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
| | # Copyright (C) 2014-2018 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
#
# represents a header value in various forms. Used for HTML generation
# in our web interface(s)
package PublicInbox::Hval;
use strict;
use warnings;
use Encode qw(find_encoding);
use PublicInbox::MID qw/mid_clean mid_escape/;
use base qw/Exporter/;
our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename/;
# User-generated content (UGC) may have excessively long lines
# and screw up rendering on some browsers, so we use pre-wrap.
#
# We also force everything to the same scaled font-size because GUI
# browsers (tested both Firefox and surf (webkit)) uses a larger font
# for the Search <form> element than the rest of the page. Font size
# uniformity is important to people who rely on gigantic fonts.
# Finally, we use monospace to ensure the Search field and button
# has the same size and spacing as everything else which is
# <pre>-formatted anyways.
use constant STYLE =>
'<style>pre{white-space:pre-wrap}' .
'*{font-size:100%;font-family:monospace}</style>';
my $enc_ascii = find_encoding('us-ascii');
sub new {
my ($class, $raw, $href) = @_;
# we never care about trailing whitespace
$raw =~ s/\s*\z//;
bless {
raw => $raw,
href => defined $href ? $href : $raw,
}, $class;
}
sub new_msgid {
my ($class, $msgid) = @_;
$class->new($msgid, mid_escape($msgid));
}
sub new_oneline {
my ($class, $raw) = @_;
$raw = '' unless defined $raw;
$raw =~ tr/\t\n / /s; # squeeze spaces
$raw =~ tr/\r//d; # kill CR
$class->new($raw);
}
my %xhtml_map = (
'"' => '"',
'&' => '&',
"'" => ''',
'<' => '<',
'>' => '>',
);
$xhtml_map{chr($_)} = sprintf('\\x%02x', $_) for (0..31);
# some of these overrides are standard C escapes so they're
# easy-to-understand when rendered.
$xhtml_map{"\x00"} = '\\0'; # NUL
$xhtml_map{"\x07"} = '\\a'; # bell
$xhtml_map{"\x08"} = '\\b'; # backspace
$xhtml_map{"\x09"} = "\t"; # obvious to show as-is
$xhtml_map{"\x0a"} = "\n"; # obvious to show as-is
$xhtml_map{"\x0b"} = '\\v'; # vertical tab
$xhtml_map{"\x0c"} = '\\f'; # form feed
$xhtml_map{"\x0d"} = '\\r'; # carriage ret (not preceding \n)
$xhtml_map{"\x1b"} = '^['; # ASCII escape (mutt seems to escape this way)
$xhtml_map{"\x7f"} = '\\x7f'; # DEL
sub ascii_html {
my ($s) = @_;
$s =~ s/\r\n/\n/sg; # fixup bad line endings
$s =~ s/([<>&'"\x7f\x00-\x1f])/$xhtml_map{$1}/sge;
$enc_ascii->encode($s, Encode::HTMLCREF);
}
sub as_html { ascii_html($_[0]->{raw}) }
sub raw {
if (defined $_[1]) {
$_[0]->{raw} = $_[1];
} else {
$_[0]->{raw};
}
}
sub prurl {
my ($env, $u) = @_;
index($u, '//') == 0 ? "$env->{'psgi.url_scheme'}:$u" : $u;
}
# for misguided people who believe in this stuff, give them a
# substitution for '.'
# ․ · and ͺ were also candidates:
# https://public-inbox.org/meta/20170615015250.GA6484@starla/
# However, • was chosen to make copy+paste errors more obvious
sub obfuscate_addrs ($$;$) {
my $ibx = $_[0];
my $repl = $_[2] || '•';
my $re = $ibx->{-no_obfuscate_re}; # regex of domains
my $addrs = $ibx->{-no_obfuscate}; # { adddress => 1 }
$_[1] =~ s/(([\w\.\+=\-]+)\@([\w\-]+\.[\w\.\-]+))/
my ($addr, $user, $domain) = ($1, $2, $3);
if ($addrs->{$addr} || ((defined $re && $domain =~ $re))) {
$addr;
} else {
$domain =~ s!([^\.]+)\.!$1$repl!;
$user . '@' . $domain
}
/sge;
}
# like format_sanitized_subject in git.git pretty.c with '%f' format string
sub to_filename ($) {
my ($s, undef) = split(/\n/, $_[0]);
$s =~ s/[^A-Za-z0-9_\.]+/-/g;
$s =~ tr/././s;
$s =~ s/[\.\-]+\z//;
$s =~ s/\A[\.\-]+//;
$s
}
1;
|