[p5sagit/p5-mst-13.2.git] / t / pragma / utf8.t

#!./perl 

BEGIN {
    chdir 't' if -d 't';
    @INC = '../lib';
    $ENV{PERL5LIB} = '../lib';
    if ( ord("\t") != 9 ) { # skip on ebcdic platforms
        print "1..0 # Skip utf8 tests on ebcdic platform.\n";
        exit;
    }
}

print "1..87\n";

my $test = 1;

sub ok {
    my ($got,$expect) = @_;
    print "# expected [$expect], got [$got]\nnot " if $got ne $expect;
    print "ok $test\n";
}

sub nok {
    my ($got,$expect) = @_;
    print "# expected not [$expect], got [$got]\nnot " if $got eq $expect;
    print "ok $test\n";
}

sub ok_bytes {
    use bytes;
    my ($got,$expect) = @_;
    print "# expected [$expect], got [$got]\nnot " if $got ne $expect;
    print "ok $test\n";
}

sub nok_bytes {
    use bytes;
    my ($got,$expect) = @_;
    print "# expected not [$expect], got [$got]\nnot " if $got eq $expect;
    print "ok $test\n";
}

{
    use utf8;
    $_ = ">\x{263A}<"; 
    s/([\x{80}-\x{10ffff}])/"&#".ord($1).";"/eg; 
    ok $_, '>&#9786;<';
    $test++;				# 1

    $_ = ">\x{263A}<"; 
    my $rx = "\x{80}-\x{10ffff}";
    s/([$rx])/"&#".ord($1).";"/eg; 
    ok $_, '>&#9786;<';
    $test++;				# 2

    $_ = ">\x{263A}<"; 
    my $rx = "\\x{80}-\\x{10ffff}";
    s/([$rx])/"&#".ord($1).";"/eg; 
    ok $_, '>&#9786;<';
    $test++;				# 3

    $_ = "alpha,numeric"; 
    m/([[:alpha:]]+)/; 
    ok $1, 'alpha';
    $test++;				# 4

    $_ = "alphaNUMERICstring";
    m/([[:^lower:]]+)/; 
    ok $1, 'NUMERIC';
    $test++;				# 5

    $_ = "alphaNUMERICstring";
    m/(\p{Ll}+)/; 
    ok $1, 'alpha';
    $test++;				# 6

    $_ = "alphaNUMERICstring"; 
    m/(\p{Lu}+)/; 
    ok $1, 'NUMERIC';
    $test++;				# 7

    $_ = "alpha,numeric"; 
    m/([\p{IsAlpha}]+)/; 
    ok $1, 'alpha';
    $test++;				# 8

    $_ = "alphaNUMERICstring";
    m/([^\p{IsLower}]+)/; 
    ok $1, 'NUMERIC';
    $test++;				# 9

    $_ = "alpha123numeric456"; 
    m/([\p{IsDigit}]+)/; 
    ok $1, '123';
    $test++;				# 10

    $_ = "alpha123numeric456"; 
    m/([^\p{IsDigit}]+)/; 
    ok $1, 'alpha';
    $test++;				# 11

    $_ = ",123alpha,456numeric"; 
    m/([\p{IsAlnum}]+)/; 
    ok $1, '123alpha';
    $test++;				# 12
}
{
    use utf8;

    $_ = "\x{263A}>\x{263A}\x{263A}"; 

    ok length, 4;
    $test++;				# 13

    ok length((m/>(.)/)[0]), 1;
    $test++;				# 14

    ok length($&), 2;
    $test++;				# 15

    ok length($'), 1;
    $test++;				# 16

    ok length($`), 1;
    $test++;				# 17

    ok length($1), 1;
    $test++;				# 18

    ok length($tmp=$&), 2;
    $test++;				# 19

    ok length($tmp=$'), 1;
    $test++;				# 20

    ok length($tmp=$`), 1;
    $test++;				# 21

    ok length($tmp=$1), 1;
    $test++;				# 22

    {
	use bytes;

	my $tmp = $&;
	ok $tmp, pack("C*", ord(">"), 0342, 0230, 0272);
	$test++;				# 23

