MediaWiki  1.28.0
migrateFileRepoLayout.php
Go to the documentation of this file.
1 <?php
24 require_once __DIR__ . '/Maintenance.php';
25 
34  public function __construct() {
35  parent::__construct();
36  $this->addDescription( 'Copy files in repo to a different layout.' );
37  $this->addOption( 'oldlayout', "Old layout; one of 'name' or 'sha1'", true, true );
38  $this->addOption( 'newlayout', "New layout; one of 'name' or 'sha1'", true, true );
39  $this->addOption( 'since', "Copy only files from after this timestamp", false, true );
40  $this->setBatchSize( 50 );
41  }
42 
43  public function execute() {
44  $oldLayout = $this->getOption( 'oldlayout' );
45  if ( !in_array( $oldLayout, [ 'name', 'sha1' ] ) ) {
46  $this->error( "Invalid old layout.", 1 );
47  }
48  $newLayout = $this->getOption( 'newlayout' );
49  if ( !in_array( $newLayout, [ 'name', 'sha1' ] ) ) {
50  $this->error( "Invalid new layout.", 1 );
51  }
52  $since = $this->getOption( 'since' );
53 
54  $repo = $this->getRepo();
55 
56  $be = $repo->getBackend();
57  if ( $be instanceof FileBackendDBRepoWrapper ) {
58  $be = $be->getInternalBackend(); // avoid path translations for this script
59  }
60 
61  $dbw = $repo->getMasterDB();
62 
63  $origBase = $be->getContainerStoragePath( "{$repo->getName()}-original" );
64  $startTime = wfTimestampNow();
65 
66  // Do current and archived versions...
67  $conds = [];
68  if ( $since ) {
69  $conds[] = 'img_timestamp >= ' . $dbw->addQuotes( $dbw->timestamp( $since ) );
70  }
71 
72  $batch = [];
73  $lastName = '';
74  do {
75  $res = $dbw->select( 'image',
76  [ 'img_name', 'img_sha1' ],
77  array_merge( [ 'img_name > ' . $dbw->addQuotes( $lastName ) ], $conds ),
78  __METHOD__,
79  [ 'LIMIT' => $this->mBatchSize, 'ORDER BY' => 'img_name' ]
80  );
81 
82  foreach ( $res as $row ) {
83  $lastName = $row->img_name;
85  $file = $repo->newFile( $row->img_name );
86  // Check in case SHA1 rows are not populated for some files
87  $sha1 = strlen( $row->img_sha1 ) ? $row->img_sha1 : $file->getSha1();
88 
89  if ( !strlen( $sha1 ) ) {
90  $this->error( "Image SHA-1 not known for {$row->img_name}." );
91  } else {
92  if ( $oldLayout === 'sha1' ) {
93  $spath = "{$origBase}/{$sha1[0]}/{$sha1[1]}/{$sha1[2]}/{$sha1}";
94  } else {
95  $spath = $file->getPath();
96  }
97 
98  if ( $newLayout === 'sha1' ) {
99  $dpath = "{$origBase}/{$sha1[0]}/{$sha1[1]}/{$sha1[2]}/{$sha1}";
100  } else {
101  $dpath = $file->getPath();
102  }
103 
104  $status = $be->prepare( [
105  'dir' => dirname( $dpath ), 'bypassReadOnly' => 1 ] );
106  if ( !$status->isOK() ) {
107  $this->error( print_r( $status->getErrors(), true ) );
108  }
109 
110  $batch[] = [ 'op' => 'copy', 'overwrite' => true,
111  'src' => $spath, 'dst' => $dpath, 'img' => $row->img_name ];
112  }
113 
114  foreach ( $file->getHistory() as $ofile ) {
115  $sha1 = $ofile->getSha1();
116  if ( !strlen( $sha1 ) ) {
117  $this->error( "Image SHA-1 not set for {$ofile->getArchiveName()}." );
118  continue;
119  }
120 
121  if ( $oldLayout === 'sha1' ) {
122  $spath = "{$origBase}/{$sha1[0]}/{$sha1[1]}/{$sha1[2]}/{$sha1}";
123  } elseif ( $ofile->isDeleted( File::DELETED_FILE ) ) {
124  $spath = $be->getContainerStoragePath( "{$repo->getName()}-deleted" ) .
125  '/' . $repo->getDeletedHashPath( $sha1 ) .
126  $sha1 . '.' . $ofile->getExtension();
127  } else {
128  $spath = $ofile->getPath();
129  }
130 
131  if ( $newLayout === 'sha1' ) {
132  $dpath = "{$origBase}/{$sha1[0]}/{$sha1[1]}/{$sha1[2]}/{$sha1}";
133  } else {
134  $dpath = $ofile->getPath();
135  }
136 
137  $status = $be->prepare( [
138  'dir' => dirname( $dpath ), 'bypassReadOnly' => 1 ] );
139  if ( !$status->isOK() ) {
140  $this->error( print_r( $status->getErrors(), true ) );
141  }
142  $batch[] = [ 'op' => 'copy', 'overwrite' => true,
143  'src' => $spath, 'dst' => $dpath, 'img' => $ofile->getArchiveName() ];
144  }
145 
146  if ( count( $batch ) >= $this->mBatchSize ) {
147  $this->runBatch( $batch, $be );
148  $batch = [];
149  }
150  }
151  } while ( $res->numRows() );
152 
153  if ( count( $batch ) ) {
154  $this->runBatch( $batch, $be );
155  }
156 
157  // Do deleted versions...
