maintenance/updateDoubleWidthSearch.php

   1 <?php
   2 /**
   3  * Normalize double-byte latin UTF-8 characters
   4  *
   5  * Usage: php updateDoubleWidthSearch.php
   6  *
   7  * This program is free software; you can redistribute it and/or modify
   8  * it under the terms of the GNU General Public License as published by
   9  * the Free Software Foundation; either version 2 of the License, or
  10  * (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful,
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License along
  18  * with this program; if not, write to the Free Software Foundation, Inc.,
  19  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  20  * http://www.gnu.org/copyleft/gpl.html
  21  *
  22  * @file
  23  * @ingroup Maintenance
  24  */
  25
  26 require_once( __DIR__ . '/Maintenance.php' );
  27
  28 /**
  29  * Maintenance script to normalize double-byte latin UTF-8 characters.
  30  *
  31  * @ingroup Maintenance
  32  */
  33 class UpdateDoubleWidthSearch extends Maintenance {
  34
  35         public function __construct() {
  36                 parent::__construct();
  37                 $this->mDescription = "Script to normalize double-byte latin UTF-8 characters";
  38                 $this->addOption( 'q', 'quiet', false, true );
  39                 $this->addOption( 'l', 'How long the searchindex and revision tables will be locked for', false, true );
  40         }
  41
  42         public function getDbType() {
  43                 return Maintenance::DB_ADMIN;
  44         }
  45
  46         public function execute() {
  47                 $maxLockTime = $this->getOption( 'l', 20 );
  48
  49                 $dbw = wfGetDB( DB_MASTER );
  50                 if ( $dbw->getType() !== 'mysql' ) {
  51                         $this->error( "This change is only needed on MySQL, quitting.\n", true );
  52                 }
  53
  54                 $res = $this->findRows( $dbw );
  55                 $this->updateSearchIndex( $maxLockTime, array( $this, 'searchIndexUpdateCallback' ), $dbw, $res );
  56
  57                 $this->output( "Done\n" );
  58         }
  59
  60         public function searchIndexUpdateCallback( $dbw, $row ) {
  61                 return $this->updateSearchIndexForPage( $dbw, $row->si_page );
  62         }
  63
  64         private function findRows( $dbw ) {
  65                 $searchindex = $dbw->tableName( 'searchindex' );
  66                 $regexp = '[[:<:]]u8efbd([89][1-9a]|8[b-f]|90)[[:>:]]';
  67                 $sql = "SELECT si_page FROM $searchindex
  68                                  WHERE ( si_text RLIKE '$regexp' )
  69                                         OR ( si_title RLIKE '$regexp' )";
  70                 return $dbw->query( $sql, __METHOD__ );
  71         }
  72 }
  73
  74 $maintClass = "UpdateDoubleWidthSearch";
  75 require_once( RUN_MAINTENANCE_IF_MAIN );