- '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 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-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',