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 (bug 54168).
  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 class CollationEt extends IcuCollation {
  30         function __construct() {
  31                 parent::__construct( 'et' );
  32         }
  33
  34         private static function mangle( $string ) {
  35                 return str_replace(
  36                         [ 'w', 'W' ],
  37                         'ᴡ', // U+1D21 'LATIN LETTER SMALL CAPITAL W'
  38                         $string
  39                 );
  40         }
  41
  42         private static function unmangle( $string ) {
  43                 // Casing data is lost…
  44                 return str_replace(
  45                         'ᴡ', // U+1D21 'LATIN LETTER SMALL CAPITAL W'
  46                         'W',
  47                         $string
  48                 );
  49         }
  50
  51         function getSortKey( $string ) {
  52                 return parent::getSortKey( self::mangle( $string ) );
  53         }
  54
  55         function getFirstLetter( $string ) {
  56                 return self::unmangle( parent::getFirstLetter( self::mangle( $string ) ) );
  57         }
  58 }