MediaWiki  1.28.1
rebuildImages.php
Go to the documentation of this file.
1 <?php
33 require_once __DIR__ . '/Maintenance.php';
34 
40 class ImageBuilder extends Maintenance {
41 
45  protected $dbw;
46 
47  function __construct() {
48  parent::__construct();
49 
51  // make sure to update old, but compatible img_metadata fields.
52  $wgUpdateCompatibleMetadata = true;
53 
54  $this->addDescription( 'Script to update image metadata records' );
55 
56  $this->addOption( 'missing', 'Check for files without associated database record' );
57  $this->addOption( 'dry-run', 'Only report, don\'t update the database' );
58  }
59 
60  public function execute() {
61  $this->dbw = $this->getDB( DB_MASTER );
62  $this->dryrun = $this->hasOption( 'dry-run' );
63  if ( $this->dryrun ) {
64  $GLOBALS['wgReadOnly'] = 'Dry run mode, image upgrades are suppressed';
65  }
66 
67  if ( $this->hasOption( 'missing' ) ) {
68  $this->crawlMissing();
69  } else {
70  $this->build();
71  }
72  }
73 
77  function getRepo() {
78  if ( !isset( $this->repo ) ) {
79  $this->repo = RepoGroup::singleton()->getLocalRepo();
80  }
81 
82  return $this->repo;
83  }
84 
85  function build() {
86  $this->buildImage();
87  $this->buildOldImage();
88  }
89 
90  function init( $count, $table ) {
91  $this->processed = 0;
92  $this->updated = 0;
93  $this->count = $count;
94  $this->startTime = microtime( true );
95  $this->table = $table;
96  }
97 
98  function progress( $updated ) {
99  $this->updated += $updated;
100  $this->processed++;
101  if ( $this->processed % 100 != 0 ) {
102  return;
103  }
104  $portion = $this->processed / $this->count;
105  $updateRate = $this->updated / $this->processed;
106 
107  $now = microtime( true );
108  $delta = $now - $this->startTime;
109  $estimatedTotalTime = $delta / $portion;
110  $eta = $this->startTime + $estimatedTotalTime;
111  $rate = $this->processed / $delta;
112 
113  $this->output( sprintf( "%s: %6.2f%% done on %s; ETA %s [%d/%d] %.2f/sec <%.2f%% updated>\n",
114  wfTimestamp( TS_DB, intval( $now ) ),
115  $portion * 100.0,
116  $this->table,
117  wfTimestamp( TS_DB, intval( $eta ) ),
118  $this->processed,
119  $this->count,
120  $rate,
121  $updateRate * 100.0 ) );
122  flush();
123  }
124 
125  function buildTable( $table, $key, $callback ) {
126  $count = $this->dbw->selectField( $table, 'count(*)', '', __METHOD__ );
127  $this->init( $count, $table );
128  $this->output( "Processing $table...\n" );
129 
130  $result = $this->getDB( DB_REPLICA )->select( $table, '*', [], __METHOD__ );
131 
132  foreach ( $result as $row ) {
133  $update = call_user_func( $callback, $row, null );
134  if ( $update ) {
135  $this->progress( 1 );
136  } else {
137  $this->progress( 0 );
138  }
139  }
140  $this->output( "Finished $table... $this->updated of $this->processed rows updated\n" );
141  }
142 
143  function buildImage() {
144  $callback = [ $this, 'imageCallback' ];
145  $this->buildTable( 'image', 'img_name', $callback );
146  }
147 
148  function imageCallback( $row, $copy ) {
149  // Create a File object from the row
150  // This will also upgrade it
151  $file = $this->getRepo()->newFileFromRow( $row );
152 
153  return $file->getUpgraded();
154  }
155 
156  function buildOldImage() {
157  $this->buildTable( 'oldimage', 'oi_archive_name', [ $this, 'oldimageCallback' ] );
158  }
159 
160  function oldimageCallback( $row, $copy ) {
161  // Create a File object from the row
162  // This will also upgrade it
163  if ( $row->oi_archive_name == '' ) {
164  $this->output( "Empty oi_archive_name for oi_name={$row->oi_name}\n" );
165 
166  return false;
167  }
168  $file = $this->getRepo()->newFileFromRow( $row );
169 
170  return $file->getUpgraded();
171  }
172 
173  function crawlMissing() {
174  $this->getRepo()->enumFiles( [ $this, 'checkMissingImage' ] );
175  }
176 
177  function checkMissingImage( $fullpath ) {
178  $filename = wfBaseName( $fullpath );
179  $row = $this->dbw->selectRow( 'image',
180  [ 'img_name' ],
181  [ 'img_name' => $filename ],
182  __METHOD__ );
183 
184  if ( !$row ) { // file not registered
185  $this->addMissingImage( $filename, $fullpath );
186  }
187  }
188 
189  function addMissingImage( $filename, $fullpath ) {
191 
192  $timestamp = $this->dbw->timestamp( $this->getRepo()->getFileTimestamp( $fullpath ) );
193 
194  $altname = $wgContLang->checkTitleEncoding( $filename );
195  if ( $altname != $filename ) {
196  if ( $this->dryrun ) {
197  $filename = $altname;
198  $this->output( "Estimating transcoding... $altname\n" );
199  } else {
200  # @todo FIXME: create renameFile()
201  $filename = $this->renameFile( $filename );
202  }
203  }
204 
205  if ( $filename == '' ) {
206  $this->output( "Empty filename for $fullpath\n" );
207 
208  return;
