includes/jobqueue/jobs/HTMLCacheUpdateJob.php

   1 <?php
   2 /**
   3  * HTML cache invalidation of all pages linking to a given title.
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License along
  16  * with this program; if not, write to the Free Software Foundation, Inc.,
  17  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18  * http://www.gnu.org/copyleft/gpl.html
  19  *
  20  * @file
  21  * @ingroup Cache
  22  */
  23
  24 /**
  25  * Job to purge the cache for all pages that link to or use another page or file
  26  *
  27  * This job comes in a few variants:
  28  *   - a) Recursive jobs to purge caches for backlink pages for a given title.
  29  *        These jobs have (recursive:true,table:<table>) set.
  30  *   - b) Jobs to purge caches for a set of titles (the job title is ignored).
  31  *            These jobs have (pages:(<page ID>:(<namespace>,<title>),...) set.
  32  *
  33  * @ingroup JobQueue
  34  */
  35 class HTMLCacheUpdateJob extends Job {
  36         function __construct( $title, $params = '' ) {
  37                 parent::__construct( 'htmlCacheUpdate', $title, $params );
  38                 // Base backlink purge jobs can be de-duplicated
  39                 $this->removeDuplicates = ( !isset( $params['range'] ) && !isset( $params['pages'] ) );
  40         }
  41
  42         function run() {
  43                 global $wgUpdateRowsPerJob, $wgUpdateRowsPerQuery;
  44
  45                 if ( isset( $this->params['table'] ) && !isset( $this->params['pages'] ) ) {
  46                         $this->params['recursive'] = true; // b/c; base job
  47                 }
  48
  49                 // Job to purge all (or a range of) backlink pages for a page
  50                 if ( !empty( $this->params['recursive'] ) ) {
  51                         // Convert this into no more than $wgUpdateRowsPerJob HTMLCacheUpdateJob per-title
  52                         // jobs and possibly a recursive HTMLCacheUpdateJob job for the rest of the backlinks
  53                         $jobs = BacklinkJobUtils::partitionBacklinkJob(
  54                                 $this,
  55                                 $wgUpdateRowsPerJob,
  56                                 $wgUpdateRowsPerQuery, // jobs-per-title
  57                                 // Carry over information for de-duplication
  58                                 array( 'params' => $this->getRootJobParams() )
  59                         );
  60                         JobQueueGroup::singleton()->push( $jobs );
  61                 // Job to purge pages for a set of titles
  62                 } elseif ( isset( $this->params['pages'] ) ) {
  63                         $this->invalidateTitles( $this->params['pages'] );
  64                 // Job to update a single title
  65                 } else {
  66                         $t = $this->title;
  67                         $this->invalidateTitles( array(
  68                                 $t->getArticleID() => array( $t->getNamespace(), $t->getDBkey() )
  69                         ) );
  70                 }
  71
  72                 return true;
  73         }
  74
  75         /**
  76          * @param array $pages Map of (page ID => (namespace, DB key)) entries
  77          */
  78         protected function invalidateTitles( array $pages ) {
  79                 global $wgUpdateRowsPerQuery, $wgUseFileCache, $wgUseSquid;
  80
  81                 // Get all page IDs in this query into an array
  82                 $pageIds = array_keys( $pages );
  83                 if ( !$pageIds ) {
  84                         return;
  85                 }
  86
  87                 $dbw = wfGetDB( DB_MASTER );
  88
  89                 // The page_touched field will need to be bumped for these pages.
  90                 // Only bump it to the present time if no "rootJobTimestamp" was known.
  91                 // If it is known, it can be used instead, which avoids invalidating output
  92                 // that was in fact generated *after* the relevant dependency change time
  93                 // (e.g. template edit). This is particularily useful since refreshLinks jobs
  94                 // save back parser output and usually run along side htmlCacheUpdate jobs;
  95                 // their saved output would be invalidated by using the current timestamp.
  96                 if ( isset( $this->params['rootJobTimestamp'] ) ) {
  97                         $touchTimestamp = $this->params['rootJobTimestamp'];
  98                 } else {
  99                         $touchTimestamp = wfTimestampNow();
 100                 }
 101
 102                 // Update page_touched (skipping pages already touched since the root job).
 103                 // Check $wgUpdateRowsPerQuery for sanity; batch jobs are sized by that already.
 104                 foreach ( array_chunk( $pageIds, $wgUpdateRowsPerQuery ) as $batch ) {
 105                         $dbw->update( 'page',
 106                                 array( 'page_touched' => $dbw->timestamp( $touchTimestamp ) ),
 107                                 array( 'page_id' => $batch,
 108                                         // don't invalidated pages that were already invalidated
 109                                         "page_touched < " . $dbw->addQuotes( $dbw->timestamp( $touchTimestamp ) )
 110                                 ),
 111                                 __METHOD__
 112                         );
 113                 }
 114                 // Get the list of affected pages (races only mean something else did the purge)
 115                 $titleArray = TitleArray::newFromResult( $dbw->select(
 116                         'page',
 117                         array( 'page_namespace', 'page_title' ),
 118                         array( 'page_id' => $pageIds, 'page_touched' => $dbw->timestamp( $touchTimestamp ) ),
 119                         __METHOD__
 120                 ) );
 121
 122                 // Update squid
 123                 if ( $wgUseSquid ) {
 124                         $u = SquidUpdate::newFromTitles( $titleArray );
 125                         $u->doUpdate();
 126                 }
 127
 128                 // Update file cache
 129                 if ( $wgUseFileCache ) {
 130                         foreach ( $titleArray as $title ) {
 131                                 HTMLFileCache::clearFileCache( $title );
 132                         }
 133                 }
 134         }
 135
 136         public function workItemCount() {
 137                 return isset( $this->params['pages'] ) ? count( $this->params['pages'] ) : 1;
 138         }
 139 }