includes/SpecialExport.php

   1 <?php
   2 # Copyright (C) 2003 Brion Vibber <brion@pobox.com>
   3 # http://www.mediawiki.org/
   4 #
   5 # This program is free software; you can redistribute it and/or modify
   6 # it under the terms of the GNU General Public License as published by
   7 # the Free Software Foundation; either version 2 of the License, or
   8 # (at your option) any later version.
   9 #
  10 # This program is distributed in the hope that it will be useful,
  11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13 # GNU General Public License for more details.
  14 #
  15 # You should have received a copy of the GNU General Public License along
  16 # with this program; if not, write to the Free Software Foundation, Inc.,
  17 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18 # http://www.gnu.org/copyleft/gpl.html
  19 /**
  20  * @file
  21  * @ingroup SpecialPage
  22  */
  23
  24 function wfExportGetPagesFromCategory( $title ) {
  25         global $wgContLang;
  26
  27         $name = $title->getDBkey();
  28
  29         $dbr = wfGetDB( DB_SLAVE );
  30
  31         list( $page, $categorylinks ) = $dbr->tableNamesN( 'page', 'categorylinks' );
  32         $sql = "SELECT page_namespace, page_title FROM $page " .
  33                 "JOIN $categorylinks ON cl_from = page_id " .
  34                 "WHERE cl_to = " . $dbr->addQuotes( $name );
  35
  36         $pages = array();
  37         $res = $dbr->query( $sql, 'wfExportGetPagesFromCategory' );
  38         while ( $row = $dbr->fetchObject( $res ) ) {
  39                 $n = $row->page_title;
  40                 if ($row->page_namespace) {
  41                         $ns = $wgContLang->getNsText( $row->page_namespace );
  42                         $n = $ns . ':' . $n;
  43                 }
  44
  45                 $pages[] = $n;
  46         }
  47         $dbr->freeResult($res);
  48
  49         return $pages;
  50 }
  51
  52 /**
  53  * Expand a list of pages to include templates used in those pages.
  54  * @param $inputPages array, list of titles to look up
  55  * @param $pageSet array, associative array indexed by titles for output
  56  * @return array associative array index by titles
  57  */
  58 function wfExportGetTemplates( $inputPages, $pageSet ) {
  59         return wfExportGetLinks( $inputPages, $pageSet,
  60                 'templatelinks',
  61                 array( 'tl_namespace AS namespace', 'tl_title AS title' ),
  62                 array( 'page_id=tl_from' ) );
  63 }
  64
  65 /**
  66  * Expand a list of pages to include images used in those pages.
  67  * @param $inputPages array, list of titles to look up
  68  * @param $pageSet array, associative array indexed by titles for output
  69  * @return array associative array index by titles
  70  */
  71 function wfExportGetImages( $inputPages, $pageSet ) {
  72         return wfExportGetLinks( $inputPages, $pageSet,
  73                 'imagelinks',
  74                 array( NS_IMAGE . ' AS namespace', 'il_to AS title' ),
  75                 array( 'page_id=il_from' ) );
  76 }
  77
  78 /**
  79  * Expand a list of pages to include items used in those pages.
  80  * @private
  81  */
  82 function wfExportGetLinks( $inputPages, $pageSet, $table, $fields, $join ) {
  83         $dbr = wfGetDB( DB_SLAVE );
  84         foreach( $inputPages as $page ) {
  85                 $title = Title::newFromText( $page );
  86                 if( $title ) {
  87                         $pageSet[$title->getPrefixedText()] = true;
  88                         /// @fixme May or may not be more efficient to batch these
  89                         ///        by namespace when given multiple input pages.
  90                         $result = $dbr->select(
  91                                 array( 'page', $table ),
  92                                 $fields,
  93                                 array_merge( $join,
  94                                         array(
  95                                                 'page_namespace' => $title->getNamespace(),
  96                                                 'page_title' => $title->getDbKey() ) ),
  97                                 __METHOD__ );
  98                         foreach( $result as $row ) {
  99                                 $template = Title::makeTitle( $row->namespace, $row->title );
 100                                 $pageSet[$template->getPrefixedText()] = true;
 101                         }
 102                 }
 103         }
 104         return $pageSet;
 105 }
 106
 107 /**
 108  * Callback function to remove empty strings from the pages array.
