Commit | Line | Data |
25a47338 |
1 | #!perl -w |
8b731da2 |
2 | BEGIN { |
3 | if (ord("A") == 193) { |
4 | print "1..0 # Skip: EBCDIC\n"; |
5 | exit 0; |
6 | } |
a778afa6 |
7 | chdir 't' if -d 't'; |
8 | @INC = '../lib'; |
e69a2255 |
9 | @INC = "::lib" if $^O eq 'MacOS'; # module parses @INC itself |
25a47338 |
10 | require Config; import Config; |
11 | if ($Config{'extensions'} !~ /\bStorable\b/) { |
12 | print "1..0 # Skip: Storable was not built; Unicode::UCD uses Storable\n"; |
13 | exit 0; |
14 | } |
8b731da2 |
15 | } |
16 | |
a778afa6 |
17 | use strict; |
18 | use Unicode::UCD; |
f5c9f3db |
19 | use Test::More; |
8b731da2 |
20 | |
ea508aee |
21 | BEGIN { plan tests => 194 }; |
561c79ed |
22 | |
55d7b906 |
23 | use Unicode::UCD 'charinfo'; |
561c79ed |
24 | |
b08cd201 |
25 | my $charinfo; |
26 | |
27 | $charinfo = charinfo(0x41); |
28 | |
f5c9f3db |
29 | is($charinfo->{code}, '0041', 'LATIN CAPITAL LETTER A'); |
30 | is($charinfo->{name}, 'LATIN CAPITAL LETTER A'); |
31 | is($charinfo->{category}, 'Lu'); |
32 | is($charinfo->{combining}, '0'); |
33 | is($charinfo->{bidi}, 'L'); |
34 | is($charinfo->{decomposition}, ''); |
35 | is($charinfo->{decimal}, ''); |
36 | is($charinfo->{digit}, ''); |
37 | is($charinfo->{numeric}, ''); |
38 | is($charinfo->{mirrored}, 'N'); |
39 | is($charinfo->{unicode10}, ''); |
40 | is($charinfo->{comment}, ''); |
41 | is($charinfo->{upper}, ''); |
42 | is($charinfo->{lower}, '0061'); |
43 | is($charinfo->{title}, ''); |
44 | is($charinfo->{block}, 'Basic Latin'); |
45 | is($charinfo->{script}, 'Latin'); |
b08cd201 |
46 | |
47 | $charinfo = charinfo(0x100); |
48 | |
f5c9f3db |
49 | is($charinfo->{code}, '0100', 'LATIN CAPITAL LETTER A WITH MACRON'); |
50 | is($charinfo->{name}, 'LATIN CAPITAL LETTER A WITH MACRON'); |
51 | is($charinfo->{category}, 'Lu'); |
52 | is($charinfo->{combining}, '0'); |
53 | is($charinfo->{bidi}, 'L'); |
54 | is($charinfo->{decomposition}, '0041 0304'); |
55 | is($charinfo->{decimal}, ''); |
56 | is($charinfo->{digit}, ''); |
57 | is($charinfo->{numeric}, ''); |
58 | is($charinfo->{mirrored}, 'N'); |
59 | is($charinfo->{unicode10}, 'LATIN CAPITAL LETTER A MACRON'); |
60 | is($charinfo->{comment}, ''); |
61 | is($charinfo->{upper}, ''); |
62 | is($charinfo->{lower}, '0101'); |
63 | is($charinfo->{title}, ''); |
64 | is($charinfo->{block}, 'Latin Extended-A'); |
65 | is($charinfo->{script}, 'Latin'); |
a196fbfd |
66 | |
67 | # 0x0590 is in the Hebrew block but unused. |
561c79ed |
68 | |
b08cd201 |
69 | $charinfo = charinfo(0x590); |
70 | |
f5c9f3db |
71 | is($charinfo->{code}, undef, '0x0590 - unused Hebrew'); |
72 | is($charinfo->{name}, undef); |
73 | is($charinfo->{category}, undef); |
74 | is($charinfo->{combining}, undef); |
75 | is($charinfo->{bidi}, undef); |
76 | is($charinfo->{decomposition}, undef); |
77 | is($charinfo->{decimal}, undef); |
78 | is($charinfo->{digit}, undef); |
79 | is($charinfo->{numeric}, undef); |
80 | is($charinfo->{mirrored}, undef); |
81 | is($charinfo->{unicode10}, undef); |
82 | is($charinfo->{comment}, undef); |
83 | is($charinfo->{upper}, undef); |
84 | is($charinfo->{lower}, undef); |
85 | is($charinfo->{title}, undef); |
86 | is($charinfo->{block}, undef); |
87 | is($charinfo->{script}, undef); |
a196fbfd |
88 | |
89 | # 0x05d0 is in the Hebrew block and used. |
561c79ed |
90 | |
b08cd201 |
91 | $charinfo = charinfo(0x5d0); |
92 | |
f5c9f3db |
93 | is($charinfo->{code}, '05D0', '05D0 - used Hebrew'); |
94 | is($charinfo->{name}, 'HEBREW LETTER ALEF'); |
95 | is($charinfo->{category}, 'Lo'); |
96 | is($charinfo->{combining}, '0'); |
97 | is($charinfo->{bidi}, 'R'); |
98 | is($charinfo->{decomposition}, ''); |
99 | is($charinfo->{decimal}, ''); |
100 | is($charinfo->{digit}, ''); |
101 | is($charinfo->{numeric}, ''); |
102 | is($charinfo->{mirrored}, 'N'); |
103 | is($charinfo->{unicode10}, ''); |
104 | is($charinfo->{comment}, ''); |
105 | is($charinfo->{upper}, ''); |
106 | is($charinfo->{lower}, ''); |
107 | is($charinfo->{title}, ''); |
108 | is($charinfo->{block}, 'Hebrew'); |
109 | is($charinfo->{script}, 'Hebrew'); |
561c79ed |
110 | |
74f8133e |
111 | # An open syllable in Hangul. |
a6fa416b |
112 | |
113 | $charinfo = charinfo(0xAC00); |
114 | |
f5c9f3db |
115 | is($charinfo->{code}, 'AC00', 'HANGUL SYLLABLE-AC00'); |
116 | is($charinfo->{name}, 'HANGUL SYLLABLE-AC00'); |
117 | is($charinfo->{category}, 'Lo'); |
118 | is($charinfo->{combining}, '0'); |
119 | is($charinfo->{bidi}, 'L'); |
120 | is($charinfo->{decomposition}, undef); |
121 | is($charinfo->{decimal}, ''); |
122 | is($charinfo->{digit}, ''); |
123 | is($charinfo->{numeric}, ''); |
124 | is($charinfo->{mirrored}, 'N'); |
125 | is($charinfo->{unicode10}, ''); |
126 | is($charinfo->{comment}, ''); |
127 | is($charinfo->{upper}, ''); |
128 | is($charinfo->{lower}, ''); |
129 | is($charinfo->{title}, ''); |
130 | is($charinfo->{block}, 'Hangul Syllables'); |
131 | is($charinfo->{script}, 'Hangul'); |
a6fa416b |
132 | |
74f8133e |
133 | # A closed syllable in Hangul. |
a6fa416b |
134 | |
135 | $charinfo = charinfo(0xAE00); |
136 | |
f5c9f3db |
137 | is($charinfo->{code}, 'AE00', 'HANGUL SYLLABLE-AE00'); |
138 | is($charinfo->{name}, 'HANGUL SYLLABLE-AE00'); |
139 | is($charinfo->{category}, 'Lo'); |
140 | is($charinfo->{combining}, '0'); |
141 | is($charinfo->{bidi}, 'L'); |
142 | is($charinfo->{decomposition}, undef); |
143 | is($charinfo->{decimal}, ''); |
144 | is($charinfo->{digit}, ''); |
145 | is($charinfo->{numeric}, ''); |
146 | is($charinfo->{mirrored}, 'N'); |
147 | is($charinfo->{unicode10}, ''); |
148 | is($charinfo->{comment}, ''); |
149 | is($charinfo->{upper}, ''); |
150 | is($charinfo->{lower}, ''); |
151 | is($charinfo->{title}, ''); |
152 | is($charinfo->{block}, 'Hangul Syllables'); |
153 | is($charinfo->{script}, 'Hangul'); |
a6fa416b |
154 | |
155 | $charinfo = charinfo(0x1D400); |
156 | |
f5c9f3db |
157 | is($charinfo->{code}, '1D400', 'MATHEMATICAL BOLD CAPITAL A'); |
158 | is($charinfo->{name}, 'MATHEMATICAL BOLD CAPITAL A'); |
159 | is($charinfo->{category}, 'Lu'); |
160 | is($charinfo->{combining}, '0'); |
161 | is($charinfo->{bidi}, 'L'); |
162 | is($charinfo->{decomposition}, '<font> 0041'); |
163 | is($charinfo->{decimal}, ''); |
164 | is($charinfo->{digit}, ''); |
