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  * (It supports digraphs, trigraphs etc. though.)
  36  *
  37  * It is expected most people will subclass this and just override the
  38  * constructor to hard-code an alphabet.
  39  */
  40 class CustomUppercaseCollation extends NumericUppercaseCollation {
  41
  42         /** @var array $alphabet Sorted array of letters */
  43         private $alphabet;
  44
  45         /** @var array $puaSubset List of private use area codes */
  46         private $puaSubset;
  47
  48         /** @var array */
  49         private $firstLetters;
  50
  51         /**
  52          * @note This assumes $alphabet does not contain U+F3000-U+F3FFF
  53          *
  54          * @param array $alphabet Sorted array of uppercase characters.
  55          * @param Language $lang What language for number sorting.
  56          */
  57         public function __construct( array $alphabet, Language $lang ) {
  58                 if ( count( $alphabet ) < 1 || count( $alphabet ) >= 4096 ) {
  59                         throw new UnexpectedValueException( "Alphabet must be < 4096 items" );
  60                 }
  61                 $this->firstLetters = $alphabet;
  62                 // For digraphs, only the first letter is capitalized in input
  63                 $this->alphabet = array_map( [ $lang, 'uc' ], $alphabet );
  64
  65                 $this->puaSubset = [];
  66                 $len = count( $alphabet );
  67                 for ( $i = 0; $i < $len; $i++ ) {
  68                         $this->puaSubset[] = "\xF3\xB3" . chr( floor( $i / 64 ) + 128 ) . chr( ( $i % 64 ) + 128 );
  69                 }
  70
  71                 // Sort these arrays so that any trigraphs, digraphs etc. are first
  72                 // (and they get replaced first in convertToPua()).
  73                 $lengths = array_map( 'mb_strlen', $this->alphabet );
  74                 array_multisort( $lengths, SORT_DESC, $this->firstLetters, $this->alphabet, $this->puaSubset );
  75
  76                 parent::__construct( $lang );
  77         }
  78
  79         private function convertToPua( $string ) {
  80                 return str_replace( $this->alphabet, $this->puaSubset, $string );
  81         }
  82
  83         public function getSortKey( $string ) {
  84                 return $this->convertToPua( parent::getSortKey( $string ) );
  85         }
  86
  87         public function getFirstLetter( $string ) {
  88                 $sortkey = $this->getSortKey( $string );
  89
  90                 // In case a title begins with a character from our alphabet, return the corresponding
  91                 // first-letter. (This also happens if the title has a corresponding PUA code in it, to avoid
  92                 // inconsistent behaviour. This class mostly assumes that people will not use PUA codes.)
  93                 $index = array_search( substr( $sortkey, 0, 4 ), $this->puaSubset );
  94                 if ( $index !== false ) {
  95                         return $this->firstLetters[ $index ];
  96                 }
  97
  98                 // String begins with a character outside of our alphabet, fall back
  99                 return parent::getFirstLetter( $string );
 100         }
 101 }