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
|
<?php
/**
* An aggressive spam cleanup script.
* Searches the database for matching pages, and reverts them to the last non-spammed revision.
* If all revisions contain spam, deletes the page
*/
require_once( '../../maintenance/commandLine.inc' );
require_once( 'SpamBlacklist_body.php' );
/**
* Find the latest revision of the article that does not contain spam and revert to it
*/
function cleanupArticle( Revision $rev, $regexes, $match ) {
$title = $rev->getTitle();
$revId = $rev->getId();
while ( $rev ) {
$matches = false;
foreach ( $regexes as $regex ) {
$matches = $matches || preg_match( $regex, $rev->getText() );
}
if ( !$matches ) {
// Didn't find any spam
break;
}
# Revision::getPrevious can't be used in this way before MW 1.6 (Revision.php 1.26)
#$rev = $rev->getPrevious();
$revId = $title->getPreviousRevisionID( $revId );
if ( $revId ) {
$rev = Revision::newFromTitle( $title, $revId );
} else {
$rev = false;
}
}
$dbw = wfGetDB( DB_MASTER );
$dbw->begin();
if ( !$rev ) {
// Didn't find a non-spammy revision, delete the page
/*
print "All revisions are spam, deleting...\n";
$article = new Article( $title );
$article->doDeleteArticle( "All revisions matched the spam blacklist" );
*/
// Too scary, blank instead
print "All revisions are spam, blanking...\n";
$text = '';
$comment = "All revisions matched the spam blacklist ($match), blanking";
} else {
// Revert to this revision
$text = $rev->getText();
$comment = "Cleaning up links to $match";
}
$wikiPage = new WikiPage( $title );
$wikiPage->doEdit( $text, $comment );
$dbw->commit();
}
//------------------------------------------------------------------------------
$username = 'Spam cleanup script';
$wgUser = User::newFromName( $username );
if ( $wgUser->idForName() == 0 ) {
// Create the user
$status = $wgUser->addToDatabase();
if ( $status === null || $status->isOK() ) {
$dbw = wfGetDB( DB_MASTER );
$dbw->update( 'user', array( 'user_password' => 'nologin' ),
array( 'user_name' => $username ), $username );
}
}
if ( isset( $options['n'] ) ) {
$dryRun = true;
} else {
$dryRun = false;
}
$sb = new SpamBlacklist( $wgSpamBlacklistSettings );
if ( $wgSpamBlacklistFiles ) {
$sb->files = $wgSpamBlacklistFiles;
}
$regexes = $sb->getBlacklists();
if ( !$regexes ) {
print "Invalid regex, can't clean up spam\n";
exit( 1 );
}
$dbr = wfGetDB( DB_SLAVE );
$maxID = $dbr->selectField( 'page', 'MAX(page_id)' );
$reportingInterval = 100;
print "Regexes are " . implode( ', ', array_map( 'count', $regexes ) ) . " bytes\n";
print "Searching for spam in $maxID pages...\n";
if ( $dryRun ) {
print "Dry run only\n";
}
for ( $id = 1; $id <= $maxID; $id++ ) {
if ( $id % $reportingInterval == 0 ) {
printf( "%-8d %-5.2f%%\r", $id, $id / $maxID * 100 );
}
$revision = Revision::loadFromPageId( $dbr, $id );
if ( $revision ) {
$text = $revision->getText();
if ( $text ) {
foreach ( $regexes as $regex ) {
if ( preg_match( $regex, $text, $matches ) ) {
$title = $revision->getTitle();
$titleText = $title->getPrefixedText();
if ( $dryRun ) {
print "\nFound spam in [[$titleText]]\n";
} else {
print "\nCleaning up links to {$matches[0]} in [[$titleText]]\n";
$match = str_replace( 'http://', '', $matches[0] );
cleanupArticle( $revision, $regexes, $match );
}
}
}
}
}
}
// Just for satisfaction
printf( "%-8d %-5.2f%%\n", $id - 1, ( $id - 1 ) / $maxID * 100 );
|
