<?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
+# 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.,
-# 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
# http://www.gnu.org/copyleft/gpl.html
-
-require_once( 'Revision.php' );
-
/**
*
- * @package MediaWiki
- * @subpackage SpecialPage
+ * @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;
+}
+
/**
*
*/
function wfSpecialExport( $page = '' ) {
- global $wgOut, $wgLang, $wgRequest;
-
- if( $wgRequest->getVal( 'action' ) == 'submit') {
+ 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 ) {
+ $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 {
- # Pre-check the 'current version only' box in the UI
- $curonly = true;
- }
-
- if( $page != '' ) {
- $wgOut->disable();
- header( "Content-type: application/xml; charset=utf-8" );
- $pages = explode( "\n", $page );
- $xml = pages2xml( $pages, $curonly );
- echo $xml;
- return;
+ // 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;
}
-
- $wgOut->addWikiText( wfMsg( "exporttext" ) );
- $titleObj = Title::makeTitle( NS_SPECIAL, "Export" );
- $action = $titleObj->escapeLocalURL();
- $wgOut->addHTML( "
-<form method='post' action=\"$action\">
-<input type='hidden' name='action' value='submit' />
-<textarea name='pages' cols='40' rows='10'></textarea><br />
-<label><input type='checkbox' name='curonly' value='true' checked='checked' />
-" . wfMsg( "exportcuronly" ) . "</label><br />
-<input type='submit' />
-</form>
-" );
-}
-function pages2xml( $pages, $curonly = false ) {
- $fname = 'pages2xml';
- wfProfileIn( $fname );
-
- global $wgContLanguageCode, $wgInputEncoding, $wgContLang;
- $xml = "<" . "?xml version=\"1.0\" encoding=\"UTF-8\" ?" . ">\n" .
- "<mediawiki version=\"0.1\" xml:lang=\"$wgContLanguageCode\">\n";
- foreach( $pages as $page ) {
- $xml .= page2xml( $page, $curonly );
+ if( !$wgExportAllowHistory ) {
+ // Override
+ $history = WikiExporter::CURRENT;
}
- $xml .= "</mediawiki>\n";
- if($wgInputEncoding != "utf-8")
- $xml = $wgContLang->iconv( $wgInputEncoding, "utf-8", $xml );
- wfProfileOut( $fname );
- return $xml;
-}
+ $list_authors = $wgRequest->getCheck( 'listauthors' );
+ if ( !$curonly || !$wgExportAllowListContributors ) $list_authors = false ;
-function page2xml( $page, $curonly, $full = false ) {
- global $wgLang;
- $fname = 'page2xml';
- wfProfileIn( $fname );
-
- $title = Title::NewFromText( $page );
- if( !$title ) {
- wfProfileOut( $fname );
- return "";
- }
-
- $dbr =& wfGetDB( DB_SLAVE );
- $s = $dbr->selectRow( 'page',
- array( 'page_id', 'page_restrictions' ),
- array( 'page_namespace' => $title->getNamespace(),
- 'page_title' => $title->getDbkey() ) );
- if( $s ) {
- $tl = xmlsafe( $title->getPrefixedText() );
- $xml = " <page>\n";
- $xml .= " <title>$tl</title>\n";
+ if ( $doexport ) {
+ $wgOut->disable();
- if( $full ) {
- $xml .= " <id>$s->page_id</id>\n";
- }
- if( $s->page_restrictions ) {
- $xml .= " <restrictions>" . xmlsafe( $s->page_restrictions ) . "</restrictions>\n";
+ // 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}" );
}
+ $pages = explode( "\n", $page );
- if( $curonly ) {
- $res = Revision::fetchRevision( $title );
- } else {
- $res = Revision::fetchAllRevisions( $title );
- }
- if( $res ) {
- while( $s = $res->fetchObject() ) {
- $rev = new Revision( $s );
- $xml .= revision2xml( $rev, $full, false );
- }
- $res->free();
+ $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->userCan( 'read' ) ) continue; #TODO: perhaps output an <error> tag or something.
