|
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 <[email protected]> |
|
10
|
|
|
* https://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 __DIR__ . '/Maintenance.php'; |
|
32
|
|
|
|
|
33
|
|
|
/** |
|
34
|
|
|
* Maintenance script that takes page text out of an XML dump file |
|
35
|
|
|
* and render basic HTML out to files. |
|
36
|
|
|
* |
|
37
|
|
|
* @ingroup Maintenance |
|
38
|
|
|
*/ |
|
39
|
|
|
class DumpRenderer extends Maintenance { |
|
40
|
|
|
|
|
41
|
|
|
private $count = 0; |
|
42
|
|
|
private $outputDirectory, $startTime; |
|
43
|
|
|
|
|
44
|
|
|
public function __construct() { |
|
45
|
|
|
parent::__construct(); |
|
46
|
|
|
$this->addDescription( |
|
47
|
|
|
'Take page text out of an XML dump file and render basic HTML out to files' ); |
|
48
|
|
|
$this->addOption( 'output-dir', 'The directory to output the HTML files to', true, true ); |
|
49
|
|
|
$this->addOption( 'prefix', 'Prefix for the rendered files (defaults to wiki)', false, true ); |
|
50
|
|
|
$this->addOption( 'parser', 'Use an alternative parser class', false, true ); |
|
51
|
|
|
} |
|
52
|
|
|
|
|
53
|
|
|
public function execute() { |
|
54
|
|
|
$this->outputDirectory = $this->getOption( 'output-dir' ); |
|
55
|
|
|
$this->prefix = $this->getOption( 'prefix', 'wiki' ); |
|
|
|
|
|
|
56
|
|
|
$this->startTime = microtime( true ); |
|
57
|
|
|
|
|
58
|
|
|
if ( $this->hasOption( 'parser' ) ) { |
|
59
|
|
|
global $wgParserConf; |
|
60
|
|
|
$wgParserConf['class'] = $this->getOption( 'parser' ); |
|
61
|
|
|
$this->prefix .= "-{$wgParserConf['class']}"; |
|
62
|
|
|
} |
|
63
|
|
|
|
|
64
|
|
|
$source = new ImportStreamSource( $this->getStdin() ); |
|
65
|
|
|
$importer = new WikiImporter( $source, $this->getConfig() ); |
|
66
|
|
|
|
|
67
|
|
|
$importer->setRevisionCallback( |
|
68
|
|
|
[ $this, 'handleRevision' ] ); |
|
69
|
|
|
|
|
70
|
|
|
$importer->doImport(); |
|
71
|
|
|
|
|
72
|
|
|
$delta = microtime( true ) - $this->startTime; |
|
73
|
|
|
$this->error( "Rendered {$this->count} pages in " . round( $delta, 2 ) . " seconds " ); |
|
74
|
|
|
if ( $delta > 0 ) { |
|
75
|
|
|
$this->error( round( $this->count / $delta, 2 ) . " pages/sec" ); |
|
76
|
|
|
} |
|
77
|
|
|
$this->error( "\n" ); |
|
78
|
|
|
} |
|
79
|
|
|
|
|
80
|
|
|
/** |
|
81
|
|
|
* Callback function for each revision, turn into HTML and save |
|
82
|
|
|
* @param Revision $rev |
|
83
|
|
|
*/ |
|
84
|
|
|
public function handleRevision( $rev ) { |
|
85
|
|
|
$title = $rev->getTitle(); |
|
86
|
|
|
if ( !$title ) { |
|
87
|
|
|
$this->error( "Got bogus revision with null title!" ); |
|
88
|
|
|
|
|
89
|
|
|
return; |
|
90
|
|
|
} |
|
91
|
|
|
$display = $title->getPrefixedText(); |
|
92
|
|
|
|
|
93
|
|
|
$this->count++; |
|
94
|
|
|
|
|
95
|
|
|
$sanitized = rawurlencode( $display ); |
|
96
|
|
|
$filename = sprintf( "%s/%s-%07d-%s.html", |
|
97
|
|
|
$this->outputDirectory, |
|
98
|
|
|
$this->prefix, |
|
99
|
|
|
$this->count, |
|
100
|
|
|
$sanitized ); |
|
101
|
|
|
$this->output( sprintf( "%s\n", $filename, $display ) ); |
|
102
|
|
|
|
|
103
|
|
|
$user = new User(); |
|
104
|
|
|
$options = ParserOptions::newFromUser( $user ); |
|
105
|
|
|
|
|
106
|
|
|
$content = $rev->getContent(); |
|
107
|
|
|
$output = $content->getParserOutput( $title, null, $options ); |
|
108
|
|
|
|
|
109
|
|
|
file_put_contents( $filename, |
|
110
|
|
|
"<!DOCTYPE html>\n" . |
|
111
|
|
|
"<html lang=\"en\" dir=\"ltr\">\n" . |
|
112
|
|
|
"<head>\n" . |
|
113
|
|
|
"<meta charset=\"UTF-8\" />\n" . |
|
114
|
|
|
"<title>" . htmlspecialchars( $display ) . "</title>\n" . |
|
115
|
|
|
"</head>\n" . |
|
116
|
|
|
"<body>\n" . |
|
117
|
|
|
$output->getText() . |
|
118
|
|
|
"</body>\n" . |
|
119
|
|
|
"</html>" ); |
|
120
|
|
|
} |
|
121
|
|
|
} |
|
122
|
|
|
|
|
123
|
|
|
$maintClass = "DumpRenderer"; |
|
124
|
|
|
require_once RUN_MAINTENANCE_IF_MAIN; |
|
125
|
|
|
|
In PHP it is possible to write to properties without declaring them. For example, the following is perfectly valid PHP code:
Generally, it is a good practice to explictly declare properties to avoid accidental typos and provide IDE auto-completion: