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         public 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         public function execute() {
  35                 $lastName = $this->getOption( 'start', '' );
  36
  37                 $repo = $this->getServiceContainer()->getRepoGroup()->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                 $queryBuilder = $dbr->newSelectQueryBuilder()
  46                         ->select( [ 'name' => 'img_name' ] )
  47                         ->from( 'image' )
  48                         ->where( [ "img_name > " . $dbr->addQuotes( $lastName ) ] )
  49                         ->groupBy( 'name' )
  50                         ->orderBy( 'name' )
  51                         ->limit( $batchSize );
  52
  53                 if ( $mtime1 || $mtime2 ) {
  54                         $queryBuilder->join( 'page', null, 'page_title = img_name' );
  55                         $queryBuilder->andWhere( [ 'page_namespace' => NS_FILE ] );
  56
  57                         $queryBuilder->join( 'logging', null, 'log_page = page_id' );
  58                         $queryBuilder->andWhere( [ 'log_type' => [ 'upload', 'move', 'delete' ] ] );
  59                         if ( $mtime1 ) {
  60                                 $queryBuilder->andWhere( "log_timestamp > {$dbr->addQuotes($mtime1)}" );
  61                         }
  62                         if ( $mtime2 ) {
  63                                 $queryBuilder->andWhere( "log_timestamp < {$dbr->addQuotes($mtime2)}" );
  64                         }
  65                 }
  66
  67                 do {
  68                         $res = $queryBuilder->caller( __METHOD__ )->fetchResultSet();
  69
  70                         // Check if any of these files are missing...
  71                         $pathsByName = [];
  72                         foreach ( $res as $row ) {
  73                                 $file = $repo->newFile( $row->name );
  74                                 $pathsByName[$row->name] = $file->getPath();
  75                                 $lastName = $row->name;
  76                         }
  77                         $be->preloadFileStat( [ 'srcs' => $pathsByName ] );
  78                         foreach ( $pathsByName as $path ) {
  79                                 if ( $be->fileExists( [ 'src' => $path ] ) === false ) {
  80                                         $this->output( "$path\n" );
  81                                 }
  82                         }
  83
  84                         // Find all missing old versions of any of the files in this batch...
  85                         if ( count( $pathsByName ) ) {
  86                                 $ores = $dbr->newSelectQueryBuilder()
  87                                         ->select( [ 'oi_name', 'oi_archive_name' ] )
  88                                         ->from( 'oldimage' )
  89                                         ->where( [ 'oi_name' => array_map( 'strval', array_keys( $pathsByName ) ) ] )
  90                                         ->caller( __METHOD__ )->fetchResultSet();
  91
  92                                 $checkPaths = [];
  93                                 foreach ( $ores as $row ) {
  94                                         if ( !strlen( $row->oi_archive_name ) ) {
  95                                                 // broken row
  96                                                 continue;
  97                                         }
  98                                         $file = $repo->newFromArchiveName( $row->oi_name, $row->oi_archive_name );
  99                                         $checkPaths[] = $file->getPath();
 100                                 }
 101
 102                                 foreach ( array_chunk( $checkPaths, $batchSize ) as $paths ) {
 103                                         $be->preloadFileStat( [ 'srcs' => $paths ] );
 104                                         foreach ( $paths as $path ) {
 105                                                 if ( $be->fileExists( [ 'src' => $path ] ) === false ) {
 106                                                         $this->output( "$path\n" );
 107                                                 }
 108                                         }
 109                                 }
 110                         }
 111                 } while ( $res->numRows() >= $batchSize );
 112         }
 113 }
 114
 115 $maintClass = FindMissingFiles::class;
 116 require_once RUN_MAINTENANCE_IF_MAIN;