[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;

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-AC00');
ok($charinfo->{category},       'Lo');
ok($charinfo->{combining},      '0');
ok($charinfo->{bidi},           'L');
ok($charinfo->{decomposition},  undef);
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-AE00');
ok($charinfo->{category},       'Lo');
ok($charinfo->{combining},      '0');
ok($charinfo->{bidi},           'L');
ok($charinfo->{decomposition},  undef);
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
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;
8b731da2	12	use Test;
8b731da2	13
74f8133e	14	BEGIN { plan tests => 162 };
561c79ed	15
55d7b906	16	use Unicode::UCD 'charinfo';
561c79ed	17
b08cd201	18	my $charinfo;
	19
	20	$charinfo = charinfo(0x41);
	21
	22	ok($charinfo->{code}, '0041');
	23	ok($charinfo->{name}, 'LATIN CAPITAL LETTER A');
	24	ok($charinfo->{category}, 'Lu');
	25	ok($charinfo->{combining}, '0');
	26	ok($charinfo->{bidi}, 'L');
	27	ok($charinfo->{decomposition}, '');
	28	ok($charinfo->{decimal}, '');
	29	ok($charinfo->{digit}, '');
	30	ok($charinfo->{numeric}, '');
	31	ok($charinfo->{mirrored}, 'N');
	32	ok($charinfo->{unicode10}, '');
	33	ok($charinfo->{comment}, '');
	34	ok($charinfo->{upper}, '');
	35	ok($charinfo->{lower}, '0061');
	36	ok($charinfo->{title}, '');
	37	ok($charinfo->{block}, 'Basic Latin');
	38	ok($charinfo->{script}, 'Latin');
	39
	40	$charinfo = charinfo(0x100);
	41
	42	ok($charinfo->{code}, '0100');
	43	ok($charinfo->{name}, 'LATIN CAPITAL LETTER A WITH MACRON');
	44	ok($charinfo->{category}, 'Lu');
	45	ok($charinfo->{combining}, '0');
	46	ok($charinfo->{bidi}, 'L');
	47	ok($charinfo->{decomposition}, '0041 0304');
	48	ok($charinfo->{decimal}, '');
	49	ok($charinfo->{digit}, '');
	50	ok($charinfo->{numeric}, '');
	51	ok($charinfo->{mirrored}, 'N');
	52	ok($charinfo->{unicode10}, 'LATIN CAPITAL LETTER A MACRON');
	53	ok($charinfo->{comment}, '');
	54	ok($charinfo->{upper}, '');
	55	ok($charinfo->{lower}, '0101');
	56	ok($charinfo->{title}, '');
	57	ok($charinfo->{block}, 'Latin Extended-A');
	58	ok($charinfo->{script}, 'Latin');
a196fbfd	59
a196fbfd	60	# 0x0590 is in the Hebrew block but unused.
561c79ed	61
b08cd201	62	$charinfo = charinfo(0x590);
	63
	64	ok($charinfo->{code}, undef);
	65	ok($charinfo->{name}, undef);
	66	ok($charinfo->{category}, undef);
	67	ok($charinfo->{combining}, undef);
	68	ok($charinfo->{bidi}, undef);
	69	ok($charinfo->{decomposition}, undef);
	70	ok($charinfo->{decimal}, undef);
	71	ok($charinfo->{digit}, undef);
	72	ok($charinfo->{numeric}, undef);
	73	ok($charinfo->{mirrored}, undef);
	74	ok($charinfo->{unicode10}, undef);
	75	ok($charinfo->{comment}, undef);
	76	ok($charinfo->{upper}, undef);
	77	ok($charinfo->{lower}, undef);
	78	ok($charinfo->{title}, undef);
	79	ok($charinfo->{block}, undef);
	80	ok($charinfo->{script}, undef);
a196fbfd	81
a196fbfd	82	# 0x05d0 is in the Hebrew block and used.
561c79ed	83
b08cd201	84	$charinfo = charinfo(0x5d0);
	85
	86	ok($charinfo->{code}, '05D0');
	87	ok($charinfo->{name}, 'HEBREW LETTER ALEF');
	88	ok($charinfo->{category}, 'Lo');
	89	ok($charinfo->{combining}, '0');
	90	ok($charinfo->{bidi}, 'R');
	91	ok($charinfo->{decomposition}, '');
	92	ok($charinfo->{decimal}, '');
	93	ok($charinfo->{digit}, '');
	94	ok($charinfo->{numeric}, '');
	95	ok($charinfo->{mirrored}, 'N');
	96	ok($charinfo->{unicode10}, '');
	97	ok($charinfo->{comment}, '');
	98	ok($charinfo->{upper}, '');
	99	ok($charinfo->{lower}, '');
	100	ok($charinfo->{title}, '');
	101	ok($charinfo->{block}, 'Hebrew');
	102	ok($charinfo->{script}, 'Hebrew');
561c79ed	103
74f8133e	104	# An open syllable in Hangul.
a6fa416b	105
	106	$charinfo = charinfo(0xAC00);
	107
	108	ok($charinfo->{code}, 'AC00');
ac5ea531	109	ok($charinfo->{name}, 'HANGUL SYLLABLE-AC00');
a6fa416b	110	ok($charinfo->{category}, 'Lo');
	111	ok($charinfo->{combining}, '0');
	112	ok($charinfo->{bidi}, 'L');
ac5ea531	113	ok($charinfo->{decomposition}, undef);
a6fa416b	114	ok($charinfo->{decimal}, '');
	115	ok($charinfo->{digit}, '');
	116	ok($charinfo->{numeric}, '');
	117	ok($charinfo->{mirrored}, 'N');
	118	ok($charinfo->{unicode10}, '');
	119	ok($charinfo->{comment}, '');
	120	ok($charinfo->{upper}, '');
	121	ok($charinfo->{lower}, '');
	122	ok($charinfo->{title}, '');
	123	ok($charinfo->{block}, 'Hangul Syllables');
	124	ok($charinfo->{script}, 'Hangul');
	125
74f8133e	126	# A closed syllable in Hangul.
a6fa416b	127
	128	$charinfo = charinfo(0xAE00);
	129
	130	ok($charinfo->{code}, 'AE00');
ac5ea531	131	ok($charinfo->{name}, 'HANGUL SYLLABLE-AE00');
a6fa416b	132	ok($charinfo->{category}, 'Lo');
	133	ok($charinfo->{combining}, '0');
	134	ok($charinfo->{bidi}, 'L');
ac5ea531	135	ok($charinfo->{decomposition}, undef);
a6fa416b	136	ok($charinfo->{decimal}, '');
	137	ok($charinfo->{digit}, '');
	138	ok($charinfo->{numeric}, '');
	139	ok($charinfo->{mirrored}, 'N');
	140	ok($charinfo->{unicode10}, '');
	141	ok($charinfo->{comment}, '');
	142	ok($charinfo->{upper}, '');
	143	ok($charinfo->{lower}, '');
	144	ok($charinfo->{title}, '');
	145	ok($charinfo->{block}, 'Hangul Syllables');
	146	ok($charinfo->{script}, 'Hangul');
	147
	148	$charinfo = charinfo(0x1D400);
	149
	150	ok($charinfo->{code}, '1D400');
	151	ok($charinfo->{name}, 'MATHEMATICAL BOLD CAPITAL A');
	152	ok($charinfo->{category}, 'Lu');
	153	ok($charinfo->{combining}, '0');
	154	ok($charinfo->{bidi}, 'L');
	155	ok($charinfo->{decomposition}, '<font> 0041');
	156	ok($charinfo->{decimal}, '');
	157	ok($charinfo->{digit}, '');
	158	ok($charinfo->{numeric}, '');
	159	ok($charinfo->{mirrored}, 'N');
	160	ok($charinfo->{unicode10}, '');
	161	ok($charinfo->{comment}, '');
	162	ok($charinfo->{upper}, '');
	163	ok($charinfo->{lower}, '');
	164	ok($charinfo->{title}, '');
	165	ok($charinfo->{block}, 'Mathematical Alphanumeric Symbols');
	166	ok($charinfo->{script}, undef);
	167
55d7b906	168	use Unicode::UCD qw(charblock charscript);
a196fbfd	169
a196fbfd	170	# 0x0590 is in the Hebrew block but unused.
