maintenance/rebuildtextindex.php

   1 <?php
   2 /**
   3  * Rebuild search index table from scratch.  This takes several
   4  * hours, depending on the database size and server configuration.
   5  *
   6  * This is only for MySQL (see bug 9905).
   7  * Postgres is trigger-based and should never need rebuilding.
   8  *
   9  * This program is free software; you can redistribute it and/or modify
  10  * it under the terms of the GNU General Public License as published by
  11  * the Free Software Foundation; either version 2 of the License, or
  12  * (at your option) any later version.
  13  *
  14  * This program is distributed in the hope that it will be useful,
  15  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  16  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  17  * GNU General Public License for more details.
  18  *
  19  * You should have received a copy of the GNU General Public License along
  20  * with this program; if not, write to the Free Software Foundation, Inc.,
  21  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  22  * http://www.gnu.org/copyleft/gpl.html
  23  *
  24  * @ingroup Maintenance
  25  * @todo document
  26  */
  27
  28 require_once( dirname(__FILE__) . '/Maintenance.php' );
  29
  30 class RebuildTextIndex extends Maintenance {
  31
  32         const RTI_CHUNK_SIZE = 500;
  33
  34         public function __construct() {
  35                 parent::__construct();
  36                 $this->mDescription = "Rebuild search index table from scratch";
  37         }
  38
  39         protected function getDbType() {
  40                 return Maintenance::DB_ADMIN;
  41         }
  42
  43         public function execute() {
  44                 global $wgTitle;
  45
  46                 // Only do this for MySQL
  47                 $database = wfGetDB( DB_MASTER );
  48                 if( !$database instanceof DatabaseMysql ) {
  49                         $this->error( "This script is only for MySQL.", true );
  50                 }
  51
  52                 $wgTitle = Title::newFromText( "Rebuild text index script" );
  53
  54                 $this->dropTextIndex( $database );
  55                 $this->doRebuildTextIndex( $database );
  56                 $this->createTextIndex( $database );
  57
  58                 $this->output( "Done.\n" );
  59         }
  60
  61         private function dropTextIndex( &$database ) {
  62                 $searchindex = $database->tableName( 'searchindex' );
  63                 if ( $database->indexExists( "searchindex", "si_title" ) ) {
  64                         $this->output( "Dropping index...\n" );
  65                         $sql = "ALTER TABLE $searchindex DROP INDEX si_title, DROP INDEX si_text";
  66                         $database->query($sql, "dropTextIndex" );
  67                 }
  68         }
  69
  70         private function createTextIndex( &$database ) {
  71                 $searchindex = $database->tableName( 'searchindex' );
  72                 $this->output( "\nRebuild the index...\n" );
  73                 $sql = "ALTER TABLE $searchindex ADD FULLTEXT si_title (si_title), " .
  74                   "ADD FULLTEXT si_text (si_text)";
  75                 $database->query($sql, "createTextIndex" );
  76         }
  77
  78         private function doRebuildTextIndex( &$database ) {
  79                 list ($page, $revision, $text, $searchindex) = $database->tableNamesN( 'page', 'revision', 'text', 'searchindex' );
  80
  81                 $sql = "SELECT MAX(page_id) AS count FROM $page";
  82                 $res = $database->query($sql, "rebuildTextIndex" );
  83                 $s = $database->fetchObject($res);
  84                 $count = $s->count;
  85                 $this->output( "Rebuilding index fields for {$count} pages...\n" );
  86                 $n = 0;
  87
  88                 while ( $n < $count ) {
  89                         $this->output( $n . "\n" );
  90                         $end = $n + self::RTI_CHUNK_SIZE - 1;
  91                         $sql = "SELECT page_id, page_namespace, page_title, old_flags, old_text
  92                                           FROM $page, $revision, $text
  93                                          WHERE page_id BETWEEN $n AND $end
  94                                            AND page_latest=rev_id
  95                                            AND rev_text_id=old_id";
  96                         $res = $database->query($sql, "rebuildTextIndex" );
  97
  98                         foreach( $res as $s ) {
  99                                 $revtext = Revision::getRevisionText( $s );
 100                                 $u = new SearchUpdate( $s->page_id, $s->page_title, $revtext );
 101                                 $u->doUpdate();
 102                         }
 103                         $database->freeResult( $res );
 104                         $n += self::RTI_CHUNK_SIZE;
 105                 }
 106         }
 107 }
 108
 109 $maintClass = "RebuildTextIndex";
 110 require_once( DO_MAINTENANCE );