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  * @since 1.28
  28  */
  29 class NumericUppercaseCollation extends UppercaseCollation {
  30         public function getSortKey( $string ) {
  31                 $sortkey = parent::getSortKey( $string );
  32
  33                 // For each sequence of digits, insert the digit '0' and then the length of the sequence
  34                 // (encoded in two bytes) before it. That's all folks, it sorts correctly now! The '0' ensures
  35                 // correct position (where digits would normally sort), then the length will be compared putting
  36                 // shorter numbers before longer ones; if identical, then the characters will be compared, which
  37                 // generates the correct results for numbers of equal length.
  38                 $sortkey = preg_replace_callback( '/\d+/', function ( $matches ) {
  39                         $len = strlen( $matches[0] );
  40                         // This allows sequences of up to 65536 numeric characters to be handled correctly. One byte
  41                         // would allow only for 256, which doesn't feel future-proof.
  42                         $prefix = chr( floor( $len / 256 ) ) . chr( $len % 256 );
  43                         return '0' . $prefix . $matches[0];
  44                 }, $sortkey );
  45
  46                 return $sortkey;
  47         }
  48
  49         public function getFirstLetter( $string ) {
  50                 if ( preg_match( '/^\d/', $string ) ) {
  51                         // Note that we pass 0 and 9 as normal params, not numParams(). This only works for 0-9
  52                         // and not localised digits, so we don't want them to be converted.
  53                         return wfMessage( 'category-header-numerals' )->params( 0, 9 )->text();
  54                 } else {
  55                         return parent::getFirstLetter( $string );
  56                 }
  57         }
  58 }