MediaWiki  1.30.0
SpamBlacklistHooks.php
Go to the documentation of this file.
1 <?php
2 
4 
9 
10  public static function registerExtension() {
11  global $wgDisableAuthManager, $wgAuthManagerAutoConfig;
12 
13  if ( class_exists( AuthManager::class ) && !$wgDisableAuthManager ) {
16  } else {
17  Hooks::register( 'AbortNewAccount', 'SpamBlacklistHooks::abortNewAccount' );
18  }
19  }
20 
33  static function filterMergedContent(
35  Content $content,
37  $summary,
38  User $user,
39  $minoredit
40  ) {
42 
43  // get the link from the not-yet-saved page content.
44  $editInfo = $context->getWikiPage()->prepareContentForEdit( $content );
45  $pout = $editInfo->output;
46  $links = array_keys( $pout->getExternalLinks() );
47 
48  // HACK: treat the edit summary as a link if it contains anything
49  // that looks like it could be a URL or e-mail address.
50  if ( preg_match( '/\S(\.[^\s\d]{2,}|[\/@]\S)/', $summary ) ) {
51  $links[] = $summary;
52  }
53 
54  $spamObj = BaseBlacklist::getInstance( 'spam' );
55  $matches = $spamObj->filter( $links, $title );
56 
57  if ( $matches !== false ) {
58  $status->fatal( 'spamprotectiontext' );
59 
60  foreach ( $matches as $match ) {
61  $status->fatal( 'spamprotectionmatch', $match );
62  }
63 
64  $status->apiHookResult = [
65  'spamblacklist' => implode( '|', $matches ),
66  ];
67  }
68 
69  // Always return true, EditPage will look at $status->isOk().
70  return true;
71  }
72 
73  public static function onParserOutputStashForEdit(
74  WikiPage $page,
75  Content $content,
77  ) {
78  $links = array_keys( $output->getExternalLinks() );
79  $spamObj = BaseBlacklist::getInstance( 'spam' );
80  $spamObj->warmCachesForFilter( $page->getTitle(), $links );
81  }
82 
90  public static function userCanSendEmail( &$user, &$hookErr ) {
92  $blacklist = BaseBlacklist::getInstance( 'email' );
93  if ( $blacklist->checkUser( $user ) ) {
94  return true;
95  }
96 
97  $hookErr = [ 'spam-blacklisted-email', 'spam-blacklisted-email-text', null ];
98 
99  return false;
100  }
101 
109  public static function abortNewAccount( $user, &$abortError ) {
111  $blacklist = BaseBlacklist::getInstance( 'email' );
112  if ( $blacklist->checkUser( $user ) ) {
113  return true;
114  }
115 
116  $abortError = wfMessage( 'spam-blacklisted-email-signup' )->escaped();
117  return false;
118  }
119 
131  static function validate( EditPage $editPage, $text, $section, &$hookError ) {
132  $title = $editPage->getTitle();
133  $thisPageName = $title->getPrefixedDBkey();
134 
136  wfDebugLog( 'SpamBlacklist',
137  "Spam blacklist validator: [[$thisPageName]] not a local blacklist\n"
138  );
139  return true;
140  }
141 
143  if ( $type === false ) {
144  return true;
145  }
146 
147  $lines = explode( "\n", $text );
148 
150  if ( $badLines ) {
151  wfDebugLog( 'SpamBlacklist',
152  "Spam blacklist validator: [[$thisPageName]] given invalid input lines: " .
153  implode( ', ', $badLines ) . "\n"
154  );
155 
156  $badList = "*<code>" .
157  implode( "</code>\n*<code>",
158  array_map( 'wfEscapeWikiText', $badLines ) ) .
159  "</code>\n";
160  $hookError =
161  "<div class='errorbox'>" .
162  wfMessage( 'spam-invalid-lines' )->numParams( $badLines )->text() . "<br />" .
163  $badList .
164  "</div>\n" .