165 | is($charinfo->{numeric}, ''); |
166 | is($charinfo->{mirrored}, 'N'); |
167 | is($charinfo->{unicode10}, ''); |
168 | is($charinfo->{comment}, ''); |
169 | is($charinfo->{upper}, ''); |
170 | is($charinfo->{lower}, ''); |
171 | is($charinfo->{title}, ''); |
172 | is($charinfo->{block}, 'Mathematical Alphanumeric Symbols'); |
7be0dac3 |
173 | is($charinfo->{script}, 'Common'); |
a6fa416b |
174 | |
55d7b906 |
175 | use Unicode::UCD qw(charblock charscript); |
a196fbfd |
176 | |
177 | # 0x0590 is in the Hebrew block but unused. |
561c79ed |
178 | |
f5c9f3db |
179 | is(charblock(0x590), 'Hebrew', '0x0590 - Hebrew unused charblock'); |
180 | is(charscript(0x590), undef, '0x0590 - Hebrew unused charscript'); |
561c79ed |
181 | |
b08cd201 |
182 | $charinfo = charinfo(0xbe); |
183 | |
f5c9f3db |
184 | is($charinfo->{code}, '00BE', 'VULGAR FRACTION THREE QUARTERS'); |
185 | is($charinfo->{name}, 'VULGAR FRACTION THREE QUARTERS'); |
186 | is($charinfo->{category}, 'No'); |
187 | is($charinfo->{combining}, '0'); |
188 | is($charinfo->{bidi}, 'ON'); |
189 | is($charinfo->{decomposition}, '<fraction> 0033 2044 0034'); |
190 | is($charinfo->{decimal}, ''); |
191 | is($charinfo->{digit}, ''); |
192 | is($charinfo->{numeric}, '3/4'); |
193 | is($charinfo->{mirrored}, 'N'); |
194 | is($charinfo->{unicode10}, 'FRACTION THREE QUARTERS'); |
195 | is($charinfo->{comment}, ''); |
196 | is($charinfo->{upper}, ''); |
197 | is($charinfo->{lower}, ''); |
198 | is($charinfo->{title}, ''); |
199 | is($charinfo->{block}, 'Latin-1 Supplement'); |
7be0dac3 |
200 | is($charinfo->{script}, 'Common'); |
10a6ecd2 |
201 | |
55d7b906 |
202 | use Unicode::UCD qw(charblocks charscripts); |
10a6ecd2 |
203 | |
b08cd201 |
204 | my $charblocks = charblocks(); |
10a6ecd2 |
205 | |
f5c9f3db |
206 | ok(exists $charblocks->{Thai}, 'Thai charblock exists'); |
207 | is($charblocks->{Thai}->[0]->[0], hex('0e00')); |
208 | ok(!exists $charblocks->{PigLatin}, 'PigLatin charblock does not exist'); |
10a6ecd2 |
209 | |
b08cd201 |
210 | my $charscripts = charscripts(); |
10a6ecd2 |
211 | |
f5c9f3db |
212 | ok(exists $charscripts->{Armenian}, 'Armenian charscript exists'); |
213 | is($charscripts->{Armenian}->[0]->[0], hex('0531')); |
214 | ok(!exists $charscripts->{PigLatin}, 'PigLatin charscript does not exist'); |
10a6ecd2 |
215 | |
216 | my $charscript; |
217 | |
218 | $charscript = charscript("12ab"); |
f5c9f3db |
219 | is($charscript, 'Ethiopic', 'Ethiopic charscript'); |
10a6ecd2 |
220 | |
221 | $charscript = charscript("0x12ab"); |
f5c9f3db |
222 | is($charscript, 'Ethiopic'); |
10a6ecd2 |
223 | |
224 | $charscript = charscript("U+12ab"); |
f5c9f3db |
225 | is($charscript, 'Ethiopic'); |
10a6ecd2 |
226 | |
227 | my $ranges; |
228 | |
229 | $ranges = charscript('Ogham'); |
7be0dac3 |
230 | is($ranges->[1]->[0], hex('1681'), 'Ogham charscript'); |
231 | is($ranges->[1]->[1], hex('169a')); |
10a6ecd2 |
232 | |
55d7b906 |
233 | use Unicode::UCD qw(charinrange); |
10a6ecd2 |
234 | |
235 | $ranges = charscript('Cherokee'); |
f5c9f3db |
236 | ok(!charinrange($ranges, "139f"), 'Cherokee charscript'); |
10a6ecd2 |
237 | ok( charinrange($ranges, "13a0")); |
