4 require Config; import Config;
5 if ($Config{'extensions'} !~ /\bEncode\b/) {
6 print "1..0 # Skip: Encode was not built\n";
11 use Encode qw(from_to encode decode
12 encode_utf8 decode_utf8
13 find_encoding is_utf8);
14 use charnames qw(greek);
15 my @encodings = grep(/iso-?8859/,Encode::encodings());
17 my @character_set = ('0'..'9', 'A'..'Z', 'a'..'z');
18 my @source = qw(ascii iso8859-1 cp1250);
19 my @destiny = qw(cp1047 cp37 posix-bc);
20 my @ebcdic_sets = qw(cp1047 cp37 posix-bc);
21 plan test => 38+$n*@encodings + 2*@source*@destiny*@character_set + 2*@ebcdic_sets*256 + 6;
22 my $str = join('',map(chr($_),0x20..0x7E));
24 ok(length($str),from_to($cpy,'iso8859-1','Unicode'),"Length Wrong");
25 ok($cpy,$str,"ASCII mangled by translating from iso8859-1 to Unicode");
27 ok(from_to($cpy,'Unicode','iso8859-1'),length($str),"Length wrong");
28 ok($cpy,$str,"ASCII mangled by translating from Unicode to iso8859-1");
30 $str = join('',map(chr($_),0xa0..0xff));
32 ok(length($str),from_to($cpy,'iso8859-1','Unicode'),"Length Wrong");
34 my $sym = Encode->getEncoding('symbol');
35 my $uni = $sym->decode(encode(ascii => 'a'));
36 ok("\N{alpha}",substr($uni,0,1),"alpha does not map to symbol 'a'");
37 $str = $sym->encode("\N{Beta}");
38 ok("B",decode(ascii => substr($str,0,1)),"Symbol 'B' does not map to Beta");
40 foreach my $enc (qw(symbol dingbats ascii),@encodings)
42 my $tab = Encode->getEncoding($enc);
43 ok(1,defined($tab),"Could not load $enc");
44 $str = join('',map(chr($_),0x20..0x7E));
45 $uni = $tab->decode($str);
46 $cpy = $tab->encode($uni);
47 ok($cpy,$str,"$enc mangled translating to Unicode and back");
50 # On ASCII based machines see if we can map several codepoints from
51 # three distinct ASCII sets to three distinct EBCDIC coded character sets.
52 # On EBCDIC machines see if we can map from three EBCDIC sets to three
53 # distinct ASCII sets.
55 my @expectation = (240..249, 193..201,209..217,226..233, 129..137,145..153,162..169);
61 @expectation = (48..57, 65..90, 97..122);
64 foreach my $to (@destiny)
66 foreach my $from (@source)
68 my @expected = @expectation;
69 foreach my $chr (@character_set)
71 my $native_chr = $chr;
73 my $rc = from_to($cpy,$from,$to);
74 ok(1,$rc,"Could not translate from $from to $to");
75 ok(ord($cpy),shift(@expected),"mangled translating $native_chr from $from to $to");
80 # On either ASCII or EBCDIC machines ensure we can take the full one
81 # byte repetoire to EBCDIC sets and back.
83 my $enc_as = 'iso8859-1';
84 foreach my $enc_eb (@ebcdic_sets)
86 foreach my $ord (0..255)
89 my $rc = from_to($str,$enc_as,$enc_eb);
90 $rc += from_to($str,$enc_eb,$enc_as);
91 ok($rc,2,"return code for $ord $enc_eb -> $enc_as -> $enc_eb was not obtained");
92 ok($ord,ord($str),"$enc_as mangled translating $ord to $enc_eb and back");
96 my $mime = find_encoding('iso-8859-2');
97 ok(defined($mime),1,"Cannot find MIME-ish'iso-8859-2'");
98 my $x11 = find_encoding('iso8859-2');
99 ok(defined($x11),1,"Cannot find X11-ish 'iso8859-2'");
100 ok($mime,$x11,"iso8598-2 and iso-8859-2 not same");
101 my $spc = find_encoding('iso 8859-2');
102 ok(defined($spc),1,"Cannot find 'iso 8859-2'");
103 ok($spc,$mime,"iso 8859-2 and iso-8859-2 not same");
105 for my $i (256,128,129,256)
108 my $s = "$c\n".sprintf("%02X",$i);
109 ok(utf8::valid($s),1,"concat of $i botched");
111 ok(utf8::valid($s),1,"concat of $i botched");
114 # Spot check a few points in/out of utf8
115 for my $i (0x41,128,256,0x20AC)
118 my $o = encode_utf8($c);
119 ok(decode_utf8($o),$c,"decode_utf8 not inverse of encode_utf8 for $i");
120 ok(encode('utf8',$c),$o,"utf8 encode by name broken for $i");
121 ok(decode('utf8',$o),$c,"utf8 decode by name broken for $i");
127 ok( is_utf8("\x{100}"));
131 ok( is_utf8($1)); # ID 20011127.151
136 ok( is_utf8($a)); # weird but true: an empty UTF-8 string