LanguageCode.php

Go to the documentation of this file.

<?php
class LanguageCode {
    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',
    ];
 
    public static function getDeprecatedCodeMapping() {
        return self::$deprecatedLanguageCodeMapping;
    }
 
    public static function replaceDeprecatedCodes( $code ) {
        if ( isset( self::$deprecatedLanguageCodeMapping[$code] ) ) {
            return self::$deprecatedLanguageCodeMapping[$code];
        }
        return $code;
    }
 
    public static function bcp47( $code ) {
        $codeSegment = explode( '-', $code );
        $codeBCP = [];
        foreach ( $codeSegment as $segNo => $seg ) {
            // when previous segment is x, it is a private segment and should be lc
            if ( $segNo > 0 && strtolower( $codeSegment[( $segNo - 1 )] ) == 'x' ) {
                $codeBCP[$segNo] = strtolower( $seg );
            // ISO 3166 country code
            } elseif ( ( strlen( $seg ) == 2 ) && ( $segNo > 0 ) ) {
                $codeBCP[$segNo] = strtoupper( $seg );
            // ISO 15924 script code
            } elseif ( ( strlen( $seg ) == 4 ) && ( $segNo > 0 ) ) {
                $codeBCP[$segNo] = ucfirst( strtolower( $seg ) );
            // Use lowercase for other cases
            } else {
                $codeBCP[$segNo] = strtolower( $seg );
            }
        }
        $langCode = implode( '-', $codeBCP );
        return $langCode;
    }
}