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 require_once __DIR__ . '/dumpIterator.php';
  29
  30 /**
  31  * Maintenance script that takes page text out of an XML dump file and
  32  * preprocesses it to obj.
  33  *
  34  * @ingroup Maintenance
  35  */
  36 class PreprocessDump extends DumpIterator {
  37
  38         /* Variables for dressing up as a parser */
  39         public $mTitle = 'PreprocessDump';
  40         public $mPPNodeCount = 0;
  41
  42         public function getStripList() {
  43                 global $wgParser;
  44
  45                 return $wgParser->getStripList();
  46         }
  47
  48         public function __construct() {
  49                 parent::__construct();
  50                 $this->addOption( 'cache', 'Use and populate the preprocessor cache.', false, false );
  51                 $this->addOption( 'preprocessor', 'Preprocessor to use.', false, false );
  52         }
  53
  54         public function getDbType() {
  55                 return Maintenance::DB_NONE;
  56         }
  57
  58         public function checkOptions() {
  59                 global $wgParser, $wgParserConf, $wgPreprocessorCacheThreshold;
  60
  61                 if ( !$this->hasOption( 'cache' ) ) {
  62                         $wgPreprocessorCacheThreshold = false;
  63                 }
  64
  65                 if ( $this->hasOption( 'preprocessor' ) ) {
  66                         $name = $this->getOption( 'preprocessor' );
  67                 } elseif ( isset( $wgParserConf['preprocessorClass'] ) ) {
  68                         $name = $wgParserConf['preprocessorClass'];
  69                 } else {
  70                         $name = 'Preprocessor_DOM';
  71                 }
  72
  73                 $wgParser->firstCallInit();
  74                 $this->mPreprocessor = new $name( $this );
  75         }
  76
  77         /**
  78          * Callback function for each revision, preprocessToObj()
  79          * @param Revision $rev
  80          */
  81         public function processRevision( $rev ) {
  82                 $content = $rev->getContent( Revision::RAW );
  83
  84                 if ( $content->getModel() !== CONTENT_MODEL_WIKITEXT ) {
  85                         return;
  86                 }
  87
  88                 try {
  89                         $this->mPreprocessor->preprocessToObj( strval( $content->getNativeData() ), 0 );
  90                 } catch ( Exception $e ) {
  91                         $this->error( "Caught exception " . $e->getMessage() . " in "
  92                                 . $rev->getTitle()->getPrefixedText() );
  93                 }
  94         }
  95 }
  96
  97 $maintClass = "PreprocessDump";
  98 require_once RUN_MAINTENANCE_IF_MAIN;