1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
|
<?php
if ( !defined( 'MEDIAWIKI' ) ) {
exit;
}
class SpamBlacklist extends BaseBlacklist {
var $files = array( "http://meta.wikimedia.org/w/index.php?title=Spam_blacklist&action=raw&sb_ver=1" );
var $ignoreEditSummary = false;
/**
* Returns the code for the blacklist implementation
*
* @return string
*/
protected function getBlacklistType() {
return 'spam';
}
/**
* @param Title $title
* @param string $text Text of section, or entire text if $editPage!=false
* @param string $section Section number or name
* @param string $editsummary Edit summary if one exists, some people use urls there too
* @param EditPage $editPage EditPage if EditFilterMerged was called, null otherwise
* @return Array Matched text(s) if the edit should not be allowed, false otherwise
*/
function filter( &$title, $text, $section, $editsummary = '', EditPage &$editPage = null ) {
/**
* @var $wgParser Parser
*/
global $wgParser, $wgUser;
$fname = 'wfSpamBlacklistFilter';
wfProfileIn( $fname );
# These don't do anything, commenting out...
#$this->title = $title;
#$this->text = $text;
#$this->section = $section;
$text = str_replace( '．', '.', $text ); //@bug 12896
$blacklists = $this->getBlacklists();
$whitelists = $this->getWhitelists();
if ( count( $blacklists ) ) {
# Run parser to strip SGML comments and such out of the markup
# This was being used to circumvent the filter (see bug 5185)
if ( $editPage ) {
$editInfo = $editPage->mArticle->prepareTextForEdit( $text );
$out = $editInfo->output;
} else {
$options = new ParserOptions();
$text = $wgParser->preSaveTransform( $text, $title, $wgUser, $options );
$out = $wgParser->parse( $text, $title, $options );
}
$newLinks = array_keys( $out->getExternalLinks() );
$oldLinks = $this->getCurrentLinks( $title );
$addedLinks = array_diff( $newLinks, $oldLinks );
// We add the edit summary if one exists
if ( !$this->ignoreEditSummary && !empty( $editsummary ) ) {
$addedLinks[] = $editsummary;
}
wfDebugLog( 'SpamBlacklist', "Old URLs: " . implode( ', ', $oldLinks ) );
wfDebugLog( 'SpamBlacklist', "New URLs: " . implode( ', ', $newLinks ) );
wfDebugLog( 'SpamBlacklist', "Added URLs: " . implode( ', ', $addedLinks ) );
$links = implode( "\n", $addedLinks );
# Strip whitelisted URLs from the match
if( is_array( $whitelists ) ) {
wfDebugLog( 'SpamBlacklist', "Excluding whitelisted URLs from " . count( $whitelists ) .
" regexes: " . implode( ', ', $whitelists ) . "\n" );
foreach( $whitelists as $regex ) {
wfSuppressWarnings();
$newLinks = preg_replace( $regex, '', $links );
wfRestoreWarnings();
if( is_string( $newLinks ) ) {
// If there wasn't a regex error, strip the matching URLs
$links = $newLinks;
}
}
}
# Do the match
wfDebugLog( 'SpamBlacklist', "Checking text against " . count( $blacklists ) .
" regexes: " . implode( ', ', $blacklists ) . "\n" );
$retVal = false;
foreach( $blacklists as $regex ) {
wfSuppressWarnings();
$matches = array();
$check = ( preg_match_all( $regex, $links, $matches ) > 0 );
wfRestoreWarnings();
if( $check ) {
wfDebugLog( 'SpamBlacklist', "Match!\n" );
global $wgRequest;
$ip = $wgRequest->getIP();
$imploded = implode( ' ', $matches[0] );
wfDebugLog( 'SpamBlacklistHit', "$ip caught submitting spam: $imploded\n" );
if( $retVal === false ){
$retVal = array();
}
$retVal = array_merge( $retVal, $matches[0] );
}
}
} else {
$retVal = false;
}
wfProfileOut( $fname );
return $retVal;
}
/**
* Look up the links currently in the article, so we can
* ignore them on a second run.
*
* WARNING: I can add more *of the same link* with no problem here.
* @param $title Title
* @return array
*/
function getCurrentLinks( $title ) {
$dbr = wfGetDB( DB_SLAVE );
$id = $title->getArticleID(); // should be zero queries
$res = $dbr->select( 'externallinks', array( 'el_to' ),
array( 'el_from' => $id ), __METHOD__ );
$links = array();
foreach ( $res as $row ) {
$links[] = $row->el_to;
}
return $links;
}
/**
* Returns the start of the regex for matches
*
* @return string
*/
public function getRegexStart() {
return '/(?:https?:)?\/\/+[a-z0-9_\-.]*(';
}
/**
* Returns the end of the regex for matches
*
* @param $batchSize
* @return string
*/
public function getRegexEnd( $batchSize ) {
return ')' . parent::getRegexEnd( $batchSize );
}
}
|
