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