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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
|
package Encode::MIME::Header;
use strict;
use warnings;
no warnings 'redefine';
our $VERSION = do { my @r = ( q$Revision: 2.11 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
use Encode qw(find_encoding encode_utf8 decode_utf8);
use MIME::Base64;
use Carp;
my %seed = (
decode_b => '1', # decodes 'B' encoding ?
decode_q => '1', # decodes 'Q' encoding ?
encode => 'B', # encode with 'B' or 'Q' ?
bpl => 75, # bytes per line
);
$Encode::Encoding{'MIME-Header'} =
bless { %seed, Name => 'MIME-Header', } => __PACKAGE__;
$Encode::Encoding{'MIME-B'} = bless {
%seed,
decode_q => 0,
Name => 'MIME-B',
} => __PACKAGE__;
$Encode::Encoding{'MIME-Q'} = bless {
%seed,
decode_q => 1,
encode => 'Q',
Name => 'MIME-Q',
} => __PACKAGE__;
use base qw(Encode::Encoding);
sub needs_lines { 1 }
sub perlio_ok { 0 }
sub decode($$;$) {
use utf8;
my ( $obj, $str, $chk ) = @_;
# zap spaces between encoded words
$str =~ s/\?=\s+=\?/\?==\?/gos;
# multi-line header to single line
$str =~ s/(?:\r\n|[\r\n])[ \t]//gos;
1 while ( $str =~
s/(=\?[-0-9A-Za-z_]+\?[Qq]\?)(.*?)\?=\1(.*?\?=)/$1$2$3/ )
; # Concat consecutive QP encoded mime headers
# Fixes breaking inside multi-byte characters
$str =~ s{
=\? # begin encoded word
([-0-9A-Za-z_]+) # charset (encoding)
(?:\*[A-Za-z]{1,8}(?:-[A-Za-z]{1,8})*)? # language (RFC 2231)
\?([QqBb])\? # delimiter
(.*?) # Base64-encodede contents
\?= # end encoded word
}{
if (uc($2) eq 'B'){
$obj->{decode_b} or croak qq(MIME "B" unsupported);
decode_b($1, $3, $chk);
} elsif (uc($2) eq 'Q'){
$obj->{decode_q} or croak qq(MIME "Q" unsupported);
decode_q($1, $3, $chk);
} else {
croak qq(MIME "$2" encoding is nonexistent!);
}
}egox;
$_[1] = $str if $chk;
return $str;
}
sub decode_b {
my $enc = shift;
my $d = find_encoding($enc) or croak qq(Unknown encoding "$enc");
my $db64 = decode_base64(shift);
my $chk = shift;
return $d->name eq 'utf8'
? Encode::decode_utf8($db64)
: $d->decode( $db64, $chk || Encode::FB_PERLQQ );
}
sub decode_q {
my ( $enc, $q, $chk ) = @_;
my $d = find_encoding($enc) or croak qq(Unknown encoding "$enc");
$q =~ s/_/ /go;
$q =~ s/=([0-9A-Fa-f]{2})/pack("C", hex($1))/ego;
return $d->name eq 'utf8'
? Encode::decode_utf8($q)
: $d->decode( $q, $chk || Encode::FB_PERLQQ );
}
my $especials =
join( '|' => map { quotemeta( chr($_) ) }
unpack( "C*", qq{()<>@,;:"'/[]?.=} ) );
my $re_encoded_word = qr{
=\? # begin encoded word
(?:[-0-9A-Za-z_]+) # charset (encoding)
(?:\*[A-Za-z]{1,8}(?:-[A-Za-z]{1,8})*)? # language (RFC 2231)
\?(?:[QqBb])\? # delimiter
(?:.*?) # Base64-encodede contents
\?= # end encoded word
}xo;
my $re_especials = qr{$re_encoded_word|$especials}xo;
sub encode($$;$) {
my ( $obj, $str, $chk ) = @_;
my @line = ();
for my $line ( split /\r\n|[\r\n]/o, $str ) {
my ( @word, @subline );
for my $word ( split /($re_especials)/o, $line ) {
if ( $word =~ /[^\x00-\x7f]/o
or $word =~ /^$re_encoded_word$/o )
