MediaWiki REL1_30
dumpCategoriesAsRdf.php
Go to the documentation of this file.
1<?php
19use Wikimedia\Purtle\RdfWriter;
20use Wikimedia\Purtle\RdfWriterFactory;
22
23require_once __DIR__ . '/Maintenance.php';
24
35 private $rdfWriter;
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
58 public function getCategoryIterator( IDatabase $dbr ) {
59 $it = new BatchRowIterator(
60 $dbr,
61 'page',
62 [ 'page_title' ],
63 $this->mBatchSize
64 );
65 $it->addConditions( [
66 'page_namespace' => NS_CATEGORY,
67 ] );
68 $it->setFetchColumns( [ 'page_title', 'page_id' ] );
69 return $it;
70 }
71
78 public function getCategoryLinksIterator( IDatabase $dbr, array $ids ) {
79 $it = new BatchRowIterator(
80 $dbr,
81 'categorylinks',
82 [ 'cl_from', 'cl_to' ],
83 $this->mBatchSize
84 );
85 $it->addConditions( [
86 'cl_type' => 'subcat',
87 'cl_from' => $ids
88 ] );
89 $it->setFetchColumns( [ 'cl_from', 'cl_to' ] );
90 return new RecursiveIteratorIterator( $it );
91 }
92
93 public function addDumpHeader( $timestamp ) {
94 global $wgRightsUrl;
95 $licenseUrl = $wgRightsUrl;
96 if ( substr( $licenseUrl, 0, 2 ) == '//' ) {
97 $licenseUrl = 'https:' . $licenseUrl;
98 }
99 $this->rdfWriter->about( wfExpandUrl( '/categoriesDump', PROTO_CANONICAL ) )
100 ->a( 'schema', 'Dataset' )
101 ->a( 'owl', 'Ontology' )
102 ->say( 'cc', 'license' )->is( $licenseUrl )
103 ->say( 'schema', 'softwareVersion' )->value( CategoriesRdf::FORMAT_VERSION )
104 ->say( 'schema', 'dateModified' )
105 ->value( wfTimestamp( TS_ISO_8601, $timestamp ), 'xsd', 'dateTime' )
106 ->say( 'schema', 'isPartOf' )->is( wfExpandUrl( '/', PROTO_CANONICAL ) )
107 ->say( 'owl', 'imports' )->is( CategoriesRdf::OWL_URL );
108 }
109
110 public function execute() {
111 $outFile = $this->getOption( 'output', 'php://stdout' );
112
113 if ( $outFile === '-' ) {
114 $outFile = 'php://stdout';
115 }
116
117 $output = fopen( $outFile, 'w' );
118 $this->rdfWriter = $this->createRdfWriter( $this->getOption( 'format', 'ttl' ) );
119 $this->categoriesRdf = new CategoriesRdf( $this->rdfWriter );
120
121 $this->categoriesRdf->setupPrefixes();
122 $this->rdfWriter->start();
123
124 $this->addDumpHeader( time() );
125 fwrite( $output, $this->rdfWriter->drain() );
126
127 $dbr = $this->getDB( DB_REPLICA, [ 'vslow' ] );
128
129 foreach ( $this->getCategoryIterator( $dbr ) as $batch ) {
130 $pages = [];
131 foreach ( $batch as $row ) {
132 $this->categoriesRdf->writeCategoryData( $row->page_title );
133 $pages[$row->page_id] = $row->page_title;
134 }
135
136 foreach ( $this->getCategoryLinksIterator( $dbr, array_keys( $pages ) ) as $row ) {
137 $this->categoriesRdf->writeCategoryLinkData( $pages[$row->cl_from], $row->cl_to );
138 }
139 fwrite( $output, $this->rdfWriter->drain() );
140 }
141 fflush( $output );
142 if ( $outFile !== '-' ) {
143 fclose( $output );
144 }
145 }
146
151 private function createRdfWriter( $format ) {
152 $factory = new RdfWriterFactory();
153 return $factory->getWriter( $factory->getFormatName( $format ) );
154 }
155}
156
157$maintClass = "DumpCategoriesAsRdf";
158require_once RUN_MAINTENANCE_IF_MAIN;
$wgRightsUrl
Set this to specify an external URL containing details about the content license used on your wiki.
wfExpandUrl( $url, $defaultProto=PROTO_CURRENT)
Expand a potentially local URL to a fully-qualified URL.
wfTimestamp( $outputtype=TS_UNIX, $ts=0)
Get a timestamp string in one of various formats.
Helper class to produce RDF representation of categories.
const FORMAT_VERSION
Current version of the dump format.
const OWL_URL
OWL description of the ontology.
Maintenance script to provide RDF representation of the category tree.
getCategoryIterator(IDatabase $dbr)
Produce row iterator for categories.
getCategoryLinksIterator(IDatabase $dbr, array $ids)
Get iterator for links for categories.
execute()
Do the actual work.
CategoriesRdf $categoriesRdf
Categories RDF helper.
__construct()
Default constructor.
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
getDB( $db, $groups=[], $wiki=false)
Returns a database to be used by current maintenance script.
addDescription( $text)
Set the description text.
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
getOption( $name, $default=null)
Get an option, or return the default.
setBatchSize( $s=0)
Set the batch size.
if(! $regexes) $dbr
Definition cleanup.php:94
static configuration should be added through ResourceLoaderGetConfigVars instead can be used to get the real title after the basic globals have been set but before ordinary actions take place $output
Definition hooks.txt:2225
const PROTO_CANONICAL
Definition Defines.php:224
const NS_CATEGORY
Definition Defines.php:79
Basic database interface for live and lazy-loaded relation database handles.
Definition IDatabase.php:40
$batch
Definition linkcache.txt:23
require_once RUN_MAINTENANCE_IF_MAIN
const DB_REPLICA
Definition defines.php:25