MediaWiki  REL1_31
cleanupSpam.php
Go to the documentation of this file.
1 <?php
24 require_once __DIR__ . '/Maintenance.php';
25 
31 class CleanupSpam extends Maintenance {
32 
33  public function __construct() {
34  parent::__construct();
35  $this->addDescription( 'Cleanup all spam from a given hostname' );
36  $this->addOption( 'all', 'Check all wikis in $wgLocalDatabases' );
37  $this->addOption( 'delete', 'Delete pages containing only spam instead of blanking them' );
38  $this->addArg(
39  'hostname',
40  'Hostname that was spamming, single * wildcard in the beginning allowed'
41  );
42  }
43 
44  public function execute() {
46 
47  $username = wfMessage( 'spambot_username' )->text();
48  $wgUser = User::newSystemUser( $username );
49  if ( !$wgUser ) {
50  $this->fatalError( "Invalid username specified in 'spambot_username' message: $username" );
51  }
52  // Hack: Grant bot rights so we don't flood RecentChanges
53  $wgUser->addGroup( 'bot' );
54 
55  $spec = $this->getArg();
56  $like = LinkFilter::makeLikeArray( $spec );
57  if ( !$like ) {
58  $this->fatalError( "Not a valid hostname specification: $spec" );
59  }
60 
61  if ( $this->hasOption( 'all' ) ) {
62  // Clean up spam on all wikis
63  $this->output( "Finding spam on " . count( $wgLocalDatabases ) . " wikis\n" );
64  $found = false;
65  foreach ( $wgLocalDatabases as $wikiID ) {
66  $dbr = $this->getDB( DB_REPLICA, [], $wikiID );
67 
68  $count = $dbr->selectField( 'externallinks', 'COUNT(*)',
69  [ 'el_index' . $dbr->buildLike( $like ) ], __METHOD__ );
70  if ( $count ) {
71  $found = true;
72  $cmd = wfShellWikiCmd( "$IP/maintenance/cleanupSpam.php",
73  [ '--wiki', $wikiID, $spec ] );
74  passthru( "$cmd | sed 's/^/$wikiID: /'" );
75  }
76  }
77  if ( $found ) {
78  $this->output( "All done\n" );
79  } else {
80  $this->output( "None found\n" );
81  }
82  } else {
83  // Clean up spam on this wiki
84 
85  $dbr = $this->getDB( DB_REPLICA );
86  $res = $dbr->select( 'externallinks', [ 'DISTINCT el_from' ],
87  [ 'el_index' . $dbr->buildLike( $like ) ], __METHOD__ );
88  $count = $dbr->numRows( $res );
89  $this->output( "Found $count articles containing $spec\n" );
90  foreach ( $res as $row ) {
91  $this->cleanupArticle( $row->el_from, $spec );
92  }
93  if ( $count ) {
94  $this->output( "Done\n" );
95  }
96  }
97  }
98 
99  private function cleanupArticle( $id, $domain ) {
100  $title = Title::newFromID( $id );
101  if ( !$title ) {
102  $this->error( "Internal error: no page for ID $id" );
103 
104  return;
105  }
106 
107  $this->output( $title->getPrefixedDBkey() . " ..." );
109  $currentRevId = $rev->getId();
110 
111  while ( $rev && ( $rev->isDeleted( Revision::DELETED_TEXT )
112  || LinkFilter::matchEntry( $rev->getContent( Revision::RAW ), $domain ) )
113  ) {
114  $rev = $rev->getPrevious();
115  }
116 
117  if ( $rev && $rev->getId() == $currentRevId ) {
118  // The regex didn't match the current article text
119  // This happens e.g. when a link comes from a template rather than the page itself
120  $this->output( "False match\n" );
121  } else {
122  $dbw = $this->getDB( DB_MASTER );
123  $this->beginTransaction( $dbw, __METHOD__ );
124  $page = WikiPage::factory( $title );
125  if ( $rev ) {
126  // Revert to this revision
127  $content = $rev->getContent( Revision::RAW );
128 
129  $this->output( "reverting\n" );
130  $page->doEditContent(
131  $content,
132  wfMessage( 'spam_reverting', $domain )->inContentLanguage()->text(),
134  $rev->getId()
135  );
136  } elseif ( $this->hasOption( 'delete' ) ) {
137  // Didn't find a non-spammy revision, blank the page
138  $this->output( "deleting\n" );
139  $page->doDeleteArticle(
140  wfMessage( 'spam_deleting', $domain )->inContentLanguage()->text()
141  );
142  } else {
143  // Didn't find a non-spammy revision, blank the page
145  $content = $handler->makeEmptyContent();
146 
147  $this->output( "blanking\n" );
148  $page->doEditContent(
149  $content,
150  wfMessage( 'spam_blanking', $domain )->inContentLanguage()->text(),
152  );
153  }
154  $this->commitTransaction( $dbw, __METHOD__ );
155  }
156  }
157 }
158 
160 require_once RUN_MAINTENANCE_IF_MAIN;
$handler
this hook is for auditing only or null if authentication failed before getting that far or null if we can t even determine that probably a stub it is not rendered in wiki pages or galleries in category pages allow injecting custom HTML after the section Any uses of the hook need to handle escaping see BaseTemplate::getToolbox and BaseTemplate::makeListItem for details on the format of individual items inside of this array or by returning and letting standard HTTP rendering take place modifiable or by returning false and taking over the output modifiable modifiable after all normalizations have been except for the $wgMaxImageArea check set to true or false to override the $wgMaxImageArea check result gives extension the possibility to transform it themselves $handler
Definition: hooks.txt:903
$wgUser
$wgUser
Definition: Setup.php:902
CleanupSpam
Maintenance script to cleanup all spam from a given hostname.
