3 * Script to normalize double-byte latin UTF-8 characters
5 * Usage: php updateDoubleWidthSearch.php
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.
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.
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
22 * @ingroup Maintenance
25 require_once( dirname( __FILE__
) . '/Maintenance.php' );
27 class UpdateDoubleWidthSearch
extends Maintenance
{
29 public function __construct() {
30 parent
::__construct();
31 $this->mDescription
= "Script to normalize double-byte latin UTF-8 characters";
32 $this->addOption( 'q', 'quiet', false, true );
33 $this->addOption( 'l', 'How long the searchindex and revision tables will be locked for', false, true );
36 public function getDbType() {
37 return Maintenance
::DB_ADMIN
;
40 public function execute() {
41 $quiet = $this->hasOption( 'q' );
42 $maxLockTime = $this->getOption( 'l', 20 );
45 $dbw = wfGetDB( DB_MASTER
);
46 if ( $dbw->getType() !== 'mysql' ) {
47 $this->output( "This change is only needed on MySQL, quitting.\n" );
51 $res = $this->findRows( $dbw );
52 $this->updateSearchIndex( $maxLockTime, array( $this, 'searchIndexUpdateCallback' ), $dbw, $res );
54 $this->output( "Done\n" );
57 public function searchIndexUpdateCallback( $dbw, $row ) {
58 return $this->updateSearchIndexForPage( $dbw, $row->si_page
);
61 private function findRows( $dbw ) {
62 $searchindex = $dbw->tableName( 'searchindex' );
63 $regexp = '[[:<:]]u8efbd([89][1-9a]|8[b-f]|90)[[:>:]]';
64 $sql = "SELECT si_page FROM $searchindex
65 WHERE ( si_text RLIKE '$regexp' )
66 OR ( si_title RLIKE '$regexp' )";
67 return $dbw->query( $sql, __METHOD__
);
71 $maintClass = "UpdateDoubleWidthSearch";
72 require_once( DO_MAINTENANCE
);