 109  */
 110 function wfFilterPage( $page ) {
 111         return $page !== '' && $page !== null;
 112 }
 113
 114 /**
 115  *
 116  */
 117 function wfSpecialExport( $page = '' ) {
 118         global $wgOut, $wgRequest, $wgSitename, $wgExportAllowListContributors;
 119         global $wgExportAllowHistory, $wgExportMaxHistory;
 120
 121         $curonly = true;
 122         $doexport = false;
 123
 124         if ( $wgRequest->getCheck( 'addcat' ) ) {
 125                 $page = $wgRequest->getText( 'pages' );
 126                 $catname = $wgRequest->getText( 'catname' );
 127
 128                 if ( $catname !== '' && $catname !== NULL && $catname !== false ) {
 129                         $t = Title::makeTitleSafe( NS_CATEGORY, $catname );
 130                         if ( $t ) {
 131                                 /**
 132                                  * @fixme This can lead to hitting memory limit for very large
 133                                  * categories. Ideally we would do the lookup synchronously
 134                                  * during the export in a single query.
 135                                  */
 136                                 $catpages = wfExportGetPagesFromCategory( $t );
 137                                 if ( $catpages ) $page .= "\n" . implode( "\n", $catpages );
 138                         }
 139                 }
 140         }
 141         else if( $wgRequest->wasPosted() && $page == '' ) {
 142                 $page = $wgRequest->getText( 'pages' );
 143                 $curonly = $wgRequest->getCheck( 'curonly' );
 144                 $rawOffset = $wgRequest->getVal( 'offset' );
 145                 if( $rawOffset ) {
 146                         $offset = wfTimestamp( TS_MW, $rawOffset );
 147                 } else {
 148                         $offset = null;
 149                 }
 150                 $limit = $wgRequest->getInt( 'limit' );
 151                 $dir = $wgRequest->getVal( 'dir' );
 152                 $history = array(
 153                         'dir' => 'asc',
 154                         'offset' => false,
 155                         'limit' => $wgExportMaxHistory,
 156                 );
 157                 $historyCheck = $wgRequest->getCheck( 'history' );
 158                 if ( $curonly ) {
 159                         $history = WikiExporter::CURRENT;
 160                 } elseif ( !$historyCheck ) {
 161                         if ( $limit > 0 && $limit < $wgExportMaxHistory ) {
 162                                 $history['limit'] = $limit;
 163                         }
 164                         if ( !is_null( $offset ) ) {
 165                                 $history['offset'] = $offset;
 166                         }
 167                         if ( strtolower( $dir ) == 'desc' ) {
 168                                 $history['dir'] = 'desc';
 169                         }
 170                 }
 171
 172                 if( $page != '' ) $doexport = true;
 173         } else {
 174                 // Default to current-only for GET requests
 175                 $page = $wgRequest->getText( 'pages', $page );
 176                 $historyCheck = $wgRequest->getCheck( 'history' );
 177                 if( $historyCheck ) {
 178                         $history = WikiExporter::FULL;
 179                 } else {
 180                         $history = WikiExporter::CURRENT;
 181                 }
 182
 183                 if( $page != '' ) $doexport = true;
 184         }
 185
 186         if( !$wgExportAllowHistory ) {
 187                 // Override
 188                 $history = WikiExporter::CURRENT;
 189         }
 190
 191         $list_authors = $wgRequest->getCheck( 'listauthors' );
 192         if ( !$curonly || !$wgExportAllowListContributors ) $list_authors = false ;
 193
 194         if ( $doexport ) {
 195                 $wgOut->disable();
 196
 197                 // Cancel output buffering and gzipping if set
 198                 // This should provide safer streaming for pages with history
 199                 wfResetOutputBuffers();
 200                 header( "Content-type: application/xml; charset=utf-8" );
 201                 if( $wgRequest->getCheck( 'wpDownload' ) ) {
 202                         // Provide a sane filename suggestion
