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