+
+ $exporter->pageByTitle( $title );
}
- $xml .= " </page>\n";
- wfProfileOut( $fname );
- return $xml;
- } else {
- wfProfileOut( $fname );
- return "";
+ $exporter->closeStream();
+ return;
}
-}
-/**
- * @return string
- * @param Revision $rev
- * @param bool $full
- * @access private
- */
-function revision2xml( $rev, $full ) {
- $fname = 'revision2xml';
- wfProfileIn( $fname );
+ $self = SpecialPage::getTitleFor( 'Export' );
+ $wgOut->addHtml( wfMsgExt( 'exporttext', 'parse' ) );
- global $wgParser , $wgUseXMLparser ; # So we can return *real* XML
-
- $xml = " <revision>\n";
- if( $full )
- $xml .= " <id>" . $rev->getId() . "</id>\n";
+ $form = Xml::openElement( 'form', array( 'method' => 'post',
+ 'action' => $self->getLocalUrl( 'action=submit' ) ) );
- $ts = wfTimestamp2ISO8601( $rev->getTimestamp() );
- $xml .= " <timestamp>$ts</timestamp>\n";
+ $form .= Xml::inputLabel( wfMsg( 'export-addcattext' ) , 'catname', 'catname', 40 ) . ' ';
+ $form .= Xml::submitButton( wfMsg( 'export-addcat' ), array( 'name' => 'addcat' ) ) . '<br />';
- if( $rev->getUser() ) {
- $u = "<username>" . xmlsafe( $rev->getUserText() ) . "</username>";
- if( $full )
- $u .= "<id>" . $rev->getUser() . "</id>";
- } else {
- $u = "<ip>" . xmlsafe( $rev->getUserText() ) . "</ip>";
- }
- $xml .= " <contributor>$u</contributor>\n";
+ $form .= Xml::openElement( 'textarea', array( 'name' => 'pages', 'cols' => 40, 'rows' => 10 ) );
+ $form .= htmlspecialchars( $page );
+ $form .= Xml::closeElement( 'textarea' );
+ $form .= '<br />';
- if( $rev->isMinor() ) {
- $xml .= " <minor/>\n";
- }
- if($rev->getComment() != "") {
- $c = xmlsafe( $rev->getComment() );
- $xml .= " <comment>$c</comment>\n";
- }
-
- $t = $rev->getText() ;
- if ( $wgUseXMLparser )
- {
- $wgParser->runXMLparser ( $t ) ;
- }
- $t = xmlsafe( $t ) ;
-
- $xml .= " <text>$t</text>\n";
- $xml .= " </revision>\n";
- wfProfileOut( $fname );
- return $xml;
-}
-
-function wfTimestamp2ISO8601( $ts ) {
- #2003-08-05T18:30:02Z
- return preg_replace( '/^(....)(..)(..)(..)(..)(..)$/', '$1-$2-$3T$4:$5:$6Z', $ts );
-}
-
-function xmlsafe( $string ) {
- $fname = 'xmlsafe';
- wfProfileIn( $fname );
-
- /**
- * The page may contain old data which has not been properly normalized.
- * Invalid UTF-8 sequences or forbidden control characters will make our
- * XML output invalid, so be sure to strip them out.
- */
- global $wgUseLatin1;
- if( $wgUseLatin1 ) {
- /**
- * We know the UTF-8 is valid since we converted outselves.
- * Just check for forbidden controls...
- */
- $string = preg_replace( '/[\x00-\x08\x0b-\x1f]/', '', $string );
+ if( $wgExportAllowHistory ) {
+ $form .= Xml::checkLabel( wfMsg( 'exportcuronly' ), 'curonly', 'curonly', true ) . '<br />';
} else {
- $string = UtfNormal::cleanUp( $string );
+ $wgOut->addHtml( wfMsgExt( 'exportnohistory', 'parse' ) );
}
+ $form .= Xml::checkLabel( wfMsg( 'export-download' ), 'wpDownload', 'wpDownload', true ) . '<br />';
- $string = htmlspecialchars( $string );
- wfProfileOut( $fname );
- return $string;
-}
-
-?>
+ $form .= Xml::submitButton( wfMsg( 'export-submit' ) );
+ $form .= Xml::closeElement( 'form' );
+ $wgOut->addHtml( $form );
+}
\ No newline at end of file