[p5sagit/p5-mst-13.2.git] / lib / Unicode / UCD.t

BEGIN {
    if (ord("A") == 193) {
	print "1..0 # Skip: EBCDIC\n";
	exit 0;
    }
    chdir 't' if -d 't';
    @INC = '../lib';
}

use strict;
use Unicode::UCD;
use Test::More;

BEGIN { plan tests => 162 };

use Unicode::UCD 'charinfo';

my $charinfo;

$charinfo = charinfo(0x41);

is($charinfo->{code},           '0041', 'LATIN CAPITAL LETTER A');
is($charinfo->{name},           'LATIN CAPITAL LETTER A');
is($charinfo->{category},       'Lu');
is($charinfo->{combining},      '0');
is($charinfo->{bidi},           'L');
is($charinfo->{decomposition},  '');
is($charinfo->{decimal},        '');
is($charinfo->{digit},          '');
is($charinfo->{numeric},        '');
is($charinfo->{mirrored},       'N');
is($charinfo->{unicode10},      '');
is($charinfo->{comment},        '');
is($charinfo->{upper},          '');
is($charinfo->{lower},          '0061');
is($charinfo->{title},          '');
is($charinfo->{block},          'Basic Latin');
is($charinfo->{script},         'Latin');

$charinfo = charinfo(0x100);

is($charinfo->{code},           '0100', 'LATIN CAPITAL LETTER A WITH MACRON');
is($charinfo->{name},           'LATIN CAPITAL LETTER A WITH MACRON');
is($charinfo->{category},       'Lu');
is($charinfo->{combining},      '0');
is($charinfo->{bidi},           'L');
is($charinfo->{decomposition},  '0041 0304');
is($charinfo->{decimal},        '');
is($charinfo->{digit},          '');
is($charinfo->{numeric},        '');
is($charinfo->{mirrored},       'N');
is($charinfo->{unicode10},      'LATIN CAPITAL LETTER A MACRON');
is($charinfo->{comment},        '');
is($charinfo->{upper},          '');
is($charinfo->{lower},          '0101');
is($charinfo->{title},          '');
is($charinfo->{block},          'Latin Extended-A');
is($charinfo->{script},         'Latin');

# 0x0590 is in the Hebrew block but unused.

$charinfo = charinfo(0x590);

is($charinfo->{code},          undef,	'0x0590 - unused Hebrew');
is($charinfo->{name},          undef);
is($charinfo->{category},      undef);
is($charinfo->{combining},     undef);
is($charinfo->{bidi},          undef);
is($charinfo->{decomposition}, undef);
is($charinfo->{decimal},       undef);
is($charinfo->{digit},         undef);
is($charinfo->{numeric},       undef);
is($charinfo->{mirrored},      undef);
is($charinfo->{unicode10},     undef);
is($charinfo->{comment},       undef);
is($charinfo->{upper},         undef);
is($charinfo->{lower},         undef);
is($charinfo->{title},         undef);
is($charinfo->{block},         undef);
is($charinfo->{script},        undef);

# 0x05d0 is in the Hebrew block and used.

$charinfo = charinfo(0x5d0);

is($charinfo->{code},           '05D0', '05D0 - used Hebrew');
is($charinfo->{name},           'HEBREW LETTER ALEF');
is($charinfo->{category},       'Lo');
is($charinfo->{combining},      '0');
is($charinfo->{bidi},           'R');
is($charinfo->{decomposition},  '');
is($charinfo->{decimal},        '');
is($charinfo->{digit},          '');
is($charinfo->{numeric},        '');
is($charinfo->{mirrored},       'N');
is($charinfo->{unicode10},      '');
is($charinfo->{comment},        '');
is($charinfo->{upper},          '');
is($charinfo->{lower},          '');
is($charinfo->{title},          '');
is($charinfo->{block},          'Hebrew');
is($charinfo->{script},         'Hebrew');

