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  */
  20
  21 namespace MediaWiki\Title;
  22
  23 /**
  24  * A parser that translates page titles on a foreign wiki into ForeignTitle
  25  * objects, using information about the namespace setup on the foreign site.
  26  */
  27 class NamespaceAwareForeignTitleFactory implements ForeignTitleFactory {
  28         /**
  29          * @var array
  30          */
  31         protected $foreignNamespaces;
  32         /**
  33          * @var array
  34          */
  35         private $foreignNamespacesFlipped;
  36
  37         /**
  38          * Normalizes an array name for $foreignNamespacesFlipped.
  39          * @param string $name
  40          * @return string
  41          */
  42         private function normalizeNamespaceName( $name ) {
  43                 return strtolower( str_replace( ' ', '_', $name ) );
  44         }
  45
  46         /**
  47          * @param array|null $foreignNamespaces An array 'id' => 'name' which contains
  48          * the complete namespace setup of the foreign wiki. Such data could be
  49          * obtained from siteinfo/namespaces in an XML dump file, or by an action API
  50          * query such as api.php?action=query&meta=siteinfo&siprop=namespaces. If
  51          * this data is unavailable, use NaiveForeignTitleFactory instead.
  52          */
  53         public function __construct( $foreignNamespaces ) {
  54                 $this->foreignNamespaces = $foreignNamespaces;
  55                 if ( $foreignNamespaces !== null ) {
  56                         $this->foreignNamespacesFlipped = [];
  57                         foreach ( $foreignNamespaces as $id => $name ) {
  58                                 $newKey = self::normalizeNamespaceName( $name );
  59                                 $this->foreignNamespacesFlipped[$newKey] = $id;
  60                         }
  61                 }
  62         }
  63
  64         /**
  65          * Create a ForeignTitle object.
  66          *
  67          * Based on the page title and optionally the namespace ID, of a page on a foreign wiki.
  68          * These values could be, for example, the `<title>` and `<ns>` attributes found in an
  69          * XML dump.
  70          *
  71          * @param string $title The page title
  72          * @param int|null $ns The namespace ID, or null if this data is not available
  73          * @return ForeignTitle
  74          */
  75         public function createForeignTitle( $title, $ns = null ) {
  76                 // Export schema version 0.5 and earlier (MW 1.18 and earlier) does not
  77                 // contain a <ns> tag, so we need to be able to handle that case.
  78                 if ( $ns === null ) {
  79                         return self::parseTitleNoNs( $title );
  80                 } else {
  81                         return self::parseTitleWithNs( $title, $ns );
  82                 }
  83         }
  84
  85         /**
  86          * Helper function to parse the title when the namespace ID is not specified.
  87          *
  88          * @param string $title
  89          * @return ForeignTitle
  90          */
  91         protected function parseTitleNoNs( $title ) {
  92                 $pieces = explode( ':', $title, 2 );
  93                 $key = self::normalizeNamespaceName( $pieces[0] );
  94
  95                 // Does the part before the colon match a known namespace? Check the
  96                 // foreign namespaces
  97                 $isNamespacePartValid = isset( $this->foreignNamespacesFlipped[$key] );
  98
  99                 if ( count( $pieces ) === 2 && $isNamespacePartValid ) {
 100                         [ $namespaceName, $pageName ] = $pieces;
 101                         $ns = $this->foreignNamespacesFlipped[$key];
 102                 } else {
 103                         $namespaceName = '';
 104                         $pageName = $title;
 105                         $ns = 0;
 106                 }
 107
 108                 return new ForeignTitle( $ns, $namespaceName, $pageName );
 109         }
 110
 111         /**
 112          * Helper function to parse the title when the namespace value is known.
 113          *
 114          * @param string $title
 115          * @param int $ns
 116          * @return ForeignTitle
 117          */
 118         protected function parseTitleWithNs( $title, $ns ) {
 119                 $pieces = explode( ':', $title, 2 );
 120
 121                 // Is $title of the form Namespace:Title (true), or just Title (false)?
 122                 $titleIncludesNamespace = ( $ns != '0' && count( $pieces ) === 2 );
 123
 124                 if ( isset( $this->foreignNamespaces[$ns] ) ) {
 125                         $namespaceName = $this->foreignNamespaces[$ns];
 126                 } else {
 127                         // If the foreign wiki is misconfigured, XML dumps can contain a page with
 128                         // a non-zero namespace ID, but whose title doesn't contain a colon
 129                         // (T114115). In those cases, output a made-up namespace name to avoid
 130                         // collisions. The ImportTitleFactory might replace this with something
 131                         // more appropriate.
 132                         $namespaceName = $titleIncludesNamespace ? $pieces[0] : "Ns$ns";
 133                 }
 134
 135                 // We assume that the portion of the page title before the colon is the
 136                 // namespace name, except in the case of namespace 0.
 137                 if ( $titleIncludesNamespace ) {
 138                         $pageName = $pieces[1];
 139                 } else {
 140                         $pageName = $title;
 141                 }
 142
 143                 return new ForeignTitle( $ns, $namespaceName, $pageName );
 144         }
 145 }
 146
 147 /** @deprecated class alias since 1.41 */
 148 class_alias( NamespaceAwareForeignTitleFactory::class, 'NamespaceAwareForeignTitleFactory' );