xref: /openbsd/gnu/usr.bin/perl/cpan/Encode/t/at-cn.t (revision 264ca280) 
1BEGIN {
2    if ($ENV{'PERL_CORE'}){
3        chdir 't';
4    unshift @INC, '../lib';
5    }
6    require Config; import Config;
7    if ($Config{'extensions'} !~ /\bEncode\b/) {
8      print "1..0 # Skip: Encode was not built\n";
9      exit 0;
10    }
11    if (ord("A") == 193) {
12    print "1..0 # Skip: EBCDIC\n";
13    exit 0;
14    }
15    $| = 1;
16}
17
18use strict;
19use Test::More tests => 29;
20use Encode;
21
22no utf8; # we have raw Chinese encodings here
23
24use_ok('Encode::CN');
25
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.
31
32# So, here we just test a typical snippet spanning multiple Unicode
33# blocks, and hope it can point out obvious errors.
34
35run_tests('Simplified Chinese only', {
36    'utf'	=> (
3712298.26131.32463.12299.31532.19968.21350.
3824406.26352.65306.
3922823.21705.20094.20803.65292.19975.29289.36164.22987.65292.
4020035.32479.22825.12290.
4120113.34892.38632.26045.65292.21697.29289.27969.24418.12290.
4222823.26126.22987.32456.65292.20845.20301.26102.25104.65292.
4326102.20056.20845.40857.20197.24481.22825.12290.
4420094.36947.21464.21270.65292.21508.27491.24615.21629.65292.
4520445.21512.22823.21644.65292.20035.21033.36126.12290.
4639318.20986.24246.29289.65292.19975.22269.21688.23425.12290
47    ),
48
49    'euc-cn'	=> join('',
50'���׾�����һ��',
51'��Ի��',
52'����ǬԪ��������ʼ��',
53'��ͳ�졣',
54'������ʩ��Ʒ�����Ρ�',
55'����ʼ�գ���λʱ�ɣ�',
56'ʱ�����������졣',
57'Ǭ���仯������������',
58'���ϴ�ͣ������ꡣ',
59'�׳�������������',
60    ),
61
62    'gb2312-raw'	=> join('',
63'!6RW>-!75ZR;XT',
64'ehT;#:',
65'4sTUG,T*#,MrNoWJJ<#,',
66'DKM3Ll!#',
67'TFPPSjJ)#,F7NoAwPN!#',
68'4sCwJ<VU#,AyN;J13I#,',
69'J13KAyAzRTSyLl!#',
70'G,5@1d;/#,8wU}PTC|#,',
71'1#:O4s:M#,DK@{Uj!#',
72'JW3vJ|No#,Mr9zOLD~!#'
73    ),
74
75    'iso-ir-165'=> join('',
76'!6RW>-!75ZR;XT',
77'ehT;#:',
78'4sTUG,T*#,MrNoWJJ<#,',
79'DKM3Ll!#',
80'TFPPSjJ)#,F7NoAwPN!#',
81'4sCwJ<VU#,AyN;J13I#,',
82'J13KAyAzRTSyLl!#',
83'G,5@1d;/#,8wU}PTC|#,',
84'1#:O4s:M#,DK@{Uj!#',
85'JW3vJ|No#,Mr9zOLD~!#'
86    ),
87});
88
89run_tests('Simplified Chinese + ASCII', {
90    'utf'	=> (
9135937.26352.65306.10.
9222825.34892.20581.65292.21531.23376.20197.33258.24378.19981.24687.12290.10.
9328508.40857.21247.29992.65292.38451.22312.19979.20063.12290.32.
9435265.40857.22312.30000.65292.24503.26045.26222.20063.12290.32.
9532456.26085.20094.20094.65292.21453.22797.36947.20063.12290.10.
9625110.36291.22312.28170.65292.36827.26080.21646.20063.12290.39134.
9740857.22312.22825.65292.22823.20154.36896.20063.12290.32.
9820130.40857.26377.24724.65292.30408.19981.21487.20037.20063.12290.10.
9929992.20061.65292.22825.24503.19981.21487.20026.39318.20063.12290
100    ),
101
102    'cp936'	=> join(chr(10),
103'��Ի��',
104'���н�����������ǿ��Ϣ��',
105'DZ�����ã�������Ҳ�� ���������ʩ��Ҳ�� ����ǬǬ��������Ҳ��',
106'��Ծ��Ԩ�����޾�Ҳ���������죬������Ҳ�� �����лڣ�ӯ���ɾ�Ҳ��',
107'�þţ���²���Ϊ��Ҳ��',
108    ),
109
110    'hz'	=> join(chr(10),
111'~{OsT;#:~}',
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!#~}',
116    ),
117});
118
119run_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����ؑ',
123});
124
125sub run_tests {
126    my ($title, $tests) = @_;
127    my $utf = delete $tests->{'utf'};
128
129    # $enc = encoding, $str = content
130    foreach my $enc (sort keys %{$tests}) {
131    my $str = $tests->{$enc};
132
133    is(Encode::decode($enc, $str), $utf, "[$enc] decode - $title");
134    is(Encode::encode($enc, $utf), $str, "[$enc] encode - $title");
135
136    my $str2 = $str;
137    my $utf8 = Encode::encode('utf-8', $utf);
138
139    Encode::from_to($str2, $enc, 'utf-8');
140    is($str2, $utf8, "[$enc] from_to => utf8 - $title");
141
142    Encode::from_to($utf8, 'utf-8', $enc); # convert $utf8 as $enc
143    is($utf8, $str,  "[$enc] utf8 => from_to - $title");
144    }
145}
146