summaryrefslogtreecommitdiff
path: root/includes/SpecialExport.php
blob: 1fe2e44b8ff97fc7b31a538b4c893cf27c3ad317 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
<?php
# Copyright (C) 2003 Brion Vibber <brion@pobox.com>
# http://www.mediawiki.org/
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, write to the Free Software Foundation, Inc.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
# http://www.gnu.org/copyleft/gpl.html
/**
 *
 * @addtogroup SpecialPage
 */

function wfExportGetPagesFromCategory( $title ) {
	global $wgContLang;

	$name = $title->getDBkey();

	$dbr = wfGetDB( DB_SLAVE );

	list( $page, $categorylinks ) = $dbr->tableNamesN( 'page', 'categorylinks' );
	$sql = "SELECT page_namespace, page_title FROM $page " .
		"JOIN $categorylinks ON cl_from = page_id " .
		"WHERE cl_to = " . $dbr->addQuotes( $name );

	$pages = array();
	$res = $dbr->query( $sql, 'wfExportGetPagesFromCategory' );
	while ( $row = $dbr->fetchObject( $res ) ) {
		$n = $row->page_title;
		if ($row->page_namespace) {
			$ns = $wgContLang->getNsText( $row->page_namespace );
			$n = $ns . ':' . $n;
		}

		$pages[] = $n;
	}
	$dbr->freeResult($res);

	return $pages;
}

/**
 * Expand a list of pages to include templates used in those pages.
 * @param $inputPages array, list of titles to look up
 * @param $pageSet array, associative array indexed by titles for output
 * @return array associative array index by titles
 */
function wfExportGetTemplates( $inputPages, $pageSet ) {
	return wfExportGetLinks( $inputPages, $pageSet,
		'templatelinks', 
	 	array( 'tl_namespace AS namespace', 'tl_title AS title' ),
		array( 'page_id=tl_from' ) );
}

/**
 * Expand a list of pages to include images used in those pages.
 * @param $inputPages array, list of titles to look up
 * @param $pageSet array, associative array indexed by titles for output
 * @return array associative array index by titles
 */
function wfExportGetImages( $inputPages, $pageSet ) {
	return wfExportGetLinks( $inputPages, $pageSet,
		'imagelinks',
		array( NS_IMAGE . ' AS namespace', 'il_to AS title' ),
		array( 'page_id=il_from' ) );
}

/**
 * Expand a list of pages to include items used in those pages.
 * @private
 */
function wfExportGetLinks( $inputPages, $pageSet, $table, $fields, $join ) {
	$dbr = wfGetDB( DB_SLAVE );
	foreach( $inputPages as $page ) {
		$title = Title::newFromText( $page );
		if( $title ) {
			$pageSet[$title->getPrefixedText()] = true;
			/// @fixme May or may not be more efficient to batch these
			///        by namespace when given multiple input pages.
			$result = $dbr->select(
				array( 'page', $table ),
				$fields,
				array_merge( $join,
					array(
						'page_namespace' => $title->getNamespace(),
						'page_title' => $title->getDbKey() ) ),
				__METHOD__ );
			foreach( $result as $row ) {
				$template = Title::makeTitle( $row->namespace, $row->title );
				$pageSet[$template->getPrefixedText()] = true;
			}
		}
	}
	return $pageSet;
}

/**
 * Callback function to remove empty strings from the pages array.
 */
function wfFilterPage( $page ) {
	return $page !== '' && $page !== null;
}

/**
 *
 */
function wfSpecialExport( $page = '' ) {
	global $wgOut, $wgRequest, $wgSitename, $wgExportAllowListContributors;
	global $wgExportAllowHistory, $wgExportMaxHistory;

	$curonly = true;
	$doexport = false;

	if ( $wgRequest->getCheck( 'addcat' ) ) {
		$page = $wgRequest->getText( 'pages' );
		$catname = $wgRequest->getText( 'catname' );
		
		if ( $catname !== '' && $catname !== NULL && $catname !== false ) {
			$t = Title::makeTitleSafe( NS_CATEGORY, $catname );
			if ( $t ) {
				/**
				 * @fixme This can lead to hitting memory limit for very large
				 * categories. Ideally we would do the lookup synchronously
				 * during the export in a single query.
				 */
				$catpages = wfExportGetPagesFromCategory( $t );
				if ( $catpages ) $page .= "\n" . implode( "\n", $catpages );
			}
		}
	}
	else if( $wgRequest->wasPosted() && $page == '' ) {
		$page = $wgRequest->getText( 'pages' );
		$curonly = $wgRequest->getCheck( 'curonly' );
		$rawOffset = $wgRequest->getVal( 'offset' );
		if( $rawOffset ) {
			$offset = wfTimestamp( TS_MW, $rawOffset );
		} else {
			$offset = null;
		}
		$limit = $wgRequest->getInt( 'limit' );
		$dir = $wgRequest->getVal( 'dir' );
		$history = array(
			'dir' => 'asc',
			'offset' => false,
			'limit' => $wgExportMaxHistory,
		);
		$historyCheck = $wgRequest->getCheck( 'history' );
		if ( $curonly ) {
			$history = WikiExporter::CURRENT;
		} elseif ( !$historyCheck ) {
			if ( $limit > 0 && $limit < $wgExportMaxHistory ) {
				$history['limit'] = $limit;
			}
			if ( !is_null( $offset ) ) {
				$history['offset'] = $offset;
			}
			if ( strtolower( $dir ) == 'desc' ) {
				$history['dir'] = 'desc';
			}
		}
		
