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 use MediaWiki\MediaWikiServices;
  24
  25 /**
  26  * @since 1.16.3
  27  * @author Tim Starling
  28  */
  29 abstract class Collation {
  30         private static $instance;
  31
  32         /**
  33          * @since 1.16.3
  34          * @return Collation
  35          */
  36         public static function singleton() {
  37                 if ( !self::$instance ) {
  38                         global $wgCategoryCollation;
  39                         self::$instance = self::factory( $wgCategoryCollation );
  40                 }
  41                 return self::$instance;
  42         }
  43
  44         /**
  45          * @since 1.16.3
  46          * @throws MWException
  47          * @param string $collationName
  48          * @return Collation
  49          */
  50         public static function factory( $collationName ) {
  51                 switch ( $collationName ) {
  52                         case 'uppercase':
  53                                 return new UppercaseCollation;
  54                         case 'numeric':
  55                                 return new NumericUppercaseCollation(
  56                                         MediaWikiServices::getInstance()->getContentLanguage() );
  57                         case 'identity':
  58                                 return new IdentityCollation;
  59                         case 'uca-default':
  60                                 return new IcuCollation( 'root' );
  61                         case 'uca-default-u-kn':
  62                                 return new IcuCollation( 'root-u-kn' );
  63                         case 'xx-uca-ckb':
  64                                 return new CollationCkb;
  65                         case 'xx-uca-et':
  66                                 return new CollationEt;
  67                         case 'uppercase-ab':
  68                                 return new AbkhazUppercaseCollation;
  69                         case 'uppercase-ba':
  70                                 return new BashkirUppercaseCollation;
  71                         default:
  72                                 $match = [];
  73                                 if ( preg_match( '/^uca-([A-Za-z@=-]+)$/', $collationName, $match ) ) {
  74                                         return new IcuCollation( $match[1] );
  75                                 }
  76
  77                                 # Provide a mechanism for extensions to hook in.
  78                                 $collationObject = null;
  79                                 Hooks::run( 'Collation::factory', [ $collationName, &$collationObject ] );
  80
  81                                 if ( $collationObject instanceof Collation ) {
  82                                         return $collationObject;
  83                                 }
  84
  85                                 // If all else fails...
  86                                 throw new MWException( __METHOD__ . ": unknown collation type \"$collationName\"" );
  87                 }
  88         }
  89
  90         /**
  91          * Given a string, convert it to a (hopefully short) key that can be used
  92          * for efficient sorting.  A binary sort according to the sortkeys
  93          * corresponds to a logical sort of the corresponding strings.  Current
  94          * code expects that a line feed character should sort before all others, but
  95          * has no other particular expectations (and that one can be changed if
  96          * necessary).
  97          *
  98          * @since 1.16.3
  99          *
 100          * @param string $string UTF-8 string
 101          * @return string Binary sortkey
 102          */
 103         abstract function getSortKey( $string );
 104
 105         /**
 106          * Given a string, return the logical "first letter" to be used for
 107          * grouping on category pages and so on.  This has to be coordinated
 108          * carefully with convertToSortkey(), or else the sorted list might jump
 109          * back and forth between the same "initial letters" or other pathological
 110          * behavior.  For instance, if you just return the first character, but "a"
 111          * sorts the same as "A" based on getSortKey(), then you might get a
 112          * list like
 113          *
 114          * == A ==
 115          * * [[Aardvark]]
 116          *
 117          * == a ==
 118          * * [[antelope]]
 119          *
 120          * == A ==
 121          * * [[Ape]]
 122          *
 123          * etc., assuming for the sake of argument that $wgCapitalLinks is false.
 124          *
 125          * @since 1.16.3
 126          *
 127          * @param string $string UTF-8 string
 128          * @return string UTF-8 string corresponding to the first letter of input
 129          */
 130         abstract function getFirstLetter( $string );
 131
 132 }