MediaWiki REL1_32
orphans.php
Go to the documentation of this file.
1<?php
31require_once __DIR__ . '/Maintenance.php';
32
35
42class 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 # Does not work yet, do not use
57 # $this->checkWidows( $this->hasOption( 'fix' ) );
58 }
59
65 private function lockTables( $db, $extraTable = [] ) {
66 $tbls = [ 'page', 'revision', 'redirect' ];
67 if ( $extraTable ) {
68 $tbls = array_merge( $tbls, $extraTable );
69 }
70 $db->lockTables( [], $tbls, __METHOD__, false );
71 }
72
77 private function checkOrphans( $fix ) {
78 $dbw = $this->getDB( DB_MASTER );
79 $commentStore = CommentStore::getStore();
80
81 if ( $fix ) {
82 $this->lockTables( $dbw );
83 }
84
85 $commentQuery = $commentStore->getJoin( 'rev_comment' );
86 $actorQuery = ActorMigration::newMigration()->getJoin( 'rev_user' );
87
88 $this->output( "Checking for orphan revision table entries... "
89 . "(this may take a while on a large wiki)\n" );
90 $result = $dbw->select(
91 [ 'revision', 'page' ] + $commentQuery['tables'] + $actorQuery['tables'],
92 [ 'rev_id', 'rev_page', 'rev_timestamp' ] + $commentQuery['fields'] + $actorQuery['fields'],
93 [ 'page_id' => null ],
94 __METHOD__,
95 [],
96 [ 'page' => [ 'LEFT JOIN', [ 'rev_page=page_id' ] ] ] + $commentQuery['joins']
97 + $actorQuery['joins']
98 );
99 $orphans = $result->numRows();
100 if ( $orphans > 0 ) {
101 $this->output( "$orphans orphan revisions...\n" );
102 $this->output( sprintf(
103 "%10s %10s %14s %20s %s\n",
104 'rev_id', 'rev_page', 'rev_timestamp', 'rev_user_text', 'rev_comment'
105 ) );
106
107 $contLang = MediaWikiServices::getInstance()->getContentLanguage();
108 foreach ( $result as $row ) {
109 $comment = $commentStore->getComment( 'rev_comment', $row )->text;
110 if ( $comment !== '' ) {
111 $comment = '(' . $contLang->truncateForVisual( $comment, 40 ) . ')';
112 }
113 $rev_user_text = $contLang->truncateForVisual( $row->rev_user_text, 20 );
114 # pad $rev_user_text to 20 characters. Note that this may
115 # yield poor results if $rev_user_text contains combining
116 # or half-width characters. Alas.
117 if ( mb_strlen( $rev_user_text ) < 20 ) {
118 $rev_user_text = str_repeat( ' ', 20 - mb_strlen( $rev_user_text ) );
119 }
120 $this->output( sprintf( "%10d %10d %14s %s %s\n",
121 $row->rev_id,
122 $row->rev_page,
123 $row->rev_timestamp,
124 $rev_user_text,
125 $comment ) );
126 if ( $fix ) {
127 $dbw->delete( 'revision', [ 'rev_id' => $row->rev_id ] );
128 }
129 }
130 if ( !$fix ) {
131 $this->output( "Run again with --fix to remove these entries automatically.\n" );
132 }
133 } else {
134 $this->output( "No orphans! Yay!\n" );
135 }
136
137 if ( $fix ) {
138 $dbw->unlockTables( __METHOD__ );
139 }
140 }
141
148 private function checkWidows( $fix ) {
149 $dbw = $this->getDB( DB_MASTER );
150 $page = $dbw->tableName( 'page' );
151 $revision = $dbw->tableName( 'revision' );
152
153 if ( $fix ) {
154 $this->lockTables( $dbw );
155 }
156
157 $this->output( "\nChecking for childless page table entries... "
158 . "(this may take a while on a large wiki)\n" );
159 $result = $dbw->query( "
160 SELECT *
161 FROM $page LEFT OUTER JOIN $revision ON page_latest=rev_id
162 WHERE rev_id IS NULL
163 " );
164 $widows = $result->numRows();
165 if ( $widows > 0 ) {
166 $this->output( "$widows childless pages...\n" );
167 $this->output( sprintf( "%10s %11s %2s %s\n", 'page_id', 'page_latest', 'ns', 'page_title' ) );
168 foreach ( $result as $row ) {
169 printf( "%10d %11d %2d %s\n",
170 $row->page_id,
171 $row->page_latest,
172 $row->page_namespace,
173 $row->page_title );
174 if ( $fix ) {
175 $dbw->delete( 'page', [ 'page_id' => $row->page_id ] );
176 }
177 }
178 if ( !$fix ) {
179 $this->output( "Run again with --fix to remove these entries automatically.\n" );
180 }
181 } else {
182 $this->output( "No childless pages! Yay!\n" );
183 }
184
185 if ( $fix ) {
186 $dbw->unlockTables( __METHOD__ );
187 }
188 }
189
194 private function checkSeparation( $fix ) {
195 $dbw = $this->getDB( DB_MASTER );
196 $page = $dbw->tableName( 'page' );
