[perl5.git] / lib / Unicode / UCD.t

use Unicode::UCD;

use Test;
use strict;

BEGIN { plan tests => 162 };

use Unicode::UCD 'charinfo';

my $charinfo;

$charinfo = charinfo(0x41);

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

$charinfo = charinfo(0x100);

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

# 0x0590 is in the Hebrew block but unused.

$charinfo = charinfo(0x590);

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

# 0x05d0 is in the Hebrew block and used.

$charinfo = charinfo(0x5d0);

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

# An open syllable in Hangul.

$charinfo = charinfo(0xAC00);

ok($charinfo->{code},           'AC00');
ok($charinfo->{name},           'HANGUL SYLLABLE GA');
ok($charinfo->{category},       'Lo');
ok($charinfo->{combining},      '0');
ok($charinfo->{bidi},           'L');
ok($charinfo->{decomposition},  '1100 1161');
ok($charinfo->{decimal},        '');
ok($charinfo->{digit},          '');
ok($charinfo->{numeric},        '');
ok($charinfo->{mirrored},       'N');
ok($charinfo->{unicode10},      '');
ok($charinfo->{comment},        '');
ok($charinfo->{upper},          '');
ok($charinfo->{lower},          '');
ok($charinfo->{title},          '');
ok($charinfo->{block},          'Hangul Syllables');
ok($charinfo->{script},         'Hangul');

# A closed syllable in Hangul.

$charinfo = charinfo(0xAE00);

ok($charinfo->{code},           'AE00');
ok($charinfo->{name},           'HANGUL SYLLABLE GEUL');
ok($charinfo->{category},       'Lo');
ok($charinfo->{combining},      '0');
ok($charinfo->{bidi},           'L');
ok($charinfo->{decomposition},  '1100 1173 11AF');
ok($charinfo->{decimal},        '');
ok($charinfo->{digit},          '');
ok($charinfo->{numeric},        '');
ok($charinfo->{mirrored},       'N');
ok($charinfo->{unicode10},      '');
ok($charinfo->{comment},        '');
ok($charinfo->{upper},          '');
ok($charinfo->{lower},          '');
ok($charinfo->{title},          '');
ok($charinfo->{block},          'Hangul Syllables');
ok($charinfo->{script},         'Hangul');

$charinfo = charinfo(0x1D400);

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

use Unicode::UCD qw(charblock charscript);

# 0x0590 is in the Hebrew block but unused.

ok(charblock(0x590),          'Hebrew');
ok(charscript(0x590),         undef);

$charinfo = charinfo(0xbe);

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

use Unicode::UCD qw(charblocks charscripts);

my $charblocks = charblocks();

ok(exists $charblocks->{Thai});
ok($charblocks->{Thai}->[0]->[0], hex('0e00'));
ok(!exists $charblocks->{PigLatin});

my $charscripts = charscripts();

ok(exists $charscripts->{Armenian});
ok($charscripts->{Armenian}->[0]->[0], hex('0531'));
ok(!exists $charscripts->{PigLatin});

my $charscript;

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

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

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

my $ranges;

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

use Unicode::UCD qw(charinrange);

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

ok(Unicode::UCD::UnicodeVersion, '3.1.1');

use Unicode::UCD qw(compexcl);

ok(!compexcl(0x0100));
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 = casefold(0xdf);

