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
|
package URI::_punycode;
use strict;
use warnings;
our $VERSION = '5.10';
use Exporter 'import';
our @EXPORT = qw(encode_punycode decode_punycode);
use integer;
our $DEBUG = 0;
use constant BASE => 36;
use constant TMIN => 1;
use constant TMAX => 26;
use constant SKEW => 38;
use constant DAMP => 700;
use constant INITIAL_BIAS => 72;
use constant INITIAL_N => 128;
my $Delimiter = chr 0x2D;
my $BasicRE = qr/[\x00-\x7f]/;
sub _croak { require Carp; Carp::croak(@_); }
sub digit_value {
my $code = shift;
return ord($code) - ord("A") if $code =~ /[A-Z]/;
return ord($code) - ord("a") if $code =~ /[a-z]/;
return ord($code) - ord("0") + 26 if $code =~ /[0-9]/;
return;
}
sub code_point {
my $digit = shift;
return $digit + ord('a') if 0 <= $digit && $digit <= 25;
return $digit + ord('0') - 26 if 26 <= $digit && $digit <= 36;
die 'NOT COME HERE';
}
sub adapt {
my($delta, $numpoints, $firsttime) = @_;
$delta = $firsttime ? $delta / DAMP : $delta / 2;
$delta += $delta / $numpoints;
my $k = 0;
while ($delta > ((BASE - TMIN) * TMAX) / 2) {
$delta /= BASE - TMIN;
$k += BASE;
}
return $k + (((BASE - TMIN + 1) * $delta) / ($delta + SKEW));
}
sub decode_punycode {
my $code = shift;
my $n = INITIAL_N;
my $i = 0;
my $bias = INITIAL_BIAS;
my @output;
if ($code =~ s/(.*)$Delimiter//o) {
push @output, map ord, split //, $1;
return _croak('non-basic code point') unless $1 =~ /^$BasicRE*$/o;
}
while ($code) {
my $oldi = $i;
my $w = 1;
LOOP:
for (my $k = BASE; 1; $k += BASE) {
my $cp = substr($code, 0, 1, '');
my $digit = digit_value($cp);
defined $digit or return _croak("invalid punycode input");
$i += $digit * $w;
my $t = ($k <= $bias) ? TMIN
: ($k >= $bias + TMAX) ? TMAX : $k - $bias;
last LOOP if $digit < $t;
$w *= (BASE - $t);
}
$bias = adapt($i - $oldi, @output + 1, $oldi == 0);
warn "bias becomes $bias" if $DEBUG;
$n += $i / (@output + 1);
$i = $i % (@output + 1);
splice(@output, $i, 0, $n);
warn join " ", map sprintf('%04x', $_), @output if $DEBUG;
$i++;
}
return join '', map chr, @output;
}
sub encode_punycode {
my $input = shift;
my @input = split //, $input;
my $n = INITIAL_N;
my $delta = 0;
my $bias = INITIAL_BIAS;
my @output;
my @basic = grep /$BasicRE/, @input;
my $h = my $b = @basic;
push @output, @basic;
push @output, $Delimiter if $b && $h < @input;
warn "basic codepoints: (@output)" if $DEBUG;
while ($h < @input) {
my $m = min(grep { $_ >= $n } map ord, @input);
warn sprintf "next code point to insert is %04x", $m if $DEBUG;
$delta += ($m - $n) * ($h + 1);
$n = $m;
for my $i (@input) {
my $c = ord($i);
$delta++ if $c < $n;
if ($c == $n) {
my $q = $delta;
LOOP:
for (my $k = BASE; 1; $k += BASE) {
my $t = ($k <= $bias) ? TMIN :
($k >= $bias + TMAX) ? TMAX : $k - $bias;
last LOOP if $q < $t;
my $cp = code_point($t + (($q - $t) % (BASE - $t)));
push @output, chr($cp);
$q = ($q - $t) / (BASE - $t);
}
push @output, chr(code_point($q));
$bias = adapt($delta, $h + 1, $h == $b);
warn "bias becomes $bias" if $DEBUG;
$delta = 0;
$h++;
}
}
$delta++;
$n++;
}
return join '', @output;
}
sub min {
my $min = shift;
for (@_) { $min = $_ if $_ <= $min }
return $min;
}
1;
__END__
=encoding utf8
=head1 NAME
URI::_punycode - encodes Unicode string in Punycode
=head1 SYNOPSIS
use strict;
use warnings;
use utf8;
use URI::_punycode qw(encode_punycode decode_punycode);
# encode a unicode string
my $punycode = encode_punycode('http://☃.net'); # http://.net-xc8g
$punycode = encode_punycode('bücher'); # bcher-kva
$punycode = encode_punycode('他们为什么不说中文'); # ihqwcrb4cv8a8dqg056pqjye
# decode a punycode string back into a unicode string
my $unicode = decode_punycode('http://.net-xc8g'); # http://☃.net
$unicode = decode_punycode('bcher-kva'); # bücher
$unicode = decode_punycode('ihqwcrb4cv8a8dqg056pqjye'); # 他们为什么不说中文
=head1 DESCRIPTION
L<URI::_punycode> is a module to encode / decode Unicode strings into
L<Punycode|https://tools.ietf.org/html/rfc3492>, an efficient
encoding of Unicode for use with L<IDNA|https://tools.ietf.org/html/rfc5890>.
=head1 FUNCTIONS
All functions throw exceptions on failure. You can C<catch> them with
L<Syntax::Keyword::Try> or L<Try::Tiny>. The following functions are exported
by default.
=head2 encode_punycode
my $punycode = encode_punycode('http://☃.net'); # http://.net-xc8g
$punycode = encode_punycode('bücher'); # bcher-kva
$punycode = encode_punycode('他们为什么不说中文') # ihqwcrb4cv8a8dqg056pqjye
Takes a Unicode string (UTF8-flagged variable) and returns a Punycode
encoding for it.
=head2 decode_punycode
my $unicode = decode_punycode('http://.net-xc8g'); # http://☃.net
$unicode = decode_punycode('bcher-kva'); # bücher
$unicode = decode_punycode('ihqwcrb4cv8a8dqg056pqjye'); # 他们为什么不说中文
Takes a Punycode encoding and returns original Unicode string.
=head1 AUTHOR
Tatsuhiko Miyagawa <F<miyagawa@bulknews.net>> is the author of
L<IDNA::Punycode> which was the basis for this module.
=head1 SEE ALSO
L<IDNA::Punycode>, L<RFC 3492|https://tools.ietf.org/html/rfc3492>,
L<RFC 5891|https://tools.ietf.org/html/rfc5891>
=head1 COPYRIGHT AND LICENSE
This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself.
=cut
|
