#
-# $Id: Unicode.t,v 1.2 2002/04/07 17:22:31 dankogai Exp dankogai $
+# $Id: Unicode.t,v 2.1 2006/05/03 18:24:10 dankogai Exp $
#
# This script is written entirely in ASCII, even though quoted literals
# do include non-BMP unicode characters -- Are you happy, jhi?
#
BEGIN {
- require Config; import Config;
- if ($Config{'extensions'} !~ /\bEncode\b/) {
- print "1..0 # Skip: Encode was not built\n";
- exit 0;
- }
-# should work without perlio
-# unless (find PerlIO::Layer 'perlio') {
-# print "1..0 # Skip: PerlIO was not built\n";
-# exit 0;
-# }
-# should work on EBCDIC
-# if (ord("A") == 193) {
-# print "1..0 # Skip: EBCDIC\n";
-# exit 0;
-# }
- $| = 1;
+ require Config; import Config;
+ if ($Config{'extensions'} !~ /\bEncode\b/) {
+ print "1..0 # Skip: Encode was not built\n";
+ exit 0;
+ }
+ if (ord("A") == 193) {
+ print "1..0 # Skip: EBCDIC\n";
+ exit 0;
+ }
+ $| = 1;
}
use strict;
#use Test::More 'no_plan';
-use Test::More tests => 22;
+use Test::More tests => 37;
use Encode qw(encode decode);
#
# http://www.unicode.org/unicode/reports/tr19/
#
-my $nasty = "\x{004D}\x{0061}\x{1abcd}";
-my $fallback = "\x{004D}\x{0061}\x{fffd}";
+my $dankogai = "\x{5c0f}\x{98fc}\x{3000}\x{5f3e}";
+my $nasty = "$dankogai\x{1abcd}";
+my $fallback = "$dankogai\x{fffd}";
#hi: (0x1abcd - 0x10000) / 0x400 + 0xD800 = 0xd82a
#lo: (0x1abcd - 0x10000) % 0x400 + 0xDC00 = 0xdfcd
-my $n_16be =
- pack("C*", map {hex($_)} qw<00 4D 00 61 d8 2a df cd>);
+my $n_16be =
+ pack("C*", map {hex($_)} qw<5c 0f 98 fc 30 00 5f 3e d8 2a df cd>);
my $n_16le =
- pack("C*", map {hex($_)} qw<4D 00 61 00 2a d8 cd df>);
-my $f_16be =
- pack("C*", map {hex($_)} qw<00 4D 00 61 ff fd>);
+ pack("C*", map {hex($_)} qw<0f 5c fc 98 00 30 3e 5f 2a d8 cd df>);
+my $f_16be =
+ pack("C*", map {hex($_)} qw<5c 0f 98 fc 30 00 5f 3e ff fd>);
my $f_16le =
- pack("C*", map {hex($_)} qw<4D 00 61 00 fd ff>);
+ pack("C*", map {hex($_)} qw<0f 5c fc 98 00 30 3e 5f fd ff>);
my $n_32be =
- pack("C*", map {hex($_)} qw<00 00 00 4D 00 00 00 61 00 01 ab cd>);
-my $n_32le =
- pack("C*", map {hex($_)} qw<4D 00 00 00 61 00 00 00 cd ab 01 00>);
+ pack("C*", map {hex($_)}
+ qw<00 00 5c 0f 00 00 98 fc 00 00 30 00 00 00 5f 3e 00 01 ab cd>);
+my $n_32le =
+ pack("C*", map {hex($_)}
+ qw<0f 5c 00 00 fc 98 00 00 00 30 00 00 3e 5f 00 00 cd ab 01 00>);
-my $n_16bb = pack('n', Encode::Unicode::BOM_BE) . $n_16be;
-my $n_16lb = pack('n', Encode::Unicode::BOM16LE) . $n_16le;
-my $n_32bb = pack('N', Encode::Unicode::BOM_BE ) . $n_32be;
-my $n_32lb = pack('N', Encode::Unicode::BOM32LE) . $n_32le;
+my $n_16bb = pack('n', 0xFeFF) . $n_16be;
+my $n_16lb = pack('v', 0xFeFF) . $n_16le;
+my $n_32bb = pack('N', 0xFeFF) . $n_32be;
+my $n_32lb = pack('V', 0xFeFF) . $n_32le;
is($n_16be, encode('UTF-16BE', $nasty), qq{encode UTF-16BE});
is($n_16le, encode('UTF-16LE', $nasty), qq{encode UTF-16LE});
is(decode('UCS-2BE', $n_16be), $fallback, "decode UCS-2BE: fallback");
is(decode('UCS-2LE', $n_16le), $fallback, "decode UCS-2LE: fallback");
-eval { decode('UCS-2BE', $n_16be, 1) };
-ok($@=~/^UCS-2BE:/, "decode UCS-2BE: exception");
+eval { decode('UCS-2BE', $n_16be, 1) };
+is (index($@,'UCS-2BE:'), 0, "decode UCS-2BE: exception");
eval { decode('UCS-2LE', $n_16le, 1) };
-ok($@=~/^UCS-2LE:/, "decode UCS-2LE: exception");
+is (index($@,'UCS-2LE:'), 0, "decode UCS-2LE: exception");
is(encode('UCS-2BE', $nasty), $f_16be, "encode UCS-2BE: fallback");
is(encode('UCS-2LE', $nasty), $f_16le, "encode UCS-2LE: fallback");
-eval { encode('UCS-2BE', $nasty, 1) };
-ok($@=~/^UCS-2BE:/, "encode UCS-2BE: exception");
-eval { encode('UCS-2LE', $nasty, 1) };
-ok($@=~/^UCS-2LE:/, "encode UCS-2LE: exception");
+eval { encode('UCS-2BE', $nasty, 1) };
+is(index($@, 'UCS-2BE'), 0, "encode UCS-2BE: exception");
+eval { encode('UCS-2LE', $nasty, 1) };
+is(index($@, 'UCS-2LE'), 0, "encode UCS-2LE: exception");
+#
+# SvGROW test for (en|de)code_xs
+#
+SKIP: {
+ my $utf8 = '';
+ for my $j (0,0x10){
+ for my $i (0..0xffff){
+ $j == 0 and (0xD800 <= $i && $i <= 0xDFFF) and next;
+ $utf8 .= ord($j+$i);
+ }
+ for my $major ('UTF-16', 'UTF-32'){
+ for my $minor ('BE', 'LE'){
+ my $enc = $major.$minor;
+ is(decode($enc, encode($enc, $utf8)), $utf8, "$enc RT");
+ }
+ }
+ }
+};
+
+#
+# CJKT vs. UTF-7
+#
+
+use File::Spec;
+use File::Basename;
+
+my $dir = dirname(__FILE__);
+opendir my $dh, $dir or die "$dir:$!";
+my @file = sort grep {/\.utf$/o} readdir $dh;
+closedir $dh;
+for my $file (@file){
+ my $path = File::Spec->catfile($dir, $file);
+ open my $fh, '<', $path or die "$path:$!";
+ my $content;
+ if (PerlIO::Layer->find('perlio')){
+ binmode $fh => ':utf8';
+ $content = join('' => <$fh>);
+ }else{ # ugh!
+ binmode $fh;
+ $content = join('' => <$fh>);
+ Encode::_utf8_on($content)
+ }
+ close $fh;
+ is(decode("UTF-7", encode("UTF-7", $content)), $content,
+ "UTF-7 RT:$file");
+}
1;
__END__