includes/CategoriesRdf.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  */
  19 use Wikimedia\Purtle\RdfWriter;
  20
  21 /**
  22  * Helper class to produce RDF representation of categories.
  23  */
  24 class CategoriesRdf {
  25         /**
  26          * Prefix used for Mediawiki ontology in the dump.
  27          */
  28         const ONTOLOGY_PREFIX = 'mediawiki';
  29         /**
  30          * Base URL for Mediawiki ontology.
  31          */
  32         const ONTOLOGY_URL = 'https://www.mediawiki.org/ontology#';
  33         /**
  34          * OWL description of the ontology.
  35          */
  36         const OWL_URL = 'https://www.mediawiki.org/ontology/ontology.owl';
  37         /**
  38          * Current version of the dump format.
  39          */
  40         const FORMAT_VERSION = "1.1";
  41         /**
  42          * Special page for Dump identification.
  43          * Used as head URI for each wiki's category dump, e.g.:
  44          * https://en.wikipedia.org/wiki/Special:CategoryDump
  45          */
  46         const SPECIAL_DUMP = 'Special:CategoryDump';
  47         /**
  48          * @var RdfWriter
  49          */
  50         private $rdfWriter;
  51
  52         public function __construct( RdfWriter $writer ) {
  53                 $this->rdfWriter = $writer;
  54         }
  55
  56         /**
  57          * Setup prefixes relevant for the dump
  58          */
  59         public function setupPrefixes() {
  60                 $this->rdfWriter->prefix( self::ONTOLOGY_PREFIX, self::ONTOLOGY_URL );
  61                 $this->rdfWriter->prefix( 'rdfs', 'http://www.w3.org/2000/01/rdf-schema#' );
  62                 $this->rdfWriter->prefix( 'owl', 'http://www.w3.org/2002/07/owl#' );
  63                 $this->rdfWriter->prefix( 'schema', 'http://schema.org/' );
  64                 $this->rdfWriter->prefix( 'cc', 'http://creativecommons.org/ns#' );
  65         }
  66
  67         /**
  68          * Write RDF data for link between categories.
  69          * @param string $fromName Child category name
  70          * @param string $toName Parent category name
  71          */
  72         public function writeCategoryLinkData( $fromName, $toName ) {
  73                 $titleFrom = Title::makeTitle( NS_CATEGORY, $fromName );
  74                 $titleTo = Title::makeTitle( NS_CATEGORY, $toName );
  75                 $this->rdfWriter->about( $this->titleToUrl( $titleFrom ) )
  76                         ->say( self::ONTOLOGY_PREFIX, 'isInCategory' )
  77                         ->is( $this->titleToUrl( $titleTo ) );
  78         }
  79
  80         /**
  81          * Write out the data for single category.
  82          * @param string $categoryName Category name
  83          * @param bool $isHidden Hidden category?
  84          * @param int $pages Page count (note this includes only Wiki articles, not subcats or files)
  85          * @param int $subcategories Subcategory count
  86          */
  87         public function writeCategoryData( $categoryName, $isHidden, $pages, $subcategories ) {
  88                 $title = Title::makeTitle( NS_CATEGORY, $categoryName );
  89                 $this->rdfWriter->about( $this->titleToUrl( $title ) )
  90                         ->say( 'a' )
  91                         ->is( self::ONTOLOGY_PREFIX, 'Category' );
  92                 if ( $isHidden ) {
  93                         $this->rdfWriter->is( self::ONTOLOGY_PREFIX, 'HiddenCategory' );
  94                 }
  95                 $titletext = $title->getText();
  96                 $this->rdfWriter->say( 'rdfs', 'label' )->value( $titletext );
  97                 $this->rdfWriter->say( self::ONTOLOGY_PREFIX, 'pages' )->value( $pages );
  98                 $this->rdfWriter->say( self::ONTOLOGY_PREFIX, 'subcategories' )->value( $subcategories );
  99                 // TODO: do we want files too here? Easy to add, but don't have use case so far.
 100         }
 101
 102         /**
 103          * Make URL from title label
 104          * @param string $titleLabel Short label (without namespace) of the category
 105          * @return string URL for the category
 106          */
 107         public function labelToUrl( $titleLabel ) {
 108                 return $this->titleToUrl( Title::makeTitle( NS_CATEGORY, $titleLabel ) );
 109         }
 110
 111         /**
 112          * Convert Title to link to target page.
 113          * @param Title $title
 114          * @return string URL for the category
 115          */
 116         private function titleToUrl( Title $title ) {
 117                 return $title->getFullURL( '', false, PROTO_CANONICAL );
 118         }
 119
 120         /**
 121          * Get URI of the dump for this particular wiki.
 122          * @return false|string
 123          */
 124         public function getDumpURI() {
 125                 return $this->titleToUrl( Title::makeTitle( NS_MAIN, self::SPECIAL_DUMP ) );
 126         }
 127
 128 }