maintenance/updateSearchIndex.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  * @file
  19  */
  20
  21 use MediaWiki\Maintenance\Maintenance;
  22 use MediaWiki\Revision\SlotRecord;
  23 use MediaWiki\Search\SearchUpdate;
  24 use MediaWiki\Title\Title;
  25 use MediaWiki\WikiMap\WikiMap;
  26 use Wikimedia\Rdbms\IDBAccessObject;
  27
  28 // @codeCoverageIgnoreStart
  29 require_once __DIR__ . '/Maintenance.php';
  30 // @codeCoverageIgnoreEnd
  31
  32 /**
  33  * Periodic off-peak updating of the search index.
  34  *
  35  * Usage: php updateSearchIndex.php [-s START] [-e END] [-p POSFILE] [-l LOCKTIME] [-q]
  36  * Where START is the starting timestamp
  37  * END is the ending timestamp
  38  * POSFILE is a file to load timestamps from and save them to, searchUpdate.WIKI_ID.pos by default
  39  * LOCKTIME is how long the searchindex and revision tables will be locked for
  40  * -q means quiet
  41  *
  42  * @ingroup Search
  43  * @ingroup Maintenance
  44  */
  45 class UpdateSearchIndex extends Maintenance {
  46
  47         public function __construct() {
  48                 parent::__construct();
  49                 $this->addDescription( 'Script for periodic off-peak updating of the search index' );
  50                 $this->addOption( 's', 'Starting timestamp', false, true );
  51                 $this->addOption( 'e', 'Ending timestamp', false, true );
  52                 $this->addOption(
  53                         'p',
  54                         'File for saving/loading timestamps, searchUpdate.WIKI_ID.pos by default',
  55                         false,
  56                         true
  57                 );
  58                 $this->addOption(
  59                         'l',
  60                         'Deprecated, has no effect (formerly lock time)',
  61                         false,
  62                         true
  63                 );
  64         }
  65
  66         public function getDbType() {
  67                 return Maintenance::DB_ADMIN;
  68         }
  69
  70         public function execute() {
  71                 $dbDomain = WikiMap::getCurrentWikiDbDomain()->getId();
  72                 $posFile = $this->getOption( 'p', 'searchUpdate.' . rawurlencode( $dbDomain ) . '.pos' );
  73                 $end = $this->getOption( 'e', wfTimestampNow() );
  74                 if ( $this->hasOption( 's' ) ) {
  75                         $start = $this->getOption( 's' );
  76                 } elseif ( is_readable( $posFile ) ) {
  77                         $start = file_get_contents( $posFile );
  78                 } else {
  79                         $start = wfTimestamp( TS_MW, time() - 86400 );
  80                 }
  81
  82                 $this->doUpdateSearchIndex( $start, $end );
  83                 $file = fopen( $posFile, 'w' );
  84                 if ( $file !== false ) {
  85                         fwrite( $file, $end );
  86                         fclose( $file );
  87                 } else {
  88                         $this->error( "*** Couldn't write to the $posFile!\n" );
  89                 }
  90         }
  91
  92         private function doUpdateSearchIndex( $start, $end ) {
  93                 global $wgDisableSearchUpdate;
  94
  95                 $wgDisableSearchUpdate = false;
  96
  97                 $dbw = $this->getPrimaryDB();
  98
  99                 $this->output( "Updating searchindex between $start and $end\n" );
 100
 101                 # Select entries from recentchanges which are on top and between the specified times
 102                 $start = $dbw->timestamp( $start );
 103                 $end = $dbw->timestamp( $end );
 104
 105                 $res = $dbw->newSelectQueryBuilder()
 106                         ->select( 'rc_cur_id' )
 107                         ->from( 'recentchanges' )
 108                         ->join( 'page', null, 'rc_cur_id=page_id AND rc_this_oldid=page_latest' )
 109                         ->where( [
 110                                 $dbw->expr( 'rc_type', '!=', RC_LOG ),
 111                                 $dbw->expr( 'rc_timestamp', '>=', $start ),
 112                                 $dbw->expr( 'rc_timestamp', '<=', $end ),
 113                         ] )
 114                         ->caller( __METHOD__ )->fetchResultSet();
 115
 116                 foreach ( $res as $row ) {
 117                         $this->updateSearchIndexForPage( (int)$row->rc_cur_id );
 118                 }
 119                 $this->output( "Done\n" );
 120         }
 121
 122         /**
 123          * Update the searchindex table for a given pageid
 124          * @param int $pageId The page ID to update.
 125          * @return null|string
 126          */
 127         private function updateSearchIndexForPage( int $pageId ) {
 128                 // Get current revision
 129                 $rev = $this->getServiceContainer()
 130                         ->getRevisionLookup()
 131                         ->getRevisionByPageId( $pageId, 0, IDBAccessObject::READ_LATEST );
 132                 $title = null;
 133                 if ( $rev ) {
 134                         $titleObj = Title::newFromLinkTarget( $rev->getPageAsLinkTarget() );
 135                         $title = $titleObj->getPrefixedDBkey();
 136                         $this->output( "$title..." );
 137                         # Update searchindex
 138                         $u = new SearchUpdate( $pageId, $titleObj, $rev->getContent( SlotRecord::MAIN ) );
 139                         $u->doUpdate();
 140                         $this->output( "\n" );
 141                 }
 142
 143                 return $title;
 144         }
 145 }
 146
 147 // @codeCoverageIgnoreStart
 148 $maintClass = UpdateSearchIndex::class;
 149 require_once RUN_MAINTENANCE_IF_MAIN;
 150 // @codeCoverageIgnoreEnd