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
|
BEGIN {
if ($ENV{'PERL_CORE'}){
chdir 't';
unshift @INC, '../lib';
}
require Config; import Config;
if ($Config{'extensions'} !~ /\bEncode\b/) {
print "1..0 # Skip: Encode was not built\n";
exit 0;
}
unless (find PerlIO::Layer 'perlio') {
print "1..0 # Skip: PerlIO was not built\n";
exit 0;
}
if (ord("A") == 193) {
print "1..0 # Skip: EBCDIC\n";
exit 0;
}
$| = 1;
}
use strict;
use Test::More tests => 17;
use Encode;
use_ok('Encode::TW');
# Since JP.t already test basic file IO, we will just focus on
# internal encode / decode test here. Unfortunately, to test
# against all the UniHan characters will take a huge disk space,
# not to mention the time it will take, and the fact that Perl
# did not bundle UniHan.txt anyway.
# So, here we just test a typical snippet spanning multiple Unicode
# blocks, and hope it can point out obvious errors.
run_tests('Basic Big5 range', {
'utf' => (
24093.39640.38525.20043.33495.35028.20846.65292.
26389.30343.32771.26352.20271.24248.65108.
25885.25552.35998.20110.23391.38508.20846.65292.
24799.24218.23493.21566.20197.38477.65108
),
'big5' => (join('',
'帝高陽之苗裔兮，朕皇考曰伯庸﹔',
'攝提貞于孟陬兮，惟庚寅吾以降﹔',
)),
'big5-hkscs'=> (join('',
'帝高陽之苗裔兮，朕皇考曰伯庸﹔',
'攝提貞于孟陬兮，惟庚寅吾以降﹔',
)),
'cp950' => (join('',
'帝高陽之苗裔兮，朕皇考曰伯庸﹔',
'攝提貞于孟陬兮，惟庚寅吾以降﹔',
)),
});
run_tests('Hong Kong Extensions', {
'utf' => (
24863.35613.25152.26377.20351.29992.32.80.101.114.108.32.
22021.26379.21451.65292.32102.25105.21707.22021.
25903.25345.12289.24847.35211.21644.40723.21237.
22914.26524.32232.30908.26377.20219.20309.37679.28431.
65292.35531.21578.35380.25105.21707.12290
),
'big5-hkscs' => join('',
'感謝所有使用 Perl 麊B友，給我]鴾銕龤B意見和鼓勵',
'如果編碼有任何錯漏，請告訴我]。'
),
});
sub run_tests {
my ($title, $tests) = @_;
my $utf = delete $tests->{'utf'};
# $enc = encoding, $str = content
foreach my $enc (sort keys %{$tests}) {
my $str = $tests->{$enc};
is(Encode::decode($enc, $str), $utf, "[$enc] decode - $title");
is(Encode::encode($enc, $utf), $str, "[$enc] encode - $title");
my $str2 = $str;
my $utf8 = Encode::encode('utf-8', $utf);
Encode::from_to($str2, $enc, 'utf-8');
is($str2, $utf8, "[$enc] from_to => utf8 - $title");
Encode::from_to($utf8, 'utf-8', $enc); # convert $utf8 as $enc
is($utf8, $str, "[$enc] utf8 => from_to - $title");
}
}
|
