diff options
Diffstat (limited to 'i18npool/source/isolang/isolang.cxx')
-rw-r--r-- | i18npool/source/isolang/isolang.cxx | 61 |
1 files changed, 58 insertions, 3 deletions
diff --git a/i18npool/source/isolang/isolang.cxx b/i18npool/source/isolang/isolang.cxx index 9d80bf7050e6..357be80a69ea 100644 --- a/i18npool/source/isolang/isolang.cxx +++ b/i18npool/source/isolang/isolang.cxx @@ -287,8 +287,9 @@ static MsLangId::IsoLangEntry const aImplIsoLangEntries[] = { LANGUAGE_BELARUSIAN, "be", "BY" }, { LANGUAGE_CATALAN, "ca", "ES" }, // Spain (default) { LANGUAGE_CATALAN, "ca", "AD" }, // Andorra - { LANGUAGE_USER_CATALAN_VALENCIAN, "ca", "XV" }, // XV: ISO 3166 user-assigned; old workaround for UI localization only, do not use in document content! Kept just in case.. - { LANGUAGE_USER_CATALAN_VALENCIAN, "qcv", "ES" }, // qcv: ISO 639-3 reserved-for-local-use; for UI localization, use in document content on own risk! + { LANGUAGE_USER_CATALAN_VALENCIAN, "ca", "XV" }, // XV: ISO 3166 user-assigned; workaround for UI localization only, do not use in document content! + { LANGUAGE_CATALAN, "qcv", "ES" }, // qcv: ISO 639-3 reserved-for-local-use; UI localization quirk only, do not use in document content! +// { LANGUAGE_USER_CATALAN_VALENCIAN, "ca", "ES" }, // In case MS format files escaped into the wild, map them back. { LANGUAGE_FRENCH_CAMEROON, "fr", "CM" }, { LANGUAGE_FRENCH_COTE_D_IVOIRE, "fr", "CI" }, { LANGUAGE_FRENCH_HAITI, "fr", "HT" }, @@ -457,6 +458,9 @@ static MsLangId::IsoLangEntry const aImplIsoLangEntries[] = { LANGUAGE_USER_TAHITIAN, "ty", "PF" }, { LANGUAGE_USER_MALAGASY_PLATEAU, "plt", "MG" }, { LANGUAGE_USER_BAFIA, "ksf", "CM" }, + { LANGUAGE_USER_GIKUYU, "ki", "KE" }, + { LANGUAGE_USER_RUSYN_UKRAINE, "rue", "UA" }, + { LANGUAGE_USER_RUSYN_SLOVAKIA, "rue", "SK" }, { LANGUAGE_NONE, "zxx", "" }, // added to ISO 639-2 on 2006-01-11: Used to declare the absence of linguistic information { LANGUAGE_DONTKNOW, "", "" } // marks end of table }; @@ -1005,6 +1009,28 @@ LanguageType MsLangId::convertIsoByteStringToLanguage( } // ----------------------------------------------------------------------- + +struct IsoLangGLIBCModifiersEntry +{ + LanguageType mnLang; + sal_Char maLangStr[4]; + sal_Char maCountry[3]; + sal_Char maAtString[9]; +}; + +static IsoLangGLIBCModifiersEntry const aImplIsoLangGLIBCModifiersEntries[] = +{ + // MS-LANGID codes ISO639-1/2/3 ISO3166 glibc modifier + { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs", "BA", "cyrillic" }, + { LANGUAGE_USER_SERBIAN_LATIN_SERBIA, "sr", "RS", "latin" }, // Serbian Latin in Serbia + { LANGUAGE_SERBIAN_LATIN, "sr", "CS", "latin" }, // Serbian Latin in Serbia and Montenegro + { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO, "sr", "ME", "latin" }, // Serbian Latin in Montenegro + { LANGUAGE_SERBIAN_LATIN_NEUTRAL, "sr", "", "latin" }, + { LANGUAGE_AZERI_CYRILLIC, "az", "AZ", "cyrillic" }, + { LANGUAGE_UZBEK_CYRILLIC, "uz", "UZ", "cyrillic" }, + { LANGUAGE_DONTKNOW, "", "", "" } // marks end of table +}; + // convert a unix locale string into LanguageType // static @@ -1013,15 +1039,20 @@ LanguageType MsLangId::convertUnxByteStringToLanguage( { rtl::OString aLang; rtl::OString aCountry; + rtl::OString aAtString; sal_Int32 nLangSepPos = rString.indexOf( (sal_Char)'_' ); sal_Int32 nCountrySepPos = rString.indexOf( (sal_Char)'.' ); + sal_Int32 nAtPos = rString.indexOf( (sal_Char)'@' ); if (nCountrySepPos < 0) - nCountrySepPos = rString.indexOf( (sal_Char)'@' ); + nCountrySepPos = nAtPos; if (nCountrySepPos < 0) nCountrySepPos = rString.getLength(); + if (nAtPos >= 0) + aAtString = rString.copy( nAtPos+1 ); + if ( ((nLangSepPos >= 0) && (nLangSepPos > nCountrySepPos)) || ((nLangSepPos < 0)) ) { @@ -1035,6 +1066,30 @@ LanguageType MsLangId::convertUnxByteStringToLanguage( aCountry = rString.copy( nLangSepPos+1, nCountrySepPos - nLangSepPos - 1); } + // if there is a glibc modifier, first look for exact match in modifier table + if (aAtString.getLength()) + { + // language is lower case in table + rtl::OString aLowerLang = aLang.toAsciiLowerCase(); + // country is upper case in table + rtl::OString aUpperCountry = aCountry.toAsciiUpperCase(); + const IsoLangGLIBCModifiersEntry* pGLIBCModifiersEntry = aImplIsoLangGLIBCModifiersEntries; + do + { + if (( aLowerLang.equals( pGLIBCModifiersEntry->maLangStr ) ) && + ( aAtString.equals( pGLIBCModifiersEntry->maAtString ) )) + { + if ( !aUpperCountry.getLength() || + aUpperCountry.equals( pGLIBCModifiersEntry->maCountry ) ) + { + return pGLIBCModifiersEntry->mnLang; + } + } + ++pGLIBCModifiersEntry; + } + while ( pGLIBCModifiersEntry->mnLang != LANGUAGE_DONTKNOW ); + } + return convertIsoNamesToLanguage( aLang, aCountry ); } |