includes/jobqueue/jobs/ParsoidCachePrewarmJob.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\Logger\LoggerFactory;
  22 use MediaWiki\Page\PageLookup;
  23 use MediaWiki\Page\PageRecord;
  24 use MediaWiki\Page\ParserOutputAccess;
  25 use MediaWiki\Parser\ParserOptions;
  26 use MediaWiki\Parser\Parsoid\Config\SiteConfig as ParsoidSiteConfig;
  27 use MediaWiki\Revision\RevisionLookup;
  28 use MediaWiki\Revision\SlotRecord;
  29 use Psr\Log\LoggerInterface;
  30
  31 /**
  32  * @ingroup JobQueue
  33  * @internal
  34  * @since 1.40
  35  */
  36 class ParsoidCachePrewarmJob extends Job {
  37         private LoggerInterface $logger;
  38         private ParserOutputAccess $parserOutputAccess;
  39         private PageLookup $pageLookup;
  40         private RevisionLookup $revisionLookup;
  41         private ParsoidSiteConfig $parsoidSiteConfig;
  42
  43         /**
  44          * @param array $params
  45          * @param ParserOutputAccess $parserOutputAccess
  46          * @param PageLookup $pageLookup
  47          * @param RevisionLookup $revisionLookup
  48          * @param ParsoidSiteConfig $parsoidSiteConfig
  49          */
  50         public function __construct(
  51                 array $params,
  52                 ParserOutputAccess $parserOutputAccess,
  53                 PageLookup $pageLookup,
  54                 RevisionLookup $revisionLookup,
  55                 ParsoidSiteConfig $parsoidSiteConfig
  56         ) {
  57                 parent::__construct( 'parsoidCachePrewarm', $params );
  58
  59                 // TODO: find a way to inject the logger
  60                 $this->logger = LoggerFactory::getInstance( 'ParsoidCachePrewarmJob' );
  61                 $this->parserOutputAccess = $parserOutputAccess;
  62                 $this->pageLookup = $pageLookup;
  63                 $this->revisionLookup = $revisionLookup;
  64                 $this->parsoidSiteConfig = $parsoidSiteConfig;
  65         }
  66
  67         /**
  68          * @param int $revisionId
  69          * @param PageRecord $page
  70          * @param array $params Additional options for the job. Known keys:
  71          * - causeAction: Indicate what action caused the job to be scheduled. Used for monitoring.
  72          * - options: Flags to be passed to ParserOutputAccess:getParserOutput.
  73          *   May be set to ParserOutputAccess::OPT_FORCE_PARSE to force a parsing even if there
  74          *   already is cached output.
  75          *
  76          * @return JobSpecification
  77          */
  78         public static function newSpec(
  79                 int $revisionId,
  80                 PageRecord $page,
  81                 array $params = []
  82         ): JobSpecification {
  83                 $pageId = $page->getId();
  84                 $pageTouched = $page->getTouched();
  85
  86                 $params += [ 'options' => 0 ];
  87
  88                 $params += self::newRootJobParams(
  89                         "parsoidCachePrewarm:$pageId:$revisionId:$pageTouched:{$params['options']}"
  90                 );
  91
  92                 $opts = [ 'removeDuplicates' => true ];
  93
  94                 return new JobSpecification(
  95                         'parsoidCachePrewarm',
  96                         [
  97                                 'revId' => $revisionId,
  98                                 'pageId' => $pageId,
  99                                 'page_touched' => $pageTouched,
 100                         ] + $params,
 101                         $opts
 102                 );
 103         }
 104
 105         private function doParsoidCacheUpdate() {
 106                 $page = $this->pageLookup->getPageById( $this->params['pageId'] );
 107                 $revId = $this->params['revId'];
 108
 109                 if ( $page === null ) {
 110                         // This happens when the page got deleted in the meantime.
 111                         $this->logger->info( "Page with ID {$this->params['pageId']} not found" );
 112                         return;
 113                 }
 114
 115                 if ( $page->getLatest() !== $revId ) {
 116                         $this->logger->info(
 117                                 'ParsoidCachePrewarmJob: The ID of the new revision does not match the page\'s current revision ID'
 118                         );
 119                         return;
 120                 }
 121
 122                 $rev = $this->revisionLookup->getRevisionById( $revId );
 123                 if ( !$rev ) {
 124                         return;
 125                 }
 126
 127                 $parserOpts = ParserOptions::newFromAnon();
 128                 $parserOpts->setUseParsoid();
 129
 130                 $renderReason = $this->params['causeAction'] ?? $this->command;
 131                 $parserOpts->setRenderReason( $renderReason );
 132
 133                 $mainSlot = $rev->getSlot( SlotRecord::MAIN );
 134                 if ( !$this->parsoidSiteConfig->supportsContentModel( $mainSlot->getModel() ) ) {
 135                         $this->logger->debug( __METHOD__ . ': Parsoid does not support content model ' . $mainSlot->getModel() );
 136                         return;
 137                 }
 138
 139                 $this->logger->debug( __METHOD__ . ': generating Parsoid output' );
 140
 141                 // We may get the OPT_FORCE_PARSE flag this way
 142                 $options = $this->params['options'] ?? 0;
 143
 144                 // getParserOutput() will write to ParserCache.
 145                 $status = $this->parserOutputAccess->getParserOutput(
 146                         $page,
 147                         $parserOpts,
 148                         $rev,
 149                         $options
 150                 );
 151
 152                 if ( !$status->isOK() ) {
 153                         $this->logger->error( __METHOD__ . ': Parsoid error', [
 154                                 'errors' => $status->getErrors(),
 155                                 'page' => $page->getDBkey(),
 156                                 'rev' => $rev->getId(),
 157                         ] );
 158                 }
 159         }
 160
 161         public function run() {
 162                 $this->doParsoidCacheUpdate();
 163
 164                 return true;
 165         }
 166 }