X-Git-Url: https://git.cyclocoop.org/?a=blobdiff_plain;f=includes%2Fspecials%2FSpecialExport.php;h=4e2d00e547c9b825e5ab02737fc572ad33ea6b04;hb=7cf8b3197c58b7c938e33f3eea2e119fa7cf8cf8;hp=d729abf03baf6835feda9a8fd067c133c5a3b09f;hpb=ed420e0a54b95c606d1e2f967bd058b6ca579e71;p=lhc%2Fweb%2Fwiklou.git diff --git a/includes/specials/SpecialExport.php b/includes/specials/SpecialExport.php index d729abf03b..4e2d00e547 100644 --- a/includes/specials/SpecialExport.php +++ b/includes/specials/SpecialExport.php @@ -1,26 +1,33 @@ -# 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 /** + * Implements Special:Export + * + * Copyright © 2003-2008 Brion Vibber + * + * 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 + * * @file * @ingroup SpecialPage */ +/** + * A special page that allows users to export pages in a XML file + * + * @ingroup SpecialPage + */ class SpecialExport extends SpecialPage { private $curonly, $doExport, $pageLinkDepth, $templates; @@ -29,10 +36,10 @@ class SpecialExport extends SpecialPage { public function __construct() { parent::__construct( 'Export' ); } - + public function execute( $par ) { - global $wgOut, $wgRequest, $wgSitename, $wgExportAllowListContributors; - global $wgExportAllowHistory, $wgExportMaxHistory; + global $wgSitename, $wgExportAllowListContributors, $wgExportFromNamespaces; + global $wgExportAllowHistory, $wgExportMaxHistory, $wgExportMaxLinkDepth; $this->setHeaders(); $this->outputHeader(); @@ -40,48 +47,71 @@ class SpecialExport extends SpecialPage { // Set some variables $this->curonly = true; $this->doExport = false; - $this->templates = $wgRequest->getCheck( 'templates' ); - $this->images = $wgRequest->getCheck( 'images' ); // Doesn't do anything yet - $this->pageLinkDepth = $wgRequest->getIntOrNull( 'pagelink-depth' ); - - if ( $wgRequest->getCheck( 'addcat' ) ) { - $page = $wgRequest->getText( 'pages' ); - $catname = $wgRequest->getText( 'catname' ); - - if ( $catname !== '' && $catname !== NULL && $catname !== false ) { + $request = $this->getRequest(); + $this->templates = $request->getCheck( 'templates' ); + $this->images = $request->getCheck( 'images' ); // Doesn't do anything yet + $this->pageLinkDepth = $this->validateLinkDepth( + $request->getIntOrNull( 'pagelink-depth' ) + ); + $nsindex = ''; + + if ( $request->getCheck( 'addcat' ) ) { + $page = $request->getText( 'pages' ); + $catname = $request->getText( 'catname' ); + + if ( $catname !== '' && $catname !== null && $catname !== false ) { $t = Title::makeTitleSafe( NS_MAIN, $catname ); if ( $t ) { /** - * @fixme This can lead to hitting memory limit for very large + * @todo 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 = $this->getPagesFromCategory( $t ); - if ( $catpages ) $page .= "\n" . implode( "\n", $catpages ); + if ( $catpages ) { + $page .= "\n" . implode( "\n", $catpages ); + } } } } - else if( $wgRequest->wasPosted() && $page == '' ) { - $page = $wgRequest->getText( 'pages' ); - $this->curonly = $wgRequest->getCheck( 'curonly' ); - $rawOffset = $wgRequest->getVal( 'offset' ); + elseif( $request->getCheck( 'addns' ) && $wgExportFromNamespaces ) { + $page = $request->getText( 'pages' ); + $nsindex = $request->getText( 'nsindex', '' ); + + if ( strval( $nsindex ) !== '' ) { + /** + * Same implementation as above, so same @todo + */ + $nspages = $this->getPagesFromNamespace( $nsindex ); + if ( $nspages ) { + $page .= "\n" . implode( "\n", $nspages ); + } + } + } + elseif( $request->wasPosted() && $par == '' ) { + $page = $request->getText( 'pages' ); + $this->curonly = $request->getCheck( 'curonly' ); + $rawOffset = $request->getVal( 'offset' ); + if( $rawOffset ) { $offset = wfTimestamp( TS_MW, $rawOffset ); } else { $offset = null; } - $limit = $wgRequest->getInt( 'limit' ); - $dir = $wgRequest->getVal( 'dir' ); + + $limit = $request->getInt( 'limit' ); + $dir = $request->getVal( 'dir' ); $history = array( 'dir' => 'asc', 'offset' => false, 'limit' => $wgExportMaxHistory, ); - $historyCheck = $wgRequest->getCheck( 'history' ); + $historyCheck = $request->getCheck( 'history' ); + if ( $this->curonly ) { $history = WikiExporter::CURRENT; } elseif ( !