includes/collation/NumericUppercaseCollation.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  * Collation that orders text with numbers "naturally", so that 'Foo 1' < 'Foo 2' < 'Foo 12'.
  23  *
  24  * Note that this only works in terms of sequences of digits, and the behavior for decimal fractions
  25  * or pretty-formatted numbers may be unexpected.
  26  *
  27  * Digits will be based on the wiki's content language settings. If
  28  * you change the content langauge of a wiki you will need to run
  29  * updateCollation.php --force. Only English (ASCII 0-9) and the
  30  * localized version will be counted. Localized digits from other languages
  31  * or weird unicode digit equivalents (e.g. ４, 𝟜, ⓸ , ⁴, etc) will not count.
  32  *
  33  * @since 1.28
  34  */
  35 class NumericUppercaseCollation extends UppercaseCollation {
  36
  37         /**
  38          * @var $digitTransformLang Language How to convert digits (usually $wgContLang)
  39          */
  40         private $digitTransformLang;
  41
  42         /**
  43          * @param Language $lang How to convert digits.
  44          *  For example, if given language "my" than ၇ is treated like 7.
  45          *
  46          * It is expected that usually this is given $wgContLang.
  47          */
  48         public function __construct( Language $lang ) {
  49                 $this->digitTransformLang = $lang;
  50                 parent::__construct();
  51         }
  52
  53         public function getSortKey( $string ) {
  54                 $sortkey = parent::getSortKey( $string );
  55                 $sortkey = $this->convertDigits( $sortkey );
  56                 // For each sequence of digits, insert the digit '0' and then the length of the sequence
  57                 // (encoded in two bytes) before it. That's all folks, it sorts correctly now! The '0' ensures
  58                 // correct position (where digits would normally sort), then the length will be compared putting
  59                 // shorter numbers before longer ones; if identical, then the characters will be compared, which
  60                 // generates the correct results for numbers of equal length.
  61                 $sortkey = preg_replace_callback( '/\d+/', function ( $matches ) {
  62                         // Strip any leading zeros
  63                         $number = ltrim( $matches[0], '0' );
  64                         $len = strlen( $number );
  65                         // This allows sequences of up to 65536 numeric characters to be handled correctly. One byte
  66                         // would allow only for 256, which doesn't feel future-proof.
  67                         $prefix = chr( floor( $len / 256 ) ) . chr( $len % 256 );
  68                         return '0' . $prefix . $number;
  69                 }, $sortkey );
  70
  71                 return $sortkey;
  72         }
  73
  74         /**
  75          * Convert localized digits to english digits.
  76          *
  77          * based on Language::parseFormattedNumber but without commas.
  78          *
  79          * @param string $string sortkey to unlocalize digits of
  80          * @return string Sortkey with all localized digits replaced with ASCII digits.
  81          */
  82         private function convertDigits( $string ) {
  83                 $table = $this->digitTransformLang->digitTransformTable();
  84                 if ( $table ) {
  85                         $table = array_filter( $table );
  86                         $flipped = array_flip( $table );
  87                         // Some languages seem to also have commas in this table.
  88                         $flipped = array_filter( $flipped, 'is_numeric' );
  89                         $string = strtr( $string, $flipped );
  90                 }
  91                 return $string;
  92         }
  93
  94         public function getFirstLetter( $string ) {
  95                 $convertedString = $this->convertDigits( $string );
  96
  97                 if ( preg_match( '/^\d/', $convertedString ) ) {
  98                         return wfMessage( 'category-header-numerals' )
  99                                 ->numParams( 0, 9 )
 100                                 ->text();
 101                 } else {
 102                         return parent::getFirstLetter( $string );
 103                 }
 104         }
 105 }