Commit | Line | Data |
656753f8 |
1 | BEGIN { |
037b88d6 |
2 | if ($ENV{'PERL_CORE'}){ |
3 | chdir 't'; |
4 | unshift @INC, '../lib'; |
5 | } |
5a814814 |
6 | require Config; import Config; |
bb50757b |
7 | if ($Config{'extensions'} !~ /\bEncode\b/) { |
5a814814 |
8 | print "1..0 # Skip: Encode was not built\n"; |
9 | exit 0; |
10 | } |
656753f8 |
11 | } |
0e567a6c |
12 | use strict; |
656753f8 |
13 | use Test; |
2eebba1d |
14 | use Encode qw(from_to encode decode |
15 | encode_utf8 decode_utf8 |
16 | find_encoding is_utf8); |
656753f8 |
17 | use charnames qw(greek); |
51ef4e11 |
18 | my @encodings = grep(/iso-?8859/,Encode::encodings()); |
656753f8 |
19 | my $n = 2; |
f90497d6 |
20 | my @character_set = ('0'..'9', 'A'..'Z', 'a'..'z'); |
21 | my @source = qw(ascii iso8859-1 cp1250); |
22 | my @destiny = qw(cp1047 cp37 posix-bc); |
23 | my @ebcdic_sets = qw(cp1047 cp37 posix-bc); |
2eebba1d |
24 | plan test => 38+$n*@encodings + 2*@source*@destiny*@character_set + 2*@ebcdic_sets*256 + 6; |
656753f8 |
25 | my $str = join('',map(chr($_),0x20..0x7E)); |
26 | my $cpy = $str; |
27 | ok(length($str),from_to($cpy,'iso8859-1','Unicode'),"Length Wrong"); |
28 | ok($cpy,$str,"ASCII mangled by translating from iso8859-1 to Unicode"); |
29 | $cpy = $str; |
30 | ok(from_to($cpy,'Unicode','iso8859-1'),length($str),"Length wrong"); |
31 | ok($cpy,$str,"ASCII mangled by translating from Unicode to iso8859-1"); |
32 | |
33 | $str = join('',map(chr($_),0xa0..0xff)); |
87714904 |
34 | $cpy = $str; |
656753f8 |
35 | ok(length($str),from_to($cpy,'iso8859-1','Unicode'),"Length Wrong"); |
36 | |
37 | my $sym = Encode->getEncoding('symbol'); |
7d85a32c |
38 | my $uni = $sym->decode(encode(ascii => 'a')); |
f90497d6 |
39 | ok("\N{alpha}",substr($uni,0,1),"alpha does not map to symbol 'a'"); |
50d26985 |
40 | $str = $sym->encode("\N{Beta}"); |
7d85a32c |
41 | ok("B",decode(ascii => substr($str,0,1)),"Symbol 'B' does not map to Beta"); |
656753f8 |
42 | |
43 | foreach my $enc (qw(symbol dingbats ascii),@encodings) |
44 | { |
45 | my $tab = Encode->getEncoding($enc); |
46 | ok(1,defined($tab),"Could not load $enc"); |
47 | $str = join('',map(chr($_),0x20..0x7E)); |
50d26985 |
48 | $uni = $tab->decode($str); |
49 | $cpy = $tab->encode($uni); |
656753f8 |
50 | ok($cpy,$str,"$enc mangled translating to Unicode and back"); |
51 | } |
52 | |
f90497d6 |
53 | # On ASCII based machines see if we can map several codepoints from |
54 | # three distinct ASCII sets to three distinct EBCDIC coded character sets. |
a12c0f56 |
55 | # On EBCDIC machines see if we can map from three EBCDIC sets to three |
f90497d6 |
56 | # distinct ASCII sets. |
57 | |
58 | my @expectation = (240..249, 193..201,209..217,226..233, 129..137,145..153,162..169); |
59 | if (ord('A') != 65) { |
