includes/collation/CustomUppercaseCollation.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  * @since 1.30
  19  *
  20  * @file
  21  */
  22
  23 /**
  24  * Resort normal UTF-8 order by putting a bunch of stuff in PUA
  25  *
  26  * This takes a bunch of characters (The alphabet) that should,
  27  * be together, and converts them all to private-use-area characters
  28  * so that they are all sorted in the right order relative to each
  29  * other.
  30  *
  31  * This renumbers characters starting at U+F3000 (Chosen to avoid
  32  * conflicts with other people using private use area)
  33  *
  34  * This does not support fancy things like secondary differences, etc.
  35  *
  36  * It is expected most people will subclass this and just override the
  37  * constructor to hard-code an alphabet.
  38  */
  39 class CustomUppercaseCollation extends NumericUppercaseCollation {
  40
  41         /** @var array $alphabet Sorted array of letters */
  42         private $alphabet;
  43
  44         /** @var array $puaSubset List of private use area codes */
  45         private $puaSubset;
  46
  47         /**
  48          * @note This assumes $alphabet does not contain U+F3000-U+F303F
  49          *
  50          * @param array $alphabet Sorted array of uppercase characters.
  51          * @param Language $lang What language for number sorting.
  52          */
  53         public function __construct( array $alphabet, Language $lang ) {
  54                 // It'd be trivial to extend this past 64, you'd just
  55                 // need a bit of bit-fiddling. Doesn't seem necessary right
  56                 // now.
  57                 if ( count( $alphabet ) < 1 || count( $alphabet ) >= 64 ) {
  58                         throw new UnexpectedValueException( "Alphabet must be < 64 items" );
  59                 }
  60                 $this->alphabet = $alphabet;
  61
  62                 $this->puaSubset = [];
  63                 $len = count( $alphabet );
  64                 for ( $i = 0; $i < $len; $i++ ) {
  65                         $this->puaSubset[] = "\xF3\xB3\x80" . chr( $i + 128 );
  66                 }
  67                 parent::__construct( $lang );
  68         }
  69
  70         private function convertToPua( $string ) {
  71                 return str_replace( $this->alphabet, $this->puaSubset, $string );
  72         }
  73
  74         public function getSortKey( $string ) {
  75                 return $this->convertToPua( parent::getSortKey( $string ) );
  76         }
  77
  78         public function getFirstLetter( $string ) {
  79                 // In case a title has a PUA code in it, make it sort
  80                 // under the header for the character it would replace
  81                 // to avoid inconsistent behaviour. This class mostly
  82                 // assumes that people will not use PUA codes.
  83                 return parent::getFirstLetter(
  84                         str_replace( $this->puaSubset, $this->alphabet, $string )
  85                 );
  86         }
  87 }