3 * Periodic off-peak updating of the search index.
5 * Usage: php updateSearchIndex.php [-s START] [-e END] [-p POSFILE] [-l LOCKTIME] [-q]
6 * Where START is the starting timestamp
7 * END is the ending timestamp
8 * POSFILE is a file to load timestamps from and save them to, searchUpdate.WIKI_ID.pos by default
9 * LOCKTIME is how long the searchindex and revision tables will be locked for
12 * This program is free software; you can redistribute it and/or modify
13 * it under the terms of the GNU General Public License as published by
14 * the Free Software Foundation; either version 2 of the License, or
15 * (at your option) any later version.
17 * This program is distributed in the hope that it will be useful,
18 * but WITHOUT ANY WARRANTY; without even the implied warranty of
19 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
20 * GNU General Public License for more details.
22 * You should have received a copy of the GNU General Public License along
23 * with this program; if not, write to the Free Software Foundation, Inc.,
24 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
25 * http://www.gnu.org/copyleft/gpl.html
28 * @ingroup Maintenance
31 require_once __DIR__
. '/Maintenance.php';
34 * Maintenance script for periodic off-peak updating of the search index.
36 * @ingroup Maintenance
38 class UpdateSearchIndex
extends Maintenance
{
40 public function __construct() {
41 parent
::__construct();
42 $this->addDescription( 'Script for periodic off-peak updating of the search index' );
43 $this->addOption( 's', 'starting timestamp', false, true );
44 $this->addOption( 'e', 'Ending timestamp', false, true );
47 'File for saving/loading timestamps, searchUpdate.WIKI_ID.pos by default',
53 'How long the searchindex and revision tables will be locked for',
59 public function getDbType() {
60 return Maintenance
::DB_ADMIN
;
63 public function execute() {
64 $dbDomain = WikiMap
::getCurrentWikiDbDomain()->getId();
65 $posFile = $this->getOption( 'p', 'searchUpdate.' . rawurlencode( $dbDomain ) . '.pos' );
66 $end = $this->getOption( 'e', wfTimestampNow() );
67 if ( $this->hasOption( 's' ) ) {
68 $start = $this->getOption( 's' );
69 } elseif ( is_readable( 'searchUpdate.pos' ) ) {
70 # B/c to the old position file name which was hardcoded
71 # We can safely delete the file when we're done though.
72 $start = file_get_contents( 'searchUpdate.pos' );
73 unlink( 'searchUpdate.pos' );
74 } elseif ( is_readable( $posFile ) ) {
75 $start = file_get_contents( $posFile );
77 $start = wfTimestamp( TS_MW
, time() - 86400 );
79 $lockTime = $this->getOption( 'l', 20 );
81 $this->doUpdateSearchIndex( $start, $end, $lockTime );
82 if ( is_writable( dirname( realpath( $posFile ) ) ) ) {
83 $file = fopen( $posFile, 'w' );
84 if ( $file !== false ) {
85 fwrite( $file, $end );
88 $this->error( "*** Couldn't write to the $posFile!\n" );
91 $this->error( "*** Couldn't write to the $posFile!\n" );
95 private function doUpdateSearchIndex( $start, $end, $maxLockTime ) {
96 global $wgDisableSearchUpdate;
98 $wgDisableSearchUpdate = false;
100 $dbw = $this->getDB( DB_MASTER
);
101 $recentchanges = $dbw->tableName( 'recentchanges' );
103 $this->output( "Updating searchindex between $start and $end\n" );
105 # Select entries from recentchanges which are on top and between the specified times
106 $start = $dbw->timestamp( $start );
107 $end = $dbw->timestamp( $end );
109 $page = $dbw->tableName( 'page' );
110 $sql = "SELECT rc_cur_id FROM $recentchanges
111 JOIN $page ON rc_cur_id=page_id AND rc_this_oldid=page_latest
112 WHERE rc_type != " . RC_LOG
. " AND rc_timestamp BETWEEN '$start' AND '$end'";
113 $res = $dbw->query( $sql, __METHOD__
);
115 $this->updateSearchIndex( $maxLockTime, [ $this, 'searchIndexUpdateCallback' ], $dbw, $res );
117 $this->output( "Done\n" );
120 public function searchIndexUpdateCallback( $dbw, $row ) {
121 $this->updateSearchIndexForPage( $dbw, $row->rc_cur_id
);
125 $maintClass = UpdateSearchIndex
::class;
126 require_once RUN_MAINTENANCE_IF_MAIN
;