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