$historyCheck ) { - if ( $limit > 0 && $limit < $wgExportMaxHistory ) { + if ( $limit > 0 && ($wgExportMaxHistory == 0 || $limit < $wgExportMaxHistory ) ) { $history['limit'] = $limit; } if ( !is_null( $offset ) ) { @@ -92,18 +122,23 @@ class SpecialExport extends SpecialPage { } } - if( $page != '' ) $this->doExport = true; + if( $page != '' ) { + $this->doExport = true; + } } else { - // Default to current-only for GET requests - $page = $wgRequest->getText( 'pages' ); - $historyCheck = $wgRequest->getCheck( 'history' ); + // Default to current-only for GET requests. + $page = $request->getText( 'pages', $par ); + $historyCheck = $request->getCheck( 'history' ); + if( $historyCheck ) { $history = WikiExporter::FULL; } else { $history = WikiExporter::CURRENT; } - if( $page != '' ) $this->doExport = true; + if( $page != '' ) { + $this->doExport = true; + } } if( !$wgExportAllowHistory ) { @@ -111,78 +146,144 @@ class SpecialExport extends SpecialPage { $history = WikiExporter::CURRENT; } - $list_authors = $wgRequest->getCheck( 'listauthors' ); - if ( !$this->curonly || !$wgExportAllowListContributors ) $list_authors = false ; + $list_authors = $request->getCheck( 'listauthors' ); + if ( !$this->curonly || !$wgExportAllowListContributors ) { + $list_authors = false ; + } if ( $this->doExport ) { - $wgOut->disable(); + $this->getOutput()->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' ) ) { + $request->response()->header( "Content-type: application/xml; charset=utf-8" ); + + if( $request->getCheck( 'wpDownload' ) ) { // Provide a sane filename suggestion $filename = urlencode( $wgSitename . '-' . wfTimestampNow() . '.xml' ); - $wgRequest->response()->header( "Content-disposition: attachment;filename={$filename}" ); + $request->response()->header( "Content-disposition: attachment;filename={$filename}" ); } - $this->doExport( $page, $history ); + + $this->doExport( $page, $history, $list_authors ); + return; } - $wgOut->addHTML( wfMsgExt( 'exporttext', 'parse' ) ); + $out = $this->getOutput(); + $out->addWikiMsg( 'exporttext' ); $form = Xml::openElement( 'form', array( 'method' => 'post', 'action' => $this->getTitle()->getLocalUrl( 'action=submit' ) ) ); - $form .= Xml::inputLabel( wfMsg( 'export-addcattext' ) , 'catname', 'catname', 40 ) . ' '; + $form .= Xml::inputLabel( wfMsg( 'export-addcattext' ) , 'catname', 'catname', 40 ) . ' '; $form .= Xml::submitButton( wfMsg( 'export-addcat' ), array( 'name' => 'addcat' ) ) . '
'; + + if ( $wgExportFromNamespaces ) { + $form .= Xml::namespaceSelector( $nsindex, null, 'nsindex', wfMsg( 'export-addnstext' ) ) . ' '; + $form .= Xml::submitButton( wfMsg( 'export-addns' ), array( 'name' => 'addns' ) ) . '
'; + } + $form .= Xml::element( 'textarea', array( 'name' => 'pages', 'cols' => 40, 'rows' => 10 ), $page, false ); $form .= '
'; if( $wgExportAllowHistory ) { - $form .= Xml::checkLabel( wfMsg( 'exportcuronly' ), 'curonly', 'curonly', true ) . '
'; + $form .= Xml::checkLabel( + wfMsg( 'exportcuronly' ), + 'curonly', + 'curonly', + $request->wasPosted() ? $request->getCheck( 'curonly' ) : true + ) . '
'; } else { - $wgOut->addHTML( wfMsgExt( 'exportnohistory', 'parse' ) ); + $out->addHTML( wfMsgExt( 'exportnohistory', 'parse' ) ); + } + + $form .= Xml::checkLabel( + wfMsg( 'export-templates' ), + 'templates', + 'wpExportTemplates', + $request->wasPosted() ? $request->getCheck( 'templates' ) : false + ) . '
'; + + if( $wgExportMaxLinkDepth || $this->userCanOverrideExportDepth() ) { + $form .= Xml::inputLabel( wfMsg( 'export-pagelinks' ), 'pagelink-depth', 'pagelink-depth', 20, 0 ) . '
'; } - $form .= Xml::checkLabel( wfMsg( 'export-templates' ), 'templates', 'wpExportTemplates', false ) . '
'; - $form .= Xml::inputLabel( wfMsg( 'export-pagelinks' ), 'pagelink-depth', 'pagelink-depth', 20, 0 ) . '
