MediaWiki  1.33.0
orphans.php
Go to the documentation of this file.
1 <?php
31 require_once __DIR__ . '/Maintenance.php';
32 
35 
42 class Orphans extends Maintenance {
43  public function __construct() {
44  parent::__construct();
45  $this->addDescription( "Look for 'orphan' revisions hooked to pages which don't exist\n" .
46  "and 'childless' pages with no revisions\n" .
47  "Then, kill the poor widows and orphans\n" .
48  "Man this is depressing"
49  );
50  $this->addOption( 'fix', 'Actually fix broken entries' );
51  }
52 
53  public function execute() {
54  $this->checkOrphans( $this->hasOption( 'fix' ) );
55  $this->checkSeparation( $this->hasOption( 'fix' ) );
56  }
57 
63  private function lockTables( $db, $extraTable = [] ) {
64  $tbls = [ 'page', 'revision', 'redirect' ];
65  if ( $extraTable ) {
66  $tbls = array_merge( $tbls, $extraTable );
67  }
68  $db->lockTables( [], $tbls, __METHOD__ );
69  }
70 
75  private function checkOrphans( $fix ) {
76  $dbw = $this->getDB( DB_MASTER );
77  $commentStore = CommentStore::getStore();
78 
79  if ( $fix ) {
80  $this->lockTables( $dbw );
81  }
82 
83  $commentQuery = $commentStore->getJoin( 'rev_comment' );
84  $actorQuery = ActorMigration::newMigration()->getJoin( 'rev_user' );
85 
86  $this->output( "Checking for orphan revision table entries... "
87  . "(this may take a while on a large wiki)\n" );
88  $result = $dbw->select(
89  [ 'revision', 'page' ] + $commentQuery['tables'] + $actorQuery['tables'],
90  [ 'rev_id', 'rev_page', 'rev_timestamp' ] + $commentQuery['fields'] + $actorQuery['fields'],
91  [ 'page_id' => null ],
92  __METHOD__,
93  [],
94  [ 'page' => [ 'LEFT JOIN', [ 'rev_page=page_id' ] ] ] + $commentQuery['joins']
95  + $actorQuery['joins']
96  );
97  $orphans = $result->numRows();
98  if ( $orphans > 0 ) {
99  $this->output( "$orphans orphan revisions...\n" );
100  $this->output( sprintf(
101  "%10s %10s %14s %20s %s\n",
102  'rev_id', 'rev_page', 'rev_timestamp', 'rev_user_text', 'rev_comment'
103  ) );
104 
105  $contLang = MediaWikiServices::getInstance()->getContentLanguage();
106  foreach ( $result as $row ) {
107  $comment = $commentStore->getComment( 'rev_comment', $row )->text;
108  if ( $comment !== '' ) {
109  $comment = '(' . $contLang->truncateForVisual( $comment, 40 ) . ')';
110  }
111  $rev_user_text = $contLang->truncateForVisual( $row->rev_user_text, 20 );
112  # pad $rev_user_text to 20 characters. Note that this may
113  # yield poor results if $rev_user_text contains combining
114  # or half-width characters. Alas.
115  if ( mb_strlen( $rev_user_text ) < 20 ) {
116  $rev_user_text = str_repeat( ' ', 20 - mb_strlen( $rev_user_text ) );
117  }
118  $this->output( sprintf( "%10d %10d %14s %s %s\n",
119  $row->rev_id,
120  $row->rev_page,
121  $row->rev_timestamp,
122  $rev_user_text,
123  $comment ) );
124  if ( $fix ) {
125  $dbw->delete( 'revision', [ 'rev_id' => $row->rev_id ] );
126  }
127  }
128  if ( !$fix ) {
129  $this->output( "Run again with --fix to remove these entries automatically.\n" );
130  }
131  } else {
132  $this->output( "No orphans! Yay!\n" );
133  }
134 
135  if ( $fix ) {
136  $dbw->unlockTables( __METHOD__ );
137  }
138  }
139 
144  private function checkSeparation( $fix ) {
145  $dbw = $this->getDB( DB_MASTER );
146  $page = $dbw->tableName( 'page' );
147  $revision = $dbw->tableName( 'revision' );
148 
149  if ( $fix ) {
150  $this->lockTables( $dbw, [ 'user', 'text' ] );
151  }
152 
153  $this->output( "\nChecking for pages whose page_latest links are incorrect... "
154  . "(this may take a while on a large wiki)\n" );
155  $result = $dbw->query( "
156  SELECT *
157  FROM $page LEFT JOIN $revision ON page_latest=rev_id
158  " );
159  $found = 0;
160  foreach ( $result as $row ) {
161  $result2 = $dbw->query( "
162  SELECT MAX(rev_timestamp) as max_timestamp
163  FROM $revision
164  WHERE rev_page=" . (int)( $row->page_id )
165  );
166  $row2 = $dbw->fetchObject( $result2 );
167  if ( $row2 ) {
168  if ( $row->rev_timestamp != $row2->max_timestamp ) {
169  if ( $found == 0 ) {
170  $this->output( sprintf( "%10s %10s %14s %14s\n",
171  'page_id', 'rev_id', 'timestamp', 'max timestamp' ) );
172  }
173  ++$found;
174  $this->output( sprintf( "%10d %10d %14s %14s\n",
175  $row->page_id,
176  $row->page_latest,
177  $row->rev_timestamp,
178  $row2->max_timestamp ) );
179  if ( $fix ) {
180  # ...