165  "<br clear='all' />\n";
166  } else {
167  wfDebugLog( 'SpamBlacklist',
168  "Spam blacklist validator: [[$thisPageName]] ok or empty blacklist\n"
169  );
170  }
171 
172  return true;
173  }
174 
193  static function pageSaveContent(
194  Page $wikiPage,
195  User $user,
196  Content $content,
197  $summary,
198  $isMinor,
199  $isWatch,
200  $section,
201  $flags,
202  $revision,
203  Status $status,
204  $baseRevId
205  ) {
206  if ( $revision ) {
208  ->doLogging( $user, $wikiPage->getTitle(), $revision->getId() );
209  }
210 
211  if ( !BaseBlacklist::isLocalSource( $wikiPage->getTitle() ) ) {
212  return true;
213  }
214 
215  // This sucks because every Blacklist needs to be cleared
216  foreach ( BaseBlacklist::getBlacklistTypes() as $type => $class ) {
217  $blacklist = BaseBlacklist::getInstance( $type );
218  $blacklist->clearCache();
219  }
220 
221  return true;
222  }
223 
233  public static function onUploadVerifyUpload(
234  UploadBase $upload,
235  User $user,
236  array $props,
237  $comment,
238  $pageText,
239  &$error
240  ) {
241  $title = $upload->getTitle();
242 
243  // get the link from the not-yet-saved page content.
244  $content = ContentHandler::makeContent( $pageText, $title );
245  $parserOptions = $content->getContentHandler()->makeParserOptions( 'canonical' );
246  $output = $content->getParserOutput( $title, null, $parserOptions );
247  $links = array_keys( $output->getExternalLinks() );
248 
249  // HACK: treat comment as a link if it contains anything
250  // that looks like it could be a URL or e-mail address.
251  if ( preg_match( '/\S(\.[^\s\d]{2,}|[\/@]\S)/', $comment ) ) {
252  $links[] = $comment;
253  }
254  if ( !$links ) {
255  return true;
256  }
257 
258  $spamObj = BaseBlacklist::getInstance( 'spam' );
259  $matches = $spamObj->filter( $links, $title );
260 
261  if ( $matches !== false ) {
262  $error = new ApiMessage(
263  wfMessage( 'spamprotectiontext' ),
264  'spamblacklist',
265  [
266  'spamblacklist' => [ 'matches' => $matches ],
267  'message' => [
268  'key' => 'spamprotectionmatch',
269  'params' => $matches[0],
270  ],
271  ]
272  );
273  }
274 
275  return true;
276  }
277 
284  public static function onArticleDelete( WikiPage &$article, User &$user, &$reason, &$error ) {
286  $spam = BaseBlacklist::getInstance( 'spam' );
287  if ( !$spam->isLoggingEnabled() ) {
288  return;
289  }
290 
291  // Log the changes, but we only commit them once the deletion has happened.
292  // We do that since the external links table could get cleared before the
293  // ArticleDeleteComplete hook runs
294  $spam->logUrlChanges( $spam->getCurrentLinks( $article->getTitle() ), [], [] );
295  }
296 
305  public static function onArticleDeleteComplete(
306  &$page,
307  User &$user,
308  $reason,
309  $id,
310  Content $content = null,
311  LogEntry $logEntry
312  ) {
314  $spam = BaseBlacklist::getInstance( 'spam' );
315  $spam->doLogging( $user, $page->getTitle(), $page->getLatest() );
316  }
317 }
BaseBlacklist\getBlacklistTypes
static getBlacklistTypes()
Return the array of blacklist types currently defined.
Definition: BaseBlacklist.php:89
$user
please add to it if you re going to add events to the MediaWiki code where normally authentication against an external auth plugin would be creating a account $user
Definition: hooks.txt:244
Page
Interface for type hinting (accepts WikiPage, Article, ImagePage, CategoryPage)
Definition: Page.php:24
SpamBlacklistHooks\onArticleDeleteComplete
static onArticleDeleteComplete(&$page, User &$user, $reason, $id, Content $content=null, LogEntry $logEntry)
Definition: SpamBlacklistHooks.php:305
BaseBlacklist\getInstance
static getInstance( $type)
Returns an instance of the given blacklist.
Definition: BaseBlacklist.php:100
ParserOutput
Definition: ParserOutput.php:24
$context
do that in ParserLimitReportFormat instead use this to modify the parameters of the image all existing parser cache entries will be invalid To avoid you ll need to handle that somehow(e.g. with the RejectParserCacheValue hook) because MediaWiki won 't do it for you. & $defaults also a ContextSource after deleting those rows but within the same transaction you ll probably need to make sure the header is varied on and they can depend only on the ResourceLoaderContext $context
Definition: hooks.txt:2581
$wgAuthManagerAutoConfig
$wgAuthManagerAutoConfig
Definition: DefaultSettings.php:4577
SpamBlacklistHooks\pageSaveContent
static pageSaveContent(Page $wikiPage, User $user, Content $content, $summary, $isMinor, $isWatch, $section, $flags, $revision, Status $status, $baseRevId)
Hook function for PageContentSaveComplete Clear local spam blacklist caches on page save.
