MediaWiki  master
rebuildImages.php
Go to the documentation of this file.
1 <?php
33 require_once __DIR__ . '/Maintenance.php';
34 
37 
43 class ImageBuilder extends Maintenance {
44 
48  protected $dbw;
49 
50  function __construct() {
51  parent::__construct();
52 
54  // make sure to update old, but compatible img_metadata fields.
55  $wgUpdateCompatibleMetadata = true;
56 
57  $this->addDescription( 'Script to update image metadata records' );
58 
59  $this->addOption( 'missing', 'Check for files without associated database record' );
60  $this->addOption( 'dry-run', 'Only report, don\'t update the database' );
61  }
62 
63  public function execute() {
64  $this->dbw = $this->getDB( DB_MASTER );
65  $this->dryrun = $this->hasOption( 'dry-run' );
66  if ( $this->dryrun ) {
67  MediaWiki\MediaWikiServices::getInstance()->getReadOnlyMode()
68  ->setReason( 'Dry run mode, image upgrades are suppressed' );
69  }
70 
71  if ( $this->hasOption( 'missing' ) ) {
72  $this->crawlMissing();
73  } else {
74  $this->build();
75  }
76  }
77 
81  function getRepo() {
82  if ( !isset( $this->repo ) ) {
83  $this->repo = RepoGroup::singleton()->getLocalRepo();
84  }
85 
86  return $this->repo;
87  }
88 
89  function build() {
90  $this->buildImage();
91  $this->buildOldImage();
92  }
93 
94  function init( $count, $table ) {
95  $this->processed = 0;
96  $this->updated = 0;
97  $this->count = $count;
98  $this->startTime = microtime( true );
99  $this->table = $table;
100  }
101 
102  function progress( $updated ) {
103  $this->updated += $updated;
104  $this->processed++;
105  if ( $this->processed % 100 != 0 ) {
106  return;
107  }
108  $portion = $this->processed / $this->count;
109  $updateRate = $this->updated / $this->processed;
110 
111  $now = microtime( true );
112  $delta = $now - $this->startTime;
113  $estimatedTotalTime = $delta / $portion;
114  $eta = $this->startTime + $estimatedTotalTime;
115  $rate = $this->processed / $delta;
116 
117  $this->output( sprintf( "%s: %6.2f%% done on %s; ETA %s [%d/%d] %.2f/sec <%.2f%% updated>\n",
118  wfTimestamp( TS_DB, intval( $now ) ),
119  $portion * 100.0,
120  $this->table,
121  wfTimestamp( TS_DB, intval( $eta ) ),
122  $this->processed,
123  $this->count,
124  $rate,
125  $updateRate * 100.0 ) );
126  flush();
127  }
128 
129  function buildTable( $table, $key, $queryInfo, $callback ) {
130  $count = $this->dbw->selectField( $table, 'count(*)', '', __METHOD__ );
131  $this->init( $count, $table );
132  $this->output( "Processing $table...\n" );
133 
134  $result = $this->getDB( DB_REPLICA )->select(
135  $queryInfo['tables'], $queryInfo['fields'], [], __METHOD__, [], $queryInfo['joins']
136  );
137 
138  foreach ( $result as $row ) {
139  $update = call_user_func( $callback, $row, null );
140  if ( $update ) {
141  $this->progress( 1 );
142  } else {
143  $this->progress( 0 );
144  }
145  }
146  $this->output( "Finished $table... $this->updated of $this->processed rows updated\n" );
147  }
148 
149  function buildImage() {
150  $callback = [ $this, 'imageCallback' ];
151  $this->buildTable( 'image', 'img_name', LocalFile::getQueryInfo(), $callback );
152  }
153 
154  function imageCallback( $row, $copy ) {
155  // Create a File object from the row
156  // This will also upgrade it
157  $file = $this->getRepo()->newFileFromRow( $row );
158 
159  return $file->getUpgraded();
160  }
161 
162  function buildOldImage() {
163  $this->buildTable( 'oldimage', 'oi_archive_name', OldLocalFile::getQueryInfo(),
164  [ $this, 'oldimageCallback' ] );
165  }
166 
167  function oldimageCallback( $row, $copy ) {
168  // Create a File object from the row
169  // This will also upgrade it
170  if ( $row->oi_archive_name == '' ) {
171  $this->output( "Empty oi_archive_name for oi_name={$row->oi_name}\n" );
172 
173  return false;
174  }
175  $file = $this->getRepo()->newFileFromRow( $row );
176 
177  return $file->getUpgraded();
178  }
179 
180  function crawlMissing() {
181  $this->getRepo()->enumFiles( [ $this, 'checkMissingImage' ] );
182  }
183 
184  function checkMissingImage( $fullpath ) {
185  $filename = wfBaseName( $fullpath );
186  $row = $this->dbw->selectRow( 'image',
187  [ 'img_name' ],
188  [ 'img_name' => $filename ],
189  __METHOD__ );
190 
191  if ( !$row ) { // file not registered
192  $this->addMissingImage( $filename, $fullpath );
193  }
194  }
195 
196  function addMissingImage( $filename, $fullpath ) {
197  $timestamp = $this->dbw->timestamp( $this->getRepo()->getFileTimestamp( $fullpath ) );
198  $services = MediaWikiServices::getInstance();
199 
200  $altname = $services->getContentLanguage()->checkTitleEncoding( $filename );
201  if ( $altname != $filename ) {
202  if ( $this->dryrun ) {
203  $filename = $altname;
204  $this->output( "Estimating transcoding... $altname\n" );
205  } else {
206  # @todo FIXME: create renameFile()
207  $filename = $this->renameFile( $filename );
208  }
209  }
210 
211  if ( $filename == '' ) {
