MediaWiki  1.33.0
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->fatalError( "Invalid old layout." );
47  }
48  $newLayout = $this->getOption( 'newlayout' );
49  if ( !in_array( $newLayout, [ 'name', 'sha1' ] ) ) {
50  $this->fatalError( "Invalid new layout." );
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  $batchSize = $this->getBatchSize();
73  $batch = [];
74  $lastName = '';
75  do {
76  $res = $dbw->select( 'image',
77  [ 'img_name', 'img_sha1' ],
78  array_merge( [ 'img_name > ' . $dbw->addQuotes( $lastName ) ], $conds ),
79  __METHOD__,
80  [ 'LIMIT' => $batchSize, 'ORDER BY' => 'img_name' ]
81  );
82 
83  foreach ( $res as $row ) {
84  $lastName = $row->img_name;
86  $file = $repo->newFile( $row->img_name );
87  // Check in case SHA1 rows are not populated for some files
88  $sha1 = strlen( $row->img_sha1 ) ? $row->img_sha1 : $file->getSha1();
89 
90  if ( !strlen( $sha1 ) ) {
91  $this->error( "Image SHA-1 not known for {$row->img_name}." );
92  } else {
93  if ( $oldLayout === 'sha1' ) {
94  $spath = "{$origBase}/{$sha1[0]}/{$sha1[1]}/{$sha1[2]}/{$sha1}";
95  } else {
96  $spath = $file->getPath();
97  }
98 
99  if ( $newLayout === 'sha1' ) {
100  $dpath = "{$origBase}/{$sha1[0]}/{$sha1[1]}/{$sha1[2]}/{$sha1}";
101  } else {
102  $dpath = $file->getPath();
103  }
104 
105  $status = $be->prepare( [
106  'dir' => dirname( $dpath ), 'bypassReadOnly' => 1 ] );
107  if ( !$status->isOK() ) {
108  $this->error( print_r( $status->getErrors(), true ) );
109  }
110 
111  $batch[] = [ 'op' => 'copy', 'overwrite' => true,
112  'src' => $spath, 'dst' => $dpath, 'img' => $row->img_name ];
113  }
114 
115  foreach ( $file->getHistory() as $ofile ) {
116  $sha1 = $ofile->getSha1();
117  if ( !strlen( $sha1 ) ) {
118  $this->error( "Image SHA-1 not set for {$ofile->getArchiveName()}." );
119  continue;
120  }
121 
122  if ( $oldLayout === 'sha1' ) {
123  $spath = "{$origBase}/{$sha1[0]}/{$sha1[1]}/{$sha1[2]}/{$sha1}";
124  } elseif ( $ofile->isDeleted( File::DELETED_FILE ) ) {
125  $spath = $be->getContainerStoragePath( "{$repo->getName()}-deleted" ) .
126  '/' . $repo->getDeletedHashPath( $sha1 ) .
127  $sha1 . '.' . $ofile->getExtension();
128  } else {
129  $spath = $ofile->getPath();
130  }
131 
132  if ( $newLayout === 'sha1' ) {
133  $dpath = "{$origBase}/{$sha1[0]}/{$sha1[1]}/{$sha1[2]}/{$sha1}";
134  } else {
135  $dpath = $ofile->getPath();
136  }
137 
138  $status = $be->prepare( [
139  'dir' => dirname( $dpath ), 'bypassReadOnly' => 1 ] );
140  if ( !$status->isOK() ) {
141  $this->error( print_r( $status->getErrors(), true ) );
142  }
143  $batch[] = [ 'op' => 'copy', 'overwrite' => true,
144  'src' => $spath, 'dst' => $dpath, 'img' => $ofile->getArchiveName() ];
145  }
146 
147  if ( count( $batch ) >= $batchSize ) {
148  $this->runBatch( $batch, $be );
149  $batch = [];
150  }
151  }
152  } while ( $res->numRows() );
153 
154  if ( count( $batch ) ) {
155  $this->runBatch( $batch, $be );
156  }
157 
158  // Do deleted versions...
