maintenance/fixMergeHistoryCorruption.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  * @ingroup Maintenance
  20  */
  21
  22 // @codeCoverageIgnoreStart
  23 require_once __DIR__ . '/Maintenance.php';
  24 // @codeCoverageIgnoreEnd
  25
  26 use MediaWiki\Maintenance\Maintenance;
  27 use MediaWiki\Title\Title;
  28
  29 /**
  30  * Maintenance script that clears rows of pages corrupted by MergeHistory, those
  31  * pages 'exist' but have no visible revision.
  32  *
  33  * These pages are completely inaccessible via the UI due to revision/title mismatch
  34  * exceptions in RevisionStore and elsewhere.
  35  *
  36  * These are rows in page_table that have 'page_latest' entry with corresponding
  37  * 'rev_id' but no associated 'rev_page' entry in revision table. Such rows create
  38  * ghost pages because their 'page_latest' is actually living on different pages
  39  * (which possess the associated 'rev_page' on revision table now).
  40  *
  41  * @see https://phabricator.wikimedia.org/T263340
  42  * @see https://phabricator.wikimedia.org/T259022
  43  */
  44 class FixMergeHistoryCorruption extends Maintenance {
  45
  46         public function __construct() {
  47                 parent::__construct();
  48                 $this->addDescription( 'Delete pages corrupted by MergeHistory' );
  49                 $this->addOption( 'ns', 'Namespace to restrict the query', false, true );
  50                 $this->addOption( 'dry-run', 'Run in dry-mode' );
  51                 $this->addOption( 'delete', 'Actually delete the found rows' );
  52         }
  53
  54         public function execute() {
  55                 $dbr = $this->getReplicaDB();
  56                 $dbw = $this->getPrimaryDB();
  57
  58                 $dryRun = true;
  59                 if ( $this->hasOption( 'dry-run' ) && $this->hasOption( 'delete' ) ) {
  60                         $this->fatalError( 'Cannot do both --dry-run and --delete.' );
  61                 } elseif ( $this->hasOption( 'delete' ) ) {
  62                         $dryRun = false;
  63                 } elseif ( !$this->hasOption( 'dry-run' ) ) {
  64                         $this->fatalError( 'Either --dry-run or --delete must be specified.' );
  65                 }
  66
  67                 $conds = [ 'page_id<>rev_page' ];
  68                 if ( $this->hasOption( 'ns' ) ) {
  69                         $conds['page_namespace'] = (int)$this->getOption( 'ns' );
  70                 }
  71
  72                 $res = $dbr->newSelectQueryBuilder()
  73                         ->from( 'page' )
  74                         ->join( 'revision', null, 'page_latest=rev_id' )
  75                         ->fields( [ 'page_namespace', 'page_title', 'page_id' ] )
  76                         ->where( $conds )
  77                         ->caller( __METHOD__ )
  78                         ->fetchResultSet();
  79
  80                 $count = $res->numRows();
  81
  82                 if ( !$count ) {
  83                         $this->output( "Nothing was found, no page matches the criteria.\n" );
  84                         return;
  85                 }
  86
  87                 $numDeleted = 0;
  88                 $numUpdated = 0;
  89
  90                 foreach ( $res as $row ) {
  91                         $title = Title::makeTitleSafe( $row->page_namespace, $row->page_title );
  92                         if ( !$title ) {
  93                                 $this->output( "Skipping invalid title with page_id: $row->page_id\n" );
  94                                 continue;
  95                         }
  96                         $titleText = $title->getPrefixedDBkey();
  97
  98                         // Check if there are any revisions that have this $row->page_id as their
  99                         // rev_page and select the largest which should be the newest revision.
 100                         $revId = $dbr->newSelectQueryBuilder()
 101                                 ->select( 'MAX(rev_id)' )
 102                                 ->from( 'revision' )
 103                                 ->where( [ 'rev_page' => $row->page_id ] )
 104                                 ->caller( __METHOD__ )->fetchField();
 105
 106                         if ( !$revId ) {
 107                                 if ( $dryRun ) {
 108                                         $this->output( "Would delete $titleText with page_id: $row->page_id\n" );
 109                                 } else {
 110                                         $this->output( "Deleting $titleText with page_id: $row->page_id\n" );
 111                                         $dbw->newDeleteQueryBuilder()
 112                                                 ->deleteFrom( 'page' )
 113                                                 ->where( [ 'page_id' => $row->page_id ] )
 114                                                 ->caller( __METHOD__ )->execute();
 115                                 }
 116                                 $numDeleted++;
 117                         } else {
 118                                 if ( $dryRun ) {
 119                                         $this->output( "Would update page_id $row->page_id to page_latest $revId\n" );
 120                                 } else {
 121                                         $this->output( "Updating page_id $row->page_id to page_latest $revId\n" );
 122                                         $dbw->newUpdateQueryBuilder()
 123                                                 ->update( 'page' )
 124                                                 ->set( [ 'page_latest' => $revId ] )
 125                                                 ->where( [ 'page_id' => $row->page_id ] )
 126                                                 ->caller( __METHOD__ )->execute();
 127                                 }
 128                                 $numUpdated++;
 129                         }
 130                 }
 131
 132                 if ( !$dryRun ) {
 133                         $this->output( "Updated $numUpdated row(s), deleted $numDeleted row(s)\n" );
 134                 }
 135         }
 136 }
 137
 138 // @codeCoverageIgnoreStart
 139 $maintClass = FixMergeHistoryCorruption::class;
 140 require_once RUN_MAINTENANCE_IF_MAIN;
 141 // @codeCoverageIgnoreEnd