212  $this->output( "Empty filename for $fullpath\n" );
213 
214  return;
215  }
216  if ( !$this->dryrun ) {
217  $file = $services->getRepoGroup()->getLocalRepo()->newFile( $filename );
218  if ( !$file->recordUpload(
219  '',
220  '(recovered file, missing upload log entry)',
221  '',
222  '',
223  '',
224  false,
225  $timestamp
226  ) ) {
227  $this->output( "Error uploading file $fullpath\n" );
228 
229  return;
230  }
231  }
232  $this->output( $fullpath . "\n" );
233  }
234 }
235 
237 require_once RUN_MAINTENANCE_IF_MAIN;
oldimageCallback( $row, $copy)
wfBaseName( $path, $suffix='')
Return the final portion of a pathname.
Apache License January AND DISTRIBUTION Definitions License shall mean the terms and conditions for use
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
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 MediaWikiServices
Definition: injection.txt:23
hasOption( $name)
Checks to see if a particular option exists.
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
static getInstance()
Returns the global default instance of the top level service locator.
const DB_MASTER
Definition: defines.php:26
addMissingImage( $filename, $fullpath)
The index of the header message $result[1]=The index of the body text message $result[2 through n]=Parameters passed to body text message. Please note the header message cannot receive/use parameters. 'ImgAuthModifyHeaders':Executed just before a file is streamed to a user via img_auth.php, allowing headers to be modified beforehand. $title:LinkTarget object & $headers:HTTP headers(name=> value, names are case insensitive). Two headers get special handling:If-Modified-Since(value must be a valid HTTP date) and Range(must be of the form "bytes=(\*-\*)") will be honored when streaming the file. 'ImportHandleLogItemXMLTag':When parsing a XML tag in a log item. Return false to stop further processing of the tag $reader:XMLReader object $logInfo:Array of information 'ImportHandlePageXMLTag':When parsing a XML tag in a page. Return false to stop further processing of the tag $reader:XMLReader object & $pageInfo:Array of information 'ImportHandleRevisionXMLTag':When parsing a XML tag in a page revision. Return false to stop further processing of the tag $reader:XMLReader object $pageInfo:Array of page information $revisionInfo:Array of revision information 'ImportHandleToplevelXMLTag':When parsing a top level XML tag. Return false to stop further processing of the tag $reader:XMLReader object 'ImportHandleUnknownUser':When a user doesn 't exist locally, this hook is called to give extensions an opportunity to auto-create it. If the auto-creation is successful, return false. $name:User name 'ImportHandleUploadXMLTag':When parsing a XML tag in a file upload. Return false to stop further processing of the tag $reader:XMLReader object $revisionInfo:Array of information 'ImportLogInterwikiLink':Hook to change the interwiki link used in log entries and edit summaries for transwiki imports. & $fullInterwikiPrefix:Interwiki prefix, may contain colons. & $pageTitle:String that contains page title. 'ImportSources':Called when reading from the $wgImportSources configuration variable. Can be used to lazy-load the import sources list. & $importSources:The value of $wgImportSources. Modify as necessary. See the comment in DefaultSettings.php for the detail of how to structure this array. 'InfoAction':When building information to display on the action=info page. $context:IContextSource object & $pageInfo:Array of information 'InitializeArticleMaybeRedirect':MediaWiki check to see if title is a redirect. & $title:Title object for the current page & $request:WebRequest & $ignoreRedirect:boolean to skip redirect check & $target:Title/string of redirect target & $article:Article object 'InternalParseBeforeLinks':during Parser 's internalParse method before links but after nowiki/noinclude/includeonly/onlyinclude and other processings. & $parser:Parser object & $text:string containing partially parsed text & $stripState:Parser 's internal StripState object 'InternalParseBeforeSanitize':during Parser 's internalParse method just before the parser removes unwanted/dangerous HTML tags and after nowiki/noinclude/includeonly/onlyinclude and other processings. Ideal for syntax-extensions after template/parser function execution which respect nowiki and HTML-comments. & $parser:Parser object & $text:string containing partially parsed text & $stripState:Parser 's internal StripState object 'InterwikiLoadPrefix':When resolving if a given prefix is an interwiki or not. Return true without providing an interwiki to continue interwiki search. $prefix:interwiki prefix we are looking for. & $iwData:output array describing the interwiki with keys iw_url, iw_local, iw_trans and optionally iw_api and iw_wikiid. 