maintenance/deleteSelfExternals.php

   1 <?php
   2 /**
   3  * Delete self-references to $wgServer from the externallinks table.
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License along
  16  * with this program; if not, write to the Free Software Foundation, Inc.,
  17  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18  * http://www.gnu.org/copyleft/gpl.html
  19  *
  20  * @file
  21  * @ingroup Maintenance
  22  */
  23
  24 use MediaWiki\ExternalLinks\LinkFilter;
  25 use MediaWiki\MainConfigNames;
  26 use MediaWiki\Maintenance\Maintenance;
  27
  28 // @codeCoverageIgnoreStart
  29 require_once __DIR__ . '/Maintenance.php';
  30 // @codeCoverageIgnoreEnd
  31
  32 /**
  33  * Maintenance script that deletes self-references to $wgServer
  34  * from the externallinks table.
  35  *
  36  * @ingroup Maintenance
  37  */
  38 class DeleteSelfExternals extends Maintenance {
  39         public function __construct() {
  40                 parent::__construct();
  41                 $this->addDescription( 'Delete self-references to $wgServer from externallinks' );
  42                 $this->setBatchSize( 1000 );
  43         }
  44
  45         public function execute() {
  46                 // Extract the host and scheme from $wgServer
  47                 $server = $this->getConfig()->get( MainConfigNames::Server );
  48                 $bits = $this->getServiceContainer()->getUrlUtils()->parse( $server );
  49                 if ( !$bits ) {
  50                         $this->fatalError( 'Could not parse $wgServer' );
  51                 }
  52
  53                 $this->output( "Deleting self externals from $server\n" );
  54                 $db = $this->getPrimaryDB();
  55
  56                 // If it's protocol-relative, we need to do both http and https.
  57                 // Otherwise, just do the specified scheme.
  58                 $host = $bits['host'];
  59                 if ( isset( $bits['port'] ) ) {
  60                         $host .= ':' . $bits['port'];
  61                 }
  62                 if ( $bits['scheme'] != '' ) {
  63                         $conds = [ LinkFilter::getQueryConditions( $host, [ 'protocol' => $bits['scheme'] . '://' ] ) ];
  64                 } else {
  65                         $conds = [
  66                                 LinkFilter::getQueryConditions( $host, [ 'protocol' => 'http://' ] ),
  67                                 LinkFilter::getQueryConditions( $host, [ 'protocol' => 'https://' ] ),
  68                         ];
  69                 }
  70
  71                 // Convert the array of $conds into an IExpression object for use in the DELETE query
  72                 // The use of array_filter is just there for a sanity check, as LinkFilter::getQueryConditions
  73                 // only returns false if the host was invalid (we have already validated this above).
  74                 $conds = array_map( static function ( $cond ) use ( $db ) {
  75                         return $db->andExpr( $cond );
  76                 }, array_filter( $conds ) );
  77                 $domainExpr = $db->orExpr( $conds );
  78
  79                 $totalRows = 0;
  80                 $batchStart = 0;
  81                 $batchEnd = $batchStart + $this->getBatchSize();
  82                 do {
  83                         $this->output( "Deleting self-externals with el_id $batchStart to $batchEnd\n" );
  84
  85                         $db->newDeleteQueryBuilder()
  86                                 ->deleteFrom( 'externallinks' )
  87                                 ->where( $domainExpr )
  88                                 ->andWhere( $db->expr( 'el_id', '>', $batchStart ) )
  89                                 ->andWhere( $db->expr( 'el_id', '<=', $batchEnd ) )
  90                                 ->caller( __METHOD__ )
  91                                 ->execute();
  92                         $rowsDeletedInThisBatch = $db->affectedRows();
  93                         $totalRows += $rowsDeletedInThisBatch;
  94
  95                         $batchStart += $this->getBatchSize();
  96                         $batchEnd += $this->getBatchSize();
  97                         $this->waitForReplication();
  98                 } while ( $rowsDeletedInThisBatch );
  99
 100                 $this->output( "done; deleted $totalRows rows\n" );
 101         }
 102 }
 103
 104 // @codeCoverageIgnoreStart
 105 $maintClass = DeleteSelfExternals::class;
 106 require_once RUN_MAINTENANCE_IF_MAIN;
 107 // @codeCoverageIgnoreEnd