MediaWiki  1.33.0
SpamBlacklistHooks.php
Go to the documentation of this file.
1 <?php
2 
7 
20  public static function filterMergedContent(
24  $summary,
25  User $user,
26  $minoredit
27  ) {
29 
30  // get the link from the not-yet-saved page content.
31  $editInfo = $context->getWikiPage()->prepareContentForEdit( $content );
32  $pout = $editInfo->output;
33  $links = array_keys( $pout->getExternalLinks() );
34 
35  // HACK: treat the edit summary as a link if it contains anything
36  // that looks like it could be a URL or e-mail address.
37  if ( preg_match( '/\S(\.[^\s\d]{2,}|[\/@]\S)/', $summary ) ) {
38  $links[] = $summary;
39  }
40 
42  $matches = $spamObj->filter( $links, $title );
43 
44  if ( $matches !== false ) {
45  $status->fatal( 'spamprotectiontext' );
46 
47  foreach ( $matches as $match ) {
48  $status->fatal( 'spamprotectionmatch', $match );
49  }
50 
51  $status->apiHookResult = [
52  'spamblacklist' => implode( '|', $matches ),
53  ];
54  }
55 
56  // Always return true, EditPage will look at $status->isOk().
57  return true;
58  }
59 
60  public static function onParserOutputStashForEdit(
61  WikiPage $page,
64  ) {
65  $links = array_keys( $output->getExternalLinks() );
67  $spamObj->warmCachesForFilter( $page->getTitle(), $links );
68  }
69 
77  public static function userCanSendEmail( &$user, &$hookErr ) {
78  $blacklist = BaseBlacklist::getEmailBlacklist();
79  if ( $blacklist->checkUser( $user ) ) {
80  return true;
81  }
82 
83  $hookErr = [ 'spam-blacklisted-email', 'spam-blacklisted-email-text', null ];
84 
85  return false;
86  }
87 
99  public static function validate( EditPage $editPage, $text, $section, &$hookError ) {
100  $title = $editPage->getTitle();
101  $thisPageName = $title->getPrefixedDBkey();
102 
104  wfDebugLog( 'SpamBlacklist',
105  "Spam blacklist validator: [[$thisPageName]] not a local blacklist\n"
106  );
107  return true;
108  }
109 
111  if ( $type === false ) {
112  return true;
113  }
114 
115  $lines = explode( "\n", $text );
116 
118  if ( $badLines ) {
119  wfDebugLog( 'SpamBlacklist',
120  "Spam blacklist validator: [[$thisPageName]] given invalid input lines: " .
121  implode( ', ', $badLines ) . "\n"
122  );
123 
124  $badList = "*<code>" .
125  implode( "</code>\n*<code>",
126  array_map( 'wfEscapeWikiText', $badLines ) ) .
127  "</code>\n";
128  $hookError =
129  "<div class='errorbox'>" .
130  wfMessage( 'spam-invalid-lines' )->numParams( $badLines )->text() . "<br />" .
131  $badList .
132  "</div>\n" .
133  "<br clear='all' />\n";
134  } else {
135  wfDebugLog( 'SpamBlacklist',
136  "Spam blacklist validator: [[$thisPageName]] ok or empty blacklist\n"
137  );
138  }
139 
140  return true;
141  }
142 
161  public static function pageSaveContent(
162  WikiPage $wikiPage,
163  User $user,
165  $summary,
166  $isMinor,
167  $isWatch,
168  $section,
169  $flags,
170  $revision,
171  Status $status,
172  $baseRevId
173  ) {
174  if ( $revision ) {
176  ->doLogging( $user, $wikiPage->getTitle(), $revision->getId() );
177  }
178 
179  if ( !BaseBlacklist::isLocalSource( $wikiPage->getTitle() ) ) {
180  return true;
181  }
182 
183  // This sucks because every Blacklist needs to be cleared
184  foreach ( BaseBlacklist::getBlacklistTypes() as $type => $class ) {
185  $blacklist = BaseBlacklist::getInstance( $type );
186  $blacklist->clearCache();
187  }
188 
189  return true;
190  }
191 
201  public static function onUploadVerifyUpload(
202  UploadBase $upload,
203  User $user,
204  array $props,
205  $comment,
206  $pageText,
207  &$error
208  ) {
209  $title = $upload->getTitle();
210 
211  // get the link from the not-yet-saved page content.