		if( $page != '' ) $doexport = true;
	} else {
		// Default to current-only for GET requests
		$page = $wgRequest->getText( 'pages', $page );
		$historyCheck = $wgRequest->getCheck( 'history' );
		if( $historyCheck ) {
			$history = WikiExporter::FULL;
		} else {
			$history = WikiExporter::CURRENT;
		}
		
		if( $page != '' ) $doexport = true;
	}

	if( !$wgExportAllowHistory ) {
		// Override
		$history = WikiExporter::CURRENT;
	}
	
	$list_authors = $wgRequest->getCheck( 'listauthors' );
	if ( !$curonly || !$wgExportAllowListContributors ) $list_authors = false ;
	
	if ( $doexport ) {
		$wgOut->disable();
		
		// Cancel output buffering and gzipping if set
		// This should provide safer streaming for pages with history
		wfResetOutputBuffers();
		header( "Content-type: application/xml; charset=utf-8" );
		if( $wgRequest->getCheck( 'wpDownload' ) ) {
			// Provide a sane filename suggestion
			$filename = urlencode( $wgSitename . '-' . wfTimestampNow() . '.xml' );
			$wgRequest->response()->header( "Content-disposition: attachment;filename={$filename}" );
		}
		
		/* Split up the input and look up linked pages */
		$inputPages = array_filter( explode( "\n", $page ), 'wfFilterPage' );
		$pageSet = array_flip( $inputPages );

		if( $wgRequest->getCheck( 'templates' ) ) {
			$pageSet = wfExportGetTemplates( $inputPages, $pageSet );
		}

		/*
		// Enable this when we can do something useful exporting/importing image information. :)
		if( $wgRequest->getCheck( 'images' ) ) {
			$pageSet = wfExportGetImages( $inputPages, $pageSet );
		}
		*/
		
		$pages = array_keys( $pageSet );
		
		/* Ok, let's get to it... */

		$db = wfGetDB( DB_SLAVE );
		$exporter = new WikiExporter( $db, $history );
		$exporter->list_authors = $list_authors ;
		$exporter->openStream();
		
		foreach( $pages as $page ) {
			/*
			if( $wgExportMaxHistory && !$curonly ) {
				$title = Title::newFromText( $page );
				if( $title ) {
					$count = Revision::countByTitle( $db, $title );
					if( $count > $wgExportMaxHistory ) {
						wfDebug( __FUNCTION__ .
							": Skipped $page, $count revisions too big\n" );
						continue;
					}
				}
			}*/

			#Bug 8824: Only export pages the user can read
			$title = Title::newFromText( $page );
			if( is_null( $title ) ) continue; #TODO: perhaps output an <error> tag or something.
			if( !$title->userCanRead() ) continue; #TODO: perhaps output an <error> tag or something.

			$exporter->pageByTitle( $title );
		}
		
		$exporter->closeStream();
		return;
	}

	$self = SpecialPage::getTitleFor( 'Export' );
	$wgOut->addHtml( wfMsgExt( 'exporttext', 'parse' ) );
	
	$form = Xml::openElement( 'form', array( 'method' => 'post',
		'action' => $self->getLocalUrl( 'action=submit' ) ) );
	
	$form .= Xml::inputLabel( wfMsg( 'export-addcattext' )	, 'catname', 'catname', 40 ) . '&nbsp;';
	$form .= Xml::submitButton( wfMsg( 'export-addcat' ), array( 'name' => 'addcat' ) ) . '<br />';
	
	$form .= Xml::openElement( 'textarea', array( 'name' => 'pages', 'cols' => 40, 'rows' => 10 ) );
	$form .= htmlspecialchars( $page );
	$form .= Xml::closeElement( 'textarea' );
	$form .= '<br />';
	
	if( $wgExportAllowHistory ) {
		$form .= Xml::checkLabel( wfMsg( 'exportcuronly' ), 'curonly', 'curonly', true ) . '<br />';
	} else {
		$wgOut->addHtml( wfMsgExt( 'exportnohistory', 'parse' ) );
	}
	$form .= Xml::checkLabel( wfMsg( 'export-templates' ), 'templates', 'wpExportTemplates', false ) . '<br />';
	// Enable this when we can do something useful exporting/importing image information. :)
	//$form .= Xml::checkLabel( wfMsg( 'export-images' ), 'images', 'wpExportImages', false ) . '<br />';
	$form .= Xml::checkLabel( wfMsg( 'export-download' ), 'wpDownload', 'wpDownload', true ) . '<br />';
	
	$form .= Xml::submitButton( wfMsg( 'export-submit' ) );
	$form .= Xml::closeElement( 'form' );
	$wgOut->addHtml( $form );
}