 203                         $filename = urlencode( $wgSitename . '-' . wfTimestampNow() . '.xml' );
 204                         $wgRequest->response()->header( "Content-disposition: attachment;filename={$filename}" );
 205                 }
 206
 207                 /* Split up the input and look up linked pages */
 208                 $inputPages = array_filter( explode( "\n", $page ), 'wfFilterPage' );
 209                 $pageSet = array_flip( $inputPages );
 210
 211                 if( $wgRequest->getCheck( 'templates' ) ) {
 212                         $pageSet = wfExportGetTemplates( $inputPages, $pageSet );
 213                 }
 214
 215                 /*
 216                 // Enable this when we can do something useful exporting/importing image information. :)
 217                 if( $wgRequest->getCheck( 'images' ) ) {
 218                         $pageSet = wfExportGetImages( $inputPages, $pageSet );
 219                 }
 220                 */
 221
 222                 $pages = array_keys( $pageSet );
 223
 224                 /* Ok, let's get to it... */
 225
 226                 $db = wfGetDB( DB_SLAVE );
 227                 $exporter = new WikiExporter( $db, $history );
 228                 $exporter->list_authors = $list_authors ;
 229                 $exporter->openStream();
 230
 231                 foreach( $pages as $page ) {
 232                         /*
 233                         if( $wgExportMaxHistory && !$curonly ) {
 234                                 $title = Title::newFromText( $page );
 235                                 if( $title ) {
 236                                         $count = Revision::countByTitle( $db, $title );
 237                                         if( $count > $wgExportMaxHistory ) {
 238                                                 wfDebug( __FUNCTION__ .
 239                                                         ": Skipped $page, $count revisions too big\n" );
 240                                                 continue;
 241                                         }
 242                                 }
 243                         }*/
 244
 245                         #Bug 8824: Only export pages the user can read
 246                         $title = Title::newFromText( $page );
 247                         if( is_null( $title ) ) continue; #TODO: perhaps output an <error> tag or something.
 248                         if( !$title->userCanRead() ) continue; #TODO: perhaps output an <error> tag or something.
 249
 250                         $exporter->pageByTitle( $title );
 251                 }
 252
 253                 $exporter->closeStream();
 254                 return;
 255         }
 256
 257         $self = SpecialPage::getTitleFor( 'Export' );
 258         $wgOut->addHtml( wfMsgExt( 'exporttext', 'parse' ) );
 259
 260         $form = Xml::openElement( 'form', array( 'method' => 'post',
 261                 'action' => $self->getLocalUrl( 'action=submit' ) ) );
 262
 263         $form .= Xml::inputLabel( wfMsg( 'export-addcattext' )  , 'catname', 'catname', 40 ) . '&nbsp;';
 264         $form .= Xml::submitButton( wfMsg( 'export-addcat' ), array( 'name' => 'addcat' ) ) . '<br />';
 265
 266         $form .= Xml::openElement( 'textarea', array( 'name' => 'pages', 'cols' => 40, 'rows' => 10 ) );
 267         $form .= htmlspecialchars( $page );
 268         $form .= Xml::closeElement( 'textarea' );
 269         $form .= '<br />';
 270
 271         if( $wgExportAllowHistory ) {
 272                 $form .= Xml::checkLabel( wfMsg( 'exportcuronly' ), 'curonly', 'curonly', true ) . '<br />';
 273         } else {
 274                 $wgOut->addHtml( wfMsgExt( 'exportnohistory', 'parse' ) );
 275         }
 276         $form .= Xml::checkLabel( wfMsg( 'export-templates' ), 'templates', 'wpExportTemplates', false ) . '<br />';
 277         // Enable this when we can do something useful exporting/importing image information. :)
 278         //$form .= Xml::checkLabel( wfMsg( 'export-images' ), 'images', 'wpExportImages', false ) . '<br />';
 279         $form .= Xml::checkLabel( wfMsg( 'export-download' ), 'wpDownload', 'wpDownload', true ) . '<br />';
 280
 281         $form .= Xml::submitButton( wfMsg( 'export-submit' ) );
 282         $form .= Xml::closeElement( 'form' );
 283         $wgOut->addHtml( $form );
 284 }