includes/collation/CollationEt.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  */
  20
  21 /**
  22  * Workaround for incorrect collation of Estonian language ('et') in ICU (T56168).
  23  *
  24  * 'W' and 'V' should not be considered the same letter for the purposes of collation in modern
  25  * Estonian. We work around this by replacing 'W' and 'w' with 'ᴡ' U+1D21 'LATIN LETTER SMALL
  26  * CAPITAL W' for sortkey generation, which is collated like 'W' and is not tailored to have the
  27  * same primary weight as 'V' in Estonian.
  28  *
  29  * @since 1.24
  30  */
  31 class CollationEt extends IcuCollation {
  32         public function __construct() {
  33                 parent::__construct( 'et' );
  34         }
  35
  36         private static function mangle( $string ) {
  37                 return str_replace(
  38                         [ 'w', 'W' ],
  39                         'ᴡ', // U+1D21 'LATIN LETTER SMALL CAPITAL W'
  40                         $string
  41                 );
  42         }
  43
  44         private static function unmangle( $string ) {
  45                 // Casing data is lost…
  46                 return str_replace(
  47                         'ᴡ', // U+1D21 'LATIN LETTER SMALL CAPITAL W'
  48                         'W',
  49                         $string
  50                 );
  51         }
  52
  53         public function getSortKey( $string ) {
  54                 return parent::getSortKey( self::mangle( $string ) );
  55         }
  56
  57         public function getFirstLetter( $string ) {
  58                 return self::unmangle( parent::getFirstLetter( self::mangle( $string ) ) );
  59         }
  60 }