includes/title/NamespaceAwareForeignTitleFactory.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  * @license GPL 2+
  20  */
  21
  22 /**
  23  * A parser that translates page titles on a foreign wiki into ForeignTitle
  24  * objects, using information about the namespace setup on the foreign site.
  25  */
  26 class NamespaceAwareForeignTitleFactory implements ForeignTitleFactory {
  27         /**
  28          * @var array
  29          */
  30         protected $foreignNamespaces;
  31         /**
  32          * @var array
  33          */
  34         private $foreignNamespacesFlipped;
  35
  36         /**
  37          * Normalizes an array name for $foreignNamespacesFlipped.
  38          * @param string $name
  39          * @return string
  40          */
  41         private function normalizeNamespaceName( $name ) {
  42                 return strtolower( str_replace( ' ', '_', $name ) );
  43         }
  44
  45         /**
  46          * @param array|null $foreignNamespaces An array 'id' => 'name' which contains
  47          * the complete namespace setup of the foreign wiki. Such data could be
  48          * obtained from siteinfo/namespaces in an XML dump file, or by an action API
  49          * query such as api.php?action=query&meta=siteinfo&siprop=namespaces. If
  50          * this data is unavailable, use NaiveForeignTitleFactory instead.
  51          */
  52         public function __construct( $foreignNamespaces ) {
  53                 $this->foreignNamespaces = $foreignNamespaces;
  54                 if ( !is_null( $foreignNamespaces ) ) {
  55                         $this->foreignNamespacesFlipped = [];
  56                         foreach ( $foreignNamespaces as $id => $name ) {
  57                                 $newKey = self::normalizeNamespaceName( $name );
  58                                 $this->foreignNamespacesFlipped[$newKey] = $id;
  59                         }
  60                 }
  61         }
  62
  63         /**
  64          * Creates a ForeignTitle object based on the page title, and optionally the
  65          * namespace ID, of a page on a foreign wiki. These values could be, for
  66          * example, the <title> and <ns> attributes found in an XML dump.
  67          *
  68          * @param string $title The page title
  69          * @param int|null $ns The namespace ID, or null if this data is not available
  70          * @return ForeignTitle
  71          */
  72         public function createForeignTitle( $title, $ns = null ) {
  73                 // Export schema version 0.5 and earlier (MW 1.18 and earlier) does not
  74                 // contain a <ns> tag, so we need to be able to handle that case.
  75                 if ( is_null( $ns ) ) {
  76                         return self::parseTitleNoNs( $title );
  77                 } else {
  78                         return self::parseTitleWithNs( $title, $ns );
  79                 }
  80         }
  81
  82         /**
  83          * Helper function to parse the title when the namespace ID is not specified.
  84          *
  85          * @param string $title
  86          * @return ForeignTitle
  87          */
  88         protected function parseTitleNoNs( $title ) {
  89                 $pieces = explode( ':', $title, 2 );
  90                 $key = self::normalizeNamespaceName( $pieces[0] );
  91
  92                 // Does the part before the colon match a known namespace? Check the
  93                 // foreign namespaces
  94                 $isNamespacePartValid = isset( $this->foreignNamespacesFlipped[$key] );
  95
  96                 if ( count( $pieces ) === 2 && $isNamespacePartValid ) {
  97                         list( $namespaceName, $pageName ) = $pieces;
  98                         $ns = $this->foreignNamespacesFlipped[$key];
  99                 } else {
 100                         $namespaceName = '';
 101                         $pageName = $title;
 102                         $ns = 0;
 103                 }
 104
 105                 return new ForeignTitle( $ns, $namespaceName, $pageName );
 106         }
 107
 108         /**
 109          * Helper function to parse the title when the namespace value is known.
 110          *
 111          * @param string $title
 112          * @param int $ns
 113          * @return ForeignTitle
 114          */
 115         protected function parseTitleWithNs( $title, $ns ) {
 116                 $pieces = explode( ':', $title, 2 );
 117
 118                 if ( isset( $this->foreignNamespaces[$ns] ) ) {
 119                         $namespaceName = $this->foreignNamespaces[$ns];
 120                 } else {
 121                         $namespaceName = $ns == '0' ? '' : $pieces[0];
 122                 }
 123
 124                 // We assume that the portion of the page title before the colon is the
 125                 // namespace name, except in the case of namespace 0
 126                 if ( $ns != '0' ) {
 127                         $pageName = $pieces[1];
 128                 } else {
 129                         $pageName = $title;
 130                 }
 131
 132                 return new ForeignTitle( $ns, $namespaceName, $pageName );
 133         }
 134 }