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

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 = 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_i NOT_MORE_ABOVE');
Commit	Line	Data
55d7b906	1	use Unicode::UCD;
561c79ed JH	2
	3	use Test;
	4	use strict;
	5
74f8133e	6	BEGIN { plan tests => 162 };
561c79ed	7
55d7b906	8	use Unicode::UCD 'charinfo';
561c79ed	9
b08cd201 JH	10	my $charinfo;
	11
	12	$charinfo = charinfo(0x41);
	13
	14	ok($charinfo->{code}, '0041');
	15	ok($charinfo->{name}, 'LATIN CAPITAL LETTER A');
	16	ok($charinfo->{category}, 'Lu');
	17	ok($charinfo->{combining}, '0');
	18	ok($charinfo->{bidi}, 'L');
	19	ok($charinfo->{decomposition}, '');
	20	ok($charinfo->{decimal}, '');
	21	ok($charinfo->{digit}, '');
	22	ok($charinfo->{numeric}, '');
	23	ok($charinfo->{mirrored}, 'N');
	24	ok($charinfo->{unicode10}, '');
	25	ok($charinfo->{comment}, '');
	26	ok($charinfo->{upper}, '');
	27	ok($charinfo->{lower}, '0061');
	28	ok($charinfo->{title}, '');
	29	ok($charinfo->{block}, 'Basic Latin');
	30	ok($charinfo->{script}, 'Latin');
	31
	32	$charinfo = charinfo(0x100);
	33
	34	ok($charinfo->{code}, '0100');
	35	ok($charinfo->{name}, 'LATIN CAPITAL LETTER A WITH MACRON');
	36	ok($charinfo->{category}, 'Lu');
	37	ok($charinfo->{combining}, '0');
	38	ok($charinfo->{bidi}, 'L');
	39	ok($charinfo->{decomposition}, '0041 0304');
	40	ok($charinfo->{decimal}, '');
	41	ok($charinfo->{digit}, '');
	42	ok($charinfo->{numeric}, '');
	43	ok($charinfo->{mirrored}, 'N');
	44	ok($charinfo->{unicode10}, 'LATIN CAPITAL LETTER A MACRON');
	45	ok($charinfo->{comment}, '');
	46	ok($charinfo->{upper}, '');
	47	ok($charinfo->{lower}, '0101');
	48	ok($charinfo->{title}, '');
	49	ok($charinfo->{block}, 'Latin Extended-A');
	50	ok($charinfo->{script}, 'Latin');
a196fbfd JH	51
a196fbfd JH	52	# 0x0590 is in the Hebrew block but unused.
561c79ed	53
b08cd201 JH	54	$charinfo = charinfo(0x590);
	55
	56	ok($charinfo->{code}, undef);
	57	ok($charinfo->{name}, undef);
	58	ok($charinfo->{category}, undef);
	59	ok($charinfo->{combining}, undef);
	60	ok($charinfo->{bidi}, undef);
	61	ok($charinfo->{decomposition}, undef);
	62	ok($charinfo->{decimal}, undef);
	63	ok($charinfo->{digit}, undef);
	64	ok($charinfo->{numeric}, undef);
	65	ok($charinfo->{mirrored}, undef);
	66	ok($charinfo->{unicode10}, undef);
	67	ok($charinfo->{comment}, undef);
	68	ok($charinfo->{upper}, undef);
	69	ok($charinfo->{lower}, undef);
	70	ok($charinfo->{title}, undef);
	71	ok($charinfo->{block}, undef);
	72	ok($charinfo->{script}, undef);
a196fbfd JH	73
a196fbfd JH	74	# 0x05d0 is in the Hebrew block and used.
561c79ed	75
b08cd201 JH	76	$charinfo = charinfo(0x5d0);
	77
	78	ok($charinfo->{code}, '05D0');
	79	ok($charinfo->{name}, 'HEBREW LETTER ALEF');
	80	ok($charinfo->{category}, 'Lo');
	81	ok($charinfo->{combining}, '0');
	82	ok($charinfo->{bidi}, 'R');
	83	ok($charinfo->{decomposition}, '');
	84	ok($charinfo->{decimal}, '');
	85	ok($charinfo->{digit}, '');
	86	ok($charinfo->{numeric}, '');
