maintenance/findMissingFiles.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 use MediaWiki\MediaWikiServices;
  22
  23 require_once __DIR__ . '/Maintenance.php';
  24
  25 class FindMissingFiles extends Maintenance {
  26         public function __construct() {
  27                 parent::__construct();
  28
  29                 $this->addDescription( 'Find registered files with no corresponding file.' );
  30                 $this->addOption( 'start', 'Start after this file name', false, true );
  31                 $this->addOption( 'mtimeafter', 'Only include files changed since this time', false, true );
  32                 $this->addOption( 'mtimebefore', 'Only includes files changed before this time', false, true );
  33                 $this->setBatchSize( 300 );
  34         }
  35
  36         public function execute() {
  37                 $lastName = $this->getOption( 'start', '' );
  38
  39                 $repo = MediaWikiServices::getInstance()->getRepoGroup()->getLocalRepo();
  40                 $dbr = $repo->getReplicaDB();
  41                 $be = $repo->getBackend();
  42                 $batchSize = $this->getBatchSize();
  43
  44                 $mtime1 = $dbr->timestampOrNull( $this->getOption( 'mtimeafter', null ) );
  45                 $mtime2 = $dbr->timestampOrNull( $this->getOption( 'mtimebefore', null ) );
  46
  47                 $joinTables = [];
  48                 $joinConds = [];
  49                 if ( $mtime1 || $mtime2 ) {
  50                         $joinTables[] = 'page';
  51                         $joinConds['page'] = [ 'JOIN',
  52                                 [ 'page_title = img_name', 'page_namespace' => NS_FILE ] ];
  53                         $joinTables[] = 'logging';
  54                         $on = [ 'log_page = page_id', 'log_type' => [ 'upload', 'move', 'delete' ] ];
  55                         if ( $mtime1 ) {
  56                                 $on[] = "log_timestamp > {$dbr->addQuotes($mtime1)}";
  57                         }
  58                         if ( $mtime2 ) {
  59                                 $on[] = "log_timestamp < {$dbr->addQuotes($mtime2)}";
  60                         }
  61                         $joinConds['logging'] = [ 'JOIN', $on ];
  62                 }
  63
  64                 do {
  65                         $res = $dbr->select(
  66                                 array_merge( [ 'image' ], $joinTables ),
  67                                 [ 'name' => 'img_name' ],
  68                                 [ "img_name > " . $dbr->addQuotes( $lastName ) ],
  69                                 __METHOD__,
  70                                 // DISTINCT causes a pointless filesort
  71                                 [ 'ORDER BY' => 'name', 'GROUP BY' => 'name',
  72                                         'LIMIT' => $batchSize ],
  73                                 $joinConds
  74                         );
  75
  76                         // Check if any of these files are missing...
  77                         $pathsByName = [];
  78                         foreach ( $res as $row ) {
  79                                 $file = $repo->newFile( $row->name );
  80                                 $pathsByName[$row->name] = $file->getPath();
  81                                 $lastName = $row->name;
  82                         }
  83                         $be->preloadFileStat( [ 'srcs' => $pathsByName ] );
  84                         foreach ( $pathsByName as $path ) {
  85                                 if ( $be->fileExists( [ 'src' => $path ] ) === false ) {
  86                                         $this->output( "$path\n" );
  87                                 }
  88                         }
  89
  90                         // Find all missing old versions of any of the files in this batch...
  91                         if ( count( $pathsByName ) ) {
  92                                 $ores = $dbr->select( 'oldimage',
  93                                         [ 'oi_name', 'oi_archive_name' ],
  94                                         [ 'oi_name' => array_map( 'strval', array_keys( $pathsByName ) ) ],
  95                                         __METHOD__
  96                                 );
  97
  98                                 $checkPaths = [];
  99                                 foreach ( $ores as $row ) {
 100                                         if ( !strlen( $row->oi_archive_name ) ) {
 101                                                 // broken row
 102                                                 continue;
 103                                         }
 104                                         $file = $repo->newFromArchiveName( $row->oi_name, $row->oi_archive_name );
 105                                         $checkPaths[] = $file->getPath();
 106                                 }
 107
 108                                 foreach ( array_chunk( $checkPaths, $batchSize ) as $paths ) {
 109                                         $be->preloadFileStat( [ 'srcs' => $paths ] );
 110                                         foreach ( $paths as $path ) {
 111                                                 if ( $be->fileExists( [ 'src' => $path ] ) === false ) {
 112                                                         $this->output( "$path\n" );
 113                                                 }
 114                                         }
 115                                 }
 116                         }
 117                 } while ( $res->numRows() >= $batchSize );
 118         }
 119 }
 120
 121 $maintClass = FindMissingFiles::class;
 122 require_once RUN_MAINTENANCE_IF_MAIN;