Definition: SpamBlacklistHooks.php:193
MediaWiki\getTitle
getTitle()
Get the Title object that we'll be acting on, as specified in the WebRequest.
Definition: MediaWiki.php:137
$status
Status::newGood()` to allow deletion, and then `return false` from the hook function. Ensure you consume the 'ChangeTagAfterDelete' hook to carry out custom deletion actions. $tag:name of the tag $user:user initiating the action & $status:Status object. See above. 'ChangeTagsListActive':Allows you to nominate which of the tags your extension uses are in active use. & $tags:list of all active tags. Append to this array. 'ChangeTagsAfterUpdateTags':Called after tags have been updated with the ChangeTags::updateTags function. Params:$addedTags:tags effectively added in the update $removedTags:tags effectively removed in the update $prevTags:tags that were present prior to the update $rc_id:recentchanges table id $rev_id:revision table id $log_id:logging table id $params:tag params $rc:RecentChange being tagged when the tagging accompanies the action or null $user:User who performed the tagging when the tagging is subsequent to the action or null 'ChangeTagsAllowedAdd':Called when checking if a user can add tags to a change. & $allowedTags:List of all the tags the user is allowed to add. Any tags the user wants to add( $addTags) that are not in this array will cause it to fail. You may add or remove tags to this array as required. $addTags:List of tags user intends to add. $user:User who is adding the tags. 'ChangeUserGroups':Called before user groups are changed. $performer:The User who will perform the change $user:The User whose groups will be changed & $add:The groups that will be added & $remove:The groups that will be removed 'Collation::factory':Called if $wgCategoryCollation is an unknown collation. $collationName:Name of the collation in question & $collationObject:Null. Replace with a subclass of the Collation class that implements the collation given in $collationName. 'ConfirmEmailComplete':Called after a user 's email has been confirmed successfully. $user:user(object) whose email is being confirmed 'ContentAlterParserOutput':Modify parser output for a given content object. Called by Content::getParserOutput after parsing has finished. Can be used for changes that depend on the result of the parsing but have to be done before LinksUpdate is called(such as adding tracking categories based on the rendered HTML). $content:The Content to render $title:Title of the page, as context $parserOutput:ParserOutput to manipulate 'ContentGetParserOutput':Customize parser output for a given content object, called by AbstractContent::getParserOutput. May be used to override the normal model-specific rendering of page content. $content:The Content to render $title:Title of the page, as context $revId:The revision ID, as context $options:ParserOptions for rendering. To avoid confusing the parser cache, the output can only depend on parameters provided to this hook function, not on global state. $generateHtml:boolean, indicating whether full HTML should be generated. If false, generation of HTML may be skipped, but other information should still be present in the ParserOutput object. & $output:ParserOutput, to manipulate or replace 'ContentHandlerDefaultModelFor':Called when the default content model is determined for a given title. May be used to assign a different model for that title. $title:the Title in question & $model:the model name. Use with CONTENT_MODEL_XXX constants. 'ContentHandlerForModelID':Called when a ContentHandler is requested for a given content model name, but no entry for that model exists in $wgContentHandlers. Note:if your extension implements additional models via this hook, please use GetContentModels hook to make them known to core. $modeName:the requested content model name & $handler:set this to a ContentHandler object, if desired. 'ContentModelCanBeUsedOn':Called to determine whether that content model can be used on a given page. This is especially useful to prevent some content models to be used in some special location. $contentModel:ID of the content model in question $title:the Title in question. & $ok:Output parameter, whether it is OK to use $contentModel on $title. Handler functions that modify $ok should generally return false to prevent further hooks from further modifying $ok. 'ContribsPager::getQueryInfo':Before the contributions query is about to run & $pager:Pager object for contributions & $queryInfo:The query for the contribs Pager 'ContribsPager::reallyDoQuery':Called before really executing the query for My Contributions & $data:an array of results of all contribs queries $pager:The ContribsPager object hooked into $offset:Index offset, inclusive $limit:Exact query limit $descending:Query direction, false for ascending, true for descending 'ContributionsLineEnding':Called before a contributions HTML line is finished $page:SpecialPage object for contributions & $ret:the HTML line $row:the DB row for this line & $classes:the classes to add to the surrounding< li > & $attribs:associative array of other HTML attributes for the< li > element. Currently only data attributes reserved to MediaWiki are allowed(see Sanitizer::isReservedDataAttribute). 