maintenance/renderDump.php

   1 <?php
   2 /**
   3  * Take page text out of an XML dump file and render basic HTML out to files.
   4  * This is *NOT* suitable for publishing or offline use; it's intended for
   5  * running comparative tests of parsing behavior using real-world data.
   6  *
   7  * Templates etc are pulled from the local wiki database, not from the dump.
   8  *
   9  * Copyright (C) 2006 Brion Vibber <brion@pobox.com>
  10  * http://www.mediawiki.org/
  11  *
  12  * This program is free software; you can redistribute it and/or modify
  13  * it under the terms of the GNU General Public License as published by
  14  * the Free Software Foundation; either version 2 of the License, or
  15  * (at your option) any later version.
  16  *
  17  * This program is distributed in the hope that it will be useful,
  18  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  19  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  20  * GNU General Public License for more details.
  21  *
  22  * You should have received a copy of the GNU General Public License along
  23  * with this program; if not, write to the Free Software Foundation, Inc.,
  24  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  25  * http://www.gnu.org/copyleft/gpl.html
  26  *
  27  * @file
  28  * @ingroup Maintenance
  29  */
  30
  31 require_once( "Maintenance.php" );
  32
  33 class DumpRenderer extends Maintenance {
  34
  35         private $count = 0;
  36         private $outputDirectory, $startTime;
  37
  38         public function __construct() {
  39                 parent::__construct();
  40                 $this->mDescription = "Take page text out of an XML dump file and render basic HTML out to files";
  41                 $this->addParam( 'output-dir', 'The directory to output the HTML files to', true, true );
  42         }
  43
  44         public function execute() {
  45                 $this->outputDirectory = $this->getOption( 'output-dir' );
  46                 $this->startTime = wfTime();
  47
  48                 $source = new ImportStreamSource( $this->getStdin() );
  49                 $importer = new WikiImporter( $source );
  50
  51                 $importer->setRevisionCallback(
  52                         array( &$this, 'handleRevision' ) );
  53
  54                 return $importer->doImport();
  55         }
  56
  57         /**
  58          * Callback function for each revision, turn into HTML and save
  59          * @param $rev Revision
  60          */
  61         private function handleRevision( $rev ) {
  62                 $title = $rev->getTitle();
  63                 if (!$title) {
  64                         $this->error( "Got bogus revision with null title!" );
  65                         return;
  66                 }
  67                 $display = $title->getPrefixedText();
  68
  69                 $this->count++;
  70
  71                 $sanitized = rawurlencode( $display );
  72                 $filename = sprintf( "%s/wiki-%07d-%s.html",
  73                         $this->outputDirectory,
  74                         $this->count,
  75                         $sanitized );
  76                 $this->output( sprintf( $this->stderr, "%s\n", $filename, $display ) );
  77
  78                 // fixme (what?)
  79                 $user = new User();
  80                 $parser = new Parser();
  81                 $options = ParserOptions::newFromUser( $user );
  82
  83                 $output = $parser->parse( $rev->getText(), $title, $options );
  84
  85                 file_put_contents( $filename,
  86                         "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" " .
  87                         "\"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n" .
  88                         "<html xmlns=\"http://www.w3.org/1999/xhtml\">\n" .
  89                         "<head>\n" .
  90                         "<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n" .
  91                         "<title>" . htmlspecialchars( $display ) . "</title>\n" .
  92                         "</head>\n" .
  93                         "<body>\n" .
  94                         $output->getText() .
  95                         "</body>\n" .
  96                         "</html>" );
  97         }
  98 }
  99
 100 $maintClass = "DumpRenderer";
 101 require_once( DO_MAINTENANCE );