MediaWiki  REL1_31
refreshImageMetadata.php
Go to the documentation of this file.
1 <?php
30 require_once __DIR__ . '/Maintenance.php';
31 
34 
41 
45  protected $dbw;
46 
47  function __construct() {
48  parent::__construct();
49 
50  $this->addDescription( 'Script to update image metadata records' );
51  $this->setBatchSize( 200 );
52 
53  $this->addOption(
54  'force',
55  'Reload metadata from file even if the metadata looks ok',
56  false,
57  false,
58  'f'
59  );
60  $this->addOption(
61  'broken-only',
62  'Only fix really broken records, leave old but still compatible records alone.'
63  );
64  $this->addOption(
65  'verbose',
66  'Output extra information about each upgraded/non-upgraded file.',
67  false,
68  false,
69  'v'
70  );
71  $this->addOption( 'start', 'Name of file to start with', false, true );
72  $this->addOption( 'end', 'Name of file to end with', false, true );
73 
74  $this->addOption(
75  'mediatype',
76  'Only refresh files with this media type, e.g. BITMAP, UNKNOWN etc.',
77  false,
78  true
79  );
80  $this->addOption(
81  'mime',
82  "Only refresh files with this MIME type. Can accept wild-card 'image/*'. "
83  . "Potentially inefficient unless 'mediatype' is also specified",
84  false,
85  true
86  );
87  $this->addOption(
88  'metadata-contains',
89  '(Inefficient!) Only refresh files where the img_metadata field '
90  . 'contains this string. Can be used if its known a specific '
91  . 'property was being extracted incorrectly.',
92  false,
93  true
94  );
95  }
96 
97  public function execute() {
98  $force = $this->hasOption( 'force' );
99  $brokenOnly = $this->hasOption( 'broken-only' );
100  $verbose = $this->hasOption( 'verbose' );
101  $start = $this->getOption( 'start', false );
102  $this->setupParameters( $force, $brokenOnly );
103 
104  $upgraded = 0;
105  $leftAlone = 0;
106  $error = 0;
107 
108  $dbw = $this->getDB( DB_MASTER );
109  $batchSize = $this->getBatchSize();
110  if ( $batchSize <= 0 ) {
111  $this->fatalError( "Batch size is too low...", 12 );
112  }
113 
114  $repo = RepoGroup::singleton()->getLocalRepo();
115  $conds = $this->getConditions( $dbw );
116 
117  // For the WHERE img_name > 'foo' condition that comes after doing a batch
118  $conds2 = [];
119  if ( $start !== false ) {
120  $conds2[] = 'img_name >= ' . $dbw->addQuotes( $start );
121  }
122 
123  $options = [
124  'LIMIT' => $batchSize,
125  'ORDER BY' => 'img_name ASC',
126  ];
127 
128  $fileQuery = LocalFile::getQueryInfo();
129 
130  do {
131  $res = $dbw->select(
132  $fileQuery['tables'],
133  $fileQuery['fields'],
134  array_merge( $conds, $conds2 ),
135  __METHOD__,
136  $options,
137  $fileQuery['joins']
138  );
139 
140  if ( $res->numRows() > 0 ) {
141  $row1 = $res->current();
142  $this->output( "Processing next {$res->numRows()} row(s) starting with {$row1->img_name}.\n" );
143  $res->rewind();
144  }
145 
146  foreach ( $res as $row ) {
147  try {
148  // LocalFile will upgrade immediately here if obsolete
149  $file = $repo->newFileFromRow( $row );
150  if ( $file->getUpgraded() ) {
151  // File was upgraded.
152  $upgraded++;
153  $newLength = strlen( $file->getMetadata() );
154  $oldLength = strlen( $row->img_metadata );
155  if ( $newLength < $oldLength - 5 ) {
156  // If after updating, the metadata is smaller then
157  // what it was before, that's probably not a good thing
158  // because we extract more data with time, not less.
