languages/LanguageCode.php

   1 <?php
   2 /**
   3  * This program is free software; you can redistribute it and/or modify
   4  * it under the terms of the GNU General Public License as published by
   5  * the Free Software Foundation; either version 2 of the License, or
   6  * (at your option) any later version.
   7  *
   8  * This program is distributed in the hope that it will be useful,
   9  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  10  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  11  * GNU General Public License for more details.
  12  *
  13  * You should have received a copy of the GNU General Public License along
  14  * with this program; if not, write to the Free Software Foundation, Inc.,
  15  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  16  * http://www.gnu.org/copyleft/gpl.html
  17  *
  18  * @file
  19  * @ingroup Language
  20  */
  21
  22 /**
  23  * Methods for dealing with language codes.
  24  * @todo Move some of the code-related static methods out of Language into this class
  25  *
  26  * @since 1.29
  27  * @ingroup Language
  28  */
  29 class LanguageCode {
  30         /**
  31          * Mapping of deprecated language codes that were used in previous
  32          * versions of MediaWiki to up-to-date, current language codes.
  33          *
  34          * @var array Mapping from language code to language code
  35          *
  36          * @since 1.30
  37          */
  38         private static $deprecatedLanguageCodeMapping = [
  39                 // Note that als is actually a valid ISO 639 code (Tosk Albanian), but it
  40                 // was previously used in MediaWiki for Alsatian, which comes under gsw
  41                 'als' => 'gsw',
  42                 'bat-smg' => 'sgs',
  43                 'be-x-old' => 'be-tarask',
  44                 'fiu-vro' => 'vro',
  45                 'roa-rup' => 'rup',
  46                 'zh-classical' => 'lzh',
  47                 'zh-min-nan' => 'nan',
  48                 'zh-yue' => 'yue',
  49         ];
  50
  51         /**
  52          * Returns a mapping of deprecated language codes that were used in previous
  53          * versions of MediaWiki to up-to-date, current language codes.
  54          *
  55          * This array is merged into $wgDummyLanguageCodes in Setup.php, along with
  56          * the fake language codes 'qqq' and 'qqx', which are used internally by
  57          * MediaWiki's localisation system.
  58          *
  59          * @return string[]
  60          *
  61          * @since 1.29
  62          */
  63         public static function getDeprecatedCodeMapping() {
  64                 return self::$deprecatedLanguageCodeMapping;
  65         }
  66
  67         /**
  68          * Replace deprecated language codes that were used in previous
  69          * versions of MediaWiki to up-to-date, current language codes.
  70          * Other values will returned unchanged.
  71          *
  72          * @param string $code Old language code
  73          * @return string New language code
  74          *
  75          * @since 1.30
  76          */
  77         public static function replaceDeprecatedCodes( $code ) {
  78                 if ( isset( self::$deprecatedLanguageCodeMapping[$code] ) ) {
  79                         return self::$deprecatedLanguageCodeMapping[$code];
  80                 }
  81                 return $code;
  82         }
  83
  84         /**
  85          * Get the normalised IETF language tag
  86          * See unit test for examples.
  87          * See mediawiki.language.bcp47 for the JavaScript implementation.
  88          *
  89          * @param string $code The language code.
  90          * @return string The language code which complying with BCP 47 standards.
  91          *
  92          * @since 1.31
  93          */
  94         public static function bcp47( $code ) {
  95                 $codeSegment = explode( '-', $code );
  96                 $codeBCP = [];
  97                 foreach ( $codeSegment as $segNo => $seg ) {
  98                         // when previous segment is x, it is a private segment and should be lc
  99                         if ( $segNo > 0 && strtolower( $codeSegment[( $segNo - 1 )] ) == 'x' ) {
 100                                 $codeBCP[$segNo] = strtolower( $seg );
 101                         // ISO 3166 country code
 102                         } elseif ( ( strlen( $seg ) == 2 ) && ( $segNo > 0 ) ) {
 103                                 $codeBCP[$segNo] = strtoupper( $seg );
 104                         // ISO 15924 script code
 105                         } elseif ( ( strlen( $seg ) == 4 ) && ( $segNo > 0 ) ) {
 106                                 $codeBCP[$segNo] = ucfirst( strtolower( $seg ) );
 107                         // Use lowercase for other cases
 108                         } else {
 109                                 $codeBCP[$segNo] = strtolower( $seg );
 110                         }
 111                 }
 112                 $langCode = implode( '-', $codeBCP );
 113                 return $langCode;
 114         }
 115 }