|
1
|
|
|
<?php |
|
2
|
|
|
/** |
|
3
|
|
|
* MediaWiki page data importer. |
|
4
|
|
|
* |
|
5
|
|
|
* Copyright © 2003,2005 Brion Vibber <[email protected]> |
|
6
|
|
|
* https://www.mediawiki.org/ |
|
7
|
|
|
* |
|
8
|
|
|
* This program is free software; you can redistribute it and/or modify |
|
9
|
|
|
* it under the terms of the GNU General Public License as published by |
|
10
|
|
|
* the Free Software Foundation; either version 2 of the License, or |
|
11
|
|
|
* (at your option) any later version. |
|
12
|
|
|
* |
|
13
|
|
|
* This program is distributed in the hope that it will be useful, |
|
14
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
15
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
16
|
|
|
* GNU General Public License for more details. |
|
17
|
|
|
* |
|
18
|
|
|
* You should have received a copy of the GNU General Public License along |
|
19
|
|
|
* with this program; if not, write to the Free Software Foundation, Inc., |
|
20
|
|
|
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
|
21
|
|
|
* http://www.gnu.org/copyleft/gpl.html |
|
22
|
|
|
* |
|
23
|
|
|
* @file |
|
24
|
|
|
* @ingroup SpecialPage |
|
25
|
|
|
*/ |
|
26
|
|
|
|
|
27
|
|
|
/** |
|
28
|
|
|
* Imports a XML dump from a file (either from file upload, files on disk, or HTTP) |
|
29
|
|
|
* @ingroup SpecialPage |
|
30
|
|
|
*/ |
|
31
|
|
|
class ImportStreamSource implements ImportSource { |
|
32
|
|
|
function __construct( $handle ) { |
|
33
|
|
|
$this->mHandle = $handle; |
|
|
|
|
|
|
34
|
|
|
} |
|
35
|
|
|
|
|
36
|
|
|
/** |
|
37
|
|
|
* @return bool |
|
38
|
|
|
*/ |
|
39
|
|
|
function atEnd() { |
|
40
|
|
|
return feof( $this->mHandle ); |
|
41
|
|
|
} |
|
42
|
|
|
|
|
43
|
|
|
/** |
|
44
|
|
|
* @return string |
|
45
|
|
|
*/ |
|
46
|
|
|
function readChunk() { |
|
47
|
|
|
return fread( $this->mHandle, 32768 ); |
|
48
|
|
|
} |
|
49
|
|
|
|
|
50
|
|
|
/** |
|
51
|
|
|
* @param string $filename |
|
52
|
|
|
* @return Status |
|
53
|
|
|
*/ |
|
54
|
|
|
static function newFromFile( $filename ) { |
|
55
|
|
|
MediaWiki\suppressWarnings(); |
|
56
|
|
|
$file = fopen( $filename, 'rt' ); |
|
57
|
|
|
MediaWiki\restoreWarnings(); |
|
58
|
|
|
if ( !$file ) { |
|
59
|
|
|
return Status::newFatal( "importcantopen" ); |
|
60
|
|
|
} |
|
61
|
|
|
return Status::newGood( new ImportStreamSource( $file ) ); |
|
62
|
|
|
} |
|
63
|
|
|
|
|
64
|
|
|
/** |
|
65
|
|
|
* @param string $fieldname |
|
66
|
|
|
* @return Status |
|
67
|
|
|
*/ |
|
68
|
|
|
static function newFromUpload( $fieldname = "xmlimport" ) { |
|
|
|
|
|
|
69
|
|
|
$upload =& $_FILES[$fieldname]; |
|
70
|
|
|
|
|
71
|
|
|
if ( $upload === null || !$upload['name'] ) { |
|
72
|
|
|
return Status::newFatal( 'importnofile' ); |
|
73
|
|
|
} |
|
74
|
|
|
if ( !empty( $upload['error'] ) ) { |
|
75
|
|
|
switch ( $upload['error'] ) { |
|
76
|
|
|
case 1: |
|
77
|
|
|
# The uploaded file exceeds the upload_max_filesize directive in php.ini. |
|
78
|
|
|
return Status::newFatal( 'importuploaderrorsize' ); |
|
79
|
|
|
case 2: |
|
80
|
|
|
# The uploaded file exceeds the MAX_FILE_SIZE directive that |
|
81
|
|
|
# was specified in the HTML form. |
|
82
|
|
|
return Status::newFatal( 'importuploaderrorsize' ); |
|
83
|
|
|
case 3: |
|
84
|
|
|
# The uploaded file was only partially uploaded |
|
85
|
|
|
return Status::newFatal( 'importuploaderrorpartial' ); |
|
86
|
|
|
case 6: |
|
87
|
|
|
# Missing a temporary folder. |
|
88
|