159  // Thus this probably indicates an error of some sort,
160  // or at the very least is suspicious. Have the - 5 just
161  // to weed out any inconsequential changes.
162  $error++;
163  $this->output(
164  "Warning: File:{$row->img_name} used to have " .
165  "$oldLength bytes of metadata but now has $newLength bytes.\n"
166  );
167  } elseif ( $verbose ) {
168  $this->output( "Refreshed File:{$row->img_name}.\n" );
169  }
170  } else {
171  $leftAlone++;
172  if ( $force ) {
173  $file->upgradeRow();
174  $newLength = strlen( $file->getMetadata() );
175  $oldLength = strlen( $row->img_metadata );
176  if ( $newLength < $oldLength - 5 ) {
177  $error++;
178  $this->output(
179  "Warning: File:{$row->img_name} used to have " .
180  "$oldLength bytes of metadata but now has $newLength bytes. (forced)\n"
181  );
182  }
183  if ( $verbose ) {
184  $this->output( "Forcibly refreshed File:{$row->img_name}.\n" );
185  }
186  } else {
187  if ( $verbose ) {
188  $this->output( "Skipping File:{$row->img_name}.\n" );
189  }
190  }
191  }
192  } catch ( Exception $e ) {
193  $this->output( "{$row->img_name} failed. {$e->getMessage()}\n" );
194  }
195  }
196  $conds2 = [ 'img_name > ' . $dbw->addQuotes( $row->img_name ) ];
197  wfWaitForSlaves();
198  } while ( $res->numRows() === $batchSize );
199 
200  $total = $upgraded + $leftAlone;
201  if ( $force ) {
202  $this->output( "\nFinished refreshing file metadata for $total files. "
203  . "$upgraded needed to be refreshed, $leftAlone did not need to "
204  . "be but were refreshed anyways, and $error refreshes were suspicious.\n" );
205  } else {
206  $this->output( "\nFinished refreshing file metadata for $total files. "
207  . "$upgraded were refreshed, $leftAlone were already up to date, "
208  . "and $error refreshes were suspicious.\n" );
209  }
210  }
211 
216  function getConditions( $dbw ) {
217  $conds = [];
218 
219  $end = $this->getOption( 'end', false );
220  $mime = $this->getOption( 'mime', false );
221  $mediatype = $this->getOption( 'mediatype', false );
222  $like = $this->getOption( 'metadata-contains', false );
223 
224  if ( $end !== false ) {
225  $conds[] = 'img_name <= ' . $dbw->addQuotes( $end );
226  }
227  if ( $mime !== false ) {
228  list( $major, $minor ) = File::splitMime( $mime );
229  $conds['img_major_mime'] = $major;
230  if ( $minor !== '*' ) {
231  $conds['img_minor_mime'] = $minor;
232  }
233  }
234  if ( $mediatype !== false ) {
235  $conds['img_media_type'] = $mediatype;
236  }
237  if ( $like ) {
238  $conds[] = 'img_metadata ' . $dbw->buildLike( $dbw->anyString(), $like, $dbw->anyString() );
239  }
240 
241  return $conds;
242  }
243 
248  function setupParameters( $force, $brokenOnly ) {
250 
251  if ( $brokenOnly ) {
253  } else {
255  }
256 
257  if ( $brokenOnly && $force ) {
258  $this->fatalError( 'Cannot use --broken-only and --force together. ', 2 );
259  }
260  }
261 }
262 
264 require_once RUN_MAINTENANCE_IF_MAIN;
$wgUpdateCompatibleMetadata
$wgUpdateCompatibleMetadata
If to automatically update the img_metadata field if the metadata field is outdated but compatible wi...
Definition: DefaultSettings.php:698
RepoGroup\singleton
static singleton()
Get a RepoGroup instance.
Definition: RepoGroup.php:59
use
Apache License January AND DISTRIBUTION Definitions License shall mean the terms and conditions for use
Definition: APACHE-LICENSE-2.0.txt:10
Maintenance\fatalError
fatalError( $msg, $exitCode=1)
Output a message and terminate the current script.