'; // Enable this when we can do something useful exporting/importing image information. :) //$form .= Xml::checkLabel( wfMsg( 'export-images' ), 'images', 'wpExportImages', false ) . '
'; - $form .= Xml::checkLabel( wfMsg( 'export-download' ), 'wpDownload', 'wpDownload', true ) . '
'; + $form .= Xml::checkLabel( + wfMsg( 'export-download' ), + 'wpDownload', + 'wpDownload', + $request->wasPosted() ? $request->getCheck( 'wpDownload' ) : true + ) . '
'; + + if ( $wgExportAllowListContributors ) { + $form .= Xml::checkLabel( + wfMsg( 'exportlistauthors' ), + 'listauthors', + 'listauthors', + $request->wasPosted() ? $request->getCheck( 'listauthors' ) : false + ) . '
'; + } - $form .= Xml::submitButton( wfMsg( 'export-submit' ), array( 'accesskey' => 's' ) ); + $form .= Xml::submitButton( wfMsg( 'export-submit' ), Linker::tooltipAndAccesskeyAttribs( 'export' ) ); $form .= Xml::closeElement( 'form' ); - $wgOut->addHTML( $form ); + + $out->addHTML( $form ); + } + + private function userCanOverrideExportDepth() { + return $this->getUser()->isAllowed( 'override-export-depth' ); } /** * Do the actual page exporting - * @param string $page User input on what page(s) to export - * @param mixed $history one of the WikiExporter history export constants + * + * @param $page String: user input on what page(s) to export + * @param $history Mixed: one of the WikiExporter history export constants + * @param $list_authors Boolean: Whether to add distinct author list (when + * not returning full history) */ - private function doExport( $page, $history ) { - global $wgExportMaxHistory; + private function doExport( $page, $history, $list_authors ) { + $pageSet = array(); // Inverted index of all pages to look up + + // Split up and normalize input + foreach( explode( "\n", $page ) as $pageName ) { + $pageName = trim( $pageName ); + $title = Title::newFromText( $pageName ); + if( $title && $title->getInterwiki() == '' && $title->getText() !== '' ) { + // Only record each page once! + $pageSet[$title->getPrefixedText()] = true; + } + } - /* Split up the input and look up linked pages */ - $inputPages = array_filter( explode( "\n", $page ), array( $this, 'filterPage' ) ); - $pageSet = array_flip( $inputPages ); + // Set of original pages to pass on to further manipulation... + $inputPages = array_keys( $pageSet ); + // Look up any linked pages if asked... if( $this->templates ) { $pageSet = $this->getTemplates( $inputPages, $pageSet ); } - - if( $linkDepth = $this->pageLinkDepth ) { + $linkDepth = $this->pageLinkDepth; + if( $linkDepth ) { $pageSet = $this->getPageLinks( $inputPages, $pageSet, $linkDepth ); } /* - // Enable this when we can do something useful exporting/importing image information. :) - if( $this->images ) ) { - $pageSet = $this->getImages( $inputPages, $pageSet ); - } - */ + // Enable this when we can do something useful exporting/importing image information. :) + if( $this->images ) ) { + $pageSet = $this->getImages( $inputPages, $pageSet ); + } + */ $pages = array_keys( $pageSet ); + // Normalize titles to the same format and remove dupes, see bug 17374 + foreach( $pages as $k => $v ) { + $pages[$k] = str_replace( " ", "_", $v ); + } + + $pages = array_unique( $pages ); + /* Ok, let's get to it... */ if( $history == WikiExporter::CURRENT ) { $lb = false; @@ -199,31 +300,38 @@ class SpecialExport extends SpecialPage { set_time_limit(0); wfRestoreWarnings(); } - $exporter = new WikiExporter( $db, $history, $buffer ); - $exporter->list_authors = $list_authors ; + + $exporter = new WikiExporter( $db, $history, $buffer ); + $exporter->list_authors = $list_authors; $exporter->openStream(); + foreach( $pages as $page ) { /* - if( $wgExportMaxHistory && !$this->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; - } - } - }*/ + if( $wgExportMaxHistory && !$this->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( $title ) ) continue; #TODO: perhaps output an tag or something. - if( !$title->userCanRead() ) continue; #TODO: perhaps output an tag or something. + if( is_null( $title ) ) { + continue; #TODO: perhaps output an tag or something. + } + if( !