159  $conds = [];
160  if ( $since ) {
161  $conds[] = 'fa_deleted_timestamp >= ' . $dbw->addQuotes( $dbw->timestamp( $since ) );
162  }
163 
164  $batch = [];
165  $lastId = 0;
166  do {
167  $res = $dbw->select( 'filearchive', [ 'fa_storage_key', 'fa_id', 'fa_name' ],
168  array_merge( [ 'fa_id > ' . $dbw->addQuotes( $lastId ) ], $conds ),
169  __METHOD__,
170  [ 'LIMIT' => $batchSize, 'ORDER BY' => 'fa_id' ]
171  );
172 
173  foreach ( $res as $row ) {
174  $lastId = $row->fa_id;
175  $sha1Key = $row->fa_storage_key;
176  if ( !strlen( $sha1Key ) ) {
177  $this->error( "Image SHA-1 not set for file #{$row->fa_id} (deleted)." );
178  continue;
179  }
180  $sha1 = substr( $sha1Key, 0, strpos( $sha1Key, '.' ) );
181 
182  if ( $oldLayout === 'sha1' ) {
183  $spath = "{$origBase}/{$sha1[0]}/{$sha1[1]}/{$sha1[2]}/{$sha1}";
184  } else {
185  $spath = $be->getContainerStoragePath( "{$repo->getName()}-deleted" ) .
186  '/' . $repo->getDeletedHashPath( $sha1Key ) . $sha1Key;
187  }
188 
189  if ( $newLayout === 'sha1' ) {
190  $dpath = "{$origBase}/{$sha1[0]}/{$sha1[1]}/{$sha1[2]}/{$sha1}";
191  } else {
192  $dpath = $be->getContainerStoragePath( "{$repo->getName()}-deleted" ) .
193  '/' . $repo->getDeletedHashPath( $sha1Key ) . $sha1Key;
194  }
195 
196  $status = $be->prepare( [
197  'dir' => dirname( $dpath ), 'bypassReadOnly' => 1 ] );
198  if ( !$status->isOK() ) {
199  $this->error( print_r( $status->getErrors(), true ) );
200  }
201 
202  $batch[] = [ 'op' => 'copy', 'src' => $spath, 'dst' => $dpath,
203  'overwriteSame' => true, 'img' => "(ID {$row->fa_id}) {$row->fa_name}" ];
204 
205  if ( count( $batch ) >= $batchSize ) {
206  $this->runBatch( $batch, $be );
207  $batch = [];
208  }
209  }
210  } while ( $res->numRows() );
211 
212  if ( count( $batch ) ) {
213  $this->runBatch( $batch, $be );
214  }
215 
216  $this->output( "Done (started $startTime)\n" );
217  }
218 
219  protected function getRepo() {
220  return RepoGroup::singleton()->getLocalRepo();
221  }
222 
223  protected function runBatch( array $ops, FileBackend $be ) {
224  $this->output( "Migrating file batch:\n" );
225  foreach ( $ops as $op ) {
226  $this->output( "\"{$op['img']}\" (dest: {$op['dst']})\n" );
227  }
228 
229  $status = $be->doOperations( $ops, [ 'bypassReadOnly' => 1 ] );
230  if ( !$status->isOK() ) {
231  $this->output( print_r( $status->getErrors(), true ) );
232  }
233 
234  $this->output( "Batch done\n\n" );
235  }
236 }
237 
239 require_once RUN_MAINTENANCE_IF_MAIN;
$status
Status::newGood()` to allow deletion, and then `return false` from the hook function. Ensure you consume the 'ChangeTagAfterDelete' hook to carry out custom deletion actions. $tag:name of the tag $user:user initiating the action & $status:Status object. See above. 'ChangeTagsListActive':Allows you to nominate which of the tags your extension uses are in active use. & $tags:list of all active tags. Append to this array. 'ChangeTagsAfterUpdateTags':Called after tags have been updated with the ChangeTags::updateTags function. Params:$addedTags:tags effectively added in the update $removedTags:tags effectively removed in the update $prevTags:tags that were present prior to the update $rc_id:recentchanges table id $rev_id:revision table id $log_id:logging table id $params:tag params $rc:RecentChange being tagged when the tagging accompanies the action, or null $user:User who performed the tagging when the tagging is subsequent to the action, or null 'ChangeTagsAllowedAdd':Called when checking if a user can add tags to a change. & $allowedTags:List of all the tags the user is allowed to add. Any tags the user wants to add( $addTags) that are not in this array will cause it to fail. You may add or remove tags to this array as required. $addTags:List of tags user intends to add. $user:User who is adding the tags. 'ChangeUserGroups':Called before user groups are changed. $performer:The User who will perform the change $user:The User whose groups will be changed & $add:The groups that will be added & $remove:The groups that will be removed 'Collation::factory':Called if $wgCategoryCollation is an unknown collation. $collationName:Name of the collation in question & $collationObject:Null. Replace with a subclass of the Collation class that implements the collation given in $collationName. 