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  * All of the following will be considered separate letters for category headings in Persian:
  25  *  - Characters 'و' 'ا' (often appear at the beginning of words)
  26  *  - Characters 'ٲ' 'ٳ' (may appear at the beginning of words in loanwords)
  27  *  - Characters 'ء' 'ئ' (don't appear at the beginning of words, but it's easier to implement)
  28  *
  29  * @since 1.29
  30  */
  31 class CollationFa extends IcuCollation {
  32         private $tertiaryCollator;
  33
  34         public function __construct() {
  35                 parent::__construct( 'fa' );
  36                 $this->tertiaryCollator = Collator::create( 'fa' );
  37         }
  38
  39         public function getPrimarySortKey( $string ) {
  40                 $primary = parent::getPrimarySortKey( $string );
  41                 // We have to use a tertiary sortkey for everything with the primary sortkey of 2627.
  42                 // Otherwise, the "Remove duplicate prefixes" logic in IcuCollation would remove them.
  43                 // This matches sortkeys for the following characters: ء ئ ا و ٲ ٳ
  44                 if ( substr( $primary, 0, 2 ) === "\x26\x27" ) {
  45                         wfDebug( "Using tertiary sortkey for '$string'\n" );
  46                         return $this->tertiaryCollator->getSortKey( $string );
  47                 }
  48                 return $primary;
  49         }
  50 }