	87	ok($charinfo->{mirrored}, 'N');
	88	ok($charinfo->{unicode10}, '');
	89	ok($charinfo->{comment}, '');
	90	ok($charinfo->{upper}, '');
	91	ok($charinfo->{lower}, '');
	92	ok($charinfo->{title}, '');
	93	ok($charinfo->{block}, 'Hebrew');
	94	ok($charinfo->{script}, 'Hebrew');
561c79ed	95
74f8133e	96	# An open syllable in Hangul.
a6fa416b TS	97
	98	$charinfo = charinfo(0xAC00);
	99
	100	ok($charinfo->{code}, 'AC00');
	101	ok($charinfo->{name}, 'HANGUL SYLLABLE GA');
	102	ok($charinfo->{category}, 'Lo');
	103	ok($charinfo->{combining}, '0');
	104	ok($charinfo->{bidi}, 'L');
	105	ok($charinfo->{decomposition}, '1100 1161');
	106	ok($charinfo->{decimal}, '');
	107	ok($charinfo->{digit}, '');
	108	ok($charinfo->{numeric}, '');
	109	ok($charinfo->{mirrored}, 'N');
	110	ok($charinfo->{unicode10}, '');
	111	ok($charinfo->{comment}, '');
	112	ok($charinfo->{upper}, '');
	113	ok($charinfo->{lower}, '');
	114	ok($charinfo->{title}, '');
	115	ok($charinfo->{block}, 'Hangul Syllables');
	116	ok($charinfo->{script}, 'Hangul');
	117
74f8133e	118	# A closed syllable in Hangul.
a6fa416b TS	119
	120	$charinfo = charinfo(0xAE00);
	121
	122	ok($charinfo->{code}, 'AE00');
	123	ok($charinfo->{name}, 'HANGUL SYLLABLE GEUL');
	124	ok($charinfo->{category}, 'Lo');
	125	ok($charinfo->{combining}, '0');
	126	ok($charinfo->{bidi}, 'L');
	127	ok($charinfo->{decomposition}, '1100 1173 11AF');
	128	ok($charinfo->{decimal}, '');
	129	ok($charinfo->{digit}, '');
	130	ok($charinfo->{numeric}, '');
	131	ok($charinfo->{mirrored}, 'N');
	132	ok($charinfo->{unicode10}, '');
	133	ok($charinfo->{comment}, '');
	134	ok($charinfo->{upper}, '');
	135	ok($charinfo->{lower}, '');
	136	ok($charinfo->{title}, '');
	137	ok($charinfo->{block}, 'Hangul Syllables');
	138	ok($charinfo->{script}, 'Hangul');
	139
	140	$charinfo = charinfo(0x1D400);
	141
	142	ok($charinfo->{code}, '1D400');
	143	ok($charinfo->{name}, 'MATHEMATICAL BOLD CAPITAL A');
	144	ok($charinfo->{category}, 'Lu');
	145	ok($charinfo->{combining}, '0');
	146	ok($charinfo->{bidi}, 'L');
	147	ok($charinfo->{decomposition}, '<font> 0041');
	148	ok($charinfo->{decimal}, '');
	149	ok($charinfo->{digit}, '');
	150	ok($charinfo->{numeric}, '');
	151	ok($charinfo->{mirrored}, 'N');
	152	ok($charinfo->{unicode10}, '');
	153	ok($charinfo->{comment}, '');
	154	ok($charinfo->{upper}, '');
	155	ok($charinfo->{lower}, '');
	156	ok($charinfo->{title}, '');
	157	ok($charinfo->{block}, 'Mathematical Alphanumeric Symbols');
	158	ok($charinfo->{script}, undef);
	159
55d7b906	160	use Unicode::UCD qw(charblock charscript);
a196fbfd JH	161
a196fbfd JH	162	# 0x0590 is in the Hebrew block but unused.
561c79ed JH	163
561c79ed JH	164	ok(charblock(0x590), 'Hebrew');
a196fbfd	165	ok(charscript(0x590), undef);
561c79ed	166
b08cd201 JH	167	$charinfo = charinfo(0xbe);
	168
	169	ok($charinfo->{code}, '00BE');
	170	ok($charinfo->{name}, 'VULGAR FRACTION THREE QUARTERS');
	171	ok($charinfo->{category}, 'No');
	172	ok($charinfo->{combining}, '0');
