maintenance/populateInterwiki.php

   1 <?php
   2
   3 /**
   4  * Maintenance script that populates the interwiki table with list of sites from
   5  * a source wiki, such as English Wikipedia. (the default source)
   6  *
   7  * This program is free software; you can redistribute it and/or modify
   8  * it under the terms of the GNU General Public License as published by
   9  * the Free Software Foundation; either version 2 of the License, or
  10  * (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful,
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License along
  18  * with this program; if not, write to the Free Software Foundation, Inc.,
  19  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  20  * http://www.gnu.org/copyleft/gpl.html
  21  *
  22  * @file
  23  * @ingroup Maintenance
  24  * @author Katie Filbert < aude.wiki@gmail.com >
  25  */
  26
  27 use MediaWiki\Maintenance\Maintenance;
  28
  29 // @codeCoverageIgnoreStart
  30 require_once __DIR__ . '/Maintenance.php';
  31 // @codeCoverageIgnoreEnd
  32
  33 class PopulateInterwiki extends Maintenance {
  34
  35         /**
  36          * @var string
  37          */
  38         private $source;
  39
  40         public function __construct() {
  41                 parent::__construct();
  42
  43                 $this->addDescription( <<<TEXT
  44 This script will populate the interwiki table, pulling in interwiki links that are used on Wikipedia
  45 or another MediaWiki wiki.
  46
  47 When the script has finished, it will make a note of this in the database, and will not run again
  48 without the --force option.
  49
  50 --source parameter is the url for the source wiki api, such as "https://en.wikipedia.org/w/api.php"
  51 (the default) from which the script fetches the interwiki data and uses here to populate
  52 the interwiki database table.
  53 TEXT
  54                 );
  55
  56                 $this->addOption( 'source', 'Source wiki for interwiki table, such as '
  57                         . 'https://en.wikipedia.org/w/api.php (the default)', false, true );
  58                 $this->addOption( 'force', 'Run regardless of whether the database says it has '
  59                         . 'been run already.' );
  60         }
  61
  62         public function execute() {
  63                 $force = $this->hasOption( 'force' );
  64                 $this->source = $this->getOption( 'source', 'https://en.wikipedia.org/w/api.php' );
  65
  66                 $data = $this->fetchLinks();
  67
  68                 if ( $data === false ) {
  69                         $this->error( "Error during fetching data." );
  70                 } else {
  71                         $this->doPopulate( $data, $force );
  72                 }
  73         }
  74
  75         /**
  76          * @return array[]|false The 'interwikimap' sub-array or false on failure.
  77          */
  78         protected function fetchLinks() {
  79                 $url = wfArrayToCgi( [
  80                         'action' => 'query',
  81                         'meta' => 'siteinfo',
  82                         'siprop' => 'interwikimap',
  83                         'sifilteriw' => 'local',
  84                         'format' => 'json'
  85                 ] );
  86
  87                 if ( $this->source ) {
  88                         $url = rtrim( $this->source, '?' ) . '?' . $url;
  89                 }
  90
  91                 $json = $this->getServiceContainer()->getHttpRequestFactory()->get( $url, [], __METHOD__ );
  92                 $data = json_decode( $json, true );
  93
  94                 if ( is_array( $data ) ) {
  95                         return $data['query']['interwikimap'];
  96                 } else {
  97                         return false;
  98                 }
  99         }
 100
 101         /**
 102          * @param array[] $data
 103          * @param bool $force
 104          *
 105          * @return bool
 106          */
 107         protected function doPopulate( array $data, $force ) {
 108                 $dbw = $this->getPrimaryDB();
 109
 110                 if ( !$force ) {
 111                         $row = $dbw->newSelectQueryBuilder()
 112                                 ->select( '1' )
 113                                 ->from( 'updatelog' )
 114                                 ->where( [ 'ul_key' => 'populate interwiki' ] )
 115                                 ->caller( __METHOD__ )->fetchRow();
 116
 117                         if ( $row ) {
 118                                 $this->output( "Interwiki table already populated.  Use php " .
 119                                         "maintenance/populateInterwiki.php\n--force from the command line " .
 120                                         "to override.\n" );
 121                                 return true;
 122                         }
 123                 }
 124
 125                 $lookup = $this->getServiceContainer()->getInterwikiLookup();
 126                 foreach ( $data as $d ) {
 127                         $prefix = $d['prefix'];
 128
 129                         $row = $dbw->newSelectQueryBuilder()
 130                                 ->select( '1' )
 131                                 ->from( 'interwiki' )
 132                                 ->where( [ 'iw_prefix' => $prefix ] )
 133                                 ->caller( __METHOD__ )->fetchRow();
 134
 135                         if ( !$row ) {
 136                                 $dbw->newInsertQueryBuilder()
 137                                         ->insertInto( 'interwiki' )
 138                                         ->ignore()
 139                                         ->row( [
 140                                                 'iw_prefix' => $prefix,
 141                                                 'iw_url' => $d['url'],
 142                                                 'iw_local' => 1,
 143                                                 'iw_api' => '',
 144                                                 'iw_wikiid' => '',
 145                                         ] )
 146                                         ->caller( __METHOD__ )->execute();
 147                         }
 148
 149                         $lookup->invalidateCache( $prefix );
 150                 }
 151
 152                 $this->output( "Interwiki links are populated.\n" );
 153
 154                 return true;
 155         }
 156
 157 }
 158
 159 // @codeCoverageIgnoreStart
 160 $maintClass = PopulateInterwiki::class;
 161 require_once RUN_MAINTENANCE_IF_MAIN;
 162 // @codeCoverageIgnoreEnd