maintenance/fixInconsistentRedirects.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  * @file
  19  */
  20
  21 require_once __DIR__ . '/Maintenance.php';
  22
  23 /**
  24  * Fix redirect pages with missing or incomplete row in the redirect table.
  25  *
  26  * @ingroup Maintenance
  27  * @since 1.41
  28  */
  29 class FixInconsistentRedirects extends LoggedUpdateMaintenance {
  30
  31         public function __construct() {
  32                 parent::__construct();
  33                 $this->addDescription( 'Fix redirect pages with missing or incomplete row in the redirect table' );
  34                 $this->setBatchSize( 100 );
  35         }
  36
  37         protected function getUpdateKey() {
  38                 return __CLASS__;
  39         }
  40
  41         protected function doDBUpdates() {
  42                 $dbr = $this->getDB( DB_REPLICA );
  43
  44                 $builder = $dbr->newSelectQueryBuilder()
  45                         ->from( 'page' )
  46                         ->where( [ 'page_is_redirect' => 1 ] );
  47
  48                 $this->output( "Fixing inconsistent redirects ...\n" );
  49
  50                 $estimateCount = $builder->estimateRowCount();
  51                 $this->output( "Estimated redirect page count: $estimateCount\n" );
  52
  53                 $builder
  54                         ->limit( $this->getBatchSize() )
  55                         ->leftJoin( 'redirect', null, 'page_id=rd_from' )
  56                         ->select( [ 'rd_from', 'rd_interwiki', 'rd_fragment' ] );
  57
  58                 // Using the page_redirect_namespace_len index to skip non-redirects
  59                 $index = [ 'page_is_redirect', 'page_namespace', 'page_len', 'page_id' ];
  60                 $builder->select( $index )->orderBy( $index );
  61                 $prevRow = [];
  62
  63                 $total = 0;
  64                 $updated = 0;
  65                 do {
  66                         $res = ( clone $builder )
  67                                 ->where( $prevRow ? [ $dbr->buildComparison( '>', $prevRow ) ] : [] )
  68                                 ->caller( __METHOD__ )->fetchResultSet();
  69
  70                         foreach ( $res as $row ) {
  71                                 // Only attempt write queries if the row or rd_interwiki/rd_fragment fields are missing
  72                                 // (we don't include this condition in the query to avoid slow queries and bad estimates)
  73                                 if ( $row->rd_from === null || $row->rd_interwiki === null || $row->rd_fragment === null ) {
  74                                         RefreshLinks::fixRedirect( $this, $row->page_id );
  75                                         $updated++;
  76                                 }
  77                         }
  78                         if ( isset( $row ) ) {
  79                                 // Update the conditions to select the next batch
  80                                 foreach ( $index as $field ) {
  81                                         $prevRow[ $field ] = $row->$field;
  82                                 }
  83                         }
  84
  85                         $this->waitForReplication();
  86                         $total += $res->numRows();
  87                         $this->output( "$updated/$total\n" );
  88
  89                 } while ( $res->numRows() == $this->getBatchSize() );
  90
  91                 $this->output( "Done, updated $updated of $total rows.\n" );
  92                 return true;
  93         }
  94 }
  95
  96 $maintClass = FixInconsistentRedirects::class;
  97 require_once RUN_MAINTENANCE_IF_MAIN;