209  }
210  if ( !$this->dryrun ) {
211  $file = wfLocalFile( $filename );
212  if ( !$file->recordUpload(
213  '',
214  '(recovered file, missing upload log entry)',
215  '',
216  '',
217  '',
218  false,
219  $timestamp
220  ) ) {
221  $this->output( "Error uploading file $fullpath\n" );
222 
223  return;
224  }
225  }
226  $this->output( $fullpath . "\n" );
227  }
228 }
229 
230 $maintClass = 'ImageBuilder';
231 require_once RUN_MAINTENANCE_IF_MAIN;
init($count, $table)
buildTable($table, $key, $callback)
imageCallback($row, $copy)
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
Definition: maintenance.txt:39
getDB($db, $groups=[], $wiki=false)
Returns a database to be used by current maintenance script.
hasOption($name)
Checks to see if a particular param exists.
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
when a variable name is used in a it is silently declared as a new local masking the global
Definition: design.txt:93
wfLocalFile($title)
Get an object referring to a locally registered file.
const DB_MASTER
Definition: defines.php:23
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. '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 '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. 'LanguageGetMagic':DEPRECATED!Use $magicWords in a file listed in $wgExtensionMessagesFiles instead.Use this to define synonyms of magic words depending of the language &$magicExtensions:associative array of magic words synonyms $lang:language code(string) 'LanguageGetNamespaces':Provide custom ordering for namespaces or remove namespaces.Do not use this hook to add namespaces.Use CanonicalNamespaces for that.&$namespaces:Array of namespaces indexed by their numbers 'LanguageGetSpecialPageAliases':DEPRECATED!Use $specialPageAliases in a file listed in $wgExtensionMessagesFiles instead.Use to define aliases of special pages names depending of the language &$specialPageAliases:associative array of magic words synonyms $lang:language code(string) 'LanguageGetTranslatedLanguageNames':Provide translated language names.&$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.&$links:Associative array mapping language codes to prefixed links of the form"language:title".&$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!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) $result
Definition: hooks.txt:1934
wfTimestamp($outputtype=TS_UNIX, $ts=0)
Get a timestamp string in one of various formats.
$maintClass
addOption($name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
$GLOBALS['IP']
if($limit) $timestamp
static singleton()
Get a RepoGroup instance.
Definition: RepoGroup.php:59
progress($updated)
addMissingImage($filename, $fullpath)
addDescription($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
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 $wgServiceWiringFiles lists includes ServiceWiring php
Definition: injection.txt:35
oldimageCallback($row, $copy)
wfBaseName($path, $suffix= '')
Return the final portion of a pathname.
deferred txt A few of the database updates required by various functions here can be deferred until after the result page is displayed to the user For updating the view updating the linked to tables after a etc PHP does not yet have any way to tell the server to actually return and disconnect while still running these but it might have such a feature in the future We handle these by creating a deferred update object and putting those objects on a global then executing the whole list after the page is displayed We don t do anything smart like collating updates to the same table or such because the list is almost always going to have just one item on if so it s not worth the trouble Since there is a job queue in the jobs table
Definition: deferred.txt:11
checkMissingImage($fullpath)
this class mediates it Skin Encapsulates a look and feel for the wiki All of the functions that render HTML and make choices about how to render it are here and are called from various other places when and is meant to be subclassed with other skins that may override some of its functions The User object contains a reference to a and so rather than having a global skin object we just rely on the global User and get the skin with $wgUser and also has some character encoding functions and other locale stuff The current user interface language is instantiated as and the local content language as $wgContLang
Definition: design.txt:56
$count
const DB_REPLICA
Definition: defines.php:22
Database $dbw
$processed
Maintenance script to update image metadata records.
$wgUpdateCompatibleMetadata
If to automatically update the img_metadata field if the metadata field is outdated but compatible wi...
const TS_DB
MySQL DATETIME (YYYY-MM-DD HH:MM:SS)
Definition: defines.php:16