197 $revision = $dbw->tableName( 'revision' );
198
199 if ( $fix ) {
200 $this->lockTables( $dbw, [ 'user', 'text' ] );
201 }
202
203 $this->output( "\nChecking for pages whose page_latest links are incorrect... "
204 . "(this may take a while on a large wiki)\n" );
205 $result = $dbw->query( "
206 SELECT *
207 FROM $page LEFT OUTER JOIN $revision ON page_latest=rev_id
208 " );
209 $found = 0;
210 foreach ( $result as $row ) {
211 $result2 = $dbw->query( "
212 SELECT MAX(rev_timestamp) as max_timestamp
213 FROM $revision
214 WHERE rev_page=" . (int)( $row->page_id )
215 );
216 $row2 = $dbw->fetchObject( $result2 );
217 if ( $row2 ) {
218 if ( $row->rev_timestamp != $row2->max_timestamp ) {
219 if ( $found == 0 ) {
220 $this->output( sprintf( "%10s %10s %14s %14s\n",
221 'page_id', 'rev_id', 'timestamp', 'max timestamp' ) );
222 }
223 ++$found;
224 $this->output( sprintf( "%10d %10d %14s %14s\n",
225 $row->page_id,
226 $row->page_latest,
227 $row->rev_timestamp,
228 $row2->max_timestamp ) );
229 if ( $fix ) {
230 # ...
231 $maxId = $dbw->selectField(
232 'revision',
233 'rev_id',
234 [
235 'rev_page' => $row->page_id,
236 'rev_timestamp' => $row2->max_timestamp ] );
237 $this->output( "... updating to revision $maxId\n" );
238 $maxRev = Revision::newFromId( $maxId );
239 $title = Title::makeTitle( $row->page_namespace, $row->page_title );
240 $article = WikiPage::factory( $title );
241 $article->updateRevisionOn( $dbw, $maxRev );
242 }
243 }
244 } else {
245 $this->output( "wtf\n" );
246 }
247 }
248
249 if ( $found ) {
250 $this->output( "Found $found pages with incorrect latest revision.\n" );
251 } else {
252 $this->output( "No pages with incorrect latest revision. Yay!\n" );
253 }
254 if ( !$fix && $found > 0 ) {
255 $this->output( "Run again with --fix to remove these entries automatically.\n" );
256 }
257
258 if ( $fix ) {
259 $dbw->unlockTables( __METHOD__ );
260 }
261 }
262}
263
264$maintClass = Orphans::class;
265require_once RUN_MAINTENANCE_IF_MAIN;
Apache License January AND DISTRIBUTION Definitions License shall mean the terms and conditions for use
Abstract maintenance class for quickly writing and churning out maintenance scripts with minimal effo...
output( $out, $channel=null)
Throw some output to the user.
getDB( $db, $groups=[], $wiki=false)
Returns a database to be used by current maintenance script.
hasOption( $name)
Checks to see if a particular option exists.
addDescription( $text)
Set the description text.
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
MediaWikiServices is the service locator for the application scope of MediaWiki.
Maintenance script that looks for 'orphan' revisions hooked to pages which don't exist and 'childless...
Definition orphans.php:42
lockTables( $db, $extraTable=[])
Lock the appropriate tables for the script.
Definition orphans.php:65
checkSeparation( $fix)
Check for pages where page_latest is wrong.
Definition orphans.php:194
checkWidows( $fix)
Definition orphans.php:148
execute()
Do the actual work.
Definition orphans.php:53
__construct()
Default constructor.
Definition orphans.php:43
checkOrphans( $fix)
Check for orphan revisions.
Definition orphans.php:77
static newFromId( $id, $flags=0)
Load a page revision from a given revision ID number.
Definition Revision.php:114
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
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=(\d*-\d*)") 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. 'LanguageGetMagic':DEPRECATED since 1.16! 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 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:2042
namespace and then decline to actually register it file or subcat img or subcat $title
Definition hooks.txt:994
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:1619
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
Advanced database interface for IDatabase handles that include maintenance methods.
require_once RUN_MAINTENANCE_IF_MAIN
$maintClass
Definition orphans.php:264
const DB_MASTER
Definition defines.php:26