MediaWiki  master
findOrphanedFiles.php
Go to the documentation of this file.
1 <?php
21 require_once __DIR__ . '/Maintenance.php';
22 
24  function __construct() {
25  parent::__construct();
26 
27  $this->addDescription( "Find unregistered files in the 'public' repo zone." );
28  $this->addOption( 'subdir',
29  'Only scan files in this subdirectory (e.g. "a/a0")', false, true );
30  $this->addOption( 'verbose', "Mention file paths checked" );
31  $this->setBatchSize( 500 );
32  }
33 
34  function execute() {
35  $subdir = $this->getOption( 'subdir', '' );
36  $verbose = $this->hasOption( 'verbose' );
37 
38  $repo = RepoGroup::singleton()->getLocalRepo();
39  if ( $repo->hasSha1Storage() ) {
40  $this->fatalError( "Local repo uses SHA-1 file storage names; aborting." );
41  }
42 
43  $directory = $repo->getZonePath( 'public' );
44  if ( $subdir != '' ) {
45  $directory .= "/$subdir/";
46  }
47 
48  if ( $verbose ) {
49  $this->output( "Scanning files under $directory:\n" );
50  }
51 
52  $list = $repo->getBackend()->getFileList( [ 'dir' => $directory ] );
53  if ( $list === null ) {
54  $this->fatalError( "Could not get file listing." );
55  }
56 
57  $pathBatch = [];
58  foreach ( $list as $path ) {
59  if ( preg_match( '#^(thumb|deleted)/#', $path ) ) {
60  continue; // handle ugly nested containers on stock installs
61  }
62 
63  $pathBatch[] = $path;
64  if ( count( $pathBatch ) >= $this->getBatchSize() ) {
65  $this->checkFiles( $repo, $pathBatch, $verbose );
66  $pathBatch = [];
67  }
68  }
69  $this->checkFiles( $repo, $pathBatch, $verbose );
70  }
71 
72  protected function checkFiles( LocalRepo $repo, array $paths, $verbose ) {
73  if ( !count( $paths ) ) {
74  return;
75  }
76 
77  $dbr = $repo->getReplicaDB();
78 
79  $curNames = [];
80  $oldNames = [];
81  $imgIN = [];
82  $oiWheres = [];
83  foreach ( $paths as $path ) {
84  $name = basename( $path );
85  if ( preg_match( '#^archive/#', $path ) ) {
86  if ( $verbose ) {
87  $this->output( "Checking old file $name\n" );
88  }
89 
90  $oldNames[] = $name;
91  list( , $base ) = explode( '!', $name, 2 ); // <TS_MW>!<img_name>
92  $oiWheres[] = $dbr->makeList(
93  [ 'oi_name' => $base, 'oi_archive_name' => $name ],
94  LIST_AND
95  );
96  } else {
97  if ( $verbose ) {
98  $this->output( "Checking current file $name\n" );
99  }
100 
101  $curNames[] = $name;
102  $imgIN[] = $name;
103  }
104  }
105 
106  $res = $dbr->query(
107  $dbr->unionQueries(
108  [
109  $dbr->selectSQLText(
110  'image',
111  [ 'name' => 'img_name', 'old' => 0 ],
112  $imgIN ? [ 'img_name' => $imgIN ] : '1=0'
113  ),
114  $dbr->selectSQLText(
115  'oldimage',
116  [ 'name' => 'oi_archive_name', 'old' => 1 ],
117  $oiWheres ? $dbr->makeList( $oiWheres, LIST_OR ) : '1=0'
118  )
119  ],
120  $dbr::UNION_ALL
121  ),
122  __METHOD__
123  );
124 
125  $curNamesFound = [];
126  $oldNamesFound = [];
127  foreach ( $res as $row ) {
128  if ( $row->old ) {
129  $oldNamesFound[] = $row->name;
130  } else {
131  $curNamesFound[] = $row->name;
132  }
133  }
134 
135  foreach ( array_diff( $curNames, $curNamesFound ) as $name ) {
136  $file = $repo->newFile( $name );
137  // Print name and public URL to ease recovery
138  if ( $file ) {
139  $this->output( $name . "\n" . $file->getCanonicalUrl() . "\n\n" );
140  } else {
141  $this->error( "Cannot get URL for bad file title '$name'" );
142  }
143  }
144 
145  foreach ( array_diff( $oldNames, $oldNamesFound ) as $name ) {
146  list( , $base ) = explode( '!', $name, 2 ); // <TS_MW>!<img_name>
147  $file = $repo->newFromArchiveName( Title::makeTitle( NS_FILE, $base ), $name );
148  // Print name and public URL to ease recovery
149  $this->output( $name . "\n" . $file->getCanonicalUrl() . "\n\n" );
150  }
151  }
152 }
153 
155 require_once RUN_MAINTENANCE_IF_MAIN;
deferred txt A few of the database updates required by various functions here can be deferred until after the result page is displayed to the user For updating the view updating the linked to tables after a etc PHP does not yet have any way to tell the server to actually return and disconnect while still running these but it might have such a feature in the future We handle these by creating a deferred update object and putting those objects on a global list
Definition: deferred.txt:11
error( $err, $die=0)
Throw an error to the user.
newFromArchiveName( $title, $archiveName)
Definition: LocalRepo.php:85
getOption( $name, $default=null)
Get an option, or return the default.
if(PHP_SAPI !='cli-server') if(!isset( $_SERVER['SCRIPT_FILENAME'])) $file
Definition: router.php:42
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
Definition: maintenance.txt:39
getReplicaDB()
Get a connection to the replica DB.
Definition: LocalRepo.php:468
A repository that stores files in the local filesystem and registers them in the wiki&#39;s own database...
Definition: LocalRepo.php:36
setBatchSize( $s=0)
Set the batch size.
hasOption( $name)
Checks to see if a particular option exists.
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
checkFiles(LocalRepo $repo, array $paths, $verbose)
const LIST_AND
Definition: Defines.php:39
$res
Definition: database.txt:21
static singleton()
Definition: RepoGroup.php:60
addDescription( $text)
Set the description text.
newFile( $title, $time=false)
Create a new File object from the local repository.
Definition: FileRepo.php:390
this hook is for auditing only or null if authentication failed before getting that far or null if we can t even determine that When $user is not null
Definition: hooks.txt:773
const NS_FILE
Definition: Defines.php:66
output( $out, $channel=null)
Throw some output to the user.
This document is intended to provide useful advice for parties seeking to redistribute MediaWiki to end users It s targeted particularly at maintainers for Linux since it s been observed that distribution packages of MediaWiki often break We ve consistently had to recommend that users seeking support use official tarballs instead of their distribution s and this often solves whatever problem the user is having It would be nice if this could such as
Definition: distributors.txt:9
const LIST_OR
Definition: Defines.php:42
static makeTitle( $ns, $title, $fragment='', $interwiki='')
Create a new Title from a namespace index and a DB key.
Definition: Title.php:592
injection txt This is an overview of how MediaWiki makes use of dependency injection The design described here grew from the discussion of RFC T384 The term dependency this means that anything an object needs to operate should be injected from the the object itself should only know narrow no concrete implementation of the logic it relies on The requirement to inject everything typically results in an architecture that based on two main types of and essentially stateless service objects that use other service objects to operate on the value objects As of the beginning MediaWiki is only starting to use the DI approach Much of the code still relies on global state or direct resulting in a highly cyclical dependency which acts as the top level factory for services in MediaWiki which can be used to gain access to default instances of various services MediaWikiServices however also allows new services to be defined and default services to be redefined Services are defined or redefined by providing a callback the instantiator that will return a new instance of the service When it will create an instance of MediaWikiServices and populate it with the services defined in the files listed by thereby bootstrapping the DI framework Per $wgServiceWiringFiles lists includes ServiceWiring php
Definition: injection.txt:35
you have access to all of the normal MediaWiki so you can get a DB use the etc For full docs on the Maintenance class
Definition: maintenance.txt:52
getBatchSize()
Returns batch size.
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Allows to change the fields on the form that will be generated $name
Definition: hooks.txt:277
fatalError( $msg, $exitCode=1)
Output a message and terminate the current script.