158  $conds = [];
159  if ( $since ) {
160  $conds[] = 'fa_deleted_timestamp >= ' . $dbw->addQuotes( $dbw->timestamp( $since ) );
161  }
162 
163  $batch = [];
164  $lastId = 0;
165  do {
166  $res = $dbw->select( 'filearchive', [ 'fa_storage_key', 'fa_id', 'fa_name' ],
167  array_merge( [ 'fa_id > ' . $dbw->addQuotes( $lastId ) ], $conds ),
168  __METHOD__,
169  [ 'LIMIT' => $this->mBatchSize, 'ORDER BY' => 'fa_id' ]
170  );
171 
172  foreach ( $res as $row ) {
173  $lastId = $row->fa_id;
174  $sha1Key = $row->fa_storage_key;
175  if ( !strlen( $sha1Key ) ) {
176  $this->error( "Image SHA-1 not set for file #{$row->fa_id} (deleted)." );
177  continue;
178  }
179  $sha1 = substr( $sha1Key, 0, strpos( $sha1Key, '.' ) );
180 
181  if ( $oldLayout === 'sha1' ) {
182  $spath = "{$origBase}/{$sha1[0]}/{$sha1[1]}/{$sha1[2]}/{$sha1}";
183  } else {
184  $spath = $be->getContainerStoragePath( "{$repo->getName()}-deleted" ) .
185  '/' . $repo->getDeletedHashPath( $sha1Key ) . $sha1Key;
186  }
187 
188  if ( $newLayout === 'sha1' ) {
189  $dpath = "{$origBase}/{$sha1[0]}/{$sha1[1]}/{$sha1[2]}/{$sha1}";
190  } else {
191  $dpath = $be->getContainerStoragePath( "{$repo->getName()}-deleted" ) .
192  '/' . $repo->getDeletedHashPath( $sha1Key ) . $sha1Key;
193  }
194 
195  $status = $be->prepare( [
196  'dir' => dirname( $dpath ), 'bypassReadOnly' => 1 ] );
197  if ( !$status->isOK() ) {
198  $this->error( print_r( $status->getErrors(), true ) );
199  }
200 
201  $batch[] = [ 'op' => 'copy', 'src' => $spath, 'dst' => $dpath,
202  'overwriteSame' => true, 'img' => "(ID {$row->fa_id}) {$row->fa_name}" ];
203 
204  if ( count( $batch ) >= $this->mBatchSize ) {
205  $this->runBatch( $batch, $be );
206  $batch = [];
207  }
208  }
209  } while ( $res->numRows() );
210 
211  if ( count( $batch ) ) {
212  $this->runBatch( $batch, $be );
213  }
214 
215  $this->output( "Done (started $startTime)\n" );
216  }
217 
218  protected function getRepo() {
219  return RepoGroup::singleton()->getLocalRepo();
220  }
221 
222  protected function runBatch( array $ops, FileBackend $be ) {
223  $this->output( "Migrating file batch:\n" );
224  foreach ( $ops as $op ) {
225  $this->output( "\"{$op['img']}\" (dest: {$op['dst']})\n" );
226  }
227 
228  $status = $be->doOperations( $ops, [ 'bypassReadOnly' => 1 ] );
229  if ( !$status->isOK() ) {
230  $this->output( print_r( $status->getErrors(), true ) );
231  }
232 
233  $this->output( "Batch done\n\n" );
234  }
235 }
236 
237 $maintClass = 'MigrateFileRepoLayout';
238 require_once RUN_MAINTENANCE_IF_MAIN;
the array() calling protocol came about after MediaWiki 1.4rc1.
doOperations(array $ops, array $opts=[])
This is the main entry point into the backend for write operations.
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
Definition: maintenance.txt:39
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
const DELETED_FILE
Definition: File.php:52
runBatch(array $ops, FileBackend $be)
$batch
Definition: linkcache.txt:23
null means default in associative array with keys and values unescaped Should be merged with default with a value of false meaning to suppress the attribute in associative array with keys and values unescaped noclasses just before the function returns a value If you return true
Definition: hooks.txt:1936
Copy all files in FileRepo to an originals container using SHA1 paths.
addOption($name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
$res
Definition: database.txt:21
static singleton()
Get a RepoGroup instance.
Definition: RepoGroup.php:59
wfTimestampNow()
Convenience function; returns MediaWiki timestamp for the present time.
addDescription($text)
Set the description text.
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
getOption($name, $default=null)
Get an option, or return the default.
output($out, $channel=null)
Throw some output to the user.
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 $wgServiceWiringFiles lists includes ServiceWiring php
Definition: injection.txt:35
error($err, $die=0)
Throw an error to the user.
Base class for all file backend classes (including multi-write backends).
Definition: FileBackend.php:93
this hook is for auditing only RecentChangesLinked and Watchlist RecentChangesLinked and Watchlist e g Watchlist removed from all revisions and log entries to which it was applied This gives extensions a chance to take it off their books as the deletion has already been partly carried out by this point or something similar the user will be unable to create the tag set $status
Definition: hooks.txt:1046
setBatchSize($s=0)
Set the batch size.
Proxy backend that manages file layout rewriting for FileRepo.