	$tmp = $';
	ok $tmp, pack("C*", 0342, 0230, 0272);
	$test++;				# 24

	$tmp = $`;
	ok $tmp, pack("C*", 0342, 0230, 0272);
	$test++;				# 25

	$tmp = $1;
	ok $tmp, pack("C*", 0342, 0230, 0272);
	$test++;				# 26
    }

    ok_bytes $&, pack("C*", ord(">"), 0342, 0230, 0272);
    $test++;				# 27

    ok_bytes $', pack("C*", 0342, 0230, 0272);
    $test++;				# 28

    ok_bytes $`, pack("C*", 0342, 0230, 0272);
    $test++;				# 29

    ok_bytes $1, pack("C*", 0342, 0230, 0272);
    $test++;				# 30

    {
	use bytes;
	no utf8;

	ok length, 10;
	$test++;				# 31

    	ok length((m/>(.)/)[0]), 1;
    	$test++;				# 32

    	ok length($&), 2;
    	$test++;				# 33

    	ok length($'), 5;
    	$test++;				# 34

    	ok length($`), 3;
    	$test++;				# 35

    	ok length($1), 1;
    	$test++;				# 36

	ok $&, pack("C*", ord(">"), 0342);
	$test++;				# 37

	ok $', pack("C*", 0230, 0272, 0342, 0230, 0272);
	$test++;				# 38

	ok $`, pack("C*", 0342, 0230, 0272);
	$test++;				# 39

	ok $1, pack("C*", 0342);
	$test++;				# 40

    }


    {
	no utf8;
	$_="\342\230\272>\342\230\272\342\230\272";
    }

    ok length, 10;
    $test++;				# 41

    ok length((m/>(.)/)[0]), 1;
    $test++;				# 42

    ok length($&), 2;
    $test++;				# 43

    ok length($'), 1;
    $test++;				# 44

    ok length($`), 1;
    $test++;				# 45

    ok length($1), 1;
    $test++;				# 46

    ok length($tmp=$&), 2;
    $test++;				# 47

    ok length($tmp=$'), 1;
    $test++;				# 48

    ok length($tmp=$`), 1;
    $test++;				# 49

    ok length($tmp=$1), 1;
    $test++;				# 50

    {
	use bytes;

        my $tmp = $&;
	ok $tmp, pack("C*", ord(">"), 0342, 0230, 0272);
	$test++;				# 51

        $tmp = $';
	ok $tmp, pack("C*", 0342, 0230, 0272);
	$test++;				# 52

        $tmp = $`;
	ok $tmp, pack("C*", 0342, 0230, 0272);
	$test++;				# 53

        $tmp = $1;
	ok $tmp, pack("C*", 0342, 0230, 0272);
	$test++;				# 54
    }
    {
	use bytes;
	no utf8;

	ok length, 10;
	$test++;				# 55

    	ok length((m/>(.)/)[0]), 1;
    	$test++;				# 56

    	ok length($&), 2;
    	$test++;				# 57

    	ok length($'), 5;
    	$test++;				# 58

    	ok length($`), 3;
    	$test++;				# 59

    	ok length($1), 1;
    	$test++;				# 60

	ok $&, pack("C*", ord(">"), 0342);
	$test++;				# 61

	ok $', pack("C*", 0230, 0272, 0342, 0230, 0272);
	$test++;				# 62

	ok $`, pack("C*", 0342, 0230, 0272);
	$test++;				# 63

	ok $1, pack("C*", 0342);
	$test++;				# 64

    }

    ok "\x{ab}" =~ /^\x{ab}$/, 1;
    $test++;					# 65
}

{
    use utf8;
    ok_bytes chr(0xe2), pack("C*", 0xc3, 0xa2);
    $test++;                # 66
}

{
    use utf8;
    my @a = map ord, split(//, join("", map chr, (1234, 123, 2345)));
    ok "@a", "1234 123 2345";
    $test++;                # 67
}

{
    use utf8;
    my $x = chr(123);
    my @a = map ord, split(/$x/, join("", map chr, (1234, 123, 2345)));
    ok "@a", "1234 2345";
    $test++;                # 68
}

{
    # bug id 20001009.001

    my($a,$b);
    { use bytes; $a = "\xc3\xa4"; }  
    { use utf8;  $b = "\xe4"; }
    { use bytes; ok_bytes $a, $b; $test++; } # 69
    { use utf8;  nok      $a, $b; $test++; } # 70
}

