|  line  | 
 stmt  | 
 bran  | 
 cond  | 
 sub  | 
 pod  | 
 time  | 
 code  | 
| 
1
 | 
  
 
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 #========================================================================  | 
| 
2
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 #  | 
| 
3
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 # Badger::Codec::HTML  | 
| 
4
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 #  | 
| 
5
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 # DESCRIPTION  | 
| 
6
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 #   Module for encoding (escaping) and decoding (unescaping) HTML  | 
| 
7
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 #  | 
| 
8
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 # AUTHOR  | 
| 
9
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 #   Andy Wardley  based on code extracted from   | 
| 
10
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 #   Lincoln Stein's CGI.pm module.  | 
| 
11
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 #  | 
| 
12
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 #========================================================================  | 
| 
13
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
14
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 package Badger::Codec::HTML;  | 
| 
15
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
16
 | 
1
 | 
 
 | 
 
 | 
  
1
  
 | 
 
 | 
6
 | 
 use strict;  | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
1
 | 
    | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
27
 | 
    | 
| 
17
 | 
1
 | 
 
 | 
 
 | 
  
1
  
 | 
 
 | 
4
 | 
 use warnings;  | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
3
 | 
    | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
52
 | 
    | 
| 
18
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 use Badger::Class  | 
| 
19
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
9
 | 
     version => 0.01,  | 
| 
20
 | 
1
 | 
 
 | 
 
 | 
  
1
  
 | 
 
 | 
5
 | 
     base    => 'Badger::Codec';  | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
2
 | 
    | 
| 
21
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
22
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our $CHARSET = {  | 
| 
23
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     'ISO-8859-1'   => \&fix_windows,  | 
| 
24
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     'WINDOWS-1252' => \&fix_windows,  | 
| 
25
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 };  | 
| 
26
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
27
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub encode {  | 
| 
28
 | 
4
 | 
 
 | 
 
 | 
  
4
  
 | 
  
1
  
 | 
10
 | 
     my ($class, $html, $charset) = @_;  | 
| 
29
 | 
4
 | 
 
 | 
 
 | 
 
 | 
 
 | 
5
 | 
     my $filter;  | 
| 
30
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
31
 | 
4
 | 
  
 50
  
 | 
 
 | 
 
 | 
 
 | 
8
 | 
     return undef unless defined($html);  | 
| 
32
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
33
 | 
4
 | 
 
 | 
 
 | 
 
 | 
 
 | 
9
 | 
     for ($html) {  | 
| 
34
 | 
4
 | 
 
 | 
 
 | 
 
 | 
 
 | 
12
 | 
         s/&/&/g;  | 
| 
35
 | 
4
 | 
 
 | 
 
 | 
 
 | 
 
 | 
11
 | 
         s/\"/"/g;  | 
| 
36
 | 
4
 | 
 
 | 
 
 | 
 
 | 
 
 | 
10
 | 
         s/>/>/g;  | 
| 
37
 | 
4
 | 
 
 | 
 
 | 
 
 | 
 
 | 
12
 | 
         s/</g;  | 
| 
38
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     }  | 
| 
39
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
40
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     # pass resulting HTML through any corresponding filter for the   | 
| 
41
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     # character set (if specified)  | 
| 
42
 | 
4
 | 
  
 50
  
 | 
  
 33
  
 | 
 
 | 
 
 | 
8
 | 
     if ($charset && ($filter = $CHARSET->{ $charset })) {  | 
| 
43
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
         $html = &$filter($html);  | 
| 
44
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     }  | 
| 
45
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
           | 
| 
46
 | 
4
 | 
 
 | 
 
 | 
 
 | 
 
 | 
17
 | 
     return $html;  | 
| 
47
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
48
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
49
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub decode {  | 
| 
50
 | 
4
 | 
 
 | 
 
 | 
  
4
  
 | 
  
1
  
 | 
8
 | 
     my ($class, $html) = @_;  | 
| 
51
 | 
4
 | 
  
 50
  
 | 
 
 | 
 
 | 
 
 | 
8
 | 
     return undef unless defined($html);  | 
| 
52
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
53
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     # Thanks to Randal Schwartz for the correct solution to this one.  | 
| 
54
 | 
4
 | 
 
 | 
 
 | 
 
 | 
 
 | 
30
 | 
     $html =~ s[ &(.*?); ] {  | 
| 
55
 | 
28
 | 
 
 | 
 
 | 
 
 | 
 
 | 
43
 | 
         local $_ = $1;  | 
| 
56
 | 
28
 | 
  
  0
  
 | 
 
 | 
 
 | 
 
 | 
105
 | 
         /^amp$/i	   ? "&" :  | 
| 
 
 | 
 
 | 
  
  0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
 
 | 
 
 | 
  
 50
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
 
 | 
 
 | 
  
100
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
 
 | 
 
 | 
  
100
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
 
 | 
 
 | 
  
100
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
57
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
         /^quot$/i	   ? '"' :  | 
| 
58
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
         /^gt$/i		   ? ">" :  | 
| 
59
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
         /^lt$/i		   ? "<" :  | 
| 
60
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
         /^#(\d+)$/	   ? chr($1) :  | 
| 
61
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
         /^#x([0-9a-f]+)$/i ? chr(hex($1)) :  | 
| 
62
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
         $_  | 
| 
63
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     }gex;  | 
| 
64
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
65
 | 
4
 | 
 
 | 
 
 | 
 
 | 
 
 | 
18
 | 
     return $html;  | 
| 
66
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
67
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
68
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub fix_windows {  | 
| 
69
 | 
  
0
  
 | 
 
 | 
 
 | 
  
0
  
 | 
  
1
  
 | 
 
 | 
     my $html = shift;  | 
| 
70
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
71
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     # work around bug in some inferior browsers   | 
| 
72
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     for ($html) {  | 
| 
73
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
         s/'/'/g;  | 
| 
74
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
         s/\x8b/‹/g;  | 
| 
75
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
         s/\x9b/›/g;  | 
| 
76
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     }  | 
| 
77
 | 
0
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     return $html;  | 
| 
78
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
79
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
80
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 1;  | 
| 
81
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
82
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 __END__  |