'ContributionsToolLinks':Change tool links above Special:Contributions $id:User identifier $title:User page title & $tools:Array of tool links $specialPage:SpecialPage instance for context and services. Can be either SpecialContributions or DeletedContributionsPage. Extensions should type hint against a generic SpecialPage though. 'ConvertContent':Called by AbstractContent::convert when a conversion to another content model is requested. Handler functions that modify $result should generally return false to disable further attempts at conversion. $content:The Content object to be converted. $toModel:The ID of the content model to convert to. $lossy:boolean indicating whether lossy conversion is allowed. & $result:Output parameter, in case the handler function wants to provide a converted Content object. Note that $result->getContentModel() must return $toModel. 'CustomEditor':When invoking the page editor Return true to allow the normal editor to be used, or false if implementing a custom editor, e.g. for a special namespace, etc. $article:Article being edited $user:User performing the edit 'DatabaseOraclePostInit':Called after initialising an Oracle database $db:the DatabaseOracle object 'DeletedContribsPager::reallyDoQuery':Called before really executing the query for Special:DeletedContributions Similar to ContribsPager::reallyDoQuery & $data:an array of results of all contribs queries $pager:The DeletedContribsPager object hooked into $offset:Index offset, inclusive $limit:Exact query limit $descending:Query direction, false for ascending, true for descending 'DeletedContributionsLineEnding':Called before a DeletedContributions HTML line is finished. Similar to ContributionsLineEnding $page:SpecialPage object for DeletedContributions & $ret:the HTML line $row:the DB row for this line & $classes:the classes to add to the surrounding< li > & $attribs:associative array of other HTML attributes for the< li > element. Currently only data attributes reserved to MediaWiki are allowed(see Sanitizer::isReservedDataAttribute). 'DifferenceEngineAfterLoadNewText':called in DifferenceEngine::loadNewText() after the new revision 's content has been loaded into the class member variable $differenceEngine->mNewContent but before returning true from this function. $differenceEngine:DifferenceEngine object 'DifferenceEngineLoadTextAfterNewContentIsLoaded':called in DifferenceEngine::loadText() after the new revision 's content has been loaded into the class member variable $differenceEngine->mNewContent but before checking if the variable 's value is null. This hook can be used to inject content into said class member variable. $differenceEngine:DifferenceEngine object 'DifferenceEngineMarkPatrolledLink':Allows extensions to change the "mark as patrolled" link which is shown both on the diff header as well as on the bottom of a page, usually wrapped in a span element which has class="patrollink". $differenceEngine:DifferenceEngine object & $markAsPatrolledLink:The "mark as patrolled" link HTML(string) $rcid:Recent change ID(rc_id) for this change(int) 'DifferenceEngineMarkPatrolledRCID':Allows extensions to possibly change the rcid parameter. For example the rcid might be set to zero due to the user being the same as the performer of the change but an extension might still want to show it under certain conditions. & $rcid:rc_id(int) of the change or 0 $differenceEngine:DifferenceEngine object $change:RecentChange object $user:User object representing the current user 'DifferenceEngineNewHeader':Allows extensions to change the $newHeader variable, which contains information about the new revision, such as the revision 's author, whether the revision was marked as a minor edit or not, etc. $differenceEngine:DifferenceEngine object & $newHeader:The string containing the various #mw-diff-otitle[1-5] divs, which include things like revision author info, revision comment, RevisionDelete link and more $formattedRevisionTools:Array containing revision tools, some of which may have been injected with the DiffRevisionTools hook $nextlink:String containing the link to the next revision(if any) $status
Definition: hooks.txt:1245
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
WikiPage
Class representing a MediaWiki article and history.
Definition: WikiPage.php:37
BaseBlacklist\isLocalSource
static isLocalSource(Title $title)
Check if the given local page title is a spam regex source.
Definition: BaseBlacklist.php:133
BaseBlacklist\getTypeFromTitle
static getTypeFromTitle(Title $title)
Returns the type of blacklist from the given title.
Definition: BaseBlacklist.php:186
SpamRegexBatch\getBadLines
static getBadLines( $lines, BaseBlacklist $blacklist)
Returns an array of invalid lines.