{
    # bug id 20001008.001

    my @x = ("stra\337e 138","stra\337e 138");
    for (@x) {
	s/(\d+)\s*([\w\-]+)/$1 . uc $2/e;
	my($latin) = /^(.+)(?:\s+\d)/;
	print $latin eq "stra\337e" ? "ok $test\n" :
	    "#latin[$latin]\nnot ok $test\n";
	$test++;
	$latin =~ s/stra\337e/straße/; # \303\237 after the 2nd a
	use utf8;
	$latin =~ s!(s)tr(?:aß|s+e)!$1tr.!; # \303\237 after the a
    }
}

{
    # bug id 20000819.004 

    $_ = $dx = "\x{10f2}";
    s/($dx)/$dx$1/;
    {
	use bytes;
	print "not " unless $_ eq "$dx$dx";
	print "ok $test\n";
	$test++;
    }

    $_ = $dx = "\x{10f2}";
    s/($dx)/$1$dx/;
    {
	use bytes;
	print "not " unless $_ eq "$dx$dx";
	print "ok $test\n";
	$test++;
    }

    $dx = "\x{10f2}";
    $_  = "\x{10f2}\x{10f2}";
    s/($dx)($dx)/$1$2/;
    {
	use bytes;
	print "not " unless $_ eq "$dx$dx";
	print "ok $test\n";
	$test++;
    }
}

{
    # bug id 20000323.056

    use utf8;

    print "not " unless "\x{41}" eq +v65;
    print "ok $test\n";
    $test++;

    print "not " unless "\x41" eq +v65;
    print "ok $test\n";
    $test++;

    print "not " unless "\x{c8}" eq +v200;
    print "ok $test\n";
    $test++;

    print "not " unless "\xc8" eq +v200;
    print "ok $test\n";
    $test++;

    print "not " unless "\x{221b}" eq v8731;
    print "ok $test\n";
    $test++;
}

{
    # bug id 20000427.003 

    use utf8;
    use warnings;
    use strict;

    my $sushi = "\x{b36c}\x{5a8c}\x{ff5b}\x{5079}\x{505b}";

    my @charlist = split //, $sushi;
    my $r = '';
    foreach my $ch (@charlist) {
	$r = $r . " " . sprintf "U+%04X", ord($ch);
    }

    print "not " unless $r eq " U+B36C U+5A8C U+FF5B U+5079 U+505B";
    print "ok $test\n";
    $test++;
}

{
    # bug id 20000901.092
    # test that undef left and right of utf8 results in a valid string

    my $a;
    $a .= "\x{1ff}";
    print "not " unless $a eq "\x{1ff}";
    print "ok $test\n";
    $test++;
}

{
    # bug id 20000426.003

    use utf8;

    my $s = "\x20\x40\x{80}\x{100}\x{80}\x40\x20";

    my ($a, $b, $c) = split(/\x40/, $s);
    print "not "
	unless $a eq "\x20" && $b eq "\x{80}\x{100}\x{80}" && $c eq $a;
    print "ok $test\n";
    $test++;

    my ($a, $b) = split(/\x{100}/, $s);
    print "not " unless $a eq "\x20\x40\x{80}" && $b eq "\x{80}\x40\x20";
    print "ok $test\n";
    $test++;

    my ($a, $b) = split(/\x{80}\x{100}\x{80}/, $s);
    print "not " unless $a eq "\x20\x40" && $b eq "\x40\x20";
    print "ok $test\n";
    $test++;

    my ($a, $b) = split(/\x40\x{80}/, $s);
    print "not " unless $a eq "\x20" && $b eq "\x{100}\x{80}\x40\x20";
    print "ok $test\n";
    $test++;

