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
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
|
# -*- Mode: perl; indent-tabs-mode: nil -*-
#
# The contents of this file are subject to the Mozilla Public
# License Version 1.1 (the "License"); you may not use this file
# except in compliance with the License. You may obtain a copy of
# the License at http://www.mozilla.org/MPL/
#
# Software distributed under the License is distributed on an "AS
# IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
# implied. See the License for the specific language governing
# rights and limitations under the License.
#
# The Original Code is the Profanivore Bugzilla Extension.
#
# The Initial Developer of the Original Code is the Mozilla Foundation.
# Portions created by the Initial Developer are Copyright (C) 2010 the
# Initial Developer. All Rights Reserved.
#
# Contributor(s):
# Gervase Markham <gerv@gerv.net>
package Bugzilla::Extension::Profanivore;
use strict;
use base qw(Bugzilla::Extension);
use Email::MIME::ContentType qw(parse_content_type);
use Regexp::Common 'RE_ALL';
use Bugzilla::Util qw(is_7bit_clean);
our $VERSION = '0.01';
sub bug_format_comment {
my ($self, $args) = @_;
my $regexes = $args->{'regexes'};
my $comment = $args->{'comment'};
# Censor profanities if the comment author is not reasonably trusted.
# However, allow people to see their own profanities, which might stop
# them immediately noticing and trying to go around the filter. (I.e.
# it tries to stop an arms race starting.)
if ($comment &&
!$comment->author->in_group('editbugs') &&
$comment->author->id != Bugzilla->user->id)
{
push (@$regexes, {
match => RE_profanity('-i'),
replace => \&_replace_profanity
});
}
}
sub _replace_profanity {
# We don't have access to the actual profanity.
return "****";
}
sub mailer_before_send {
my ($self, $args) = @_;
my $email = $args->{'email'};
my $author = $email->header("X-Bugzilla-Who");
my $recipient = $email->header("To");
if ($author && $recipient && lc($author) ne lc($recipient)) {
my $email_suffix = Bugzilla->params->{'emailsuffix'};
if ($email_suffix ne '') {
$recipient =~ s/\Q$email_suffix\E$//;
$author =~ s/\Q$email_suffix\E$//;
}
$author = new Bugzilla::User({ name => $author });
if ($author &&
$author->id &&
!$author->in_group('editbugs'))
{
# Multipart emails
if (scalar $email->parts > 1) {
$email->walk_parts(sub {
my ($part) = @_;
return if $part->parts > 1; # Top-level
# do not filter attachments such as patches, etc.
if ($part->header('Content-Disposition')
&& $part->header('Content-Disposition') =~ /attachment/)
{
return;
}
_fix_encoding($part);
my $body = $part->body_str;
my $new_body;
if ($part->content_type =~ /^text\/html/) {
$new_body = _filter_html($body);
if ($new_body ne $body) {
# HTML::Tree removes unnecessary whitespace,
# resulting in very long lines. We need to use
# quoted-printable encoding to avoid exceeding
# email's maximum line length.
$part->encoding_set('quoted-printable');
}
}
elsif ($part->content_type =~ /^text\/plain/) {
$new_body = _filter_text($body);
}
if ($new_body && $new_body ne $body) {
$part->body_str_set($new_body);
}
});
}
# Single part email
else {
_fix_encoding($email);
$email->body_str_set(_filter_text($email->body_str));
}
}
}
}
sub _fix_encoding {
my $part = shift;
# don't touch the top-level part of multi-part mail
return if $part->parts > 1;
# nothing to do if the part already has a charset
my $ct = parse_content_type($part->content_type);
my $charset = $ct->{attributes}{charset}
? $ct->{attributes}{charset}
: '';
return unless !$charset || $charset eq 'us-ascii';
if (Bugzilla->params->{utf8}) {
$part->charset_set('UTF-8');
my $raw = $part->body_raw;
if (utf8::is_utf8($raw)) {
utf8::encode($raw);
$part->body_set($raw);
}
}
$part->encoding_set('quoted-printable');
}
sub _filter_text {
my $text = shift;
my $offensive = RE_profanity('-i');
$text =~ s/$offensive/****/g;
return $text;
}
sub _filter_html {
my $html = shift;
my $tree = HTML::Tree->new->parse_content($html);
my $comments_div = $tree->look_down( _tag => 'div', id => 'comments' );
return $html if !$comments_div;
my @comments = $comments_div->look_down( _tag => 'pre' );
my $dirty = 0;
foreach my $comment (@comments) {
_filter_html_node($comment, \$dirty);
}
return $dirty ? $tree->as_HTML : $html;
}
sub _filter_html_node {
my ($node, $dirty) = @_;
my $content = [ $node->content_list ];
foreach my $item_r ($node->content_refs_list) {
if (ref $$item_r) {
_filter_html_node($$item_r);
} else {
my $new_text = _filter_text($$item_r);
if ($new_text ne $$item_r) {
$$item_r = $new_text;
$$dirty = 1;
}
}
}
}
__PACKAGE__->NAME;
|
