MediaWiki REL1_30
findOrphanedFiles.php
Go to the documentation of this file.
1<?php
21require_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->error( "Local repo uses SHA-1 file storage names; aborting.", 1 );
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->error( "Could not get file listing.", 1 );
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->mBatchSize ) {
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 ],
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 true // UNION ALL (performance)
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" . $file->getCanonicalUrl() . "\n\n" );
150 }
151 }
152}
153
154$maintClass = 'FindOrphanedFiles';
155require_once RUN_MAINTENANCE_IF_MAIN;
newFile( $title, $time=false)
Create a new File object from the local repository.
Definition FileRepo.php:387
execute()
Do the actual work.
__construct()
Default constructor.
checkFiles(LocalRepo $repo, array $paths, $verbose)
A repository that stores files in the local filesystem and registers them in the wiki's own database.
Definition LocalRepo.php:35
getReplicaDB()
Get a connection to the replica DB.
newFromArchiveName( $title, $archiveName)
Definition LocalRepo.php:84
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
hasOption( $name)
Checks to see if a particular param exists.
addDescription( $text)
Set the description text.
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
getOption( $name, $default=null)
Get an option, or return the default.
setBatchSize( $s=0)
Set the batch size.
static singleton()
Get a RepoGroup instance.
Definition RepoGroup.php:59
if(! $regexes) $dbr
Definition cleanup.php:94
$res
Definition database.txt:21
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
design txt This is a brief overview of the new design More thorough and up to date information is available on the documentation wiki at etc Handles the details of getting and saving to the user table of the and dealing with sessions and cookies OutputPage Encapsulates the entire HTML page that will be sent in response to any server request It is used by calling its functions to add in any and then calling output() to send it all. It could be easily changed to send incrementally if that becomes useful
do that in ParserLimitReportFormat instead use this to modify the parameters of the image all existing parser cache entries will be invalid To avoid you ll need to handle that somehow(e.g. with the RejectParserCacheValue hook) because MediaWiki won 't do it for you. & $defaults error
Definition hooks.txt:2581
Allows to change the fields on the form that will be generated $name
Definition hooks.txt:302
const NS_FILE
Definition Defines.php:71
const LIST_OR
Definition Defines.php:47
const LIST_AND
Definition Defines.php:44
require_once RUN_MAINTENANCE_IF_MAIN