'ConfirmEmailComplete':Called after a user 's email has been confirmed successfully. $user:user(object) whose email is being confirmed 'ContentAlterParserOutput':Modify parser output for a given content object. Called by Content::getParserOutput after parsing has finished. Can be used for changes that depend on the result of the parsing but have to be done before LinksUpdate is called(such as adding tracking categories based on the rendered HTML). $content:The Content to render $title:Title of the page, as context $parserOutput:ParserOutput to manipulate 'ContentGetParserOutput':Customize parser output for a given content object, called by AbstractContent::getParserOutput. May be used to override the normal model-specific rendering of page content. $content:The Content to render $title:Title of the page, as context $revId:The revision ID, as context $options:ParserOptions for rendering. To avoid confusing the parser cache, the output can only depend on parameters provided to this hook function, not on global state. $generateHtml:boolean, indicating whether full HTML should be generated. If false, generation of HTML may be skipped, but other information should still be present in the ParserOutput object. & $output:ParserOutput, to manipulate or replace 'ContentHandlerDefaultModelFor':Called when the default content model is determined for a given title. May be used to assign a different model for that title. $title:the Title in question & $model:the model name. Use with CONTENT_MODEL_XXX constants. 'ContentHandlerForModelID':Called when a ContentHandler is requested for a given content model name, but no entry for that model exists in $wgContentHandlers. Note:if your extension implements additional models via this hook, please use GetContentModels hook to make them known to core. $modeName:the requested content model name & $handler:set this to a ContentHandler object, if desired. 'ContentModelCanBeUsedOn':Called to determine whether that content model can be used on a given page. This is especially useful to prevent some content models to be used in some special location. $contentModel:ID of the content model in question $title:the Title in question. & $ok:Output parameter, whether it is OK to use $contentModel on $title. Handler functions that modify $ok should generally return false to prevent further hooks from further modifying $ok. 'ContribsPager::getQueryInfo':Before the contributions query is about to run & $pager:Pager object for contributions & $queryInfo:The query for the contribs Pager 'ContribsPager::reallyDoQuery':Called before really executing the query for My Contributions & $data:an array of results of all contribs queries $pager:The ContribsPager object hooked into $offset:Index offset, inclusive $limit:Exact query limit $descending:Query direction, false for ascending, true for descending 'ContributionsLineEnding':Called before a contributions HTML line is finished $page:SpecialPage object for contributions & $ret:the HTML line $row:the DB row for this line & $classes:the classes to add to the surrounding< li > & $attribs:associative array of other HTML attributes for the< li > element. Currently only data attributes reserved to MediaWiki are allowed(see Sanitizer::isReservedDataAttribute). 'ContributionsToolLinks':Change tool links above Special:Contributions $id:User identifier $title:User page title & $tools:Array of tool links $specialPage:SpecialPage instance for context and services. Can be either SpecialContributions or DeletedContributionsPage. Extensions should type hint against a generic SpecialPage though. 'ConvertContent':Called by AbstractContent::convert when a conversion to another content model is requested. Handler functions that modify $result should generally return false to disable further attempts at conversion. $content:The Content object to be converted. $toModel:The ID of the content model to convert to. $lossy:boolean indicating whether lossy conversion is allowed. & $result:Output parameter, in case the handler function wants to provide a converted Content object. Note that $result->getContentModel() must return $toModel. 'ContentSecurityPolicyDefaultSource':Modify the allowed CSP load sources. This affects all directives except for the script directive. If you want to add a script source, see ContentSecurityPolicyScriptSource hook. & $defaultSrc:Array of Content-Security-Policy allowed sources $policyConfig:Current configuration for the Content-Security-Policy header $mode:ContentSecurityPolicy::REPORT_ONLY_MODE or ContentSecurityPolicy::FULL_MODE depending on type of header 'ContentSecurityPolicyDirectives':Modify the content security policy directives. Use this only if ContentSecurityPolicyDefaultSource and ContentSecurityPolicyScriptSource do not meet your needs. & $directives:Array of CSP directives $policyConfig:Current configuration for the CSP header $mode:ContentSecurityPolicy::REPORT_ONLY_MODE or ContentSecurityPolicy::FULL_MODE depending on type of header 'ContentSecurityPolicyScriptSource':Modify the allowed CSP script sources. Note that you also have to use ContentSecurityPolicyDefaultSource if you want non-script sources to be loaded from whatever you add. & $scriptSrc:Array of CSP directives $policyConfig:Current configuration for the CSP header $mode:ContentSecurityPolicy::REPORT_ONLY_MODE or ContentSecurityPolicy::FULL_MODE depending on type of header 'CustomEditor':When invoking the page editor Return true to allow the normal editor to be used, or false if implementing a custom editor, e.g. for a special namespace, etc. $article:Article being edited $user:User performing the edit 'DatabaseOraclePostInit':Called after initialising an Oracle database $db:the DatabaseOracle object 'DeletedContribsPager::reallyDoQuery':Called before really executing the query for Special:DeletedContributions Similar to ContribsPager::reallyDoQuery & $data:an array of results of all contribs queries $pager:The DeletedContribsPager object hooked into $offset:Index offset, inclusive $limit:Exact query limit $descending:Query direction, false for ascending, true for descending 'DeletedContributionsLineEnding':Called before a DeletedContributions HTML line is finished. Similar to ContributionsLineEnding $page:SpecialPage object for DeletedContributions & $ret:the HTML line $row:the DB row for this line & $classes:the classes to add to the surrounding< li > & $attribs:associative array of other HTML attributes for the< li > element. Currently only data attributes reserved to MediaWiki are allowed(see Sanitizer::isReservedDataAttribute). 'DeleteUnknownPreferences':Called by the cleanupPreferences.php maintenance script to build a WHERE clause with which to delete preferences that are not known about. This hook is used by extensions that have dynamically-named preferences that should not be deleted in the usual cleanup process. For example, the Gadgets extension creates preferences prefixed with 'gadget-', and so anything with that prefix is excluded from the deletion. &where:An array that will be passed as the $cond parameter to IDatabase::select() to determine what will be deleted from the user_properties table. $db:The IDatabase object, useful for accessing $db->buildLike() etc. 'DifferenceEngineAfterLoadNewText':called in DifferenceEngine::loadNewText() after the new revision 's content has been loaded into the class member variable $differenceEngine->mNewContent but before returning true from this function. $differenceEngine:DifferenceEngine object 'DifferenceEngineLoadTextAfterNewContentIsLoaded':called in DifferenceEngine::loadText() after the new revision 's content has been loaded into the class member variable $differenceEngine->mNewContent but before checking if the variable 's value is null. This hook can be used to inject content into said class member variable. $differenceEngine:DifferenceEngine object 'DifferenceEngineMarkPatrolledLink':Allows extensions to change the "mark as patrolled" link which is shown both on the diff header as well as on the bottom of a page, usually wrapped in a span element which has class="patrollink". $differenceEngine:DifferenceEngine object & $markAsPatrolledLink:The "mark as patrolled" link HTML(string) $rcid:Recent change ID(rc_id) for this change(int) 'DifferenceEngineMarkPatrolledRCID':Allows extensions to possibly change the rcid parameter. For example the rcid might be set to zero due to the user being the same as the performer of the change but an extension might still want to show it under certain conditions. & $rcid:rc_id(int) of the change or 0 $differenceEngine:DifferenceEngine object $change:RecentChange object $user:User object representing the current user 'DifferenceEngineNewHeader':Allows extensions to change the $newHeader variable, which contains information about the new revision, such as the revision 's author, whether the revision was marked as a minor edit or not, etc. $differenceEngine:DifferenceEngine object & $newHeader:The string containing the various #mw-diff-otitle[1-5] divs, which include things like revision author info, revision comment, RevisionDelete link and more $formattedRevisionTools:Array containing revision tools, some of which may have been injected with the DiffRevisionTools hook $nextlink:String containing the link to the next revision(if any) $status
Definition: hooks.txt:1266
FileBackend\doOperations
doOperations(array $ops, array $opts=[])
This is the main entry point into the backend for write operations.
