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
|
<?php
/**
* Some functions to help implement an external link filter for spam control.
*
* TODO: implement the filter. Currently these are just some functions to help
* maintenance/cleanupSpam.php remove links to a single specified domain. The
* next thing is to implement functions for checking a given page against a big
* list of domains.
*
* Another cool thing to do would be a web interface for fast spam removal.
*/
class LinkFilter {
/**
* @static
*/
static function matchEntry( $text, $filterEntry ) {
$regex = LinkFilter::makeRegex( $filterEntry );
return preg_match( $regex, $text );
}
/**
* @static
*/
private static function makeRegex( $filterEntry ) {
$regex = '!http://';
if ( substr( $filterEntry, 0, 2 ) == '*.' ) {
$regex .= '(?:[A-Za-z0-9.-]+\.|)';
$filterEntry = substr( $filterEntry, 2 );
}
$regex .= preg_quote( $filterEntry, '!' ) . '!Si';
return $regex;
}
/**
* Make a string to go after an SQL LIKE, which will match the specified
* string. There are several kinds of filter entry:
* *.domain.com - Produces http://com.domain.%, matches domain.com
* and www.domain.com
* domain.com - Produces http://com.domain./%, matches domain.com
* or domain.com/ but not www.domain.com
* *.domain.com/x - Produces http://com.domain.%/x%, matches
* www.domain.com/xy
* domain.com/x - Produces http://com.domain./x%, matches
* domain.com/xy but not www.domain.com/xy
*
* Asterisks in any other location are considered invalid.
*
* @static
* @param $filterEntry String: domainparts
* @param $prot String: protocol
*/
public static function makeLike( $filterEntry , $prot = 'http://' ) {
if ( substr( $filterEntry, 0, 2 ) == '*.' ) {
$subdomains = true;
$filterEntry = substr( $filterEntry, 2 );
if ( $filterEntry == '' ) {
// We don't want to make a clause that will match everything,
// that could be dangerous
return false;
}
} else {
$subdomains = false;
}
// No stray asterisks, that could cause confusion
// It's not simple or efficient to handle it properly so we don't
// handle it at all.
if ( strpos( $filterEntry, '*' ) !== false ) {
return false;
}
$slash = strpos( $filterEntry, '/' );
if ( $slash !== false ) {
$path = substr( $filterEntry, $slash );
$host = substr( $filterEntry, 0, $slash );
} else {
$path = '/';
$host = $filterEntry;
}
// Reverse the labels in the hostname, convert to lower case
// For emails reverse domainpart only
if ( $prot == 'mailto:' && strpos($host, '@') ) {
// complete email adress
$mailparts = explode( '@', $host );
$domainpart = strtolower( implode( '.', array_reverse( explode( '.', $mailparts[1] ) ) ) );
$host = $domainpart . '@' . $mailparts[0];
$like = "$prot$host%";
} elseif ( $prot == 'mailto:' ) {
// domainpart of email adress only. do not add '.'
$host = strtolower( implode( '.', array_reverse( explode( '.', $host ) ) ) );
$like = "$prot$host%";
} else {
$host = strtolower( implode( '.', array_reverse( explode( '.', $host ) ) ) );
if ( substr( $host, -1, 1 ) !== '.' ) {
$host .= '.';
}
$like = "$prot$host";
if ( $subdomains ) {
$like .= '%';
}
if ( !$subdomains || $path !== '/' ) {
$like .= $path . '%';
}
}
return $like;
}
}
?>
|
