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
  41                 $mtime1 = $dbr->timestampOrNull( $this->getOption( 'mtimeafter', null ) );
  42                 $mtime2 = $dbr->timestampOrNull( $this->getOption( 'mtimebefore', null ) );
  43
  44                 $joinTables = [];
  45                 $joinConds = [];
  46                 if ( $mtime1 || $mtime2 ) {
  47                         $joinTables[] = 'page';
  48                         $joinConds['page'] = [ 'INNER JOIN',
  49                                 [ 'page_title = img_name', 'page_namespace' => NS_FILE ] ];
  50                         $joinTables[] = 'logging';
  51                         $on = [ 'log_page = page_id', 'log_type' => [ 'upload', 'move', 'delete' ] ];
  52                         if ( $mtime1 ) {
  53                                 $on[] = "log_timestamp > {$dbr->addQuotes($mtime1)}";
  54                         }
  55                         if ( $mtime2 ) {
  56                                 $on[] = "log_timestamp < {$dbr->addQuotes($mtime2)}";
  57                         }
  58                         $joinConds['logging'] = [ 'INNER JOIN', $on ];
  59                 }
  60
  61                 do {
  62                         $res = $dbr->select(
  63                                 array_merge( [ 'image' ], $joinTables ),
  64                                 [ 'name' => 'img_name' ],
  65                                 [ "img_name > " . $dbr->addQuotes( $lastName ) ],
  66                                 __METHOD__,
  67                                 // DISTINCT causes a pointless filesort
  68                                 [ 'ORDER BY' => 'name', 'GROUP BY' => 'name',
  69                                         'LIMIT' => $this->mBatchSize ],
  70                                 $joinConds
  71                         );
  72
  73                         // Check if any of these files are missing...
  74                         $pathsByName = [];
  75                         foreach ( $res as $row ) {
  76                                 $file = $repo->newFile( $row->name );
  77                                 $pathsByName[$row->name] = $file->getPath();
  78                                 $lastName = $row->name;
  79                         }
  80                         $be->preloadFileStat( [ 'srcs' => $pathsByName ] );
  81                         foreach ( $pathsByName as $path ) {
  82                                 if ( $be->fileExists( [ 'src' => $path ] ) === false ) {
  83                                         $this->output( "$path\n" );
  84                                 }
  85                         }
  86
  87                         // Find all missing old versions of any of the files in this batch...
  88                         if ( count( $pathsByName ) ) {
  89                                 $ores = $dbr->select( 'oldimage',
  90                                         [ 'oi_name', 'oi_archive_name' ],
  91                                         [ 'oi_name' => array_keys( $pathsByName ) ],
  92                                         __METHOD__
  93                                 );
  94
  95                                 $checkPaths = [];
  96                                 foreach ( $ores as $row ) {
  97                                         if ( !strlen( $row->oi_archive_name ) ) {
  98                                                 continue; // broken row
  99                                         }
 100                                         $file = $repo->newFromArchiveName( $row->oi_name, $row->oi_archive_name );
 101                                         $checkPaths[] = $file->getPath();
 102                                 }
 103
 104                                 foreach ( array_chunk( $checkPaths, $this->mBatchSize ) as $paths ) {
 105                                         $be->preloadFileStat( [ 'srcs' => $paths ] );
 106                                         foreach ( $paths as $path ) {
 107                                                 if ( $be->fileExists( [ 'src' => $path ] ) === false ) {
 108                                                         $this->output( "$path\n" );
 109                                                 }
 110                                         }
 111                                 }
 112                         }
 113                 } while ( $res->numRows() >= $this->mBatchSize );
 114         }
 115 }
 116
 117 $maintClass = 'FindMissingFiles';
 118 require_once RUN_MAINTENANCE_IF_MAIN;