X-Git-Url: https://git.heureux-cyclage.org/?a=blobdiff_plain;f=languages%2FLanguageCode.php;h=7d954d38030f2de16da5fcfaa986ad9f579c0b82;hb=97c13ffeb854180843492046be6696cb0d49099e;hp=f50c55fe765d90de964ac630e2e06a5d90adcc4f;hpb=867a92fd67b0fbec2720277234ccbce169ee1160;p=lhc%2Fweb%2Fwiklou.git diff --git a/languages/LanguageCode.php b/languages/LanguageCode.php index f50c55fe76..7d954d3803 100644 --- a/languages/LanguageCode.php +++ b/languages/LanguageCode.php @@ -30,22 +30,87 @@ class LanguageCode { /** * Mapping of deprecated language codes that were used in previous * versions of MediaWiki to up-to-date, current language codes. + * These may or may not be valid BCP 47 codes; they are included here + * because MediaWiki renamed these particular codes at some point. * - * @var array Mapping from language code to language code + * @var array Mapping from deprecated MediaWiki-internal language code + * to replacement MediaWiki-internal language code. * * @since 1.30 + * @see https://meta.wikimedia.org/wiki/Special_language_codes */ private static $deprecatedLanguageCodeMapping = [ // Note that als is actually a valid ISO 639 code (Tosk Albanian), but it // was previously used in MediaWiki for Alsatian, which comes under gsw - 'als' => 'gsw', - 'bat-smg' => 'sgs', - 'be-x-old' => 'be-tarask', - 'fiu-vro' => 'vro', - 'roa-rup' => 'rup', - 'zh-classical' => 'lzh', - 'zh-min-nan' => 'nan', - 'zh-yue' => 'yue', + 'als' => 'gsw', // T25215 + 'bat-smg' => 'sgs', // T27522 + 'be-x-old' => 'be-tarask', // T11823 + 'fiu-vro' => 'vro', // T31186 + 'roa-rup' => 'rup', // T17988 + 'zh-classical' => 'lzh', // T30443 + 'zh-min-nan' => 'nan', // T30442 + 'zh-yue' => 'yue', // T30441 + ]; + + /** + * Mapping of non-standard language codes used in MediaWiki to + * standardized BCP 47 codes. These are not deprecated (yet?): + * IANA may eventually recognize the subtag, in which case the `-x-` + * infix could be removed, or else we could rename the code in + * MediaWiki, in which case they'd move up to the above mapping + * of deprecated codes. + * + * As a rule, we preserve all distinctions made by MediaWiki + * internally. For example, `de-formal` becomes `de-x-formal` + * instead of just `de` because MediaWiki distinguishes `de-formal` + * from `de` (for example, for interface translations). Similarly, + * BCP 47 indicates that `kk-Cyrl` SHOULD not be used because it + * "typically does not add information", but in our case MediaWiki + * LanguageConverter distinguishes `kk` (render content in a mix of + * Kurdish variants) from `kk-Cyrl` (convert content to be uniformly + * Cyrillic). As the BCP 47 requirement is a SHOULD not a MUST, + * `kk-Cyrl` is a valid code, although some validators may emit + * a warning note. + * + * @var array Mapping from nonstandard MediaWiki-internal codes to + * BCP 47 codes + * + * @since 1.32 + * @see https://meta.wikimedia.org/wiki/Special_language_codes + * @see https://phabricator.wikimedia.org/T125073 + */ + private static $nonstandardLanguageCodeMapping = [ + // All codes returned by Language::fetchLanguageNames() validated + // against IANA registry at + // https://www.iana.org/assignments/language-subtag-registry/language-subtag-registry + // with help of validator at + // http://schneegans.de/lv/ + 'cbk-zam' => 'cbk', // T124657 + 'de-formal' => 'de-x-formal', + 'eml' => 'egl', // T36217 + 'en-rtl' => 'en-x-rtl', + 'es-formal' => 'es-x-formal', + 'hu-formal' => 'hu-x-formal', + 'map-bms' => 'jv-x-bms', // [[en:Banyumasan_dialect]] T125073 + 'mo' => 'ro-Cyrl-MD', // T125073 + 'nrm' => 'nrf', // [[en:Norman_language]] T25216 + 'nl-informal' => 'nl-x-informal', + 'roa-tara' => 'nap-x-tara', // [[en:Tarantino_dialect]] + 'simple' => 'en-simple', + 'sr-ec' => 'sr-Cyrl', // T117845 + 'sr-el' => 'sr-Latn', // T117845 + + // Although these next codes aren't *wrong* per se, including + // both the script and the country code helps compatibility with + // other BCP 47 users. Note that MW also uses `zh-Hans`/`zh-Hant`, + // without a country code, and those should be left alone. + // (See $variantfallbacks in LanguageZh.php for Hans/Hant id.) + 'zh-cn' => 'zh-Hans-CN', + 'zh-sg' => 'zh-Hans-SG', + 'zh-my' => 'zh-Hans-MY', + 'zh-tw' => 'zh-Hant-TW', + 'zh-hk' => 'zh-Hant-HK', + 'zh-mo' => 'zh-Hant-MO', ]; /** @@ -64,6 +129,29 @@ class LanguageCode { return self::$deprecatedLanguageCodeMapping; } + /** + * Returns a mapping of non-standard language codes used by + * (current and previous version of) MediaWiki, mapped to standard + * BCP 47 names. + * + * This array is exported to JavaScript to ensure + * mediawiki.language.bcp47 stays in sync with LanguageCode::bcp47(). + * + * @return string[] + * + * @since 1.32 + */ + public static function getNonstandardLanguageCodeMapping() { + $result = []; + foreach ( self::$deprecatedLanguageCodeMapping as $code => $ignore ) { + $result[$code] = self::bcp47( $code ); + } + foreach ( self::$nonstandardLanguageCodeMapping as $code => $ignore ) { + $result[$code] = self::bcp47( $code ); + } + return $result; + } + /** * Replace deprecated language codes that were used in previous * versions of MediaWiki to up-to-date, current language codes. @@ -75,10 +163,7 @@ class LanguageCode { * @since 1.30 */ public static function replaceDeprecatedCodes( $code ) { - if ( isset( self::$deprecatedLanguageCodeMapping[$code] ) ) { - return self::$deprecatedLanguageCodeMapping[$code]; - } - return $code; + return self::$deprecatedLanguageCodeMapping[$code] ?? $code; } /** @@ -87,11 +172,15 @@ class LanguageCode { * See mediawiki.language.bcp47 for the JavaScript implementation. * * @param string $code The language code. - * @return string The language code which complying with BCP 47 standards. + * @return string A language code complying with BCP 47 standards. * * @since 1.31 */ public static function bcp47( $code ) { + $code = self::replaceDeprecatedCodes( strtolower( $code ) ); + if ( isset( self::$nonstandardLanguageCodeMapping[$code] ) ) { + $code = self::$nonstandardLanguageCodeMapping[$code]; + } $codeSegment = explode( '-', $code ); $codeBCP = []; foreach ( $codeSegment as $segNo => $seg ) {