$title->userCanRead() ) { + continue; #TODO: perhaps output an tag or something. + } - $exporter->pageByTitle( $title ); + $exporter->pageByTitle( $title ); } $exporter->closeStream(); + if( $lb ) { $lb->closeAll(); } @@ -235,15 +343,17 @@ class SpecialExport extends SpecialPage { $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 ); + $res = $dbr->select( + array( 'page', 'categorylinks' ), + array( 'page_namespace', 'page_title' ), + array( 'cl_from=page_id', 'cl_to' => $name ), + __METHOD__, + array( 'LIMIT' => '5000' ) + ); $pages = array(); - $res = $dbr->query( $sql, __METHOD__ ); - while ( $row = $dbr->fetchObject( $res ) ) { + + foreach ( $res as $row ) { $n = $row->page_title; if ($row->page_namespace) { $ns = $wgContLang->getNsText( $row->page_namespace ); @@ -252,9 +362,34 @@ class SpecialExport extends SpecialPage { $pages[] = $n; } - $dbr->freeResult($res); + return $pages; + } + + private function getPagesFromNamespace( $nsindex ) { + global $wgContLang; + + $dbr = wfGetDB( DB_SLAVE ); + $res = $dbr->select( + 'page', + array( 'page_namespace', 'page_title' ), + array( 'page_namespace' => $nsindex ), + __METHOD__, + array( 'LIMIT' => '5000' ) + ); - return $pages; + $pages = array(); + + foreach ( $res as $row ) { + $n = $row->page_title; + + if ( $row->page_namespace ) { + $ns = $wgContLang->getNsText( $row->page_namespace ); + $n = $ns . ':' . $n; + } + + $pages[] = $n; + } + return $pages; } /** @@ -265,67 +400,102 @@ class SpecialExport extends SpecialPage { */ private function getTemplates( $inputPages, $pageSet ) { return $this->getLinks( $inputPages, $pageSet, - 'templatelinks', - array( 'tl_namespace AS namespace', 'tl_title AS title' ), - array( 'page_id=tl_from' ) ); + 'templatelinks', + array( 'tl_namespace AS namespace', 'tl_title AS title' ), + array( 'page_id=tl_from' ) + ); + } + + /** + * Validate link depth setting, if available. + */ + private function validateLinkDepth( $depth ) { + global $wgExportMaxLinkDepth; + + if( $depth < 0 ) { + return 0; + } + + if ( !$this->userCanOverrideExportDepth() ) { + if( $depth > $wgExportMaxLinkDepth ) { + return $wgExportMaxLinkDepth; + } + } + + /* + * There's a HARD CODED limit of 5 levels of recursion here to prevent a + * crazy-big export from being done by someone setting the depth + * number too high. In other words, last resort safety net. + */ + return intval( min( $depth, 5 ) ); } /** Expand a list of pages to include pages linked to from that page. */ private function getPageLinks( $inputPages, $pageSet, $depth ) { - for( $depth=$depth; $depth>0; --$depth ) { - $pageSet = $this->getLinks( $inputPages, $pageSet, 'pagelinks', - array( 'pl_namespace AS namespace', 'pl_title AS title' ), - array( 'page_id=pl_from' ) ); + for( ; $depth > 0; --$depth ) { + $pageSet = $this->getLinks( + $inputPages, $pageSet, 'pagelinks', + array( 'pl_namespace AS namespace', 'pl_title AS title' ), + array( 'page_id=pl_from' ) + ); + $inputPages = array_keys( $pageSet ); } + return $pageSet; } /** * 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 */ private function getImages( $inputPages, $pageSet ) { - return $this->getLinks( $inputPages, $pageSet, - 'imagelinks', - array( NS_FILE . ' AS namespace', 'il_to AS title' ), - array( 'page_id=il_from' ) ); + return $this->getLinks( + $inputPages, + $pageSet, + 'imagelinks', + array( NS_FILE . ' AS namespace', 'il_to AS title' ), + array( 'page_id=il_from' ) + ); } /** * Expand a list of pages to include items used in those pages. - * @private */ private function getLinks( $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 + /// @todo 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_merge( + $join, array( 'page_namespace' => $title->getNamespace(), - 'page_title' => $title->getDBKey() ) ), - __METHOD__ ); + '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. - */ - private function filterPage( $page ) { - return $page !== '' && $page !== null; - } }