    my ($a, $b, $c) = split(/[\x40\x{80}]+/, $s);
    print "not " unless $a eq "\x20" && $b eq "\x{100}" && $c eq "\x20";
    print "ok $test\n";
    $test++;
}
Commit	Line	Data
f96ec2a2	1	#!./perl
	2
	3	BEGIN {
	4	chdir 't' if -d 't';
20822f61	5	@INC = '../lib';
f96ec2a2	6	$ENV{PERL5LIB} = '../lib';
f70c35af	7	if ( ord("\t") != 9 ) { # skip on ebcdic platforms
	8	print "1..0 # Skip utf8 tests on ebcdic platform.\n";
	9	exit;
	10	}
f96ec2a2	11	}
f96ec2a2	12
93f04dac	13	print "1..87\n";
f96ec2a2	14
	15	my $test = 1;
	16
	17	sub ok {
	18	my ($got,$expect) = @_;
	19	print "# expected [$expect], got [$got]\nnot " if $got ne $expect;
	20	print "ok $test\n";
	21	}
	22
7bbb0251	23	sub nok {
	24	my ($got,$expect) = @_;
	25	print "# expected not [$expect], got [$got]\nnot " if $got eq $expect;
	26	print "ok $test\n";
	27	}
	28
be341bce	29	sub ok_bytes {
	30	use bytes;
	31	my ($got,$expect) = @_;
	32	print "# expected [$expect], got [$got]\nnot " if $got ne $expect;
	33	print "ok $test\n";
	34	}
	35
7bbb0251	36	sub nok_bytes {
	37	use bytes;
	38	my ($got,$expect) = @_;
	39	print "# expected not [$expect], got [$got]\nnot " if $got eq $expect;
	40	print "ok $test\n";
	41	}
be341bce	42
f96ec2a2	43	{
	44	use utf8;
	45	$_ = ">\x{263A}<";
	46	s/([\x{80}-\x{10ffff}])/"&#".ord($1).";"/eg;
	47	ok $_, '>☺<';
c5cc3500	48	$test++; # 1
f96ec2a2	49
	50	$_ = ">\x{263A}<";
	51	my $rx = "\x{80}-\x{10ffff}";
	52	s/([$rx])/"&#".ord($1).";"/eg;
	53	ok $_, '>☺<';
c5cc3500	54	$test++; # 2
f96ec2a2	55
	56	$_ = ">\x{263A}<";
	57	my $rx = "\\x{80}-\\x{10ffff}";
	58	s/([$rx])/"&#".ord($1).";"/eg;
	59	ok $_, '>☺<';
c5cc3500	60	$test++; # 3
b8c5462f	61
	62	$_ = "alpha,numeric";
	63	m/([[:alpha:]]+)/;
	64	ok $1, 'alpha';
c5cc3500	65	$test++; # 4
b8c5462f	66
	67	$_ = "alphaNUMERICstring";
	68	m/([[:^lower:]]+)/;
	69	ok $1, 'NUMERIC';
c5cc3500	70	$test++; # 5
b8c5462f	71
	72	$_ = "alphaNUMERICstring";
	73	m/(\p{Ll}+)/;
	74	ok $1, 'alpha';
c5cc3500	75	$test++; # 6
b8c5462f	76
	77	$_ = "alphaNUMERICstring";
	78	m/(\p{Lu}+)/;
	79	ok $1, 'NUMERIC';
c5cc3500	80	$test++; # 7
b8c5462f	81
	82	$_ = "alpha,numeric";
	83	m/([\p{IsAlpha}]+)/;
	84	ok $1, 'alpha';
c5cc3500	85	$test++; # 8
b8c5462f	86
	87	$_ = "alphaNUMERICstring";
	88	m/([^\p{IsLower}]+)/;
	89	ok $1, 'NUMERIC';
c5cc3500	90	$test++; # 9
b8c5462f	91
0f4b6630	92	$_ = "alpha123numeric456";
	93	m/([\p{IsDigit}]+)/;
	94	ok $1, '123';
c5cc3500	95	$test++; # 10
b8c5462f	96
0f4b6630	97	$_ = "alpha123numeric456";
	98	m/([^\p{IsDigit}]+)/;
	99	ok $1, 'alpha';
c5cc3500	100	$test++; # 11
b8c5462f	101
0f4b6630	102	$_ = ",123alpha,456numeric";
	103	m/([\p{IsAlnum}]+)/;
	104	ok $1, '123alpha';
c5cc3500	105	$test++; # 12
0f4b6630	106	}
a197cbdd	107	{
	108	use utf8;
	109
	110	$_ = "\x{263A}>\x{263A}\x{263A}";
	111
	112	ok length, 4;
c5cc3500	113	$test++; # 13
a197cbdd	114
a197cbdd	115	ok length((m/>(.)/)[0]), 1;
c5cc3500	116	$test++; # 14
a197cbdd	117
a197cbdd	118	ok length($&), 2;
c5cc3500	119	$test++; # 15
a197cbdd	120
a197cbdd	121	ok length($'), 1;
c5cc3500	122	$test++; # 16
a197cbdd	123
a197cbdd	124	ok length($`), 1;
c5cc3500	125	$test++; # 17
a197cbdd	126
a197cbdd	127	ok length($1), 1;
c5cc3500	128	$test++; # 18
a197cbdd	129
a197cbdd	130	ok length($tmp=$&), 2;
c5cc3500	131	$test++; # 19
a197cbdd	132
a197cbdd	133	ok length($tmp=$'), 1;
c5cc3500	134	$test++; # 20
a197cbdd	135
a197cbdd	136	ok length($tmp=$`), 1;
c5cc3500	137	$test++; # 21
a197cbdd	138
a197cbdd	139	ok length($tmp=$1), 1;
c5cc3500	140	$test++; # 22
a197cbdd	141
c5cc3500	142	{
be341bce	143	use bytes;
c5cc3500	144
be341bce	145	my $tmp = $&;
c5cc3500	146	ok $tmp, pack("C*", ord(">"), 0342, 0230, 0272);
c5cc3500	147	$test++; # 23
a197cbdd	148
c5cc3500	149	$tmp = $';
	150	ok $tmp, pack("C*", 0342, 0230, 0272);
	151	$test++; # 24
a197cbdd	152
c5cc3500	153	$tmp = $`;
	154	ok $tmp, pack("C*", 0342, 0230, 0272);
	155	$test++; # 25
a197cbdd	156
c5cc3500	157	$tmp = $1;
	158	ok $tmp, pack("C*", 0342, 0230, 0272);
	159	$test++; # 26
	160	}
a197cbdd	161
be341bce	162	ok_bytes $&, pack("C*", ord(">"), 0342, 0230, 0272);
	163	$test++; # 27
	164
	165	ok_bytes $', pack("C*", 0342, 0230, 0272);
	166	$test++; # 28
	167
	168	ok_bytes $`, pack("C*", 0342, 0230, 0272);
	169	$test++; # 29
	170
	171	ok_bytes $1, pack("C*", 0342, 0230, 0272);
	172	$test++; # 30
	173
a197cbdd	174	{
	175	use bytes;
	176	no utf8;
	177
	178	ok length, 10;
be341bce	179	$test++; # 31
a197cbdd	180
a197cbdd	181	ok length((m/>(.)/)[0]), 1;
be341bce	182	$test++; # 32
a197cbdd	183
a197cbdd	184	ok length($&), 2;
be341bce	185	$test++; # 33
a197cbdd	186
a197cbdd	187	ok length($'), 5;
be341bce	188	$test++; # 34
a197cbdd	189
a197cbdd	190	ok length($`), 3;
be341bce	191	$test++; # 35
a197cbdd	192
a197cbdd	193	ok length($1), 1;
be341bce	194	$test++; # 36
a197cbdd	195
a197cbdd	196	ok $&, pack("C*", ord(">"), 0342);
be341bce	197	$test++; # 37
a197cbdd	198
a197cbdd	199	ok $', pack("C*", 0230, 0272, 0342, 0230, 0272);
be341bce	200	$test++; # 38
a197cbdd	201
a197cbdd	202	ok $`, pack("C*", 0342, 0230, 0272);
be341bce	203	$test++; # 39
a197cbdd	204
a197cbdd	205	ok $1, pack("C*", 0342);
be341bce	206	$test++; # 40
a197cbdd	207
	208	}
	209
	210
	211	{
	212	no utf8;
	213	$_="\342\230\272>\342\230\272\342\230\272";
	214	}
	215
	216	ok length, 10;
be341bce	217	$test++; # 41
a197cbdd	218
a197cbdd	219	ok length((m/>(.)/)[0]), 1;
be341bce	220	$test++; # 42
a197cbdd	221
a197cbdd	222	ok length($&), 2;
be341bce	223	$test++; # 43
a197cbdd	224
a197cbdd	225	ok length($'), 1;
be341bce	226	$test++; # 44
a197cbdd	227
a197cbdd	228	ok length($`), 1;
be341bce	229	$test++; # 45
a197cbdd	230
a197cbdd	231	ok length($1), 1;
be341bce	232	$test++; # 46
a197cbdd	233
a197cbdd	234	ok length($tmp=$&), 2;
be341bce	235	$test++; # 47
