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  * @author Aaron Schulz
  20  */
  21
  22 require_once __DIR__ . '/Maintenance.php';
  23
  24 class FindMissingFiles extends Maintenance {
  25         function __construct() {
  26                 parent::__construct();
  27
  28                 $this->mDescription = 'Find registered files with no corresponding file.';
  29                 $this->addOption( 'start', 'Starting file name', false, true );
  30                 $this->addOption( 'mtimeafter', 'Only include files changed since this time', false, true );
  31                 $this->addOption( 'mtimebefore', 'Only includes files changed before this time', false, true );
  32                 $this->setBatchSize( 300 );
  33         }
  34
  35         function execute() {
  36                 $lastName = $this->getOption( 'start', '' );
  37
  38                 $repo = RepoGroup::singleton()->getLocalRepo();
  39                 $dbr = $repo->getSlaveDB();
  40                 $be = $repo->getBackend();
  41
  42                 $mtime1 = $dbr->timestampOrNull( $this->getOption( 'mtimeafter', null ) );
  43                 $mtime2 = $dbr->timestampOrNull( $this->getOption( 'mtimebefore', null ) );
  44
  45                 $tables = array( 'image' );
  46                 $logJoinOn = array( 'log_namespace' => NS_FILE, 'log_title = img_name' );
  47                 $logJoinOn['log_type'] = array( 'upload', 'move', 'delete' );
  48                 if ( $mtime1 ) {
  49                         $logJoinOn[] = "log_timestamp > {$dbr->addQuotes($mtime1)}";
  50                 }
  51                 if ( $mtime2 ) {
  52                         $logJoinOn[] = "log_timestamp < {$dbr->addQuotes($mtime2)}";
  53                 }
  54                 if ( $mtime1 || $mtime2 ) {
  55                         $tables[] = 'logging';
  56                 }
  57
  58                 do {
  59                         $res = $dbr->select( $tables,
  60                                 array( 'img_name' => 'DISTINCT(img_name)' ),
  61                                 array( "img_name >= " . $dbr->addQuotes( $lastName ) ),
  62                                 __METHOD__,
  63                                 array( 'ORDER BY' => 'img_name', 'LIMIT' => $this->mBatchSize ),
  64                                 array( 'logging' => array( 'INNER JOIN', $logJoinOn ) )
  65                         );
  66
  67                         // Check if any of these files are missing...
  68                         $pathsByName = array();
  69                         foreach ( $res as $row ) {
  70                                 $file = $repo->newFile( $row->img_name );
  71                                 $pathsByName[$row->img_name] = $file->getPath();
  72                                 $lastName = $row->img_name;
  73                         }
  74                         $be->preloadFileStat( array( 'srcs' => $pathsByName ) );
  75                         foreach ( $pathsByName as $path ) {
  76                                 if ( $be->fileExists( array( 'src' => $path ) ) === false ) {
  77                                         $this->output( "$path\n" );
  78                                 }
  79                         }
  80
  81                         // Find all missing old versions of any of the files in this batch...
  82                         if ( count( $pathsByName ) ) {
  83                                 $ores = $dbr->select( 'oldimage',
  84                                         array( 'oi_name', 'oi_archive_name' ),
  85                                         array( 'oi_name' => array_keys( $pathsByName ) ),
  86                                         __METHOD__
  87                                 );
  88                                 foreach ( $ores as $row ) {
  89                                         if ( !strlen( $row->oi_archive_name ) ) {
  90                                                 continue; // broken row
  91                                         }
  92                                         $file = $repo->newFromArchiveName( $row->oi_name, $row->oi_archive_name );
  93                                         $path = $file->getPath();
  94                                         if ( $be->fileExists( array( 'src' => $path ) ) === false ) {
  95                                                 $this->output( "$path\n" );
  96                                         }
  97                                 }
  98                         }
  99                 } while ( $res->numRows() >= $this->mBatchSize );
 100         }
 101 }
 102
 103 $maintClass = 'FindMissingFiles';
 104 require_once RUN_MAINTENANCE_IF_MAIN;