[Summary view] [Print] [Text view]

   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(
  40              'l',
  41              'How long the searchindex and revision tables will be locked for',
  42              false,
  43              true
  44          );
  45      }
  46  
  47  	public function getDbType() {
  48          return Maintenance::DB_ADMIN;
  49      }
  50  
  51  	public function execute() {
  52          $maxLockTime = $this->getOption( 'l', 20 );
  53  
  54          $dbw = wfGetDB( DB_MASTER );
  55          if ( $dbw->getType() !== 'mysql' ) {
  56              $this->error( "This change is only needed on MySQL, quitting.\n", true );
  57          }
  58  
  59          $res = $this->findRows( $dbw );
  60          $this->updateSearchIndex( $maxLockTime, array( $this, 'searchIndexUpdateCallback' ), $dbw, $res );
  61  
  62          $this->output( "Done\n" );
  63      }
  64  
  65  	public function searchIndexUpdateCallback( $dbw, $row ) {
  66          return $this->updateSearchIndexForPage( $dbw, $row->si_page );
  67      }
  68  
  69  	private function findRows( $dbw ) {
  70          $searchindex = $dbw->tableName( 'searchindex' );
  71          $regexp = '[[:<:]]u8efbd([89][1-9a]|8[b-f]|90)[[:>:]]';
  72          $sql = "SELECT si_page FROM $searchindex
  73                   WHERE ( si_text RLIKE '$regexp' )
  74                      OR ( si_title RLIKE '$regexp' )";
  75  
  76          return $dbw->query( $sql, __METHOD__ );
  77      }
  78  }
  79  
  80  $maintClass = "UpdateDoubleWidthSearch";
  81  require_once RUN_MAINTENANCE_IF_MAIN;