a197cbdd	236
a197cbdd	237	ok length($tmp=$'), 1;
be341bce	238	$test++; # 48
a197cbdd	239
a197cbdd	240	ok length($tmp=$`), 1;
be341bce	241	$test++; # 49
a197cbdd	242
a197cbdd	243	ok length($tmp=$1), 1;
be341bce	244	$test++; # 50
a197cbdd	245
c5cc3500	246	{
c5cc3500	247	use bytes;
a197cbdd	248
c5cc3500	249	my $tmp = $&;
c5cc3500	250	ok $tmp, pack("C*", ord(">"), 0342, 0230, 0272);
be341bce	251	$test++; # 51
a197cbdd	252
c5cc3500	253	$tmp = $';
c5cc3500	254	ok $tmp, pack("C*", 0342, 0230, 0272);
be341bce	255	$test++; # 52
a197cbdd	256
c5cc3500	257	$tmp = $`;
c5cc3500	258	ok $tmp, pack("C*", 0342, 0230, 0272);
be341bce	259	$test++; # 53
a197cbdd	260
c5cc3500	261	$tmp = $1;
c5cc3500	262	ok $tmp, pack("C*", 0342, 0230, 0272);
be341bce	263	$test++; # 54
c5cc3500	264	}
a197cbdd	265	{
	266	use bytes;
	267	no utf8;
	268
	269	ok length, 10;
be341bce	270	$test++; # 55
a197cbdd	271
a197cbdd	272	ok length((m/>(.)/)[0]), 1;
be341bce	273	$test++; # 56
a197cbdd	274
a197cbdd	275	ok length($&), 2;
be341bce	276	$test++; # 57
a197cbdd	277
a197cbdd	278	ok length($'), 5;
be341bce	279	$test++; # 58
a197cbdd	280
a197cbdd	281	ok length($`), 3;
be341bce	282	$test++; # 59
a197cbdd	283
a197cbdd	284	ok length($1), 1;
be341bce	285	$test++; # 60
a197cbdd	286
a197cbdd	287	ok $&, pack("C*", ord(">"), 0342);
be341bce	288	$test++; # 61
a197cbdd	289
a197cbdd	290	ok $', pack("C*", 0230, 0272, 0342, 0230, 0272);
be341bce	291	$test++; # 62
a197cbdd	292
a197cbdd	293	ok $`, pack("C*", 0342, 0230, 0272);
be341bce	294	$test++; # 63
a197cbdd	295
a197cbdd	296	ok $1, pack("C*", 0342);
be341bce	297	$test++; # 64
a197cbdd	298
a197cbdd	299	}
de35ba6f	300
de35ba6f	301	ok "\x{ab}" =~ /^\x{ab}$/, 1;
be341bce	302	$test++; # 65
a197cbdd	303	}
aaa68c4a	304
	305	{
	306	use utf8;
	307	ok_bytes chr(0xe2), pack("C*", 0xc3, 0xa2);
	308	$test++; # 66
	309	}
28cb3359	310
	311	{
	312	use utf8;
	313	my @a = map ord, split(//, join("", map chr, (1234, 123, 2345)));
	314	ok "@a", "1234 123 2345";
	315	$test++; # 67
	316	}
	317
	318	{
	319	use utf8;
	320	my $x = chr(123);
	321	my @a = map ord, split(/$x/, join("", map chr, (1234, 123, 2345)));
	322	ok "@a", "1234 2345";
	323	$test++; # 68
	324	}
31067593	325
7bbb0251	326	{
da450f52	327	# bug id 20001009.001
	328
	329	my($a,$b);
	330	{ use bytes; $a = "\xc3\xa4"; }
	331	{ use utf8; $b = "\xe4"; }
	332	{ use bytes; ok_bytes $a, $b; $test++; } # 69
	333	{ use utf8; nok $a, $b; $test++; } # 70
7bbb0251	334	}
31067593	335
31067593	336	{
da450f52	337	# bug id 20001008.001
da450f52	338
31067593	339	my @x = ("stra\337e 138","stra\337e 138");
	340	for (@x) {
	341	s/(\d+)\s*([\w\-]+)/$1 . uc $2/e;
	342	my($latin) = /^(.+)(?:\s+\d)/;
	343	print $latin eq "stra\337e" ? "ok $test\n" :
	344	"#latin[$latin]\nnot ok $test\n";
	345	$test++;
	346	$latin =~ s/stra\337e/straße/; # \303\237 after the 2nd a
	347	use utf8;
	348	$latin =~ s!(s)tr(?:aß\|s+e)!$1tr.!; # \303\237 after the a
	349	}
	350	}
b7018214	351
b7018214	352	{
da450f52	353	# bug id 20000819.004
da450f52	354
b7018214	355	$_ = $dx = "\x{10f2}";
	356	s/($dx)/$dx$1/;
	357	{
	358	use bytes;
	359	print "not " unless $_ eq "$dx$dx";
	360	print "ok $test\n";
	361	$test++;
	362	}
	363
	364	$_ = $dx = "\x{10f2}";
	365	s/($dx)/$1$dx/;
	366	{
	367	use bytes;
	368	print "not " unless $_ eq "$dx$dx";
	369	print "ok $test\n";
	370	$test++;
	371	}
	372
	373	$dx = "\x{10f2}";
	374	$_ = "\x{10f2}\x{10f2}";
	375	s/($dx)($dx)/$1$2/;
	376	{
	377	use bytes;
	378	print "not " unless $_ eq "$dx$dx";
	379	print "ok $test\n";
	380	$test++;
	381	}
	382	}
8b72f7e2	383
8b72f7e2	384	{
da450f52	385	# bug id 20000323.056
da450f52	386
8b72f7e2	387	use utf8;
	388
	389	print "not " unless "\x{41}" eq +v65;
	390	print "ok $test\n";
	391	$test++;
	392
	393	print "not " unless "\x41" eq +v65;
	394	print "ok $test\n";
	395	$test++;
	396
	397	print "not " unless "\x{c8}" eq +v200;
	398	print "ok $test\n";
	399	$test++;
	400
	401	print "not " unless "\xc8" eq +v200;
	402	print "ok $test\n";
	403	$test++;
	404
	405	print "not " unless "\x{221b}" eq v8731;
	406	print "ok $test\n";
	407	$test++;
	408	}
da450f52	409
	410	{
	411	# bug id 20000427.003
	412
	413	use utf8;
	414	use warnings;
	415	use strict;
	416
	417	my $sushi = "\x{b36c}\x{5a8c}\x{ff5b}\x{5079}\x{505b}";
	418
	419	my @charlist = split //, $sushi;
	420	my $r = '';
	421	foreach my $ch (@charlist) {
	422	$r = $r . " " . sprintf "U+%04X", ord($ch);
	423	}
	424
	425	print "not " unless $r eq " U+B36C U+5A8C U+FF5B U+5079 U+505B";
	426	print "ok $test\n";
	427	$test++;
	428	}
	429
	430	{
	431	# bug id 20000901.092
	432	# test that undef left and right of utf8 results in a valid string
	433
	434	my $a;
	435	$a .= "\x{1ff}";
	436	print "not " unless $a eq "\x{1ff}";
	437	print "ok $test\n";
	438	$test++;
	439	}
93f04dac	440
	441	{
	442	# bug id 20000426.003
	443
	444	use utf8;
	445
	446	my $s = "\x20\x40\x{80}\x{100}\x{80}\x40\x20";
	447
	448	my ($a, $b, $c) = split(/\x40/, $s);
	449	print "not "
	450	unless $a eq "\x20" && $b eq "\x{80}\x{100}\x{80}" && $c eq $a;
	451	print "ok $test\n";
	452	$test++;
	453
	454	my ($a, $b) = split(/\x{100}/, $s);
	455	print "not " unless $a eq "\x20\x40\x{80}" && $b eq "\x{80}\x40\x20";
	456	print "ok $test\n";
	457	$test++;
	458
	459	my ($a, $b) = split(/\x{80}\x{100}\x{80}/, $s);
	460	print "not " unless $a eq "\x20\x40" && $b eq "\x40\x20";
	461	print "ok $test\n";
	462	$test++;
	463
	464	my ($a, $b) = split(/\x40\x{80}/, $s);
	465	print "not " unless $a eq "\x20" && $b eq "\x{100}\x{80}\x40\x20";
	466	print "ok $test\n";
	467	$test++;
	468
	469	my ($a, $b, $c) = split(/[\x40\x{80}]+/, $s);
	470	print "not " unless $a eq "\x20" && $b eq "\x{100}" && $c eq "\x20";
	471	print "ok $test\n";
	472	$test++;
	473	}