Definition: SpamRegexBatch.php:118
$output
static configuration should be added through ResourceLoaderGetConfigVars instead can be used to get the real title after the basic globals have been set but before ordinary actions take place $output
Definition: hooks.txt:2198
wfDebugLog
wfDebugLog( $logGroup, $text, $dest='all', array $context=[])
Send a line to a supplementary debug log file, if configured, or main debug log if not.
Definition: GlobalFunctions.php:1140
SpamBlacklistHooks\filterMergedContent
static filterMergedContent(IContextSource $context, Content $content, Status $status, $summary, User $user, $minoredit)
Hook function for EditFilterMergedContent.
Definition: SpamBlacklistHooks.php:33
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 $wgServiceWiringFiles lists includes ServiceWiring php
Definition: injection.txt:35
SpamBlacklistHooks\onArticleDelete
static onArticleDelete(WikiPage &$article, User &$user, &$reason, &$error)
Definition: SpamBlacklistHooks.php:284
ApiMessage
Extension of Message implementing IApiMessage.
Definition: ApiMessage.php:198
Status
Generic operation result class Has warning/error list, boolean status and arbitrary value.
Definition: Status.php:40
$title
namespace and then decline to actually register it file or subcat img or subcat $title
Definition: hooks.txt:932
SpamBlacklistHooks\validate
static validate(EditPage $editPage, $text, $section, &$hookError)
Hook function for EditFilter Confirm that a local blacklist page being saved is valid,...
Definition: SpamBlacklistHooks.php:131
LogEntry
Interface for log entries.
Definition: LogEntry.php:38
$matches
$matches
Definition: NoLocalSettings.php:24
$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
WikiPage\getTitle
getTitle()
Get the title object of the article.
Definition: WikiPage.php:239
SpamBlacklistHooks\onParserOutputStashForEdit
static onParserOutputStashForEdit(WikiPage $page, Content $content, ParserOutput $output)
Definition: SpamBlacklistHooks.php:73
$lines
$lines
Definition: router.php:67
global
when a variable name is used in a it is silently declared as a new masking the global
Definition: design.txt:93
ContentHandler\makeContent
static makeContent( $text, Title $title=null, $modelId=null, $format=null)
Convenience function for creating a Content object from a given textual representation.
Definition: ContentHandler.php:129
Hooks\register
static register( $name, $callback)
Attach an event handler to a given hook.
Definition: Hooks.php:49
SpamBlacklistHooks\abortNewAccount
static abortNewAccount( $user, &$abortError)
Processes new accounts for valid email addresses.
Definition: SpamBlacklistHooks.php:109
SpamBlacklistHooks\onUploadVerifyUpload
static onUploadVerifyUpload(UploadBase $upload, User $user, array $props, $comment, $pageText, &$error)
Definition: SpamBlacklistHooks.php:233
EditPage
The edit page/HTML interface (split from Article) The actual database and text munging is still in Ar...
Definition: EditPage.php:42
MediaWiki\Auth\AuthManager
This serves as the entry point to the authentication system.
Definition: AuthManager.php:82
IContextSource
Interface for objects which can provide a MediaWiki context on request.
Definition: IContextSource.php:55
Content
Base interface for content objects.
Definition: Content.php:34
SpamBlacklistHooks
Hooks for the spam blacklist extension.
Definition: SpamBlacklistHooks.php:8
$section
usually copyright or history_copyright This message must be in HTML not wikitext if the section is included from a template $section
Definition: hooks.txt:2981
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
EditPage\getTitle
getTitle()
Definition: EditPage.php:483
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 $wgRequest set to '' to unset offset - wrap String Wrap the message in html(usually something like "&lt
class
you have access to all of the normal MediaWiki so you can get a DB use the etc For full docs on the Maintenance class
Definition: maintenance.txt:52
SpamBlacklistHooks\userCanSendEmail
static userCanSendEmail(&$user, &$hookErr)
Verify that the user can send emails.
Definition: SpamBlacklistHooks.php:90
User
The User object encapsulates all of the user-specific settings (user_id, name, rights,...
Definition: User.php:51
$flags
it s the revision text itself In either if gzip is the revision text is gzipped $flags
Definition: hooks.txt:2801
array
the array() calling protocol came about after MediaWiki 1.4rc1.
SpamBlacklistHooks\registerExtension
static registerExtension()
Definition: SpamBlacklistHooks.php:10
$type
$type
Definition: testCompression.php:48