|
|
return Status::newFatal( 'importuploaderrortemp' ); |
|
89
|
|
|
# case else: # Currently impossible |
|
90
|
|
|
} |
|
91
|
|
|
|
|
92
|
|
|
} |
|
93
|
|
|
$fname = $upload['tmp_name']; |
|
94
|
|
|
if ( is_uploaded_file( $fname ) ) { |
|
95
|
|
|
return ImportStreamSource::newFromFile( $fname ); |
|
96
|
|
|
} else { |
|
97
|
|
|
return Status::newFatal( 'importnofile' ); |
|
98
|
|
|
} |
|
99
|
|
|
} |
|
100
|
|
|
|
|
101
|
|
|
/** |
|
102
|
|
|
* @param string $url |
|
103
|
|
|
* @param string $method |
|
104
|
|
|
* @return Status |
|
105
|
|
|
*/ |
|
106
|
|
|
static function newFromURL( $url, $method = 'GET' ) { |
|
107
|
|
|
wfDebug( __METHOD__ . ": opening $url\n" ); |
|
108
|
|
|
# Use the standard HTTP fetch function; it times out |
|
109
|
|
|
# quicker and sorts out user-agent problems which might |
|
110
|
|
|
# otherwise prevent importing from large sites, such |
|
111
|
|
|
# as the Wikimedia cluster, etc. |
|
112
|
|
|
$data = Http::request( $method, $url, [ 'followRedirects' => true ], __METHOD__ ); |
|
113
|
|
|
if ( $data !== false ) { |
|
114
|
|
|
$file = tmpfile(); |
|
115
|
|
|
fwrite( $file, $data ); |
|
116
|
|
|
fflush( $file ); |
|
117
|
|
|
fseek( $file, 0 ); |
|
118
|
|
|
return Status::newGood( new ImportStreamSource( $file ) ); |
|
119
|
|
|
} else { |
|
120
|
|
|
return Status::newFatal( 'importcantopen' ); |
|
121
|
|
|
} |
|
122
|
|
|
} |
|
123
|
|
|
|
|
124
|
|
|
/** |
|
125
|
|
|
* @param string $interwiki |
|
126
|
|
|
* @param string $page |
|
127
|
|
|
* @param bool $history |
|
128
|
|
|
* @param bool $templates |
|
129
|
|
|
* @param int $pageLinkDepth |
|
130
|
|
|
* @return Status |
|
131
|
|
|
*/ |
|
132
|
|
|
public static function newFromInterwiki( $interwiki, $page, $history = false, |
|
133
|
|
|
$templates = false, $pageLinkDepth = 0 |
|
134
|
|
|
) { |
|
135
|
|
|
if ( $page == '' ) { |
|
136
|
|
|
return Status::newFatal( 'import-noarticle' ); |
|
137
|
|
|
} |
|
138
|
|
|
|
|
139
|
|
|
# Look up the first interwiki prefix, and let the foreign site handle |
|
140
|
|
|
# subsequent interwiki prefixes |
|
141
|
|
|
$firstIwPrefix = strtok( $interwiki, ':' ); |
|
142
|
|
|
$firstIw = Interwiki::fetch( $firstIwPrefix ); |
|
143
|
|
|
if ( !$firstIw ) { |
|
144
|
|
|
return Status::newFatal( 'importbadinterwiki' ); |
|
145
|
|
|
} |
|
146
|
|
|
|
|
147
|
|
|
$additionalIwPrefixes = strtok( '' ); |
|
148
|
|
|
if ( $additionalIwPrefixes ) { |
|
149
|
|
|
$additionalIwPrefixes .= ':'; |
|
150
|
|
|
} |
|
151
|
|
|
# Have to do a DB-key replacement ourselves; otherwise spaces get |
|
152
|
|
|
# URL-encoded to +, which is wrong in this case. Similar to logic in |
|
153
|
|
|
# Title::getLocalURL |
|
154
|
|
|
$link = $firstIw->getURL( strtr( "${additionalIwPrefixes}Special:Export/$page", |
|
155
|
|
|
' ', '_' ) ); |
|
156
|
|
|
|
|
157
|
|
|
$params = []; |
|
158
|
|
|
if ( $history ) { |
|
159
|
|
|
$params['history'] = 1; |
|
160
|
|
|
} |
|
161
|
|
|
if ( $templates ) { |
|
162
|
|
|
$params['templates'] = 1; |
|
163
|
|
|
} |
|
164
|
|
|
if ( $pageLinkDepth ) { |
|
165
|
|
|
$params['pagelink-depth'] = $pageLinkDepth; |
|
166
|
|
|
} |
|
167
|
|
|
|
|
168
|
|
|
$url = wfAppendQuery( $link, $params ); |
|
169
|
|
|
# For interwikis, use POST to avoid redirects. |
|
170
|
|
|
return ImportStreamSource::newFromURL( $url, "POST" ); |
|
171
|
|
|
} |
|
172
|
|
|
} |
|
173
|
|
|
|
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: