2
if ($ENV{'PERL_CORE'}){
4
unshift @INC, '../lib';
6
require Config; import Config;
7
if ($Config{'extensions'} !~ /\bEncode\b/) {
8
print "1..0 # Skip: Encode was not built\n";
11
if (ord("A") == 193) {
12
print "1..0 # Skip: EBCDIC\n";
19
use Test::More tests => 29;
22
no utf8; # we have raw Chinese encodings here
26
# Since JP.t already tests basic file IO, we will just focus on
27
# internal encode / decode test here. Unfortunately, to test
28
# against all the UniHan characters will take a huge disk space,
29
# not to mention the time it will take, and the fact that Perl
30
# did not bundle UniHan.txt anyway.
32
# So, here we just test a typical snippet spanning multiple Unicode
33
# blocks, and hope it can point out obvious errors.
35
run_tests('Simplified Chinese only', {
37
12298.26131.32463.12299.31532.19968.21350.
39
22823.21705.20094.20803.65292.19975.29289.36164.22987.65292.
40
20035.32479.22825.12290.
41
20113.34892.38632.26045.65292.21697.29289.27969.24418.12290.
42
22823.26126.22987.32456.65292.20845.20301.26102.25104.65292.
43
26102.20056.20845.40857.20197.24481.22825.12290.
44
20094.36947.21464.21270.65292.21508.27491.24615.21629.65292.
45
20445.21512.22823.21644.65292.20035.21033.36126.12290.
46
39318.20986.24246.29289.65292.19975.22269.21688.23425.12290
62
'gb2312-raw' => join('',
65
'4sTUG,T*#,MrNoWJJ<#,',
67
'TFPPSjJ)#,F7NoAwPN!#',
68
'4sCwJ<VU#,AyN;J13I#,',
70
'G,5@1d;/#,8wU}PTC|#,',
72
'JW3vJ|No#,Mr9zOLD~!#'
75
'iso-ir-165'=> join('',
78
'4sTUG,T*#,MrNoWJJ<#,',
80
'TFPPSjJ)#,F7NoAwPN!#',
81
'4sCwJ<VU#,AyN;J13I#,',
83
'G,5@1d;/#,8wU}PTC|#,',
85
'JW3vJ|No#,Mr9zOLD~!#'
89
run_tests('Simplified Chinese + ASCII', {
92
22825.34892.20581.65292.21531.23376.20197.33258.24378.19981.24687.12290.10.
93
28508.40857.21247.29992.65292.38451.22312.19979.20063.12290.32.
94
35265.40857.22312.30000.65292.24503.26045.26222.20063.12290.32.
95
32456.26085.20094.20094.65292.21453.22797.36947.20063.12290.10.
96
25110.36291.22312.28170.65292.36827.26080.21646.20063.12290.39134.
97
40857.22312.22825.65292.22823.20154.36896.20063.12290.32.
98
20130.40857.26377.24724.65292.30408.19981.21487.20037.20063.12290.10.
99
29992.20061.65292.22825.24503.19981.21487.20026.39318.20063.12290
102
'cp936' => join(chr(10),
104
'���н�����������ǿ��Ϣ��',
105
'DZ�����ã�������Ҳ�� ���������ʩ��Ҳ�� ����ǬǬ��������Ҳ��',
106
'��Ծ��Ԩ������Ҳ���������죬������Ҳ�� �����лڣ�ӯ���ɾ�Ҳ��',
110
'hz' => join(chr(10),
112
'~{LlPP=!#,>}WSRTWTG?2;O"!#~}',
113
'~{G1AzNpSC#,QtTZOBR2!#~} ~{<{AzTZLo#,5BJ)FUR2!#~} ~{VUHUG,G,#,74845@R2!#~}',
114
'~{;rT>TZT(#,=xN^>LR2!#7IAzTZLl#,4sHKTlR2!#~} ~{?:AzSP;Z#,S/2;?I>CR2!#~}',
115
'~{SC>E#,Ll5B2;?IN*JWR2!#~}',
119
run_tests('Traditional Chinese', {
120
'utf', => 20094.65306.20803.12289.20136.12289.21033.12289.35998,
121
'gb12345-raw' => 'G,#:T*!":`!"@{!"Uj',
122
'gbk' => 'Ǭ��Ԫ���ࡢ����ؑ',
126
my ($title, $tests) = @_;
127
my $utf = delete $tests->{'utf'};
129
# $enc = encoding, $str = content
130
foreach my $enc (sort keys %{$tests}) {
131
my $str = $tests->{$enc};
133
is(Encode::decode($enc, $str), $utf, "[$enc] decode - $title");
134
is(Encode::encode($enc, $utf), $str, "[$enc] encode - $title");
137
my $utf8 = Encode::encode('utf-8', $utf);
139
Encode::from_to($str2, $enc, 'utf-8');
140
is($str2, $utf8, "[$enc] from_to => utf8 - $title");
142
Encode::from_to($utf8, 'utf-8', $enc); # convert $utf8 as $enc
143
is($utf8, $str, "[$enc] utf8 => from_to - $title");