Definition: cleanupSpam.php:31
wfMessage
either a unescaped string or a HtmlArmor object after in associative array form externallinks including delete and has completed for all link tables whether this was an auto creation default is conds Array Extra conditions for the No matching items in log is displayed if loglist is empty msgKey Array If you want a nice box with a set this to the key of the message First element is the message additional optional elements are parameters for the key that are processed with wfMessage() -> params() ->parseAsBlock() - offset Set to overwrite offset parameter in $wgRequest set to '' to unset offset - wrap String Wrap the message in html(usually something like "&lt
EDIT_FORCE_BOT
const EDIT_FORCE_BOT
Definition: Defines.php:166
Maintenance\fatalError
fatalError( $msg, $exitCode=1)
Output a message and terminate the current script.
Definition: Maintenance.php:439
text
design txt This is a brief overview of the new design More thorough and up to date information is available on the documentation wiki at etc Handles the details of getting and saving to the user table of the and dealing with sessions and cookies OutputPage Encapsulates the entire HTML page that will be sent in response to any server request It is used by calling its functions to add text
Definition: design.txt:18
Maintenance\addDescription
addDescription( $text)
Set the description text.
Definition: Maintenance.php:291
LinkFilter\matchEntry
static matchEntry(Content $content, $filterEntry)
Check whether $content contains a link to $filterEntry.
Definition: LinkFilter.php:43
RUN_MAINTENANCE_IF_MAIN
require_once RUN_MAINTENANCE_IF_MAIN
Definition: maintenance.txt:50
ContentHandler\getForTitle
static getForTitle(Title $title)
Returns the appropriate ContentHandler singleton for the given title.
Definition: ContentHandler.php:240
$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
$maintClass
$maintClass
Definition: cleanupSpam.php:159
wfShellWikiCmd
wfShellWikiCmd( $script, array $parameters=[], array $options=[])
Generate a shell-escaped command line string to run a MediaWiki cli script.
Definition: GlobalFunctions.php:2334
CleanupSpam\cleanupArticle
cleanupArticle( $id, $domain)
Definition: cleanupSpam.php:99
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
$dbr
$dbr
Definition: testCompression.php:50
User\newSystemUser
static newSystemUser( $name, $options=[])
Static factory method for creation of a "system" user from username.
Definition: User.php:791
Maintenance\beginTransaction
beginTransaction(IDatabase $dbw, $fname)
Begin a transcation on a DB.
Definition: Maintenance.php:1336
Revision\newFromTitle
static newFromTitle(LinkTarget $linkTarget, $id=0, $flags=0)
Load either the current, or a specified, revision that's attached to a given link target.
Definition: Revision.php:133
WikiPage\factory
static factory(Title $title)
Create a WikiPage object of the appropriate class for the given title.
Definition: WikiPage.php:115
Maintenance\addOption
addOption( $name, $description, $required=false, $withArg=false, $shortName=false, $multiOccurrence=false)
Add a parameter to the script.
Definition: Maintenance.php:219
LinkFilter\makeLikeArray
static makeLikeArray( $filterEntry, $protocol='http://')
Make an array to be used for calls to Database::buildLike(), which will match the specified string.
Definition: LinkFilter.php:95
$title
namespace and then decline to actually register it file or subcat img or subcat $title
Definition: hooks.txt:964
global
when a variable name is used in a it is silently declared as a new masking the global
Definition: design.txt:95
DB_REPLICA
const DB_REPLICA
Definition: defines.php:25
DB_MASTER
const DB_MASTER
Definition: defines.php:26
$wgLocalDatabases
$wgLocalDatabases
Other wikis on this site, can be administered from a single developer account.
Definition: DefaultSettings.php:2094
EDIT_UPDATE
const EDIT_UPDATE
Definition: Defines.php:163
Maintenance\commitTransaction
commitTransaction(IDatabase $dbw, $fname)
Commit the transcation on a DB handle and wait for replica DBs to catch up.
Definition: Maintenance.php:1351
Revision\RAW
const RAW
Definition: Revision.php:57
CleanupSpam\__construct
__construct()
Default constructor.
Definition: cleanupSpam.php:33
$rev
presenting them properly to the user as errors is done by the caller return true use this to change the list i e etc $rev
Definition: hooks.txt:1777
Maintenance\addArg
addArg( $arg, $description, $required=true)
Add some args that are needed.
Definition: Maintenance.php:271
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
$username
this hook is for auditing only or null if authentication failed before getting that far $username
Definition: hooks.txt:785
Maintenance\error
error( $err, $die=0)
Throw an error to the user.
Definition: Maintenance.php:416
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
CleanupSpam\execute
execute()
Do the actual work.
Definition: cleanupSpam.php:44
Maintenance\getArg
getArg( $argId=0, $default=null)
Get an argument.
Definition: Maintenance.php:310
$IP
$IP
Definition: WebStart.php:52
Title\newFromID
static newFromID( $id, $flags=0)
Create a new Title from an article ID.
Definition: Title.php:416
Revision\DELETED_TEXT
const DELETED_TEXT
Definition: Revision.php:47