	173	ok($charinfo->{bidi}, 'ON');
	174	ok($charinfo->{decomposition}, '<fraction> 0033 2044 0034');
	175	ok($charinfo->{decimal}, '');
	176	ok($charinfo->{digit}, '');
	177	ok($charinfo->{numeric}, '3/4');
	178	ok($charinfo->{mirrored}, 'N');
	179	ok($charinfo->{unicode10}, 'FRACTION THREE QUARTERS');
	180	ok($charinfo->{comment}, '');
	181	ok($charinfo->{upper}, '');
	182	ok($charinfo->{lower}, '');
	183	ok($charinfo->{title}, '');
	184	ok($charinfo->{block}, 'Latin-1 Supplement');
	185	ok($charinfo->{script}, undef);
10a6ecd2	186
55d7b906	187	use Unicode::UCD qw(charblocks charscripts);
10a6ecd2	188
b08cd201	189	my $charblocks = charblocks();
10a6ecd2	190
b08cd201 JH	191	ok(exists $charblocks->{Thai});
	192	ok($charblocks->{Thai}->[0]->[0], hex('0e00'));
	193	ok(!exists $charblocks->{PigLatin});
10a6ecd2	194
b08cd201	195	my $charscripts = charscripts();
10a6ecd2	196
b08cd201 JH	197	ok(exists $charscripts->{Armenian});
	198	ok($charscripts->{Armenian}->[0]->[0], hex('0531'));
	199	ok(!exists $charscripts->{PigLatin});
10a6ecd2 JH	200
	201	my $charscript;
	202
	203	$charscript = charscript("12ab");
	204	ok($charscript, 'Ethiopic');
	205
	206	$charscript = charscript("0x12ab");
	207	ok($charscript, 'Ethiopic');
	208
	209	$charscript = charscript("U+12ab");
	210	ok($charscript, 'Ethiopic');
	211
	212	my $ranges;
	213
	214	$ranges = charscript('Ogham');
	215	ok($ranges->[0]->[0], hex('1681'));
	216	ok($ranges->[0]->[1], hex('169a'));
	217
55d7b906	218	use Unicode::UCD qw(charinrange);
10a6ecd2 JH	219
	220	$ranges = charscript('Cherokee');
	221	ok(!charinrange($ranges, "139f"));
	222	ok( charinrange($ranges, "13a0"));
	223	ok( charinrange($ranges, "13f4"));
	224	ok(!charinrange($ranges, "13f5"));
	225
f499c386	226	ok(Unicode::UCD::UnicodeVersion, '3.1.1');
b08cd201	227
55d7b906	228	use Unicode::UCD qw(compexcl);
b08cd201 JH	229
	230	ok(!compexcl(0x0100));
	231	ok( compexcl(0x0958));
	232
55d7b906	233	use Unicode::UCD qw(casefold);
b08cd201 JH	234
	235	my $casefold;
	236
	237	$casefold = casefold(0x41);
	238
	239	ok($casefold->{code} eq '0041' &&
	240	$casefold->{status} eq 'C' &&
	241	$casefold->{mapping} eq '0061');
	242
	243	$casefold = casefold(0xdf);
	244
	245	ok($casefold->{code} eq '00DF' &&
	246	$casefold->{status} eq 'F' &&
	247	$casefold->{mapping} eq '0073 0073');
	248
	249	ok(!casefold(0x20));
	250
55d7b906	251	use Unicode::UCD qw(casespec);
b08cd201 JH	252
	253	my $casespec;
	254
	255	ok(!casespec(0x41));
	256
	257	$casespec = casespec(0xdf);
	258
	259	ok($casespec->{code} eq '00DF' &&
	260	$casespec->{lower} eq '00DF' &&
	261	$casespec->{title} eq '0053 0073' &&
	262	$casespec->{upper} eq '0053 0053' &&
	263	$casespec->{condition} eq undef);
	264
	265	$casespec = casespec(0x307);
	266
f499c386 JH	267	ok($casespec->{az}->{code} eq '0307' &&
	268	$casespec->{az}->{lower} eq '' &&
	269	$casespec->{az}->{title} eq '0307' &&
	270	$casespec->{az}->{upper} eq '0307' &&
	271	$casespec->{az}->{condition} eq 'az AFTER_i NOT_MORE_ABOVE');