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 comparitive 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  * @package MediaWiki
  28  * @subpackage Maintenance
  29  */
  30
  31 $optionsWithArgs = array( 'report' );
  32
  33 require_once( 'commandLine.inc' );
  34 require_once( 'SpecialImport.php' );
  35
  36 class DumpRenderer {
  37         function __construct( $dir ) {
  38                 $this->stderr = fopen( "php://stderr", "wt" );
  39                 $this->outputDirectory = $dir;
  40                 $this->count = 0;
  41         }
  42
  43         function handleRevision( $rev ) {
  44                 $title = $rev->getTitle();
  45                 if (!$title) {
  46                         fprintf( $this->stderr, "Got bogus revision with null title!" );
  47                         return;
  48                 }
  49                 $display = $title->getPrefixedText();
  50
  51                 $this->count++;
  52
  53                 $sanitized = rawurlencode( $display );
  54                 $filename = sprintf( "%s/wiki-%07d-%s.html",
  55                         $this->outputDirectory,
  56                         $this->count,
  57                         $sanitized );
  58                 fprintf( $this->stderr, "%s\n", $filename, $display );
  59
  60                 // fixme
  61                 $user = new User();
  62                 $parser = new Parser();
  63                 $options = ParserOptions::newFromUser( $user );
  64
  65                 $output = $parser->parse( $rev->getText(), $title, $options );
  66
  67                 file_put_contents( $filename,
  68                         "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" " .
  69                         "\"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n" .
  70                         "<html xmlns=\"http://www.w3.org/1999/xhtml\">\n" .
  71                         "<head>\n" .
  72                         "<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n" .
  73                         "<title>" . htmlspecialchars( $display ) . "</title>\n" .
  74                         "</head>\n" .
  75                         "<body>\n" .
  76                         $output->getText() .
  77                         "</body>\n" .
  78                         "</html>" );
  79         }
  80
  81         function run() {
  82                 $this->startTime = wfTime();
  83
  84                 $file = fopen( 'php://stdin', 'rt' );
  85                 $source = new ImportStreamSource( $file );
  86                 $importer = new WikiImporter( $source );
  87
  88                 $importer->setRevisionCallback(
  89                         array( &$this, 'handleRevision' ) );
  90
  91                 return $importer->doImport();
  92         }
  93 }
  94
  95 if( isset( $options['output-dir'] ) ) {
  96         $dir = $options['output-dir'];
  97 } else {
  98         wfDie( "Must use --output-dir=/some/dir\n" );
  99 }
 100 $render = new DumpRenderer( $dir );
 101 $render->run();
 102
 103 ?>