'InvalidateEmailComplete':Called after a user 's email has been invalidated successfully. $user:user(object) whose email is being invalidated 'IRCLineURL':When constructing the URL to use in an IRC notification. Callee may modify $url and $query, URL will be constructed as $url . $query & $url:URL to index.php & $query:Query string $rc:RecentChange object that triggered url generation 'IsFileCacheable':Override the result of Article::isFileCacheable()(if true) & $article:article(object) being checked 'IsTrustedProxy':Override the result of IP::isTrustedProxy() & $ip:IP being check & $result:Change this value to override the result of IP::isTrustedProxy() 'IsUploadAllowedFromUrl':Override the result of UploadFromUrl::isAllowedUrl() $url:URL used to upload from & $allowed:Boolean indicating if uploading is allowed for given URL 'isValidEmailAddr':Override the result of Sanitizer::validateEmail(), for instance to return false if the domain name doesn 't match your organization. $addr:The e-mail address entered by the user & $result:Set this and return false to override the internal checks 'isValidPassword':Override the result of User::isValidPassword() $password:The password entered by the user & $result:Set this and return false to override the internal checks $user:User the password is being validated for 'Language::getMessagesFileName':$code:The language code or the language we 're looking for a messages file for & $file:The messages file path, you can override this to change the location. 'LanguageGetNamespaces':Provide custom ordering for namespaces or remove namespaces. Do not use this hook to add namespaces. Use CanonicalNamespaces for that. & $namespaces:Array of namespaces indexed by their numbers 'LanguageGetTranslatedLanguageNames':Provide translated language names. & $names:array of language code=> language name $code:language of the preferred translations 'LanguageLinks':Manipulate a page 's language links. This is called in various places to allow extensions to define the effective language links for a page. $title:The page 's Title. & $links:Array with elements of the form "language:title" in the order that they will be output. & $linkFlags:Associative array mapping prefixed links to arrays of flags. Currently unused, but planned to provide support for marking individual language links in the UI, e.g. for featured articles. 'LanguageSelector':Hook to change the language selector available on a page. $out:The output page. $cssClassName:CSS class name of the language selector. 'LinkBegin':DEPRECATED since 1.28! Use HtmlPageLinkRendererBegin instead. Used when generating internal and interwiki links in Linker::link(), before processing starts. Return false to skip default processing and return $ret. See documentation for Linker::link() for details on the expected meanings of parameters. $skin:the Skin object $target:the Title that the link is pointing to & $html:the contents that the< a > tag should have(raw HTML) $result
Definition: hooks.txt:1970
$maintClass
wfTimestamp( $outputtype=TS_UNIX, $ts=0)
Get a timestamp string in one of various formats.
init( $count, $table)
static configuration should be added through ResourceLoaderGetConfigVars instead can be used to get the real title e g db for database replication lag or jobqueue for job queue size converted to pseudo seconds It is possible to add more fields and they will be returned to the user in the API response after the basic globals have been set but before ordinary actions take place or wrap services the preferred way to define a new service is the $wgServiceWiringFiles array $services
Definition: hooks.txt:2205
static singleton()
Definition: RepoGroup.php:60
addDescription( $text)
Set the description text.
IMaintainableDatabase $dbw
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:767
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
static getQueryInfo(array $options=[])
Return the tables, fields, and join conditions to be selected to create a new oldlocalfile object...
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
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 then executing the whole list after the page is displayed We don t do anything smart like collating updates to the same table or such because the list is almost always going to have just one item on if so it s not worth the trouble Since there is a job queue in the jobs table
Definition: deferred.txt:11
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
buildTable( $table, $key, $queryInfo, $callback)
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
const DB_REPLICA
Definition: defines.php:25
static getQueryInfo(array $options=[])
Return the tables, fields, and join conditions to be selected to create a new localfile object...
Definition: LocalFile.php:254
Maintenance script to update image metadata records.
getDB( $db, $groups=[], $dbDomain=false)
Returns a database to be used by current maintenance script.
checkMissingImage( $fullpath)
$wgUpdateCompatibleMetadata
If to automatically update the img_metadata field if the metadata field is outdated but compatible wi...
imageCallback( $row, $copy)
progress( $updated)