213  $parserOptions = ParserOptions::newCanonical( 'canonical' );
214  $output = $content->getParserOutput( $title, null, $parserOptions );
215  $links = array_keys( $output->getExternalLinks() );
216 
217  // HACK: treat comment as a link if it contains anything
218  // that looks like it could be a URL or e-mail address.
219  if ( preg_match( '/\S(\.[^\s\d]{2,}|[\/@]\S)/', $comment ) ) {
220  $links[] = $comment;
221  }
222  if ( !$links ) {
223  return true;
224  }
225 
226  $spamObj = BaseBlacklist::getSpamBlacklist();
227  $matches = $spamObj->filter( $links, $title );
228 
229  if ( $matches !== false ) {
230  $error = new ApiMessage(
231  wfMessage( 'spamprotectiontext' ),
232  'spamblacklist',
233  [
234  'spamblacklist' => [ 'matches' => $matches ],
235  'message' => [
236  'key' => 'spamprotectionmatch',
237  'params' => $matches[0],
238  ],
239  ]
240  );
241  }
242 
243  return true;
244  }
245 
252  public static function onArticleDelete( WikiPage &$article, User &$user, &$reason, &$error ) {
254  if ( !$spam->isLoggingEnabled() ) {
255  return;
256  }
257 
258  // Log the changes, but we only commit them once the deletion has happened.
259  // We do that since the external links table could get cleared before the
260  // ArticleDeleteComplete hook runs
261  $spam->logUrlChanges( $spam->getCurrentLinks( $article->getTitle() ), [], [] );
262  }
263 
273  public static function onArticleDeleteComplete(
274  &$page,
275  User &$user,
276  $reason,
277  $id,
278  Content $content = null,
279  LogEntry $logEntry
280  ) {
282  $spam->doLogging( $user, $page->getTitle(), $page->getLatest() );
283  }
284 }
BaseBlacklist\getSpamBlacklist
static getSpamBlacklist()
Definition: BaseBlacklist.php:96
$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. 'ContentSecurityPolicyDefaultSource':Modify the allowed CSP load sources. This affects all directives except for the script directive. If you want to add a script source, see ContentSecurityPolicyScriptSource hook. & $defaultSrc:Array of Content-Security-Policy allowed sources $policyConfig:Current configuration for the Content-Security-Policy header $mode:ContentSecurityPolicy::REPORT_ONLY_MODE or ContentSecurityPolicy::FULL_MODE depending on type of header 'ContentSecurityPolicyDirectives':Modify the content security policy directives. Use this only if ContentSecurityPolicyDefaultSource and ContentSecurityPolicyScriptSource do not meet your needs. & $directives:Array of CSP directives $policyConfig:Current configuration for the CSP header $mode:ContentSecurityPolicy::REPORT_ONLY_MODE or ContentSecurityPolicy::FULL_MODE depending on type of header 'ContentSecurityPolicyScriptSource':Modify the allowed CSP script sources. Note that you also have to use ContentSecurityPolicyDefaultSource if you want non-script sources to be loaded from whatever you add. & $scriptSrc:Array of CSP directives $policyConfig:Current configuration for the CSP header $mode:ContentSecurityPolicy::REPORT_ONLY_MODE or ContentSecurityPolicy::FULL_MODE depending on type of header '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). 'DeleteUnknownPreferences':Called by the cleanupPreferences.php maintenance script to build a WHERE clause with which to delete preferences that are not known about. This hook is used by extensions that have dynamically-named preferences that should not be deleted in the usual cleanup process. For example, the Gadgets extension creates preferences prefixed with 'gadget-', and so anything with that prefix is excluded from the deletion. &where:An array that will be passed as the $cond parameter to IDatabase::select() to determine what will be deleted from the user_properties table. $db:The IDatabase object, useful for accessing $db->buildLike() etc. '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:1266
BaseBlacklist\getBlacklistTypes
static getBlacklistTypes()
Return the array of blacklist types currently defined.
