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