", "ME", k0 }, + { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_MONTENEGRO,"sr-Latn", "ME", k0 }, + { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA, "sr-Latn", "BA", k0 }, + { 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 + { LANGUAGE_SERBIAN_LATIN_SAM, "sr-Latn", "YU", k0 }, // legacy Serbian Latin in Yugoslavia + { LANGUAGE_SERBIAN_LATIN_LSO, "sr-Latn", "" , k0 }, { LANGUAGE_SERBIAN_LATIN_NEUTRAL, "sr-Latn", "" , LANGUAGE_SERBIAN_LATIN_LSO }, // MS lists this as 'sr' only, what a mess { LANGUAGE_SERBIAN_CYRILLIC_SERBIA, "sr-Cyrl", "RS", kSAME }, // MS { LANGUAGE_SERBIAN_CYRILLIC_MONTENEGRO, "sr-Cyrl", "ME", kSAME }, // MS { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr-Cyrl", "BA", kSAME }, // MS { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr-Cyrl", "CS", kSAME }, // MS { LANGUAGE_SERBIAN_CYRILLIC_LSO, "sr-Cyrl", "" , kSAME }, // MS - { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs-Cyrl", "BA", 0 }, - { LANGUAGE_BOSNIAN_CYRILLIC_LSO, "bs-Cyrl", "" , 0 }, - { LANGUAGE_AZERI_CYRILLIC, "az-Cyrl", "AZ", 0 }, // macrolanguage code - { LANGUAGE_AZERI_CYRILLIC_LSO, "az-Cyrl", "" , 0 }, // macrolanguage code - { LANGUAGE_UZBEK_CYRILLIC, "uz-Cyrl", "UZ", 0 }, // macrolanguage code - { LANGUAGE_UZBEK_CYRILLIC_LSO, "uz-Cyrl", "" , 0 }, // macrolanguage code - { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA, "mn-Cyrl", "MN", 0 }, // macrolanguage code; should be khk-MN or khk-Cyrl-MN - { LANGUAGE_MONGOLIAN_CYRILLIC_LSO, "mn-Cyrl", "" , 0 }, // macrolanguage code; MS, should be khk or khk-Cyrl - { LANGUAGE_MONGOLIAN_MONGOLIAN_MONGOLIA, "mn-Mong", "MN", 0 }, // macrolanguage code; MS, should be khk-Mong-MN - { LANGUAGE_MONGOLIAN_MONGOLIAN_CHINA, "mn-Mong", "CN", 0 }, // macrolanguage code; MS, should actually be mvf-CN - { LANGUAGE_MONGOLIAN_MONGOLIAN_LSO, "mn-Mong", "" , 0 }, // macrolanguage code - { LANGUAGE_USER_PALI_LATIN, "pi-Latn", "" , 0 }, - { LANGUAGE_USER_KARAKALPAK_LATIN, "kaa-Latn", "UZ", 0 }, - { LANGUAGE_TAJIK, "tg-Cyrl", "TJ", 0 }, // MS - { LANGUAGE_TAJIK_LSO, "tg-Cyrl", "" , 0 }, // MS - { LANGUAGE_AZERI_LATIN, "az-Latn", "AZ", 0 }, // macrolanguage code; MS - { LANGUAGE_AZERI_LATIN_LSO, "az-Latn", "" , 0 }, // macrolanguage code; MS + { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs-Cyrl", "BA", k0 }, + { LANGUAGE_BOSNIAN_CYRILLIC_LSO, "bs-Cyrl", "" , k0 }, + { LANGUAGE_AZERI_CYRILLIC, "az-Cyrl", "AZ", k0 }, // macrolanguage code + { LANGUAGE_AZERI_CYRILLIC_LSO, "az-Cyrl", "" , k0 }, // macrolanguage code + { LANGUAGE_UZBEK_CYRILLIC, "uz-Cyrl", "UZ", k0 }, // macrolanguage code + { LANGUAGE_UZBEK_CYRILLIC_LSO, "uz-Cyrl", "" , k0 }, // macrolanguage code + { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA, "mn-Cyrl", "MN", k0 }, // macrolanguage code; should be khk-MN or khk-Cyrl-MN + { LANGUAGE_MONGOLIAN_CYRILLIC_LSO, "mn-Cyrl", "" , k0 }, // macrolanguage code; MS, should be khk or khk-Cyrl + { LANGUAGE_MONGOLIAN_MONGOLIAN_MONGOLIA, "mn-Mong", "MN", k0 }, // macrolanguage code; MS, should be khk-Mong-MN + { LANGUAGE_MONGOLIAN_MONGOLIAN_CHINA, "mn-Mong", "CN", k0 }, // macrolanguage code; MS, should actually be mvf-CN + { LANGUAGE_MONGOLIAN_MONGOLIAN_LSO, "mn-Mong", "" , k0 }, // macrolanguage code + { LANGUAGE_USER_PALI_LATIN, "pi-Latn", "" , k0 }, + { LANGUAGE_USER_KARAKALPAK_LATIN, "kaa-Latn", "UZ", k0 }, + { LANGUAGE_TAJIK, "tg-Cyrl", "TJ", k0 }, // MS + { LANGUAGE_TAJIK_LSO, "tg-Cyrl", "" , k0 }, // MS + { LANGUAGE_AZERI_LATIN, "az-Latn", "AZ", k0 }, // macrolanguage code; MS + { LANGUAGE_AZERI_LATIN_LSO, "az-Latn", "" , k0 }, // macrolanguage code; MS { LANGUAGE_USER_YIDDISH_US, "yi-Hebr", "US", kSAME }, // macrolanguage code; MS, Hebr is suppress-script { LANGUAGE_YIDDISH, "yi-Hebr", "IL", kSAME }, // macrolanguage code; MS, Hebr is suppress-script - { LANGUAGE_UZBEK_LATIN, "uz-Latn", "UZ", 0 }, // macrolanguage code - { LANGUAGE_UZBEK_LATIN_LSO, "uz-Latn", "" , 0 }, -// { LANGUAGE_SINDHI, "sd-Deva", "IN", 0 }, // MS, TODO: see comment above in aImplIsoLangEntries - { LANGUAGE_SINDHI_PAKISTAN, "sd-Arab", "PK", 0 }, // MS - { LANGUAGE_SINDHI_ARABIC_LSO, "sd-Arab", "" , 0 }, - { LANGUAGE_CHEROKEE_UNITED_STATES, "chr-Cher", "US", 0 }, // MS - { LANGUAGE_CHEROKEE_CHEROKEE_LSO, "chr-Cher", "" , 0 }, - { LANGUAGE_INUKTITUT_SYLLABICS_CANADA, "iu-Cans", "CA", 0 }, // macrolanguage code, MS - { LANGUAGE_INUKTITUT_SYLLABICS_LSO, "iu-Cans", "" , 0 }, // macrolanguage code, MS - { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu-Latn", "CA", 0 }, // macrolanguage code, MS - { LANGUAGE_INUKTITUT_LATIN_LSO, "iu-Latn", "" , 0 }, // macrolanguage code, MS - { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "tzm-Tfng", "MA", 0 }, - { LANGUAGE_TAMAZIGHT_TIFINAGH_LSO, "tzm-Tfng", "" , 0 }, - { LANGUAGE_KASHMIRI_INDIA, "ks-Deva", "IN", 0 }, // MS - { LANGUAGE_KASHMIRI, "ks-Arab", "" , 0 }, // MS, Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that - { LANGUAGE_HAUSA_NIGERIA, "ha-Latn", "NG", 0 }, // MS - { LANGUAGE_USER_HAUSA_GHANA, "ha-Latn", "GH", 0 }, - { LANGUAGE_HAUSA_LATIN_LSO, "ha-Latn", "" , 0 }, + { LANGUAGE_UZBEK_LATIN, "uz-Latn", "UZ", k0 }, // macrolanguage code + { LANGUAGE_UZBEK_LATIN_LSO, "uz-Latn", "" , k0 }, +// { LANGUAGE_SINDHI, "sd-Deva", "IN", k0 }, // MS, TODO: see comment above in aImplIsoLangEntries + { LANGUAGE_SINDHI_PAKISTAN, "sd-Arab", "PK", k0 }, // MS + { LANGUAGE_SINDHI_ARABIC_LSO, "sd-Arab", "" , k0 }, + { LANGUAGE_CHEROKEE_UNITED_STATES, "chr-Cher", "US", k0 }, // MS + { LANGUAGE_CHEROKEE_CHEROKEE_LSO, "chr-Cher", "" , k0 }, + { LANGUAGE_INUKTITUT_SYLLABICS_CANADA, "iu-Cans", "CA", k0 }, // macrolanguage code, MS + { LANGUAGE_INUKTITUT_SYLLABICS_LSO, "iu-Cans", "" , k0 }, // macrolanguage code, MS + { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu-Latn", "CA", k0 }, // macrolanguage code, MS + { LANGUAGE_INUKTITUT_LATIN_LSO, "iu-Latn", "" , k0 }, // macrolanguage code, MS + { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "tzm-Tfng", "MA", k0 }, + { LANGUAGE_TAMAZIGHT_TIFINAGH_LSO, "tzm-Tfng", "" , k0 }, + { LANGUAGE_KASHMIRI_INDIA, "ks-Deva", "IN", k0 }, // MS + { LANGUAGE_KASHMIRI, "ks-Arab", "" , k0 }, // MS, Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that + { LANGUAGE_HAUSA_NIGERIA, "ha-Latn", "NG", k0 }, // MS + { LANGUAGE_USER_HAUSA_GHANA, "ha-Latn", "GH", k0 }, + { LANGUAGE_HAUSA_LATIN_LSO, "ha-Latn", "" , k0 }, { LANGUAGE_LATIN_LSO, "la-Latn", "" , kSAME }, // MS, though Latn is suppress-script - { LANGUAGE_TAI_NUA_CHINA, "tdd-Tale", "CN", 0 }, // MS reserved - { LANGUAGE_LU_CHINA, "khb-Talu", "CN", 0 }, // MS reserved + { LANGUAGE_TAI_NUA_CHINA, "tdd-Tale", "CN", k0 }, // MS reserved + { LANGUAGE_LU_CHINA, "khb-Talu", "CN", k0 }, // MS reserved { LANGUAGE_KURDISH_ARABIC_IRAQ, "ku-Arab", "IQ", kSAME }, // macrolanguage code, MS { LANGUAGE_KURDISH_ARABIC_LSO, "ku-Arab", "" , kSAME }, // macrolanguage code, MS - { LANGUAGE_USER_KURDISH_TURKEY, "kmr-Latn", "TR", 0 }, - { LANGUAGE_USER_KURDISH_SYRIA, "kmr-Latn", "SY", 0 }, - { LANGUAGE_PUNJABI_PAKISTAN, "pnb-Arab", "PK", 0 }, - { LANGUAGE_PUNJABI_ARABIC_LSO, "pnb-Arab", "" , 0 }, - { LANGUAGE_PUNJABI_PAKISTAN, "pa-Arab", "PK", 0 }, // MS, incorrect - { LANGUAGE_PUNJABI_ARABIC_LSO, "pa-Arab", "" , 0 }, // MS, incorrect + { LANGUAGE_USER_KURDISH_TURKEY, "kmr-Latn", "TR", k0 }, + { LANGUAGE_USER_KURDISH_SYRIA, "kmr-Latn", "SY", k0 }, + { LANGUAGE_PUNJABI_PAKISTAN, "pnb-Arab", "PK", k0 }, + { LANGUAGE_PUNJABI_ARABIC_LSO, "pnb-Arab", "" , k0 }, + { LANGUAGE_PUNJABI_PAKISTAN, "pa-Arab", "PK", k0 }, // MS, incorrect + { LANGUAGE_PUNJABI_ARABIC_LSO, "pa-Arab", "" , k0 }, // MS, incorrect { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "tzm-Latn", "DZ", kSAME }, // MS - { LANGUAGE_TAMAZIGHT_LATIN_LSO, "tzm-Latn", "" , 0 }, // MS - { LANGUAGE_FULFULDE_SENEGAL, "ff-Latn", "SN", 0 }, // macrolanguage code, MS - { LANGUAGE_FULFULDE_LATIN_LSO, "ff-Latn", "" , 0 }, // macrolanguage code + { LANGUAGE_TAMAZIGHT_LATIN_LSO, "tzm-Latn", "" , k0 }, // MS + { LANGUAGE_FULFULDE_SENEGAL, "ff-Latn", "SN", k0 }, // macrolanguage code, MS + { LANGUAGE_FULFULDE_LATIN_LSO, "ff-Latn", "" , k0 }, // macrolanguage code { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA, "bs-Latn", "BA", kSAME }, // MS, though Latn is suppress-script { LANGUAGE_BOSNIAN_LATIN_LSO, "bs-Latn", "" , LANGUAGE_BOSNIAN_LSO }, // MS, though Latn is suppress-script - { LANGUAGE_CHINESE_TRADITIONAL_LSO, "zh-Hant", "" , 0 }, - { LANGUAGE_USER_MANINKAKAN_EASTERN_LATIN, "emk-Latn", "GN", 0 }, - { LANGUAGE_USER_CREE_PLAINS_LATIN, "crk-Latn", "CA", 0 }, - { LANGUAGE_USER_CREE_PLAINS_SYLLABICS, "crk-Cans", "CA", 0 }, + { LANGUAGE_CHINESE_TRADITIONAL_LSO, "zh-Hant", "" , k0 }, + { LANGUAGE_USER_MANINKAKAN_EASTERN_LATIN, "emk-Latn", "GN", k0 }, + { LANGUAGE_USER_CREE_PLAINS_LATIN, "crk-Latn", "CA", k0 }, + { LANGUAGE_USER_CREE_PLAINS_SYLLABICS, "crk-Cans", "CA", k0 }, { LANGUAGE_USER_CREE_PLAINS_LATIN, "crk-Latn", "CN", kSAME }, // erroneous tdf#73973 { LANGUAGE_USER_CREE_PLAINS_SYLLABICS, "crk-Cans", "CN", kSAME }, // erroneous tdf#73973 - { LANGUAGE_USER_HUNGARIAN_ROVAS, "hu-Hung", "HU", 0 }, - { LANGUAGE_DONTKNOW, "", "" , 0 } // marks end of table + { LANGUAGE_USER_HUNGARIAN_ROVAS, "hu-Hung", "HU", k0 }, + { LANGUAGE_DONTKNOW, "", "" , k0 } // marks end of table }; static Bcp47CountryEntry const aImplBcp47CountryEntries[] = { // MS-LangID full BCP47, ISO3166, ISO639-Variant or other fallback - { LANGUAGE_CATALAN_VALENCIAN, "ca-ES-valencia", "ES", "ca-valencia", 0 }, - { LANGUAGE_OBSOLETE_USER_CATALAN_VALENCIAN, "ca-ES-valencia", "ES", "", 0 }, // In case MS format files using the old value escaped into the wild, map them back. - { LANGUAGE_USER_ENGLISH_UK_OXENDICT, "en-GB-oxendict", "GB", "", 0 }, + { LANGUAGE_CATALAN_VALENCIAN, "ca-ES-valencia", "ES", "ca-valencia", k0 }, + { 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. + { LANGUAGE_USER_ENGLISH_UK_OXENDICT, "en-GB-oxendict", "GB", "", k0 }, { LANGUAGE_USER_ENGLISH_UK_OED, "en-GB-oed", "GB", "", LANGUAGE_USER_ENGLISH_UK_OXENDICT }, // grandfathered, deprecated, prefer en-GB-oxendict // { 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! - { LANGUAGE_DONTKNOW, "", "", "", 0 } // marks end of table + { LANGUAGE_DONTKNOW, "", "", "", k0 } // marks end of table }; static IsoLanguageCountryEntry aLastResortFallbackEntry = -{ LANGUAGE_ENGLISH_US, "en", "US", 0 }; +{ LANGUAGE_ENGLISH_US, "en", "US", k0 }; OUString IsoLanguageCountryEntry::getTagString() const { @@ -1137,22 +1138,20 @@ css::lang::Locale MsLangId::Conversion::lookupFallbackLocale( } else { - switch (pEntry->mnLang) - { + if (pEntry->mnLang.anyOf( // These are known to have no country assigned. - case LANGUAGE_USER_ESPERANTO: - case LANGUAGE_USER_INTERLINGUA: - case LANGUAGE_USER_INTERLINGUE: - case LANGUAGE_USER_LOJBAN: - case LANGUAGE_KASHMIRI: - case LANGUAGE_USER_KEYID: + LANGUAGE_USER_ESPERANTO, + LANGUAGE_USER_INTERLINGUA, + LANGUAGE_USER_INTERLINGUE, + LANGUAGE_USER_LOJBAN, + LANGUAGE_KASHMIRI, + LANGUAGE_USER_KEYID, // And the special codes without country. - case LANGUAGE_MULTIPLE: - case LANGUAGE_UNDETERMINED: - case LANGUAGE_NONE: - return getLocale( pEntry); // may override - default: - ; // nothing + LANGUAGE_MULTIPLE, + LANGUAGE_UNDETERMINED, + LANGUAGE_NONE)) + { + return getLocale( pEntry); // may override } } if (!pFirstLang) |