# An open syllable in Hangul.

$charinfo = charinfo(0xAC00);

is($charinfo->{code},           'AC00', 'HANGUL SYLLABLE-AC00');
is($charinfo->{name},           'HANGUL SYLLABLE-AC00');
is($charinfo->{category},       'Lo');
is($charinfo->{combining},      '0');
is($charinfo->{bidi},           'L');
is($charinfo->{decomposition},  undef);
is($charinfo->{decimal},        '');
is($charinfo->{digit},          '');
is($charinfo->{numeric},        '');
is($charinfo->{mirrored},       'N');
is($charinfo->{unicode10},      '');
is($charinfo->{comment},        '');
is($charinfo->{upper},          '');
is($charinfo->{lower},          '');
is($charinfo->{title},          '');
is($charinfo->{block},          'Hangul Syllables');
is($charinfo->{script},         'Hangul');

# A closed syllable in Hangul.

$charinfo = charinfo(0xAE00);

is($charinfo->{code},           'AE00', 'HANGUL SYLLABLE-AE00');
is($charinfo->{name},           'HANGUL SYLLABLE-AE00');
is($charinfo->{category},       'Lo');
is($charinfo->{combining},      '0');
is($charinfo->{bidi},           'L');
is($charinfo->{decomposition},  undef);
is($charinfo->{decimal},        '');
is($charinfo->{digit},          '');
is($charinfo->{numeric},        '');
is($charinfo->{mirrored},       'N');
is($charinfo->{unicode10},      '');
is($charinfo->{comment},        '');
is($charinfo->{upper},          '');
is($charinfo->{lower},          '');
is($charinfo->{title},          '');
is($charinfo->{block},          'Hangul Syllables');
is($charinfo->{script},         'Hangul');

$charinfo = charinfo(0x1D400);

is($charinfo->{code},           '1D400', 'MATHEMATICAL BOLD CAPITAL A');
is($charinfo->{name},           'MATHEMATICAL BOLD CAPITAL A');
is($charinfo->{category},       'Lu');
is($charinfo->{combining},      '0');
is($charinfo->{bidi},           'L');
is($charinfo->{decomposition},  '<font> 0041');
is($charinfo->{decimal},        '');
is($charinfo->{digit},          '');
is($charinfo->{numeric},        '');
is($charinfo->{mirrored},       'N');
is($charinfo->{unicode10},      '');
is($charinfo->{comment},        '');
is($charinfo->{upper},          '');
is($charinfo->{lower},          '');
is($charinfo->{title},          '');
is($charinfo->{block},          'Mathematical Alphanumeric Symbols');
is($charinfo->{script},         undef);

use Unicode::UCD qw(charblock charscript);

# 0x0590 is in the Hebrew block but unused.

is(charblock(0x590),          'Hebrew', '0x0590 - Hebrew unused charblock');
is(charscript(0x590),         undef,    '0x0590 - Hebrew unused charscript');

$charinfo = charinfo(0xbe);

is($charinfo->{code},           '00BE', 'VULGAR FRACTION THREE QUARTERS');
is($charinfo->{name},           'VULGAR FRACTION THREE QUARTERS');
is($charinfo->{category},       'No');
is($charinfo->{combining},      '0');
is($charinfo->{bidi},           'ON');
is($charinfo->{decomposition},  '<fraction> 0033 2044 0034');
is($charinfo->{decimal},        '');
is($charinfo->{digit},          '');
is($charinfo->{numeric},        '3/4');
is($charinfo->{mirrored},       'N');
is($charinfo->{unicode10},      'FRACTION THREE QUARTERS');
is($charinfo->{comment},        '');
is($charinfo->{upper},          '');
is($charinfo->{lower},          '');
is($charinfo->{title},          '');
is($charinfo->{block},          'Latin-1 Supplement');
is($charinfo->{script},         undef);

use Unicode::UCD qw(charblocks charscripts);

my $charblocks = charblocks();

ok(exists $charblocks->{Thai}, 'Thai charblock exists');
is($charblocks->{Thai}->[0]->[0], hex('0e00'));
ok(!exists $charblocks->{PigLatin}, 'PigLatin charblock does not exist');

my $charscripts = charscripts();

ok(exists $charscripts->{Armenian}, 'Armenian charscript exists');
is($charscripts->{Armenian}->[0]->[0], hex('0531'));
ok(!exists $charscripts->{PigLatin}, 'PigLatin charscript does not exist');

my $charscript;

$charscript = charscript("12ab");
is($charscript, 'Ethiopic', 'Ethiopic charscript');

$charscript = charscript("0x12ab");
is($charscript, 'Ethiopic');

$charscript = charscript("U+12ab");
is($charscript, 'Ethiopic');

my $ranges;

$ranges = charscript('Ogham');
is($ranges->[0]->[0], hex('1681'), 'Ogham charscript');
is($ranges->[0]->[1], hex('169a'));

use Unicode::UCD qw(charinrange);

$ranges = charscript('Cherokee');
ok(!charinrange($ranges, "139f"), 'Cherokee charscript');
ok( charinrange($ranges, "13a0"));
ok( charinrange($ranges, "13f4"));
ok(!charinrange($ranges, "13f5"));

is(Unicode::UCD::UnicodeVersion, '3.2.0', 'UnicodeVersion');

use Unicode::UCD qw(compexcl);

ok(!compexcl(0x0100), 'compexcl');
ok( compexcl(0x0958));

use Unicode::UCD qw(casefold);

my $casefold;

$casefold = casefold(0x41);

ok($casefold->{code} eq '0041' &&
   $casefold->{status} eq 'C'  &&
   $casefold->{mapping} eq '0061', 'casefold 0x41');

$casefold = casefold(0xdf);

ok($casefold->{code} eq '00DF' &&
   $casefold->{status} eq 'F'  &&
   $casefold->{mapping} eq '0073 0073', 'casefold 0xDF');

ok(!casefold(0x20));

use Unicode::UCD qw(casespec);

my $casespec;

ok(!casespec(0x41));

$casespec = casespec(0xdf);

ok($casespec->{code} eq '00DF' &&
   $casespec->{lower} eq '00DF'  &&
   $casespec->{title} eq '0053 0073'  &&
   $casespec->{upper} eq '0053 0053' &&
   $casespec->{condition} eq undef, 'casespec 0xDF');

$casespec = casespec(0x307);

ok($casespec->{az}->{code} eq '0307' &&
   $casespec->{az}->{lower} eq ''  &&
   $casespec->{az}->{title} eq '0307'  &&
   $casespec->{az}->{upper} eq '0307' &&
   $casespec->{az}->{condition} eq 'az After_Soft_Dotted',
   'casespec 0x307');
Commit	Line	Data
8b731da2	1	BEGIN {
	2	if (ord("A") == 193) {
	3	print "1..0 # Skip: EBCDIC\n";
	4	exit 0;
	5	}
a778afa6	6	chdir 't' if -d 't';
a778afa6	7	@INC = '../lib';
8b731da2	8	}
8b731da2	9
a778afa6	10	use strict;
a778afa6	11	use Unicode::UCD;
f5c9f3db	12	use Test::More;
8b731da2	13
74f8133e	14	BEGIN { plan tests => 162 };
561c79ed	15
55d7b906	16	use Unicode::UCD 'charinfo';
561c79ed	17
b08cd201	18	my $charinfo;
	19
	20	$charinfo = charinfo(0x41);
	21
f5c9f3db	22	is($charinfo->{code}, '0041', 'LATIN CAPITAL LETTER A');
	23	is($charinfo->{name}, 'LATIN CAPITAL LETTER A');
	24	is($charinfo->{category}, 'Lu');
	25	is($charinfo->{combining}, '0');
	26	is($charinfo->{bidi}, 'L');
	27	is($charinfo->{decomposition}, '');
	28	is($charinfo->{decimal}, '');
	29	is($charinfo->{digit}, '');
	30	is($charinfo->{numeric}, '');
	31	is($charinfo->{mirrored}, 'N');
	32	is($charinfo->{unicode10}, '');
	33	is($charinfo->{comment}, '');
	34	is($charinfo->{upper}, '');
	35	is($charinfo->{lower}, '0061');
	36	is($charinfo->{title}, '');
	37	is($charinfo->{block}, 'Basic Latin');
	38	is($charinfo->{script}, 'Latin');
b08cd201	39
	40	$charinfo = charinfo(0x100);
	41
f5c9f3db	42	is($charinfo->{code}, '0100', 'LATIN CAPITAL LETTER A WITH MACRON');
	43	is($charinfo->{name}, 'LATIN CAPITAL LETTER A WITH MACRON');
	44	is($charinfo->{category}, 'Lu');
	45	is($charinfo->{combining}, '0');
	46	is($charinfo->{bidi}, 'L');
	47	is($charinfo->{decomposition}, '0041 0304');
	48	is($charinfo->{decimal}, '');
	49	is($charinfo->{digit}, '');
	50	is($charinfo->{numeric}, '');
	51	is($charinfo->{mirrored}, 'N');
	52	is($charinfo->{unicode10}, 'LATIN CAPITAL LETTER A MACRON');
	53	is($charinfo->{comment}, '');
	54	is($charinfo->{upper}, '');
	55	is($charinfo->{lower}, '0101');
	56	is($charinfo->{title}, '');
	57	is($charinfo->{block}, 'Latin Extended-A');
	58	is($charinfo->{script}, 'Latin');
a196fbfd	59
a196fbfd	60	# 0x0590 is in the Hebrew block but unused.
561c79ed	61
b08cd201	62	$charinfo = charinfo(0x590);
b08cd201	63
f5c9f3db	64	is($charinfo->{code}, undef, '0x0590 - unused Hebrew');
	65	is($charinfo->{name}, undef);
	66	is($charinfo->{category}, undef);
	67	is($charinfo->{combining}, undef);
	68	is($charinfo->{bidi}, undef);
	69	is($charinfo->{decomposition}, undef);
	70	is($charinfo->{decimal}, undef);
	71	is($charinfo->{digit}, undef);
	72	is($charinfo->{numeric}, undef);
	73	is($charinfo->{mirrored}, undef);
	74	is($charinfo->{unicode10}, undef);
	75	is($charinfo->{comment}, undef);
	76	is($charinfo->{upper}, undef);
	77	is($charinfo->{lower}, undef);
	78	is($charinfo->{title}, undef);
	79	is($charinfo->{block}, undef);
	80	is($charinfo->{script}, undef);
a196fbfd	81
a196fbfd	82	# 0x05d0 is in the Hebrew block and used.
561c79ed	83
b08cd201	84	$charinfo = charinfo(0x5d0);
b08cd201	85
f5c9f3db	86	is($charinfo->{code}, '05D0', '05D0 - used Hebrew');
	87	is($charinfo->{name}, 'HEBREW LETTER ALEF');
	88	is($charinfo->{category}, 'Lo');
	89	is($charinfo->{combining}, '0');
	90	is($charinfo->{bidi}, 'R');
	91	is($charinfo->{decomposition}, '');
	92	is($charinfo->{decimal}, '');
	93	is($charinfo->{digit}, '');
	94	is($charinfo->{numeric}, '');
	95	is($charinfo->{mirrored}, 'N');
	96	is($charinfo->{unicode10}, '');
	97	is($charinfo->{comment}, '');
	98	is($charinfo->{upper}, '');
	99	is($charinfo->{lower}, '');
	100	is($charinfo->{title}, '');
	101	is($charinfo->{block}, 'Hebrew');
	102	is($charinfo->{script}, 'Hebrew');
561c79ed	103
74f8133e	104	# An open syllable in Hangul.
a6fa416b	105
	106	$charinfo = charinfo(0xAC00);
	107
f5c9f3db	108	is($charinfo->{code}, 'AC00', 'HANGUL SYLLABLE-AC00');
	109	is($charinfo->{name}, 'HANGUL SYLLABLE-AC00');
	110	is($charinfo->{category}, 'Lo');
	111	is($charinfo->{combining}, '0');
	112	is($charinfo->{bidi}, 'L');
	113	is($charinfo->{decomposition}, undef);
	114	is($charinfo->{decimal}, '');
	115	is($charinfo->{digit}, '');
	116	is($charinfo->{numeric}, '');
	117	is($charinfo->{mirrored}, 'N');
	118	is($charinfo->{unicode10}, '');
	119	is($charinfo->{comment}, '');
	120	is($charinfo->{upper}, '');
	121	is($charinfo->{lower}, '');
	122	is($charinfo->{title}, '');
	123	is($charinfo->{block}, 'Hangul Syllables');
	124	is($charinfo->{script}, 'Hangul');
a6fa416b	125
74f8133e	126	# A closed syllable in Hangul.
a6fa416b	127
	128	$charinfo = charinfo(0xAE00);
	129
f5c9f3db	130	is($charinfo->{code}, 'AE00', 'HANGUL SYLLABLE-AE00');
	131	is($charinfo->{name}, 'HANGUL SYLLABLE-AE00');
	132	is($charinfo->{category}, 'Lo');
	133	is($charinfo->{combining}, '0');
	134	is($charinfo->{bidi}, 'L');
	135	is($charinfo->{decomposition}, undef);
	136	is($charinfo->{decimal}, '');
	137	is($charinfo->{digit}, '');
	138	is($charinfo->{numeric}, '');
	139	is($charinfo->{mirrored}, 'N');
	140	is($charinfo->{unicode10}, '');
	141	is($charinfo->{comment}, '');
	142	is($charinfo->{upper}, '');
	143	is($charinfo->{lower}, '');
	144	is($charinfo->{title}, '');
	145	is($charinfo->{block}, 'Hangul Syllables');
	146	is($charinfo->{script}, 'Hangul');
a6fa416b	147
	148	$charinfo = charinfo(0x1D400);
	149
f5c9f3db	150	is($charinfo->{code}, '1D400', 'MATHEMATICAL BOLD CAPITAL A');
	151	is($charinfo->{name}, 'MATHEMATICAL BOLD CAPITAL A');
	152	is($charinfo->{category}, 'Lu');
	153	is($charinfo->{combining}, '0');
	154	is($charinfo->{bidi}, 'L');
	155	is($charinfo->{decomposition}, '<font> 0041');
	156	is($charinfo->{decimal}, '');
	157	is($charinfo->{digit}, '');
	158	is($charinfo->{numeric}, '');
	159	is($charinfo->{mirrored}, 'N');
	160	is($charinfo->{unicode10}, '');
	161	is($charinfo->{comment}, '');
	162	is($charinfo->{upper}, '');
	163	is($charinfo->{lower}, '');
	164	is($charinfo->{title}, '');
	165	is($charinfo->{block}, 'Mathematical Alphanumeric Symbols');
	166	is($charinfo->{script}, undef);
a6fa416b	167
55d7b906	168	use Unicode::UCD qw(charblock charscript);
a196fbfd	169
a196fbfd	170	# 0x0590 is in the Hebrew block but unused.
561c79ed	171
f5c9f3db	172	is(charblock(0x590), 'Hebrew', '0x0590 - Hebrew unused charblock');
f5c9f3db	173	is(charscript(0x590), undef, '0x0590 - Hebrew unused charscript');
561c79ed	174
b08cd201	175	$charinfo = charinfo(0xbe);
b08cd201	176
f5c9f3db	177	is($charinfo->{code}, '00BE', 'VULGAR FRACTION THREE QUARTERS');
	178	is($charinfo->{name}, 'VULGAR FRACTION THREE QUARTERS');
	179	is($charinfo->{category}, 'No');
	180	is($charinfo->{combining}, '0');
	181	is($charinfo->{bidi}, 'ON');
	182	is($charinfo->{decomposition}, '<fraction> 0033 2044 0034');
	183	is($charinfo->{decimal}, '');
	184	is($charinfo->{digit}, '');
	185	is($charinfo->{numeric}, '3/4');
	186	is($charinfo->{mirrored}, 'N');
	187	is($charinfo->{unicode10}, 'FRACTION THREE QUARTERS');
	188	is($charinfo->{comment}, '');
	189	is($charinfo->{upper}, '');
	190	is($charinfo->{lower}, '');
	191	is($charinfo->{title}, '');
	192	is($charinfo->{block}, 'Latin-1 Supplement');
	193	is($charinfo->{script}, undef);
10a6ecd2	194
55d7b906	195	use Unicode::UCD qw(charblocks charscripts);
10a6ecd2	196
b08cd201	197	my $charblocks = charblocks();
10a6ecd2	198
f5c9f3db	199	ok(exists $charblocks->{Thai}, 'Thai charblock exists');
	200	is($charblocks->{Thai}->[0]->[0], hex('0e00'));
	201	ok(!exists $charblocks->{PigLatin}, 'PigLatin charblock does not exist');
10a6ecd2	202
b08cd201	203	my $charscripts = charscripts();
10a6ecd2	204
f5c9f3db	205	ok(exists $charscripts->{Armenian}, 'Armenian charscript exists');
	206	is($charscripts->{Armenian}->[0]->[0], hex('0531'));
	207	ok(!exists $charscripts->{PigLatin}, 'PigLatin charscript does not exist');
10a6ecd2	208
	209	my $charscript;
	210
	211	$charscript = charscript("12ab");
f5c9f3db	212	is($charscript, 'Ethiopic', 'Ethiopic charscript');
10a6ecd2	213
10a6ecd2	214	$charscript = charscript("0x12ab");
f5c9f3db	215	is($charscript, 'Ethiopic');
10a6ecd2	216
10a6ecd2	217	$charscript = charscript("U+12ab");
f5c9f3db	218	is($charscript, 'Ethiopic');
10a6ecd2	219
	220	my $ranges;
	221
	222	$ranges = charscript('Ogham');
f5c9f3db	223	is($ranges->[0]->[0], hex('1681'), 'Ogham charscript');
f5c9f3db	224	is($ranges->[0]->[1], hex('169a'));
10a6ecd2	225
55d7b906	226	use Unicode::UCD qw(charinrange);
10a6ecd2	227
10a6ecd2	228	$ranges = charscript('Cherokee');
f5c9f3db	229	ok(!charinrange($ranges, "139f"), 'Cherokee charscript');
10a6ecd2	230	ok( charinrange($ranges, "13a0"));
	231	ok( charinrange($ranges, "13f4"));
	232	ok(!charinrange($ranges, "13f5"));
	233
822ebcc8	234	is(Unicode::UCD::UnicodeVersion, '3.2.0', 'UnicodeVersion');
b08cd201	235
55d7b906	236	use Unicode::UCD qw(compexcl);
b08cd201	237
f5c9f3db	238	ok(!compexcl(0x0100), 'compexcl');
b08cd201	239	ok( compexcl(0x0958));
b08cd201	240
55d7b906	241	use Unicode::UCD qw(casefold);
b08cd201	242
	243	my $casefold;
	244
	245	$casefold = casefold(0x41);
	246
	247	ok($casefold->{code} eq '0041' &&
	248	$casefold->{status} eq 'C' &&
f5c9f3db	249	$casefold->{mapping} eq '0061', 'casefold 0x41');
b08cd201	250
	251	$casefold = casefold(0xdf);
	252
	253	ok($casefold->{code} eq '00DF' &&
	254	$casefold->{status} eq 'F' &&
f5c9f3db	255	$casefold->{mapping} eq '0073 0073', 'casefold 0xDF');
b08cd201	256
	257	ok(!casefold(0x20));
	258
55d7b906	259	use Unicode::UCD qw(casespec);
b08cd201	260
	261	my $casespec;
	262
	263	ok(!casespec(0x41));
	264
	265	$casespec = casespec(0xdf);
	266
	267	ok($casespec->{code} eq '00DF' &&
	268	$casespec->{lower} eq '00DF' &&
	269	$casespec->{title} eq '0053 0073' &&
	270	$casespec->{upper} eq '0053 0053' &&
f5c9f3db	271	$casespec->{condition} eq undef, 'casespec 0xDF');
b08cd201	272
	273	$casespec = casespec(0x307);
	274
f499c386	275	ok($casespec->{az}->{code} eq '0307' &&
	276	$casespec->{az}->{lower} eq '' &&
	277	$casespec->{az}->{title} eq '0307' &&
	278	$casespec->{az}->{upper} eq '0307' &&
822ebcc8	279	$casespec->{az}->{condition} eq 'az After_Soft_Dotted',
f5c9f3db	280	'casespec 0x307');