[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';
    @INC = "::lib" if $^O eq 'MacOS'; # module parses @INC itself
}

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';
e69a2255	8	@INC = "::lib" if $^O eq 'MacOS'; # module parses @INC itself
8b731da2	9	}
8b731da2	10
a778afa6	11	use strict;
a778afa6	12	use Unicode::UCD;
f5c9f3db	13	use Test::More;
8b731da2	14
74f8133e	15	BEGIN { plan tests => 162 };
561c79ed	16
55d7b906	17	use Unicode::UCD 'charinfo';
561c79ed	18
b08cd201	19	my $charinfo;
	20
	21	$charinfo = charinfo(0x41);
	22
f5c9f3db	23	is($charinfo->{code}, '0041', 'LATIN CAPITAL LETTER A');
	24	is($charinfo->{name}, 'LATIN CAPITAL LETTER A');
	25	is($charinfo->{category}, 'Lu');
	26	is($charinfo->{combining}, '0');
	27	is($charinfo->{bidi}, 'L');
	28	is($charinfo->{decomposition}, '');
	29	is($charinfo->{decimal}, '');
	30	is($charinfo->{digit}, '');
	31	is($charinfo->{numeric}, '');
	32	is($charinfo->{mirrored}, 'N');
	33	is($charinfo->{unicode10}, '');
	34	is($charinfo->{comment}, '');
	35	is($charinfo->{upper}, '');
	36	is($charinfo->{lower}, '0061');
	37	is($charinfo->{title}, '');
	38	is($charinfo->{block}, 'Basic Latin');
	39	is($charinfo->{script}, 'Latin');
b08cd201	40
	41	$charinfo = charinfo(0x100);
	42
f5c9f3db	43	is($charinfo->{code}, '0100', 'LATIN CAPITAL LETTER A WITH MACRON');
	44	is($charinfo->{name}, 'LATIN CAPITAL LETTER A WITH MACRON');
	45	is($charinfo->{category}, 'Lu');
	46	is($charinfo->{combining}, '0');
	47	is($charinfo->{bidi}, 'L');
	48	is($charinfo->{decomposition}, '0041 0304');
	49	is($charinfo->{decimal}, '');
	50	is($charinfo->{digit}, '');
	51	is($charinfo->{numeric}, '');
	52	is($charinfo->{mirrored}, 'N');
	53	is($charinfo->{unicode10}, 'LATIN CAPITAL LETTER A MACRON');
	54	is($charinfo->{comment}, '');
	55	is($charinfo->{upper}, '');
	56	is($charinfo->{lower}, '0101');
	57	is($charinfo->{title}, '');
	58	is($charinfo->{block}, 'Latin Extended-A');
	59	is($charinfo->{script}, 'Latin');
a196fbfd	60
a196fbfd	61	# 0x0590 is in the Hebrew block but unused.
561c79ed	62
b08cd201	63	$charinfo = charinfo(0x590);
b08cd201	64
f5c9f3db	65	is($charinfo->{code}, undef, '0x0590 - unused Hebrew');
	66	is($charinfo->{name}, undef);
	67	is($charinfo->{category}, undef);
	68	is($charinfo->{combining}, undef);
	69	is($charinfo->{bidi}, undef);
	70	is($charinfo->{decomposition}, undef);
	71	is($charinfo->{decimal}, undef);
	72	is($charinfo->{digit}, undef);
	73	is($charinfo->{numeric}, undef);
	74	is($charinfo->{mirrored}, undef);
	75	is($charinfo->{unicode10}, undef);
	76	is($charinfo->{comment}, undef);
	77	is($charinfo->{upper}, undef);
	78	is($charinfo->{lower}, undef);
	79	is($charinfo->{title}, undef);
	80	is($charinfo->{block}, undef);
	81	is($charinfo->{script}, undef);
a196fbfd	82
a196fbfd	83	# 0x05d0 is in the Hebrew block and used.
561c79ed	84
b08cd201	85	$charinfo = charinfo(0x5d0);
b08cd201	86
f5c9f3db	87	is($charinfo->{code}, '05D0', '05D0 - used Hebrew');
	88	is($charinfo->{name}, 'HEBREW LETTER ALEF');
	89	is($charinfo->{category}, 'Lo');
	90	is($charinfo->{combining}, '0');
	91	is($charinfo->{bidi}, 'R');
	92	is($charinfo->{decomposition}, '');
	93	is($charinfo->{decimal}, '');
	94	is($charinfo->{digit}, '');
	95	is($charinfo->{numeric}, '');
	96	is($charinfo->{mirrored}, 'N');
	97	is($charinfo->{unicode10}, '');
	98	is($charinfo->{comment}, '');
	99	is($charinfo->{upper}, '');
	100	is($charinfo->{lower}, '');
	101	is($charinfo->{title}, '');
	102	is($charinfo->{block}, 'Hebrew');
	103	is($charinfo->{script}, 'Hebrew');
561c79ed	104
74f8133e	105	# An open syllable in Hangul.
