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
  30 require_once __DIR__ . '/dumpIterator.php';
  31
  32 /**
  33  * Maintenance script that takes page text out of an XML dump file and
  34  * preprocesses it to obj.
  35  *
  36  * @ingroup Maintenance
  37  */
  38 class PreprocessDump extends DumpIterator {
  39
  40         /* Variables for dressing up as a parser */
  41         public $mTitle = 'PreprocessDump';
  42         public $mPPNodeCount = 0;
  43
  44         public function getStripList() {
  45                 $parser = MediaWikiServices::getInstance()->getParser();
  46
  47                 return $parser->getStripList();
  48         }
  49
  50         public function __construct() {
  51                 parent::__construct();
  52                 $this->addOption( 'cache', 'Use and populate the preprocessor cache.', false, false );
  53                 $this->addOption( 'preprocessor', 'Preprocessor to use.', false, false );
  54         }
  55
  56         public function getDbType() {
  57                 return Maintenance::DB_NONE;
  58         }
  59
  60         public function checkOptions() {
  61                 global $wgParser, $wgParserConf, $wgPreprocessorCacheThreshold;
  62
  63                 if ( !$this->hasOption( 'cache' ) ) {
  64                         $wgPreprocessorCacheThreshold = false;
  65                 }
  66
  67                 if ( $this->hasOption( 'preprocessor' ) ) {
  68                         $name = $this->getOption( 'preprocessor' );
  69                 } elseif ( isset( $wgParserConf['preprocessorClass'] ) ) {
  70                         $name = $wgParserConf['preprocessorClass'];
  71                 } else {
  72                         $name = Preprocessor_DOM::class;
  73                 }
  74
  75                 $wgParser->firstCallInit();
  76                 $this->mPreprocessor = new $name( $this );
  77         }
  78
  79         /**
  80          * Callback function for each revision, preprocessToObj()
  81          * @param Revision $rev
  82          */
  83         public function processRevision( $rev ) {
  84                 $content = $rev->getContent( Revision::RAW );
  85
  86                 if ( $content->getModel() !== CONTENT_MODEL_WIKITEXT ) {
  87                         return;
  88                 }
  89
  90                 try {
  91                         $this->mPreprocessor->preprocessToObj( strval( $content->getText() ), 0 );
  92                 } catch ( Exception $e ) {
  93                         $this->error( "Caught exception " . $e->getMessage() . " in "
  94                                 . $rev->getTitle()->getPrefixedText() );
  95                 }
  96         }
  97 }
  98
  99 $maintClass = PreprocessDump::class;
 100 require_once RUN_MAINTENANCE_IF_MAIN;