1<?php
2/**
3 * Base code for update jobs that put some secondary data extracted
4 * from article content into the database.
5 *
6 * This program is free software; you can redistribute it and/or modify
7 * it under the terms of the GNU General Public License as published by
8 * the Free Software Foundation; either version 2 of the License, or
9 * (at your option) any later version.
10 *
11 * This program is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 * GNU General Public License for more details.
15 *
16 * You should have received a copy of the GNU General Public License along
17 * with this program; if not, write to the Free Software Foundation, Inc.,
18 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
19 * http://www.gnu.org/copyleft/gpl.html
20 *
21 * @file
22 */
23use MediaWiki\MediaWikiServices;
24use Wikimedia\Rdbms\IDatabase;
25
26class PurgeJobUtils {
27	/**
28	 * Invalidate the cache of a list of pages from a single namespace.
29	 * This is intended for use by subclasses.
30	 *
31	 * @param IDatabase $dbw
32	 * @param int $namespace Namespace number
33	 * @param string[] $dbkeys
34	 */
35	public static function invalidatePages( IDatabase $dbw, $namespace, array $dbkeys ) {
36		if ( $dbkeys === [] ) {
37			return;
38		}
39		$fname = __METHOD__;
40
41		DeferredUpdates::addUpdate( new AutoCommitUpdate(
42			$dbw,
43			__METHOD__,
44			static function () use ( $dbw, $namespace, $dbkeys, $fname ) {
45				$services = MediaWikiServices::getInstance();
46				$lbFactory = $services->getDBLoadBalancerFactory();
47				// Determine which pages need to be updated.
48				// This is necessary to prevent the job queue from smashing the DB with
49				// large numbers of concurrent invalidations of the same page.
50				$now = $dbw->timestamp();
51				$ids = $dbw->selectFieldValues(
52					'page',
53					'page_id',
54					[
55						'page_namespace' => $namespace,
56						'page_title' => $dbkeys,
57						'page_touched < ' . $dbw->addQuotes( $now )
58					],
59					$fname
60				);
61
62				if ( !$ids ) {
63					return;
64				}
65
66				$batchSize = $services->getMainConfig()->get( 'UpdateRowsPerQuery' );
67				$ticket = $lbFactory->getEmptyTransactionTicket( $fname );
68				$idBatches = array_chunk( $ids, $batchSize );
69				foreach ( $idBatches as $idBatch ) {
70					$dbw->update(
71						'page',
72						[ 'page_touched' => $now ],
73						[
74							'page_id' => $idBatch,
75							'page_touched < ' . $dbw->addQuotes( $now ) // handle races
76						],
77						$fname
78					);
79					if ( count( $idBatches ) > 1 ) {
80						$lbFactory->commitAndWaitForReplication( $fname, $ticket );
81					}
82				}
83			}
84		) );
85	}
86}
87