MediaWiki  1.30.0
orphans.php
Go to the documentation of this file.
1 <?php
31 require_once __DIR__ . '/Maintenance.php';
32 
34 
41 class Orphans extends Maintenance {
42  public function __construct() {
43  parent::__construct();
44  $this->addDescription( "Look for 'orphan' revisions hooked to pages which don't exist\n" .
45  "and 'childless' pages with no revisions\n" .
46  "Then, kill the poor widows and orphans\n" .
47  "Man this is depressing"
48  );
49  $this->addOption( 'fix', 'Actually fix broken entries' );
50  }
51 
52  public function execute() {
53  $this->checkOrphans( $this->hasOption( 'fix' ) );
54  $this->checkSeparation( $this->hasOption( 'fix' ) );
55  # Does not work yet, do not use
56  # $this->checkWidows( $this->hasOption( 'fix' ) );
57  }
58 
64  private function lockTables( $db, $extraTable = [] ) {
65  $tbls = [ 'page', 'revision', 'redirect' ];
66  if ( $extraTable ) {
67  $tbls = array_merge( $tbls, $extraTable );
68  }
69  $db->lockTables( [], $tbls, __METHOD__, false );
70  }
71 
76  private function checkOrphans( $fix ) {
77  $dbw = $this->getDB( DB_MASTER );
78  $commentStore = new CommentStore( 'rev_comment' );
79 
80  if ( $fix ) {
81  $this->lockTables( $dbw );
82  }
83 
84  $commentQuery = $commentStore->getJoin();
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'],
90  [ 'rev_id', 'rev_page', 'rev_timestamp', 'rev_user_text' ] + $commentQuery['fields'],
91  [ 'page_id' => null ],
92  __METHOD__,
93  [],
94  [ 'page' => [ 'LEFT JOIN', [ 'rev_page=page_id' ] ] ] + $commentQuery['joins']
95  );
96  $orphans = $result->numRows();
97  if ( $orphans > 0 ) {
99 
100  $this->output( "$orphans orphan revisions...\n" );
101  $this->output( sprintf(
102  "%10s %10s %14s %20s %s\n",
103  'rev_id', 'rev_page', 'rev_timestamp', 'rev_user_text', 'rev_comment'
104  ) );
105 
106  foreach ( $result as $row ) {
107  $comment = $commentStore->getComment( $row )->text;
108  if ( $comment !== '' ) {
109  $comment = '(' . $wgContLang->truncate( $comment, 40 ) . ')';
110  }
111  $this->output( sprintf( "%10d %10d %14s %20s %s\n",
112  $row->rev_id,
113  $row->rev_page,
114  $row->rev_timestamp,
115  $wgContLang->truncate( $row->rev_user_text, 17 ),
116  $comment ) );
117  if ( $fix ) {
118  $dbw->delete( 'revision', [ 'rev_id' => $row->rev_id ] );
119  }
120  }
121  if ( !$fix ) {
122  $this->output( "Run again with --fix to remove these entries automatically.\n" );
123  }
124  } else {
125  $this->output( "No orphans! Yay!\n" );
126  }
127 
128  if ( $fix ) {
129  $dbw->unlockTables( __METHOD__ );
130  }
131  }
132 
139  private function checkWidows( $fix ) {
140  $dbw = $this->getDB( DB_MASTER );
141  $page = $dbw->tableName( 'page' );
142  $revision = $dbw->tableName( 'revision' );
143 
144  if ( $fix ) {
145  $this->lockTables( $dbw );
146  }
147 
148  $this->output( "\nChecking for childless page table entries... "
149  . "(this may take a while on a large wiki)\n" );
150  $result = $dbw->query( "
151  SELECT *
152  FROM $page LEFT OUTER JOIN $revision ON page_latest=rev_id
153  WHERE rev_id IS NULL
154  " );
155  $widows = $result->numRows();
156  if ( $widows > 0 ) {
157  $this->output( "$widows childless pages...\n" );
158  $this->output( sprintf( "%10s %11s %2s %s\n", 'page_id', 'page_latest', 'ns', 'page_title' ) );
159  foreach ( $result as $row ) {
160  printf( "%10d %11d %2d %s\n",
161  $row->page_id,
162  $row->page_latest,
163  $row->page_namespace,
164  $row->page_title );
165  if ( $fix ) {
166  $dbw->delete( 'page', [ 'page_id' => $row->page_id ] );
167  }
168  }
169  if ( !$fix ) {
170  $this->output( "Run again with --fix to remove these entries automatically.\n" );
171  }
172  } else {
173  $this->output( "No childless pages! Yay!\n" );
174  }
175 
176  if ( $fix ) {
177  $dbw->unlockTables( __METHOD__ );
178  }
179  }
180 
185  private function checkSeparation( $fix ) {
186  $dbw = $this->getDB( DB_MASTER );
187  $page = $dbw->tableName( 'page' );
188  $revision = $dbw->tableName( 'revision' );
189 
190  if ( $fix ) {
191  $this->lockTables( $dbw, [ 'user', 'text' ] );
192  }
193 
194  $this->output( "\nChecking for pages whose page_latest links are incorrect... "
195  . "(this may take a while on a large wiki)\n" );
196  $result = $dbw->query( "
197  SELECT *
198  FROM $page LEFT OUTER JOIN $revision ON page_latest=rev_id
199  " );
200  $found = 0;
201  foreach ( $result as $row ) {
202  $result2 = $dbw->query( "
203  SELECT MAX(rev_timestamp) as max_timestamp
204  FROM $revision
205  WHERE rev_page=$row->page_id
206  " );
207  $row2 = $dbw->fetchObject( $result2 );
208  if ( $row2 ) {
209  if ( $row->rev_timestamp != $row2->max_timestamp ) {
210  if ( $found == 0 ) {
211  $this->output( sprintf( "%10s %10s %14s %14s\n",
212  'page_id', 'rev_id', 'timestamp', 'max timestamp' ) );
213  }
214  ++$found;
215  $this->output( sprintf( "%10d %10d %14s %14s\n",
216  $row->page_id,
217  $row->page_latest,
218  $row->rev_timestamp,
219  $row2->max_timestamp ) );
220  if ( $fix ) {
221  # ...