Definition: FileBackend.php:419
RepoGroup\singleton
static singleton()
Get a RepoGroup instance.
Definition: RepoGroup.php:61
$file
if(PHP_SAPI !='cli-server') if(!isset( $_SERVER['SCRIPT_FILENAME'])) $file
Definition: router.php:42
FileBackend
Base class for all file backend classes (including multi-write backends).
Definition: FileBackend.php:92
Maintenance\fatalError
fatalError( $msg, $exitCode=1)
Output a message and terminate the current script.
Definition: Maintenance.php:485
captcha-old.count
count
Definition: captcha-old.py:249
Maintenance\addDescription
addDescription( $text)
Set the description text.
Definition: Maintenance.php:329
RUN_MAINTENANCE_IF_MAIN
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
$res
$res
Definition: database.txt:21
Maintenance
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
Definition: maintenance.txt:39
php
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
MigrateFileRepoLayout\getRepo
getRepo()
Definition: migrateFileRepoLayout.php:219
Maintenance\addOption
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Definition: Maintenance.php:248
wfTimestampNow
wfTimestampNow()
Convenience function; returns MediaWiki timestamp for the present time.
Definition: GlobalFunctions.php:1941
array
The wiki should then use memcached to cache various data To use multiple just add more items to the array To increase the weight of a make its entry a array("192.168.0.1:11211", 2))
MigrateFileRepoLayout\__construct
__construct()
Default constructor.
Definition: migrateFileRepoLayout.php:34
MigrateFileRepoLayout\runBatch
runBatch(array $ops, FileBackend $be)
Definition: migrateFileRepoLayout.php:223
MigrateFileRepoLayout\execute
execute()
Do the actual work.
Definition: migrateFileRepoLayout.php:43
Maintenance\getOption
getOption( $name, $default=null)
Get an option, or return the default.
Definition: Maintenance.php:283
Maintenance\getBatchSize
getBatchSize()
Returns batch size.
Definition: Maintenance.php:367
as
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
$batch
$batch
Definition: linkcache.txt:23
true
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:1985
Maintenance\error
error( $err, $die=0)
Throw an error to the user.
Definition: Maintenance.php:462
Maintenance\output
output( $out, $channel=null)
Throw some output to the user.
Definition: Maintenance.php:434
File\DELETED_FILE
const DELETED_FILE
Definition: File.php:54
class
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
$maintClass
$maintClass
Definition: migrateFileRepoLayout.php:238
MigrateFileRepoLayout
Copy all files in FileRepo to an originals container using SHA1 paths.
Definition: migrateFileRepoLayout.php:33
FileBackendDBRepoWrapper
Proxy backend that manages file layout rewriting for FileRepo.
Definition: FileBackendDBRepoWrapper.php:41
Maintenance\setBatchSize
setBatchSize( $s=0)
Set the batch size.
Definition: Maintenance.php:375