a6fa416b	106
	107	$charinfo = charinfo(0xAC00);
	108
f5c9f3db	109	is($charinfo->{code}, 'AC00', 'HANGUL SYLLABLE-AC00');
	110	is($charinfo->{name}, 'HANGUL SYLLABLE-AC00');
	111	is($charinfo->{category}, 'Lo');
	112	is($charinfo->{combining}, '0');
	113	is($charinfo->{bidi}, 'L');
	114	is($charinfo->{decomposition}, undef);
	115	is($charinfo->{decimal}, '');
	116	is($charinfo->{digit}, '');
	117	is($charinfo->{numeric}, '');
	118	is($charinfo->{mirrored}, 'N');
	119	is($charinfo->{unicode10}, '');
	120	is($charinfo->{comment}, '');
	121	is($charinfo->{upper}, '');
	122	is($charinfo->{lower}, '');
	123	is($charinfo->{title}, '');
	124	is($charinfo->{block}, 'Hangul Syllables');
	125	is($charinfo->{script}, 'Hangul');
a6fa416b	126
74f8133e	127	# A closed syllable in Hangul.
a6fa416b	128
	129	$charinfo = charinfo(0xAE00);
	130
f5c9f3db	131	is($charinfo->{code}, 'AE00', 'HANGUL SYLLABLE-AE00');
	132	is($charinfo->{name}, 'HANGUL SYLLABLE-AE00');
	133	is($charinfo->{category}, 'Lo');
	134	is($charinfo->{combining}, '0');
	135	is($charinfo->{bidi}, 'L');
	136	is($charinfo->{decomposition}, undef);
	137	is($charinfo->{decimal}, '');
	138	is($charinfo->{digit}, '');
	139	is($charinfo->{numeric}, '');
	140	is($charinfo->{mirrored}, 'N');
	141	is($charinfo->{unicode10}, '');
	142	is($charinfo->{comment}, '');
	143	is($charinfo->{upper}, '');
	144	is($charinfo->{lower}, '');
	145	is($charinfo->{title}, '');
	146	is($charinfo->{block}, 'Hangul Syllables');
	147	is($charinfo->{script}, 'Hangul');
a6fa416b	148
	149	$charinfo = charinfo(0x1D400);
	150
f5c9f3db	151	is($charinfo->{code}, '1D400', 'MATHEMATICAL BOLD CAPITAL A');
	152	is($charinfo->{name}, 'MATHEMATICAL BOLD CAPITAL A');
	153	is($charinfo->{category}, 'Lu');
	154	is($charinfo->{combining}, '0');
	155	is($charinfo->{bidi}, 'L');
	156	is($charinfo->{decomposition}, '<font> 0041');
	157	is($charinfo->{decimal}, '');
	158	is($charinfo->{digit}, '');
	159	is($charinfo->{numeric}, '');
	160	is($charinfo->{mirrored}, 'N');
	161	is($charinfo->{unicode10}, '');
	162	is($charinfo->{comment}, '');
	163	is($charinfo->{upper}, '');
	164	is($charinfo->{lower}, '');
	165	is($charinfo->{title}, '');
	166	is($charinfo->{block}, 'Mathematical Alphanumeric Symbols');
	167	is($charinfo->{script}, undef);
a6fa416b	168
55d7b906	169	use Unicode::UCD qw(charblock charscript);
a196fbfd	170
a196fbfd	171	# 0x0590 is in the Hebrew block but unused.
