maintenance/preprocessDump.php

   1 <?php
   2 /**
   3  * Take page text out of an XML dump file and preprocess it to obj.
   4  * It may be useful for getting preprocessor statistics or filling the
   5  * preprocessor cache.
   6  *
   7  * Copyright © 2011 Platonides - https://www.mediawiki.org/
   8  *
   9  * This program is free software; you can redistribute it and/or modify
  10  * it under the terms of the GNU General Public License as published by
  11  * the Free Software Foundation; either version 2 of the License, or
  12  * (at your option) any later version.
  13  *
  14  * This program is distributed in the hope that it will be useful,
  15  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  16  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  17  * GNU General Public License for more details.
  18  *
  19  * You should have received a copy of the GNU General Public License along
  20  * with this program; if not, write to the Free Software Foundation, Inc.,
  21  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  22  * http://www.gnu.org/copyleft/gpl.html
  23  *
  24  * @file
  25  * @ingroup Maintenance
  26  */
  27
  28 use MediaWiki\MediaWikiServices;
  29 use MediaWiki\Storage\RevisionRecord;
  30
  31 require_once __DIR__ . '/dumpIterator.php';
  32
  33 /**
  34  * Maintenance script that takes page text out of an XML dump file and
  35  * preprocesses it to obj.
  36  *
  37  * @ingroup Maintenance
  38  */
  39 class PreprocessDump extends DumpIterator {
  40
  41         /* Variables for dressing up as a parser */
  42         public $mTitle = 'PreprocessDump';
  43         public $mPPNodeCount = 0;
  44         /** @var Preprocessor */
  45         public $mPreprocessor;
  46
  47         public function getStripList() {
  48                 $parser = MediaWikiServices::getInstance()->getParser();
  49
  50                 return $parser->getStripList();
  51         }
  52
  53         public function __construct() {
  54                 parent::__construct();
  55                 $this->addOption( 'cache', 'Use and populate the preprocessor cache.', false, false );
  56                 $this->addOption( 'preprocessor', 'Preprocessor to use.', false, false );
  57         }
  58
  59         public function getDbType() {
  60                 return Maintenance::DB_NONE;
  61         }
  62
  63         public function checkOptions() {
  64                 global $wgParserConf, $wgPreprocessorCacheThreshold;
  65
  66                 if ( !$this->hasOption( 'cache' ) ) {
  67                         $wgPreprocessorCacheThreshold = false;
  68                 }
  69
  70                 if ( $this->hasOption( 'preprocessor' ) ) {
  71                         $name = $this->getOption( 'preprocessor' );
  72                 } elseif ( isset( $wgParserConf['preprocessorClass'] ) ) {
  73                         $name = $wgParserConf['preprocessorClass'];
  74                 } else {
  75                         $name = Preprocessor_DOM::class;
  76                 }
  77
  78                 $parser = MediaWikiServices::getInstance()->getParser();
  79                 $parser->firstCallInit();
  80                 $this->mPreprocessor = new $name( $parser );
  81         }
  82
  83         /**
  84          * Callback function for each revision, preprocessToObj()
  85          * @param Revision $rev
  86          */
  87         public function processRevision( $rev ) {
  88                 $content = $rev->getContent( RevisionRecord::RAW );
  89
  90                 if ( $content->getModel() !== CONTENT_MODEL_WIKITEXT ) {
  91                         return;
  92                 }
  93                 /** @var WikitextContent $content */
  94                 '@phan-var WikitextContent $content';
  95
  96                 try {
  97                         $this->mPreprocessor->preprocessToObj( strval( $content->getText() ), 0 );
  98                 } catch ( Exception $e ) {
  99                         $this->error( "Caught exception " . $e->getMessage() . " in "
 100                                 . $rev->getTitle()->getPrefixedText() );
 101                 }
 102         }
 103 }
 104
 105 $maintClass = PreprocessDump::class;
 106 require_once RUN_MAINTENANCE_IF_MAIN;