1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
|
BEGIN {
unless ("A" eq pack('U', 0x41)) {
print "1..0 # Unicode::Collate " .
"cannot stringify a Unicode code point\n";
exit 0;
}
if ($ENV{PERL_CORE}) {
chdir('t') if -d 't';
@INC = $^O eq 'MacOS' ? qw(::lib) : qw(../lib);
}
}
use Test;
BEGIN { plan tests => 41 };
use strict;
use warnings;
use Unicode::Collate;
ok(1);
#########################
my $trad = Unicode::Collate->new(
table => 'keys.txt',
normalization => undef,
ignoreName => qr/HANGUL|HIRAGANA|KATAKANA|BOPOMOFO/,
level => 3,
entry => << 'ENTRIES',
0063 0068 ; [.0A3F.0020.0002.0063] % "ch" in traditional Spanish
0043 0068 ; [.0A3F.0020.0007.0043] # "Ch" in traditional Spanish
0043 0048 ; [.0A3F.0020.0008.0043] # "CH" in traditional Spanish
ENTRIES
);
# 0063 ; [.0A3D.0020.0002.0063] # LATIN SMALL LETTER C
# 0064 ; [.0A49.0020.0002.0064] # LATIN SMALL LETTER D
##### 2..3
ok(
join(':', $trad->sort( qw/ acha aca ada acia acka / ) ),
join(':', qw/ aca acia acka acha ada / ),
);
ok(
join(':', $trad->sort( qw/ ACHA ACA ADA ACIA ACKA / ) ),
join(':', qw/ ACA ACIA ACKA ACHA ADA / ),
);
##### 4..7
ok($trad->gt("ocho", "oc\cAho")); # UCA v14
ok($trad->gt("ocho", "oc\0\cA\0\cBho")); # UCA v14
ok($trad->eq("-", ""));
ok($trad->gt("ocho", "oc-ho"));
##### 8..11
$trad->change(UCA_Version => 9);
ok($trad->eq("ocho", "oc\cAho")); # UCA v9
ok($trad->eq("ocho", "oc\0\cA\0\cBho")); # UCA v9
ok($trad->eq("-", ""));
ok($trad->gt("ocho", "oc-ho"));
##### 12..15
$trad->change(UCA_Version => 8);
ok($trad->gt("ocho", "oc\cAho"));
ok($trad->gt("ocho", "oc\0\cA\0\cBho"));
ok($trad->eq("-", ""));
ok($trad->gt("ocho", "oc-ho"));
##### 16..19
$trad->change(UCA_Version => 9);
my $hiragana = "\x{3042}\x{3044}";
my $katakana = "\x{30A2}\x{30A4}";
# HIRAGANA and KATAKANA are ignorable via ignoreName
ok($trad->eq($hiragana, ""));
ok($trad->eq("", $katakana));
ok($trad->eq($hiragana, $katakana));
ok($trad->eq($katakana, $hiragana));
##### 20..31
# According to Conformance Test (UCA_Version == 9 or 11),
# a L3-ignorable is treated as a completely ignorable.
my $L3ignorable = Unicode::Collate->new(
alternate => 'Non-ignorable',
level => 3,
table => undef,
normalization => undef,
UCA_Version => 9,
entry => <<'ENTRIES',
0000 ; [.0000.0000.0000.0000] # [0000] NULL (in 6429)
0001 ; [.0000.0000.0000.0000] # [0001] START OF HEADING (in 6429)
0591 ; [.0000.0000.0000.0591] # HEBREW ACCENT ETNAHTA
1D165 ; [.0000.0000.0000.1D165] # MUSICAL SYMBOL COMBINING STEM
0021 ; [*024B.0020.0002.0021] # EXCLAMATION MARK
09BE ; [.114E.0020.0002.09BE] # BENGALI VOWEL SIGN AA
09C7 ; [.1157.0020.0002.09C7] # BENGALI VOWEL SIGN E
09CB ; [.1159.0020.0002.09CB] # BENGALI VOWEL SIGN O
09C7 09BE ; [.1159.0020.0002.09CB] # BENGALI VOWEL SIGN O
1D1B9 ; [*098A.0020.0002.1D1B9] # MUSICAL SYMBOL SEMIBREVIS WHITE
1D1BA ; [*098B.0020.0002.1D1BA] # MUSICAL SYMBOL SEMIBREVIS BLACK
1D1BB ; [*098A.0020.0002.1D1B9][.0000.0000.0000.1D165] # M.S. MINIMA
1D1BC ; [*098B.0020.0002.1D1BA][.0000.0000.0000.1D165] # M.S. MINIMA BLACK
ENTRIES
);
ok($L3ignorable->lt("\cA", "!"));
ok($L3ignorable->lt("\x{591}", "!"));
ok($L3ignorable->eq("\cA", "\x{591}"));
ok($L3ignorable->eq("\x{09C7}\x{09BE}A", "\x{09C7}\cA\x{09BE}A"));
ok($L3ignorable->eq("\x{09C7}\x{09BE}A", "\x{09C7}\x{0591}\x{09BE}A"));
ok($L3ignorable->eq("\x{09C7}\x{09BE}A", "\x{09C7}\x{1D165}\x{09BE}A"));
ok($L3ignorable->eq("\x{09C7}\x{09BE}A", "\x{09CB}A"));
ok($L3ignorable->lt("\x{1D1BB}", "\x{1D1BC}"));
ok($L3ignorable->eq("\x{1D1BB}", "\x{1D1B9}"));
ok($L3ignorable->eq("\x{1D1BC}", "\x{1D1BA}"));
ok($L3ignorable->eq("\x{1D1BB}", "\x{1D1B9}\x{1D165}"));
ok($L3ignorable->eq("\x{1D1BC}", "\x{1D1BA}\x{1D165}"));
##### 32..41
my $c = Unicode::Collate->new(
table => 'keys.txt',
normalization => undef,
level => 1,
UCA_Version => 14,
entry => << 'ENTRIES',
034F ; [.0000.0000.0000.034F] # COMBINING GRAPHEME JOINER
0063 0068 ; [.0A3F.0020.0002.0063] % "ch" in traditional Spanish
0043 0068 ; [.0A3F.0020.0007.0043] # "Ch" in traditional Spanish
0043 0048 ; [.0A3F.0020.0008.0043] # "CH" in traditional Spanish
ENTRIES
);
# 0063 ; [.0A3D.0020.0002.0063] # LATIN SMALL LETTER C
# 0064 ; [.0A49.0020.0002.0064] # LATIN SMALL LETTER D
ok($c->gt("ocho", "oc\x00\x00ho"));
ok($c->gt("ocho", "oc\cAho"));
ok($c->gt("ocho", "oc\x{034F}ho"));
ok($c->gt("ocio", "oc\x{034F}ho"));
ok($c->lt("ocgo", "oc\x{034F}ho"));
ok($c->lt("oceo", "oc\x{034F}ho"));
ok($c->viewSortKey("ocho"), "[0B4B 0A3F 0B4B | | |]");
ok($c->viewSortKey("oc\x00\x00ho"), "[0B4B 0A3D 0AB9 0B4B | | |]");
ok($c->viewSortKey("oc\cAho"), "[0B4B 0A3D 0AB9 0B4B | | |]");
ok($c->viewSortKey("oc\x{034F}ho"), "[0B4B 0A3D 0AB9 0B4B | | |]");
|