561c79ed	172
f5c9f3db	173	is(charblock(0x590), 'Hebrew', '0x0590 - Hebrew unused charblock');
f5c9f3db	174	is(charscript(0x590), undef, '0x0590 - Hebrew unused charscript');
561c79ed	175
b08cd201	176	$charinfo = charinfo(0xbe);
b08cd201	177
f5c9f3db	178	is($charinfo->{code}, '00BE', 'VULGAR FRACTION THREE QUARTERS');
	179	is($charinfo->{name}, 'VULGAR FRACTION THREE QUARTERS');
	180	is($charinfo->{category}, 'No');
	181	is($charinfo->{combining}, '0');
	182	is($charinfo->{bidi}, 'ON');
	183	is($charinfo->{decomposition}, '<fraction> 0033 2044 0034');
	184	is($charinfo->{decimal}, '');
	185	is($charinfo->{digit}, '');
	186	is($charinfo->{numeric}, '3/4');
	187	is($charinfo->{mirrored}, 'N');
	188	is($charinfo->{unicode10}, 'FRACTION THREE QUARTERS');
	189	is($charinfo->{comment}, '');
	190	is($charinfo->{upper}, '');
	191	is($charinfo->{lower}, '');
	192	is($charinfo->{title}, '');
	193	is($charinfo->{block}, 'Latin-1 Supplement');
	194	is($charinfo->{script}, undef);
10a6ecd2	195
55d7b906	196	use Unicode::UCD qw(charblocks charscripts);
10a6ecd2	197
b08cd201	198	my $charblocks = charblocks();
10a6ecd2	199
f5c9f3db	200	ok(exists $charblocks->{Thai}, 'Thai charblock exists');
	201	is($charblocks->{Thai}->[0]->[0], hex('0e00'));
	202	ok(!exists $charblocks->{PigLatin}, 'PigLatin charblock does not exist');
10a6ecd2	203
b08cd201	204	my $charscripts = charscripts();
10a6ecd2	205
f5c9f3db	206	ok(exists $charscripts->{Armenian}, 'Armenian charscript exists');
	207	is($charscripts->{Armenian}->[0]->[0], hex('0531'));
	208	ok(!exists $charscripts->{PigLatin}, 'PigLatin charscript does not exist');
10a6ecd2	209
	210	my $charscript;
	211
	212	$charscript = charscript("12ab");
f5c9f3db	213	is($charscript, 'Ethiopic', 'Ethiopic charscript');
10a6ecd2	214
10a6ecd2	215	$charscript = charscript("0x12ab");
f5c9f3db	216	is($charscript, 'Ethiopic');
10a6ecd2	217
10a6ecd2	218	$charscript = charscript("U+12ab");
f5c9f3db	219	is($charscript, 'Ethiopic');
10a6ecd2	220
	221	my $ranges;
	222
	223	$ranges = charscript('Ogham');
f5c9f3db	224	is($ranges->[0]->[0], hex('1681'), 'Ogham charscript');
f5c9f3db	225	is($ranges->[0]->[1], hex('169a'));
10a6ecd2	226
55d7b906	227	use Unicode::UCD qw(charinrange);
10a6ecd2	228
10a6ecd2	229	$ranges = charscript('Cherokee');
f5c9f3db	230	ok(!charinrange($ranges, "139f"), 'Cherokee charscript');
10a6ecd2	231	ok( charinrange($ranges, "13a0"));
	232	ok( charinrange($ranges, "13f4"));
	233	ok(!charinrange($ranges, "13f5"));
	234
822ebcc8	235	is(Unicode::UCD::UnicodeVersion, '3.2.0', 'UnicodeVersion');
b08cd201	236
55d7b906	237	use Unicode::UCD qw(compexcl);
b08cd201	238
f5c9f3db	239	ok(!compexcl(0x0100), 'compexcl');
b08cd201	240	ok( compexcl(0x0958));
b08cd201	241
55d7b906	242	use Unicode::UCD qw(casefold);
b08cd201	243
	244	my $casefold;
	245
	246	$casefold = casefold(0x41);
	247
	248	ok($casefold->{code} eq '0041' &&
	249	$casefold->{status} eq 'C' &&
f5c9f3db	250	$casefold->{mapping} eq '0061', 'casefold 0x41');
b08cd201	251
	252	$casefold = casefold(0xdf);
	253
	254	ok($casefold->{code} eq '00DF' &&
	255	$casefold->{status} eq 'F' &&
f5c9f3db	256	$casefold->{mapping} eq '0073 0073', 'casefold 0xDF');
b08cd201	257
	258	ok(!casefold(0x20));
	259
55d7b906	260	use Unicode::UCD qw(casespec);
b08cd201	261
	262	my $casespec;
	263
	264	ok(!casespec(0x41));
	265
	266	$casespec = casespec(0xdf);
	267
	268	ok($casespec->{code} eq '00DF' &&
	269	$casespec->{lower} eq '00DF' &&
	270	$casespec->{title} eq '0053 0073' &&
	271	$casespec->{upper} eq '0053 0053' &&
f5c9f3db	272	$casespec->{condition} eq undef, 'casespec 0xDF');
b08cd201	273
	274	$casespec = casespec(0x307);
	275
f499c386	276	ok($casespec->{az}->{code} eq '0307' &&
	277	$casespec->{az}->{lower} eq '' &&
	278	$casespec->{az}->{title} eq '0307' &&
	279	$casespec->{az}->{upper} eq '0307' &&
822ebcc8	280	$casespec->{az}->{condition} eq 'az After_Soft_Dotted',
f5c9f3db	281	'casespec 0x307');