includes/linkeddata/PageDataRequestHandler.php

   1 <?php
   2 /**
   3  * This program is free software; you can redistribute it and/or modify
   4  * it under the terms of the GNU General Public License as published by
   5  * the Free Software Foundation; either version 2 of the License, or
   6  * (at your option) any later version.
   7  *
   8  * This program is distributed in the hope that it will be useful,
   9  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  10  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  11  * GNU General Public License for more details.
  12  *
  13  * You should have received a copy of the GNU General Public License along
  14  * with this program; if not, write to the Free Software Foundation, Inc.,
  15  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  16  * http://www.gnu.org/copyleft/gpl.html
  17  *
  18  * @file
  19  */
  20
  21 use Wikimedia\Http\HttpAcceptParser;
  22 use Wikimedia\Http\HttpAcceptNegotiator;
  23
  24 /**
  25  * Request handler implementing a data interface for mediawiki pages.
  26  *
  27  * @author Daniel Kinzler
  28  * @author Amir Sarabadanai
  29  */
  30 class PageDataRequestHandler {
  31
  32         /**
  33          * Checks whether the request is complete, i.e. whether it contains all information needed
  34          * to reply with page data.
  35          *
  36          * This does not check whether the request is valid and will actually produce a successful
  37          * response.
  38          *
  39          * @param string|null $subPage
  40          * @param WebRequest $request
  41          *
  42          * @return bool
  43          */
  44         public function canHandleRequest( $subPage, WebRequest $request ) {
  45                 if ( $subPage === '' || $subPage === null ) {
  46                         return $request->getText( 'target' ) !== '';
  47                 }
  48
  49                 $parts = explode( '/', $subPage, 2 );
  50                 $slot = $parts[0];
  51                 $title = $parts[1] ?? '';
  52                 return ( $slot === 'main' || $slot === '' ) && $title !== '';
  53         }
  54
  55         /**
  56          * Main method for handling requests.
  57          *
  58          * @param string|null $subPage
  59          * @param WebRequest $request The request parameters. Known parameters are:
  60          *        - title: the page title
  61          *        - format: the format
  62          *        - oldid|revision: the revision ID
  63          * @param OutputPage $output
  64          *
  65          * @note Instead of an output page, a WebResponse could be sufficient, but
  66          *        redirect logic is currently implemented in OutputPage.
  67          *
  68          * @throws HttpError
  69          */
  70         public function handleRequest( $subPage, WebRequest $request, OutputPage $output ) {
  71                 // No matter what: The response is always public
  72                 $output->getRequest()->response()->header( 'Access-Control-Allow-Origin: *' );
  73
  74                 if ( !$this->canHandleRequest( $subPage, $request ) ) {
  75                         throw new HttpError( 400, wfMessage( 'pagedata-bad-title', $subPage ) );
  76                 }
  77
  78                 $revision = 0;
  79
  80                 if ( $subPage !== '' ) {
  81                         $parts = explode( '/', $subPage, 2 );
  82                         $title = $parts[1] ?? '';
  83                 } else {
  84                         $title = $request->getText( 'target' );
  85                 }
  86
  87                 $revision = $request->getInt( 'oldid', $revision );
  88                 $revision = $request->getInt( 'revision', $revision );
  89
  90                 if ( $title === null || $title === '' ) {
  91                         //TODO: different error message?
  92                         throw new HttpError( 400, wfMessage( 'pagedata-bad-title', $title ) );
  93                 }
  94
  95                 try {
  96                         $title = Title::newFromTextThrow( $title );
  97                 } catch ( MalformedTitleException $ex ) {
  98                         throw new HttpError( 400, wfMessage( 'pagedata-bad-title', $title ) );
  99                 }
 100
 101                 $this->httpContentNegotiation( $request, $output, $title, $revision );
 102         }
 103
 104         /**
 105          * Applies HTTP content negotiation.
 106          * If the negotiation is successful, this method will set the appropriate redirect
 107          * in the OutputPage object and return. Otherwise, an HttpError is thrown.
 108          *
 109          * @param WebRequest $request
 110          * @param OutputPage $output
 111          * @param Title $title
 112          * @param int $revision The desired revision
 113          *
 114          * @throws HttpError
 115          */
 116         public function httpContentNegotiation(
 117                 WebRequest $request,
 118                 OutputPage $output,
 119                 Title $title,
 120                 $revision = 0
 121         ) {
 122                 $contentHandler = ContentHandler::getForTitle( $title );
 123                 $mimeTypes = $contentHandler->getSupportedFormats();
 124
 125                 $acceptHeader = $request->getHeader( 'Accept' );
 126                 if ( $acceptHeader !== false ) {
 127                         $parser = new HttpAcceptParser();
 128                         $accept = $parser->parseWeights( $acceptHeader );
 129                 } else {
 130                         // anything goes
 131                         $accept = [
 132                                 '*' => 0.1 // just to make extra sure
 133                         ];
 134                         // prefer the default
 135                         $accept[$mimeTypes[0]] = 1;
 136                 }
 137
 138                 $negotiator = new HttpAcceptNegotiator( $mimeTypes );
 139                 $format = $negotiator->getBestSupportedKey( $accept );
 140
 141                 if ( $format === null ) {
 142                         $format = isset( $accept['text/html'] ) ? 'text/html' : null;
 143                 }
 144
 145                 if ( $format === null ) {
 146                         $msg = wfMessage( 'pagedata-not-acceptable', implode( ', ', $mimeTypes ) );
 147                         throw new HttpError( 406, $msg );
 148                 }
 149
 150                 $url = $this->getDocUrl( $title, $format, $revision );
 151                 $output->redirect( $url, 303 );
 152         }
 153
 154         /**
 155          * Returns a url representing the given title.
 156          *
 157          * @param Title $title
 158          * @param string|null $format The (normalized) format name, or ''
 159          * @param int $revision
 160          * @return string
 161          */
 162         private function getDocUrl( Title $title, $format = '', $revision = 0 ) {
 163                 $params = [];
 164
 165                 if ( $revision > 0 ) {
 166                         $params['oldid'] = $revision;
 167                 }
 168
 169                 if ( $format === 'text/html' ) {
 170                         return $title->getFullURL( $params );
 171                 }
 172
 173                 $params[ 'action' ] = 'raw';
 174
 175                 return $title->getFullURL( $params );
 176         }
 177
 178 }