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 unless (find PerlIO::Layer 'perlio') {
12 print "1..0 # Skip: PerlIO was not built\n";
15 if (ord("A") == 193) {
16 print "1..0 # Skip: EBCDIC\n";
23 use Test::More tests => 29;
28 # Since JP.t already test basic file IO, we will just focus on
29 # internal encode / decode test here. Unfortunately, to test
30 # against all the UniHan characters will take a huge disk space,
31 # not to mention the time it will take, and the fact that Perl
32 # did not bundle UniHan.txt anyway.
34 # So, here we just test a typical snippet spanning multiple Unicode
35 # blocks, and hope it can point out obvious errors.
37 run_tests('Simplified Chinese only', {
39 12298.26131.32463.12299.31532.19968.21350.
41 22823.21705.20094.20803.65292.19975.29289.36164.22987.65292.
42 20035.32479.22825.12290.
43 20113.34892.38632.26045.65292.21697.29289.27969.24418.12290.
44 22823.26126.22987.32456.65292.20845.20301.26102.25104.65292.
45 26102.20056.20845.40857.20197.24481.22825.12290.
46 20094.36947.21464.21270.65292.21508.27491.24615.21629.65292.
47 20445.21512.22823.21644.65292.20035.21033.36126.12290.
48 39318.20986.24246.29289.65292.19975.22269.21688.23425.12290
54 '´óÔÕǬԪ£¬ÍòÎï×Êʼ£¬',
56 'ÔÆÐÐÓêÊ©£¬Æ·ÎïÁ÷ÐΡ£',
57 '´óÃ÷ʼÖÕ£¬Áùλʱ³É£¬',
59 'ǬµÀ±ä»¯£¬¸÷ÕýÐÔÃü£¬',
61 'Ê׳öÊüÎÍò¹úÏÌÄþ¡£',
64 'gb2312-raw' => join('',
67 '4sTUG,T*#,MrNoWJJ<#,',
69 'TFPPSjJ)#,F7NoAwPN!#',
70 '4sCwJ<VU#,AyN;J13I#,',
72 'G,5@1d;/#,8wU}PTC|#,',
74 'JW3vJ|No#,Mr9zOLD~!#'
77 'iso-ir-165'=> join('',
80 '4sTUG,T*#,MrNoWJJ<#,',
82 'TFPPSjJ)#,F7NoAwPN!#',
83 '4sCwJ<VU#,AyN;J13I#,',
85 'G,5@1d;/#,8wU}PTC|#,',
87 'JW3vJ|No#,Mr9zOLD~!#'
91 run_tests('Simplified Chinese + ASCII', {
94 22825.34892.20581.65292.21531.23376.20197.33258.24378.19981.24687.12290.10.
95 28508.40857.21247.29992.65292.38451.22312.19979.20063.12290.32.
96 35265.40857.22312.30000.65292.24503.26045.26222.20063.12290.32.
97 32456.26085.20094.20094.65292.21453.22797.36947.20063.12290.10.
98 25110.36291.22312.28170.65292.36827.26080.21646.20063.12290.39134.
99 40857.22312.22825.65292.22823.20154.36896.20063.12290.32.
100 20130.40857.26377.24724.65292.30408.19981.21487.20037.20063.12290.10.
101 29992.20061.65292.22825.24503.19981.21487.20026.39318.20063.12290
104 'cp936' => join(chr(10),
106 'ÌìÐн¡£¬¾ý×ÓÒÔ×ÔÇ¿²»Ï¢¡£',
107 'DZÁúÎðÓã¬ÑôÔÚÏÂÒ²¡£ ¼ûÁúÔÚÌµÂÊ©ÆÕÒ²¡£ ÖÕÈÕǬǬ£¬·´¸´µÀÒ²¡£',
108 '»òÔ¾ÔÚÔ¨£¬½øÎÞ¾ÌÒ²¡£·ÉÁúÔÚÌ죬´óÈËÔìÒ²¡£ ¿ºÁúÓлڣ¬Ó¯²»¿É¾ÃÒ²¡£',
109 'Óþţ¬ÌìµÂ²»¿ÉΪÊ×Ò²¡£',
112 'hz' => join(chr(10),
114 '~{LlPP=!#,>}WSRTWTG?2;O"!#~}',
115 '~{G1AzNpSC#,QtTZOBR2!#~} ~{<{AzTZLo#,5BJ)FUR2!#~} ~{VUHUG,G,#,74845@R2!#~}',
116 '~{;rT>TZT(#,=xN^>LR2!#7IAzTZLl#,4sHKTlR2!#~} ~{?:AzSP;Z#,S/2;?I>CR2!#~}',
117 '~{SC>E#,Ll5B2;?IN*JWR2!#~}',
121 run_tests('Traditional Chinese', {
122 'utf', => 20094.65306.20803.12289.20136.12289.21033.12289.35998,
123 'gb12345-raw' => 'G,#:T*!":`!"@{!"Uj',
124 'gbk' => 'Ǭ£ºÔª¡¢ºà¡¢Àû¡¢Ø',
128 my ($title, $tests) = @_;
129 my $utf = delete $tests->{'utf'};
131 # $enc = encoding, $str = content
132 foreach my $enc (sort keys %{$tests}) {
133 my $str = $tests->{$enc};
135 is(Encode::decode($enc, $str), $utf, "[$enc] decode - $title");
136 is(Encode::encode($enc, $utf), $str, "[$enc] encode - $title");
139 my $utf8 = Encode::encode('utf-8', $utf);
141 Encode::from_to($str2, $enc, 'utf-8');
142 is($str2, $utf8, "[$enc] from_to => utf8 - $title");
144 Encode::from_to($utf8, 'utf-8', $enc); # convert $utf8 as $enc
145 is($utf8, $str, "[$enc] utf8 => from_to - $title");