maintenance/dumpCategoriesAsRdf.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 use Wikimedia\Purtle\RdfWriterFactory;
  21 use Wikimedia\Rdbms\IDatabase;
  22
  23 require_once __DIR__ . '/Maintenance.php';
  24
  25 /**
  26  * Maintenance script to provide RDF representation of the category tree.
  27  *
  28  * @ingroup Maintenance
  29  * @since 1.30
  30  */
  31 class DumpCategoriesAsRdf extends Maintenance {
  32         /**
  33          * @var RdfWriter
  34          */
  35         private $rdfWriter;
  36         /**
  37          * Categories RDF helper.
  38          * @var CategoriesRdf
  39          */
  40         private $categoriesRdf;
  41
  42         public function __construct() {
  43                 parent::__construct();
  44
  45                 $this->addDescription( "Generate RDF dump of categories in a wiki." );
  46
  47                 $this->setBatchSize( 200 );
  48                 $this->addOption( 'output', "Output file (default is stdout). Will be overwritten.",
  49                         false, true );
  50                 $this->addOption( 'format', "Set the dump format.", false, true );
  51         }
  52
  53         /**
  54          * Produce row iterator for categories.
  55          * @param IDatabase $dbr Database connection
  56          * @param string $fname Name of the calling function
  57          * @return RecursiveIterator
  58          */
  59         public function getCategoryIterator( IDatabase $dbr, $fname ) {
  60                 $it = new BatchRowIterator(
  61                         $dbr,
  62                         [ 'page', 'page_props', 'category' ],
  63                         [ 'page_title' ],
  64                         $this->getBatchSize()
  65                 );
  66                 $it->addConditions( [
  67                         'page_namespace' => NS_CATEGORY,
  68                 ] );
  69                 $it->setFetchColumns( [
  70                         'page_title',
  71                         'page_id',
  72                         'pp_propname',
  73                         'cat_pages',
  74                         'cat_subcats',
  75                         'cat_files'
  76                 ] );
  77                 $it->addJoinConditions(
  78                         [
  79                                 'page_props' => [
  80                                         'LEFT JOIN', [ 'pp_propname' => 'hiddencat', 'pp_page = page_id' ]
  81                                 ],
  82                                 'category' => [
  83                                         'LEFT JOIN', [ 'cat_title = page_title' ]
  84                                 ]
  85                         ]
  86
  87                 );
  88                 $it->setCaller( $fname );
  89                 return $it;
  90         }
  91
  92         /**
  93          * Get iterator for links for categories.
  94          * @param IDatabase $dbr
  95          * @param int[] $ids List of page IDs
  96          * @param string $fname Name of the calling function
  97          * @return Traversable
  98          */
  99         public function getCategoryLinksIterator( IDatabase $dbr, array $ids, $fname ) {
 100                 $it = new BatchRowIterator(
 101                         $dbr,
 102                         'categorylinks',
 103                         [ 'cl_from', 'cl_to' ],
 104                         $this->getBatchSize()
 105                 );
 106                 $it->addConditions( [
 107                         'cl_type' => 'subcat',
 108                         'cl_from' => $ids
 109                 ] );
 110                 $it->setFetchColumns( [ 'cl_from', 'cl_to' ] );
 111                 $it->setCaller( $fname );
 112                 return new RecursiveIteratorIterator( $it );
 113         }
 114
 115         /**
 116          * @param int $timestamp
 117          */
 118         public function addDumpHeader( $timestamp ) {
 119                 global $wgRightsUrl;
 120                 $licenseUrl = $wgRightsUrl;
 121                 if ( substr( $licenseUrl, 0, 2 ) == '//' ) {
 122                         $licenseUrl = 'https:' . $licenseUrl;
 123                 }
 124                 $this->rdfWriter->about( $this->categoriesRdf->getDumpURI() )
 125                         ->a( 'schema', 'Dataset' )
 126                         ->a( 'owl', 'Ontology' )
 127                         ->say( 'cc', 'license' )->is( $licenseUrl )
 128                         ->say( 'schema', 'softwareVersion' )->value( CategoriesRdf::FORMAT_VERSION )
 129                         ->say( 'schema', 'dateModified' )
 130                         ->value( wfTimestamp( TS_ISO_8601, $timestamp ), 'xsd', 'dateTime' )
 131                         ->say( 'schema', 'isPartOf' )->is( wfExpandUrl( '/', PROTO_CANONICAL ) )
 132                         ->say( 'owl', 'imports' )->is( CategoriesRdf::OWL_URL );
 133         }
 134
 135         public function execute() {
 136                 $outFile = $this->getOption( 'output', 'php://stdout' );
 137
 138                 if ( $outFile === '-' ) {
 139                         $outFile = 'php://stdout';
 140                 }
 141
 142                 $output = fopen( $outFile, 'w' );
 143                 $this->rdfWriter = $this->createRdfWriter( $this->getOption( 'format', 'ttl' ) );
 144                 $this->categoriesRdf = new CategoriesRdf( $this->rdfWriter );
 145
 146                 $this->categoriesRdf->setupPrefixes();
 147                 $this->rdfWriter->start();
 148
 149                 $this->addDumpHeader( time() );
 150                 fwrite( $output, $this->rdfWriter->drain() );
 151
 152                 $dbr = $this->getDB( DB_REPLICA, [ 'vslow' ] );
 153
 154                 foreach ( $this->getCategoryIterator( $dbr, __METHOD__ ) as $batch ) {
 155                         $pages = [];
 156                         foreach ( $batch as $row ) {
 157                                 $this->categoriesRdf->writeCategoryData(
 158                                         $row->page_title,
 159                                         $row->pp_propname === 'hiddencat',
 160                                         (int)$row->cat_pages - (int)$row->cat_subcats - (int)$row->cat_files,
 161                                         (int)$row->cat_subcats
 162                                 );
 163                                 if ( $row->page_id ) {
 164                                         $pages[$row->page_id] = $row->page_title;
 165                                 }
 166                         }
 167
 168                         foreach ( $this->getCategoryLinksIterator( $dbr, array_keys( $pages ), __METHOD__ ) as $row ) {
 169                                 $this->categoriesRdf->writeCategoryLinkData( $pages[$row->cl_from], $row->cl_to );
 170                         }
 171                         fwrite( $output, $this->rdfWriter->drain() );
 172                 }
 173                 fflush( $output );
 174                 if ( $outFile !== '-' ) {
 175                         fclose( $output );
 176                 }
 177         }
 178
 179         /**
 180          * @param string $format Writer format
 181          * @return RdfWriter
 182          */
 183         private function createRdfWriter( $format ) {
 184                 $factory = new RdfWriterFactory();
 185                 return $factory->getWriter( $factory->getFormatName( $format ) );
 186         }
 187 }
 188
 189 $maintClass = DumpCategoriesAsRdf::class;
 190 require_once RUN_MAINTENANCE_IF_MAIN;