222  $maxId = $dbw->selectField(
223  'revision',
224  'rev_id',
225  [
226  'rev_page' => $row->page_id,
227  'rev_timestamp' => $row2->max_timestamp ] );
228  $this->output( "... updating to revision $maxId\n" );
229  $maxRev = Revision::newFromId( $maxId );
230  $title = Title::makeTitle( $row->page_namespace, $row->page_title );
232  $article->updateRevisionOn( $dbw, $maxRev );
233  }
234  }
235  } else {
236  $this->output( "wtf\n" );
237  }
238  }
239 
240  if ( $found ) {
241  $this->output( "Found $found pages with incorrect latest revision.\n" );
242  } else {
243  $this->output( "No pages with incorrect latest revision. Yay!\n" );
244  }
245  if ( !$fix && $found > 0 ) {
246  $this->output( "Run again with --fix to remove these entries automatically.\n" );
247  }
248 
249  if ( $fix ) {
250  $dbw->unlockTables( __METHOD__ );
251  }
252  }
253 }
254 
255 $maintClass = "Orphans";
256 require_once RUN_MAINTENANCE_IF_MAIN;
Revision\newFromId
static newFromId( $id, $flags=0)
Load a page revision from a given revision ID number.
Definition: Revision.php:116
Maintenance\addDescription
addDescription( $text)
Set the description text.
Definition: Maintenance.php:287
$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 '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: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! 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:1963
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
CommentStore
CommentStore handles storage of comments (edit summaries, log reasons, etc) in the database.
Definition: CommentStore.php:30
RUN_MAINTENANCE_IF_MAIN
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
Orphans\checkWidows
checkWidows( $fix)
Definition: orphans.php:139
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
$title
namespace and then decline to actually register it file or subcat img or subcat $title
Definition: hooks.txt:932
WikiPage\factory
static factory(Title $title)
Create a WikiPage object of the appropriate class for the given title.
Definition: WikiPage.php:121
Orphans\__construct
__construct()
Default constructor.
Definition: orphans.php:42
$article
Using a hook running we can avoid having all this option specific stuff in our mainline code Using the function array $article
Definition: hooks.txt:77
Orphans\checkSeparation
checkSeparation( $fix)
Check for pages where page_latest is wrong.
Definition: orphans.php:185
Maintenance\addOption
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Definition: Maintenance.php:215
Title\makeTitle
static makeTitle( $ns, $title, $fragment='', $interwiki='')
Create a new Title from a namespace index and a DB key.
Definition: Title.php:529
global
when a variable name is used in a it is silently declared as a new masking the global
Definition: design.txt:93
DB_MASTER
const DB_MASTER
Definition: defines.php:26
Orphans\checkOrphans
checkOrphans( $fix)
Check for orphan revisions.
Definition: orphans.php:76
Orphans\lockTables
lockTables( $db, $extraTable=[])
Lock the appropriate tables for the script.
Definition: orphans.php:64
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:1251
Orphans
Maintenance script that looks for 'orphan' revisions hooked to pages which don't exist and 'childless...
Definition: orphans.php:41
Maintenance\output
output( $out, $channel=null)
Throw some output to the user.
Definition: Maintenance.php:373
Orphans\execute
execute()
Do the actual work.
Definition: orphans.php:52
Maintenance\hasOption
hasOption( $name)
Checks to see if a particular param exists.
Definition: Maintenance.php:236
Wikimedia\Rdbms\IMaintainableDatabase
Advanced database interface for IDatabase handles that include maintenance methods.
Definition: IMaintainableDatabase.php:39
$wgContLang
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 content language as $wgContLang
Definition: design.txt:56
$maintClass
$maintClass
Definition: orphans.php:255