181  $maxId = $dbw->selectField(
182  'revision',
183  'rev_id',
184  [
185  'rev_page' => $row->page_id,
186  'rev_timestamp' => $row2->max_timestamp ] );
187  $this->output( "... updating to revision $maxId\n" );
188  $maxRev = Revision::newFromId( $maxId );
189  $title = Title::makeTitle( $row->page_namespace, $row->page_title );
191  $article->updateRevisionOn( $dbw, $maxRev );
192  }
193  }
194  } else {
195  $this->output( "wtf\n" );
196  }
197  }
198 
199  if ( $found ) {
200  $this->output( "Found $found pages with incorrect latest revision.\n" );
201  } else {
202  $this->output( "No pages with incorrect latest revision. Yay!\n" );
203  }
204  if ( !$fix && $found > 0 ) {
205  $this->output( "Run again with --fix to remove these entries automatically.\n" );
206  }
207 
208  if ( $fix ) {
209  $dbw->unlockTables( __METHOD__ );
210  }
211  }
212 }
213 
215 require_once RUN_MAINTENANCE_IF_MAIN;
$article
return true to allow those checks to and false if checking is done remove or add to the links of a group of changes in EnhancedChangesList Hook subscribers can return false to omit this line from recentchanges use this to change the tables headers change it to an object instance and return false override the list derivative used the name of the old file & $article
Definition: hooks.txt:1476
Revision\newFromId
static newFromId( $id, $flags=0)
Load a page revision from a given revision ID number.
Definition: Revision.php:118
Maintenance\addDescription
addDescription( $text)
Set the description text.
Definition: Maintenance.php:329
$result
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 '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:1983
RUN_MAINTENANCE_IF_MAIN
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
Maintenance
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
Definition: maintenance.txt:39
ActorMigration\newMigration
static newMigration()
Static constructor.
Definition: ActorMigration.php:111
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
$title
namespace and then decline to actually register it file or subcat img or subcat $title
Definition: hooks.txt:925
WikiPage\factory
static factory(Title $title)
Create a WikiPage object of the appropriate class for the given title.
Definition: WikiPage.php:138
Orphans\__construct
__construct()
Default constructor.
Definition: orphans.php:43
Orphans\checkSeparation
checkSeparation( $fix)
Check for pages where page_latest is wrong.
Definition: orphans.php:144
Maintenance\addOption
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Definition: Maintenance.php:248
use
as see the revision history and available at free of to any person obtaining a copy of this software and associated documentation to deal in the Software without including without limitation the rights to use
Definition: MIT-LICENSE.txt:10
Title\makeTitle
static makeTitle( $ns, $title, $fragment='', $interwiki='')
Create a new Title from a namespace index and a DB key.
Definition: Title.php:576
DB_MASTER
const DB_MASTER
Definition: defines.php:26
Orphans\checkOrphans
checkOrphans( $fix)
Check for orphan revisions.
Definition: orphans.php:75
Orphans\lockTables
lockTables( $db, $extraTable=[])
Lock the appropriate tables for the script.
Definition: orphans.php:63
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
Maintenance\getDB
getDB( $db, $groups=[], $wiki=false)
Returns a database to be used by current maintenance script.
Definition: Maintenance.php:1373
Orphans
Maintenance script that looks for 'orphan' revisions hooked to pages which don't exist and 'childless...
Definition: orphans.php:42
Maintenance\output
output( $out, $channel=null)
Throw some output to the user.
Definition: Maintenance.php:434
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
Orphans\execute
execute()
Do the actual work.
Definition: orphans.php:53
MediaWikiServices
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
Maintenance\hasOption
hasOption( $name)
Checks to see if a particular option exists.
Definition: Maintenance.php:269
CommentStore\getStore
static getStore()
Definition: CommentStore.php:130
Wikimedia\Rdbms\IMaintainableDatabase
Advanced database interface for IDatabase handles that include maintenance methods.
Definition: IMaintainableDatabase.php:38
$maintClass
$maintClass
Definition: orphans.php:214