561c79ed	171
561c79ed	172	ok(charblock(0x590), 'Hebrew');
a196fbfd	173	ok(charscript(0x590), undef);
561c79ed	174
b08cd201	175	$charinfo = charinfo(0xbe);
	176
	177	ok($charinfo->{code}, '00BE');
	178	ok($charinfo->{name}, 'VULGAR FRACTION THREE QUARTERS');
	179	ok($charinfo->{category}, 'No');
	180	ok($charinfo->{combining}, '0');
	181	ok($charinfo->{bidi}, 'ON');
	182	ok($charinfo->{decomposition}, '<fraction> 0033 2044 0034');
	183	ok($charinfo->{decimal}, '');
	184	ok($charinfo->{digit}, '');
	185	ok($charinfo->{numeric}, '3/4');
	186	ok($charinfo->{mirrored}, 'N');
	187	ok($charinfo->{unicode10}, 'FRACTION THREE QUARTERS');
	188	ok($charinfo->{comment}, '');
	189	ok($charinfo->{upper}, '');
	190	ok($charinfo->{lower}, '');
	191	ok($charinfo->{title}, '');
	192	ok($charinfo->{block}, 'Latin-1 Supplement');
	193	ok($charinfo->{script}, undef);
10a6ecd2	194
55d7b906	195	use Unicode::UCD qw(charblocks charscripts);
10a6ecd2	196
b08cd201	197	my $charblocks = charblocks();
10a6ecd2	198
b08cd201	199	ok(exists $charblocks->{Thai});
	200	ok($charblocks->{Thai}->[0]->[0], hex('0e00'));
	201	ok(!exists $charblocks->{PigLatin});
10a6ecd2	202
b08cd201	203	my $charscripts = charscripts();
10a6ecd2	204
b08cd201	205	ok(exists $charscripts->{Armenian});
	206	ok($charscripts->{Armenian}->[0]->[0], hex('0531'));
	207	ok(!exists $charscripts->{PigLatin});
10a6ecd2	208
	209	my $charscript;
	210
	211	$charscript = charscript("12ab");
	212	ok($charscript, 'Ethiopic');
	213
	214	$charscript = charscript("0x12ab");
	215	ok($charscript, 'Ethiopic');
	216
	217	$charscript = charscript("U+12ab");
	218	ok($charscript, 'Ethiopic');
	219
	220	my $ranges;
	221
	222	$ranges = charscript('Ogham');
	223	ok($ranges->[0]->[0], hex('1681'));
	224	ok($ranges->[0]->[1], hex('169a'));
	225
55d7b906	226	use Unicode::UCD qw(charinrange);
10a6ecd2	227
	228	$ranges = charscript('Cherokee');
	229	ok(!charinrange($ranges, "139f"));
	230	ok( charinrange($ranges, "13a0"));
	231	ok( charinrange($ranges, "13f4"));
	232	ok(!charinrange($ranges, "13f5"));
	233
f499c386	234	ok(Unicode::UCD::UnicodeVersion, '3.1.1');
b08cd201	235
55d7b906	236	use Unicode::UCD qw(compexcl);
b08cd201	237
	238	ok(!compexcl(0x0100));
	239	ok( compexcl(0x0958));
	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' &&
	249	$casefold->{mapping} eq '0061');
	250
	251	$casefold = casefold(0xdf);
	252
	253	ok($casefold->{code} eq '00DF' &&
	254	$casefold->{status} eq 'F' &&
	255	$casefold->{mapping} eq '0073 0073');
	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' &&
	271	$casespec->{condition} eq undef);
	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' &&
	279	$casespec->{az}->{condition} eq 'az AFTER_i NOT_MORE_ABOVE');