{
push @word, $obj->_encode($word);
}
else {
push @word, $word;
}
}
my $subline = '';
for my $word (@word) {
use bytes ();
if ( bytes::length($subline) + bytes::length($word) >
$obj->{bpl} )
{
push @subline, $subline;
$subline = '';
}
$subline .= $word;
}
$subline and push @subline, $subline;
push @line, join( "\n " => @subline );
}
$_[1] = '' if $chk;
return join( "\n", @line );
}
use constant HEAD => '=?UTF-8?';
use constant TAIL => '?=';
use constant SINGLE => { B => \&_encode_b, Q => \&_encode_q, };
sub _encode {
my ( $o, $str ) = @_;
my $enc = $o->{encode};
my $llen = ( $o->{bpl} - length(HEAD) - 2 - length(TAIL) );
# to coerce a floating-point arithmetics, the following contains
# .0 in numbers -- dankogai
$llen *= $enc eq 'B' ? 3.0 / 4.0 : 1.0 / 3.0;
my @result = ();
my $chunk = '';
while ( length( my $chr = substr( $str, 0, 1, '' ) ) ) {
use bytes ();
if ( bytes::length($chunk) + bytes::length($chr) > $llen ) {
push @result, SINGLE->{$enc}($chunk);
$chunk = '';
}
$chunk .= $chr;
}
length($chunk) and push @result, SINGLE->{$enc}($chunk);
return @result;
}
sub _encode_b {
HEAD . 'B?' . encode_base64( encode_utf8(shift), '' ) . TAIL;
}
sub _encode_q {
my $chunk = shift;
$chunk = encode_utf8($chunk);
$chunk =~ s{
([^0-9A-Za-z])
}{
join("" => map {sprintf "=%02X", $_} unpack("C*", $1))
}egox;
return HEAD . 'Q?' . $chunk . TAIL;
}
1;
__END__
=head1 NAME
Encode::MIME::Header -- MIME 'B' and 'Q' header encoding
=head1 SYNOPSIS
use Encode qw/encode decode/;
$utf8 = decode('MIME-Header', $header);
$header = encode('MIME-Header', $utf8);
=head1 ABSTRACT
This module implements RFC 2047 Mime Header Encoding. There are 3
variant encoding names; C<MIME-Header>, C<MIME-B> and C<MIME-Q>. The
difference is described below
decode() encode()
----------------------------------------------
MIME-Header Both B and Q =?UTF-8?B?....?=
MIME-B B only; Q croaks =?UTF-8?B?....?=
MIME-Q Q only; B croaks =?UTF-8?Q?....?=
=head1 DESCRIPTION
When you decode(=?I<encoding>?I<X>?I<ENCODED WORD>?=), I<ENCODED WORD>
is extracted and decoded for I<X> encoding (B for Base64, Q for
Quoted-Printable). Then the decoded chunk is fed to
decode(I<encoding>). So long as I<encoding> is supported by Encode,
any source encoding is fine.
When you encode, it just encodes UTF-8 string with I<X> encoding then
quoted with =?UTF-8?I<X>?....?= . The parts that RFC 2047 forbids to
encode are left as is and long lines are folded within 76 bytes per
line.
=head1 BUGS
It would be nice to support encoding to non-UTF8, such as =?ISO-2022-JP?
and =?ISO-8859-1?= but that makes the implementation too complicated.
These days major mail agents all support =?UTF-8? so I think it is
just good enough.
Due to popular demand, 'MIME-Header-ISO_2022_JP' was introduced by
Makamaka. Thre are still too many MUAs especially cellular phone
handsets which does not grok UTF-8.
=head1 SEE ALSO
L<Encode>
RFC 2047, L<http://www.faqs.org/rfcs/rfc2047.html> and many other
locations.
=cut
|