60 | my @temp = @destiny; |
61 | @destiny = @source; |
62 | @source = @temp; |
63 | undef(@temp); |
64 | @expectation = (48..57, 65..90, 97..122); |
65 | } |
66 | |
67 | foreach my $to (@destiny) |
68 | { |
69 | foreach my $from (@source) |
70 | { |
71 | my @expected = @expectation; |
72 | foreach my $chr (@character_set) |
73 | { |
74 | my $native_chr = $chr; |
75 | my $cpy = $chr; |
76 | my $rc = from_to($cpy,$from,$to); |
77 | ok(1,$rc,"Could not translate from $from to $to"); |
78 | ok(ord($cpy),shift(@expected),"mangled translating $native_chr from $from to $to"); |
79 | } |
80 | } |
81 | } |
82 | |
83 | # On either ASCII or EBCDIC machines ensure we can take the full one |
84 | # byte repetoire to EBCDIC sets and back. |
85 | |
86 | my $enc_as = 'iso8859-1'; |
87 | foreach my $enc_eb (@ebcdic_sets) |
88 | { |
89 | foreach my $ord (0..255) |
90 | { |
91 | $str = chr($ord); |
92 | my $rc = from_to($str,$enc_as,$enc_eb); |
93 | $rc += from_to($str,$enc_eb,$enc_as); |
94 | ok($rc,2,"return code for $ord $enc_eb -> $enc_as -> $enc_eb was not obtained"); |
95 | ok($ord,ord($str),"$enc_as mangled translating $ord to $enc_eb and back"); |
96 | } |
97 | } |
98 | |
51ef4e11 |
99 | my $mime = find_encoding('iso-8859-2'); |
100 | ok(defined($mime),1,"Cannot find MIME-ish'iso-8859-2'"); |
101 | my $x11 = find_encoding('iso8859-2'); |
102 | ok(defined($x11),1,"Cannot find X11-ish 'iso8859-2'"); |
103 | ok($mime,$x11,"iso8598-2 and iso-8859-2 not same"); |
104 | my $spc = find_encoding('iso 8859-2'); |
105 | ok(defined($spc),1,"Cannot find 'iso 8859-2'"); |
106 | ok($spc,$mime,"iso 8859-2 and iso-8859-2 not same"); |
107 | |
4411f3b6 |
108 | for my $i (256,128,129,256) |
a12c0f56 |
109 | { |
110 | my $c = chr($i); |
111 | my $s = "$c\n".sprintf("%02X",$i); |
1b026014 |
112 | ok(utf8::valid($s),1,"concat of $i botched"); |
113 | utf8::upgrade($s); |
114 | ok(utf8::valid($s),1,"concat of $i botched"); |
a12c0f56 |
115 | } |
116 | |
4411f3b6 |
117 | # Spot check a few points in/out of utf8 |
ed46d110 |
118 | for my $i (ord('A'),128,256,0x20AC) |
4411f3b6 |
119 | { |
120 | my $c = chr($i); |
121 | my $o = encode_utf8($c); |
122 | ok(decode_utf8($o),$c,"decode_utf8 not inverse of encode_utf8 for $i"); |
123 | ok(encode('utf8',$c),$o,"utf8 encode by name broken for $i"); |
124 | ok(decode('utf8',$o),$c,"utf8 decode by name broken for $i"); |
125 | } |
126 | |
127 | |
2eebba1d |
128 | # is_utf8 |
129 | |
130 | ok( is_utf8("\x{100}")); |
131 | ok(! is_utf8("a")); |
132 | ok(! is_utf8("")); |
133 | "\x{100}" =~ /(.)/; |
134 | ok( is_utf8($1)); # ID 20011127.151 |
135 | $a = $1; |
136 | ok( is_utf8($a)); |
137 | $a = "\x{100}"; |
138 | chop $a; |
139 | ok( is_utf8($a)); # weird but true: an empty UTF-8 string |
140 | |