includes/collation/CollationFa.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  * Temporary workaround for incorrect collation of Persian language ('fa') in ICU 52 (bug T139110).
  23  *
  24  * Replace with other letters that appear in an okish spot in the alphabet
  25  *
  26  *  - Characters 'و' 'ا' (often appear at the beginning of words)
  27  *  - Characters 'ٲ' 'ٳ' (may appear at the beginning of words in loanwords)
  28  *
  29  * @since 1.29
  30  */
  31 class CollationFa extends IcuCollation {
  32
  33         // Really hacky - replace with stuff from other blocks.
  34         private $override = [
  35                 // U+0627 ARABIC LETTER ALEF => U+0623 ARABIC LETTER ALEF WITH HAMZA ABOVE
  36                 "\xd8\xa7" => "\xd8\xa3",
  37                 // U+0648 ARABIC LETTER WAW => U+0649 ARABIC LETTER ALEF MAKSURA
  38                 "\xd9\x88" => "\xd9\x89",
  39                 // U+0672 ARABIC LETTER ALEF WITH WAVY HAMZA ABOVE => U+F3001 (private use area)
  40                 "\xd9\xb2" => "\xF3\xB3\x80\x81",
  41                 // U+0673 ARABIC LETTER ALEF WITH WAVY HAMZA BELOW => U+F3002 (private use area)
  42                 "\xd9\xb3" => "\xF3\xB3\x80\x82",
  43         ];
  44
  45         public function __construct() {
  46                 parent::__construct( 'fa' );
  47         }
  48
  49         public function getSortKey( $string ) {
  50                 $modified = strtr( $string, $this->override );
  51                 return parent::getSortKey( $modified );
  52         }
  53
  54         public function getFirstLetter( $string ) {
  55                 if ( isset( $this->override[substr( $string, 0, 2 )] ) ) {
  56                         return substr( $string, 0, 2 );
  57                 }
  58                 return parent::getFirstLetter( $string );
  59         }
  60 }