Definition: BaseBlacklist.php:89
$user
return true to allow those checks to and false if checking is done & $user
Definition: hooks.txt:1476
$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 & $article
Definition: hooks.txt:1476
SpamBlacklistHooks\onArticleDeleteComplete
static onArticleDeleteComplete(&$page, User &$user, $reason, $id, Content $content=null, LogEntry $logEntry)
Definition: SpamBlacklistHooks.php:273
BaseBlacklist\getInstance
static getInstance( $type)
Returns an instance of the given blacklist.
Definition: BaseBlacklist.php:115
ParserOutput
Definition: ParserOutput.php:25
$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:2636
MediaWiki\getTitle
getTitle()
Get the Title object that we'll be acting on, as specified in the WebRequest.
Definition: MediaWiki.php:137
WikiPage
Class representing a MediaWiki article and history.
Definition: WikiPage.php:45
BaseBlacklist\isLocalSource
static isLocalSource(Title $title)
Check if the given local page title is a spam regex source.
Definition: BaseBlacklist.php:148
BaseBlacklist\getTypeFromTitle
static getTypeFromTitle(Title $title)
Returns the type of blacklist from the given title.
Definition: BaseBlacklist.php:202
SpamRegexBatch\getBadLines
static getBadLines( $lines, BaseBlacklist $blacklist)
Returns an array of invalid lines.
Definition: SpamRegexBatch.php:119
ContextSource\getTitle
getTitle()
Definition: ContextSource.php:79
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:1043
SpamBlacklistHooks\filterMergedContent
static filterMergedContent(IContextSource $context, Content $content, Status $status, $summary, User $user, $minoredit)
Hook function for EditFilterMergedContent.
Definition: SpamBlacklistHooks.php:20
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:252
ApiMessage
Extension of Message implementing IApiMessage.
Definition: ApiMessage.php:26
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:925
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:99
LogEntry
Interface for log entries.
Definition: LogEntry.php:42
$matches
$matches
Definition: NoLocalSettings.php:24
WikiPage\getTitle
getTitle()
Get the title object of the article.
Definition: WikiPage.php:294
SpamBlacklistHooks\onParserOutputStashForEdit
static onParserOutputStashForEdit(WikiPage $page, Content $content, ParserOutput $output)
Definition: SpamBlacklistHooks.php:60
$lines
$lines
Definition: router.php:61
$output
$output
Definition: SyntaxHighlight.php:334
array
The wiki should then use memcached to cache various data To use multiple just add more items to the array To increase the weight of a make its entry a array("192.168.0.1:11211", 2))
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:133
null
this hook is for auditing only or null if authentication failed before getting that far or null if we can t even determine that When $user is not null
Definition: hooks.txt:780
ParserOptions\newCanonical
static newCanonical( $context=null, $userLang=null)
Creates a "canonical" ParserOptions object.
Definition: ParserOptions.php:1064
SpamBlacklistHooks\onUploadVerifyUpload
static onUploadVerifyUpload(UploadBase $upload, User $user, array $props, $comment, $pageText, &$error)
Definition: SpamBlacklistHooks.php:201
EditPage
The edit page/HTML interface (split from Article) The actual database and text munging is still in Ar...
Definition: EditPage.php:44
IContextSource
Interface for objects which can provide a MediaWiki context on request.
Definition: IContextSource.php:53
Content
Base interface for content objects.
Definition: Content.php:34
SpamBlacklistHooks
Hooks for the spam blacklist extension.
Definition: SpamBlacklistHooks.php:6
$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:3053
BaseBlacklist\getEmailBlacklist
static getEmailBlacklist()
Definition: BaseBlacklist.php:103
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:515
$content
$content
Definition: pageupdater.txt:72
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 use $formDescriptor instead 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 $wgRequest set to '' to unset offset - wrap String Wrap the message in html(usually something like "&lt
SpamBlacklistHooks\userCanSendEmail
static userCanSendEmail(&$user, &$hookErr)
Verify that the user can send emails.
Definition: SpamBlacklistHooks.php:77
User
The User object encapsulates all of the user-specific settings (user_id, name, rights,...
Definition: User.php:48
SpamBlacklistHooks\pageSaveContent
static pageSaveContent(WikiPage $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:161
$type
$type
Definition: testCompression.php:48