Definition: Maintenance.php:439
Maintenance\addDescription
addDescription( $text)
Set the description text.
Definition: Maintenance.php:291
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
File\splitMime
static splitMime( $mime)
Split an internet media type into its two components; if not a two-part name, set the minor type to '...
Definition: File.php:273
RefreshImageMetadata\__construct
__construct()
Default constructor.
Definition: refreshImageMetadata.php:47
RefreshImageMetadata
Maintenance script to refresh image metadata fields.
Definition: refreshImageMetadata.php:40
wfWaitForSlaves
wfWaitForSlaves( $ifWritesSince=null, $wiki=false, $cluster=false, $timeout=null)
Waits for the replica DBs to catch up to the master position.
Definition: GlobalFunctions.php:2966
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:37
Wikimedia\Rdbms\IDatabase
Basic database interface for live and lazy-loaded relation database handles.
Definition: IDatabase.php:38
Maintenance\addOption
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Definition: Maintenance.php:219
Wikimedia\Rdbms\IDatabase\buildLike
buildLike()
LIKE statement wrapper, receives a variable-length argument list with parts of pattern to match conta...
global
when a variable name is used in a it is silently declared as a new masking the global
Definition: design.txt:95
DB_MASTER
const DB_MASTER
Definition: defines.php:26
RefreshImageMetadata\getConditions
getConditions( $dbw)
Definition: refreshImageMetadata.php:216
list
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
$options
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 & $options
Definition: hooks.txt:2001
$mime
if( $ext=='php'|| $ext=='php5') $mime
Definition: router.php:59
RefreshImageMetadata\$dbw
IMaintainableDatabase $dbw
Definition: refreshImageMetadata.php:45
Wikimedia\Rdbms\IDatabase\anyString
anyString()
Returns a token for buildLike() that denotes a '' to be used in a LIKE query.
LocalFile\getQueryInfo
static getQueryInfo(array $options=[])
Return the tables, fields, and join conditions to be selected to create a new localfile object.
Definition: LocalFile.php:243
Maintenance\getOption
getOption( $name, $default=null)
Get an option, or return the default.
Definition: Maintenance.php:254
Wikimedia\Rdbms\IDatabase\addQuotes
addQuotes( $s)
Adds quotes and backslashes.
RefreshImageMetadata\setupParameters
setupParameters( $force, $brokenOnly)
Definition: refreshImageMetadata.php:248
Maintenance\getBatchSize
getBatchSize()
Returns batch size.
Definition: Maintenance.php:321
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:22
Maintenance\getDB
getDB( $db, $groups=[], $wiki=false)
Returns a database to be used by current maintenance script.
Definition: Maintenance.php:1309
Wikimedia\Rdbms\IDatabase\select
select( $table, $vars, $conds='', $fname=__METHOD__, $options=[], $join_conds=[])
Execute a SELECT query constructed using the various parameters provided.
Maintenance\output
output( $out, $channel=null)
Throw some output to the user.
Definition: Maintenance.php:388
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:56
Maintenance\hasOption
hasOption( $name)
Checks to see if a particular param exists.
Definition: Maintenance.php:240
$maintClass
$maintClass
Definition: refreshImageMetadata.php:263
Wikimedia\Rdbms\IMaintainableDatabase
Advanced database interface for IDatabase handles that include maintenance methods.
Definition: IMaintainableDatabase.php:38
RefreshImageMetadata\execute
execute()
Do the actual work.
Definition: refreshImageMetadata.php:97
Maintenance\setBatchSize
setBatchSize( $s=0)
Set the batch size.
Definition: Maintenance.php:329
$e
div flags Integer display flags(NO_ACTION_LINK, NO_EXTRA_USER_LINKS) 'LogException' returning false will NOT prevent logging $e
Definition: hooks.txt:2171