includes/collation/Collation.php

   1 <?php
   2 /**
   3  * Database row sorting.
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License along
  16  * with this program; if not, write to the Free Software Foundation, Inc.,
  17  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18  * http://www.gnu.org/copyleft/gpl.html
  19  *
  20  * @file
  21  */
  22
  23 /**
  24  * @since 1.16.3
  25  * @author Tim Starling
  26  */
  27 abstract class Collation {
  28         private static $instance;
  29
  30         /**
  31          * @since 1.16.3
  32          * @return Collation
  33          */
  34         public static function singleton() {
  35                 if ( !self::$instance ) {
  36                         global $wgCategoryCollation;
  37                         self::$instance = self::factory( $wgCategoryCollation );
  38                 }
  39                 return self::$instance;
  40         }
  41
  42         /**
  43          * @since 1.16.3
  44          * @throws MWException
  45          * @param string $collationName
  46          * @return Collation
  47          */
  48         public static function factory( $collationName ) {
  49                 global $wgContLang;
  50
  51                 switch ( $collationName ) {
  52                         case 'uppercase':
  53                                 return new UppercaseCollation;
  54                         case 'numeric':
  55                                 return new NumericUppercaseCollation( $wgContLang );
  56                         case 'identity':
  57                                 return new IdentityCollation;
  58                         case 'uca-default':
  59                                 return new IcuCollation( 'root' );
  60                         case 'uca-default-u-kn':
  61                                 return new IcuCollation( 'root-u-kn' );
  62                         case 'xx-uca-ckb':
  63                                 return new CollationCkb;
  64                         case 'xx-uca-et':
  65                                 return new CollationEt;
  66                         case 'xx-uca-fa':
  67                                 return new CollationFa;
  68                         default:
  69                                 $match = [];
  70                                 if ( preg_match( '/^uca-([A-Za-z@=-]+)$/', $collationName, $match ) ) {
  71                                         return new IcuCollation( $match[1] );
  72                                 }
  73
  74                                 # Provide a mechanism for extensions to hook in.
  75                                 $collationObject = null;
  76                                 Hooks::run( 'Collation::factory', [ $collationName, &$collationObject ] );
  77
  78                                 if ( $collationObject instanceof Collation ) {
  79                                         return $collationObject;
  80                                 }
  81
  82                                 // If all else fails...
  83                                 throw new MWException( __METHOD__ . ": unknown collation type \"$collationName\"" );
  84                 }
  85         }
  86
  87         /**
  88          * Given a string, convert it to a (hopefully short) key that can be used
  89          * for efficient sorting.  A binary sort according to the sortkeys
  90          * corresponds to a logical sort of the corresponding strings.  Current
  91          * code expects that a line feed character should sort before all others, but
  92          * has no other particular expectations (and that one can be changed if
  93          * necessary).
  94          *
  95          * @since 1.16.3
  96          *
  97          * @param string $string UTF-8 string
  98          * @return string Binary sortkey
  99          */
 100         abstract function getSortKey( $string );
 101
 102         /**
 103          * Given a string, return the logical "first letter" to be used for
 104          * grouping on category pages and so on.  This has to be coordinated
 105          * carefully with convertToSortkey(), or else the sorted list might jump
 106          * back and forth between the same "initial letters" or other pathological
 107          * behavior.  For instance, if you just return the first character, but "a"
 108          * sorts the same as "A" based on getSortKey(), then you might get a
 109          * list like
 110          *
 111          * == A ==
 112          * * [[Aardvark]]
 113          *
 114          * == a ==
 115          * * [[antelope]]
 116          *
 117          * == A ==
 118          * * [[Ape]]
 119          *
 120          * etc., assuming for the sake of argument that $wgCapitalLinks is false.
 121          *
 122          * @since 1.16.3
 123          *
 124          * @param string $string UTF-8 string
 125          * @return string UTF-8 string corresponding to the first letter of input
 126          */
 127         abstract function getFirstLetter( $string );
 128
 129 }