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\Title\Title;
  25 use Wikimedia\Diff\Diff;
  26 use Wikimedia\Diff\UnifiedDiffFormatter;
  27
  28 /**
  29  * @ingroup Maintenance
  30  */
  31 class CompareParserCache extends Maintenance {
  32         public function __construct() {
  33                 parent::__construct();
  34                 $this->addDescription( 'Parse random pages and compare output to cache.' );
  35                 $this->addOption( 'namespace', 'Page namespace number', true, true );
  36                 $this->addOption( 'maxpages', 'Number of pages to try', true, true );
  37         }
  38
  39         public function execute() {
  40                 $pages = $this->getOption( 'maxpages' );
  41
  42                 $dbr = $this->getDB( DB_REPLICA );
  43
  44                 $totalsec = 0.0;
  45                 $scanned = 0;
  46                 $withcache = 0;
  47                 $withdiff = 0;
  48                 $services = $this->getServiceContainer();
  49                 $parserCache = $services->getParserCache();
  50                 $renderer = $services->getRevisionRenderer();
  51                 $wikiPageFactory = $services->getWikiPageFactory();
  52                 while ( $pages-- > 0 ) {
  53                         $row = $dbr->newSelectQueryBuilder()
  54                                 // @todo Title::selectFields() or Title::getQueryInfo() or something
  55                                 ->select( [
  56                                         'page_namespace',
  57                                         'page_title',
  58                                         'page_id',
  59                                         'page_len',
  60                                         'page_is_redirect',
  61                                         'page_latest',
  62                                 ] )
  63                                 ->from( 'page' )
  64                                 ->where( [
  65                                         'page_namespace' => $this->getOption( 'namespace' ),
  66                                         'page_is_redirect' => 0,
  67                                         'page_random >= ' . wfRandom()
  68                                 ] )
  69                                 ->orderBy( 'page_random' )
  70                                 ->caller( __METHOD__ )->fetchRow();
  71
  72                         if ( !$row ) {
  73                                 continue;
  74                         }
  75                         ++$scanned;
  76
  77                         $title = Title::newFromRow( $row );
  78                         $page = $wikiPageFactory->newFromTitle( $title );
  79                         $revision = $page->getRevisionRecord();
  80                         $parserOptions = $page->makeParserOptions( 'canonical' );
  81
  82                         $parserOutputOld = $parserCache->get( $page, $parserOptions );
  83
  84                         if ( $parserOutputOld ) {
  85                                 $t1 = microtime( true );
  86                                 $parserOutputNew = $renderer->getRenderedRevision( $revision, $parserOptions )
  87                                         ->getRevisionParserOutput();
  88
  89                                 $sec = microtime( true ) - $t1;
  90                                 $totalsec += $sec;
  91
  92                                 $this->output( "Parsed '{$title->getPrefixedText()}' in $sec seconds.\n" );
  93
  94                                 $this->output( "Found cache entry found for '{$title->getPrefixedText()}'..." );
  95
  96                                 $oldHtml = trim( preg_replace( '#<!-- .+-->#Us', '', $parserOutputOld->getText() ) );
  97                                 $newHtml = trim( preg_replace( '#<!-- .+-->#Us', '', $parserOutputNew->getText() ) );
  98                                 $diffs = new Diff( explode( "\n", $oldHtml ), explode( "\n", $newHtml ) );
  99                                 $formatter = new UnifiedDiffFormatter();
 100                                 $unifiedDiff = $formatter->format( $diffs );
 101
 102                                 if ( strlen( $unifiedDiff ) ) {
 103                                         $this->output( "differences found:\n\n$unifiedDiff\n\n" );
 104                                         ++$withdiff;
 105                                 } else {
 106                                         $this->output( "No differences found.\n" );
 107                                 }
 108                                 ++$withcache;
 109                         } else {
 110                                 $this->output( "No parser cache entry found for '{$title->getPrefixedText()}'.\n" );
 111                         }
 112                 }
 113
 114                 $ave = $totalsec ? $totalsec / $scanned : 0;
 115                 $this->output( "Checked $scanned pages; $withcache had prior cache entries.\n" );
 116                 $this->output( "Pages with differences found: $withdiff\n" );
 117                 $this->output( "Average parse time: $ave sec\n" );
 118         }
 119 }
 120
 121 $maintClass = CompareParserCache::class;
 122 require_once RUN_MAINTENANCE_IF_MAIN;