maintenance/compareParserCache.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  * @ingroup Maintenance
  20  */
  21
  22 require_once __DIR__ . '/Maintenance.php';
  23
  24 use MediaWiki\MediaWikiServices;
  25
  26 /**
  27  * @ingroup Maintenance
  28  */
  29 class CompareParserCache extends Maintenance {
  30         public function __construct() {
  31                 parent::__construct();
  32                 $this->addDescription( 'Parse random pages and compare output to cache.' );
  33                 $this->addOption( 'namespace', 'Page namespace number', true, true );
  34                 $this->addOption( 'maxpages', 'Number of pages to try', true, true );
  35         }
  36
  37         public function execute() {
  38                 $pages = $this->getOption( 'maxpages' );
  39
  40                 $dbr = $this->getDB( DB_REPLICA );
  41
  42                 $totalsec = 0.0;
  43                 $scanned = 0;
  44                 $withcache = 0;
  45                 $withdiff = 0;
  46                 $services = MediaWikiServices::getInstance();
  47                 $parserCache = $services->getParserCache();
  48                 $renderer = $services->getRevisionRenderer();
  49                 $wikiPageFactory = $services->getWikiPageFactory();
  50                 while ( $pages-- > 0 ) {
  51                         $row = $dbr->selectRow( 'page',
  52                                 // @todo Title::selectFields() or Title::getQueryInfo() or something
  53                                 [
  54                                         'page_namespace', 'page_title', 'page_id',
  55                                         'page_len', 'page_is_redirect', 'page_latest',
  56                                 ],
  57                                 [
  58                                         'page_namespace' => $this->getOption( 'namespace' ),
  59                                         'page_is_redirect' => 0,
  60                                         'page_random >= ' . wfRandom()
  61                                 ],
  62                                 __METHOD__,
  63                                 [
  64                                         'ORDER BY' => 'page_random',
  65                                 ]
  66                         );
  67
  68                         if ( !$row ) {
  69                                 continue;
  70                         }
  71                         ++$scanned;
  72
  73                         $title = Title::newFromRow( $row );
  74                         $page = $wikiPageFactory->newFromTitle( $title );
  75                         $revision = $page->getRevisionRecord();
  76                         $parserOptions = $page->makeParserOptions( 'canonical' );
  77
  78                         $parserOutputOld = $parserCache->get( $page, $parserOptions );
  79
  80                         if ( $parserOutputOld ) {
  81                                 $t1 = microtime( true );
  82                                 $parserOutputNew = $renderer->getRenderedRevision( $revision, $parserOptions )
  83                                         ->getRevisionParserOutput();
  84
  85                                 $sec = microtime( true ) - $t1;
  86                                 $totalsec += $sec;
  87
  88                                 $this->output( "Parsed '{$title->getPrefixedText()}' in $sec seconds.\n" );
  89
  90                                 $this->output( "Found cache entry found for '{$title->getPrefixedText()}'..." );
  91
  92                                 $oldHtml = trim( preg_replace( '#<!-- .+-->#Us', '', $parserOutputOld->getText() ) );
  93                                 $newHtml = trim( preg_replace( '#<!-- .+-->#Us', '', $parserOutputNew->getText() ) );
  94                                 $diffs = new Diff( explode( "\n", $oldHtml ), explode( "\n", $newHtml ) );
  95                                 $formatter = new UnifiedDiffFormatter();
  96                                 $unifiedDiff = $formatter->format( $diffs );
  97
  98                                 if ( strlen( $unifiedDiff ) ) {
  99                                         $this->output( "differences found:\n\n$unifiedDiff\n\n" );
 100                                         ++$withdiff;
 101                                 } else {
 102                                         $this->output( "No differences found.\n" );
 103                                 }
 104                                 ++$withcache;
 105                         } else {
 106                                 $this->output( "No parser cache entry found for '{$title->getPrefixedText()}'.\n" );
 107                         }
 108                 }
 109
 110                 $ave = $totalsec ? $totalsec / $scanned : 0;
 111                 $this->output( "Checked $scanned pages; $withcache had prior cache entries.\n" );
 112                 $this->output( "Pages with differences found: $withdiff\n" );
 113                 $this->output( "Average parse time: $ave sec\n" );
 114         }
 115 }
 116
 117 $maintClass = CompareParserCache::class;
 118 require_once RUN_MAINTENANCE_IF_MAIN;