238 | ok( charinrange($ranges, "13f4")); |
239 | ok(!charinrange($ranges, "13f5")); |
240 | |
ea508aee |
241 | use Unicode::UCD qw(general_categories); |
242 | |
243 | my $gc = general_categories(); |
244 | |
245 | ok(exists $gc->{L}, 'has L'); |
246 | is($gc->{L}, 'Letter', 'L is Letter'); |
247 | is($gc->{Lu}, 'UppercaseLetter', 'Lu is UppercaseLetter'); |
248 | |
249 | use Unicode::UCD qw(bidi_types); |
250 | |
251 | my $bt = bidi_types(); |
252 | |
253 | ok(exists $bt->{L}, 'has L'); |
254 | is($bt->{L}, 'Left-to-Right', 'L is Left-to-Right'); |
255 | is($bt->{AL}, 'Right-to-Left Arabic', 'AL is Right-to-Left Arabic'); |
256 | |
98fbe989 |
257 | is(Unicode::UCD::UnicodeVersion, '5.0.0', 'UnicodeVersion'); |
b08cd201 |
258 | |
55d7b906 |
259 | use Unicode::UCD qw(compexcl); |
b08cd201 |
260 | |
f5c9f3db |
261 | ok(!compexcl(0x0100), 'compexcl'); |
b08cd201 |
262 | ok( compexcl(0x0958)); |
263 | |
55d7b906 |
264 | use Unicode::UCD qw(casefold); |
b08cd201 |
265 | |
266 | my $casefold; |
267 | |
268 | $casefold = casefold(0x41); |
269 | |
270 | ok($casefold->{code} eq '0041' && |
271 | $casefold->{status} eq 'C' && |
f5c9f3db |
272 | $casefold->{mapping} eq '0061', 'casefold 0x41'); |
b08cd201 |
273 | |
274 | $casefold = casefold(0xdf); |
275 | |
276 | ok($casefold->{code} eq '00DF' && |
277 | $casefold->{status} eq 'F' && |
f5c9f3db |
278 | $casefold->{mapping} eq '0073 0073', 'casefold 0xDF'); |
b08cd201 |
279 | |
280 | ok(!casefold(0x20)); |
281 | |
55d7b906 |
282 | use Unicode::UCD qw(casespec); |
b08cd201 |
283 | |
284 | my $casespec; |
285 | |
286 | ok(!casespec(0x41)); |
287 | |
288 | $casespec = casespec(0xdf); |
289 | |
290 | ok($casespec->{code} eq '00DF' && |
291 | $casespec->{lower} eq '00DF' && |
292 | $casespec->{title} eq '0053 0073' && |
293 | $casespec->{upper} eq '0053 0053' && |
2d3cf3ee |
294 | !defined $casespec->{condition}, 'casespec 0xDF'); |
b08cd201 |
295 | |
296 | $casespec = casespec(0x307); |
297 | |
f499c386 |
298 | ok($casespec->{az}->{code} eq '0307' && |
2d3cf3ee |
299 | !defined $casespec->{az}->{lower} && |
f499c386 |
300 | $casespec->{az}->{title} eq '0307' && |
301 | $casespec->{az}->{upper} eq '0307' && |
9c3dc587 |
302 | $casespec->{az}->{condition} eq 'az After_I', |
f5c9f3db |
303 | 'casespec 0x307'); |
6c8d78fb |
304 | |
305 | # perl #7305 UnicodeCD::compexcl is weird |
306 | |
2d3cf3ee |
307 | for (1) {my $a=compexcl $_} |
6c8d78fb |
308 | ok(1, 'compexcl read-only $_: perl #7305'); |
309 | grep {compexcl $_} %{{1=>2}}; |
310 | ok(1, 'compexcl read-only hash: perl #7305'); |
311 | |
d7829152 |
312 | is(Unicode::UCD::_getcode('123'), 123, "_getcode(123)"); |
313 | is(Unicode::UCD::_getcode('0123'), 0x123, "_getcode(0123)"); |
314 | is(Unicode::UCD::_getcode('0x123'), 0x123, "_getcode(0x123)"); |
315 | is(Unicode::UCD::_getcode('0X123'), 0x123, "_getcode(0X123)"); |
316 | is(Unicode::UCD::_getcode('U+123'), 0x123, "_getcode(U+123)"); |
317 | is(Unicode::UCD::_getcode('u+123'), 0x123, "_getcode(u+123)"); |
318 | is(Unicode::UCD::_getcode('U+1234'), 0x1234, "_getcode(U+1234)"); |
319 | is(Unicode::UCD::_getcode('U+12345'), 0x12345, "_getcode(U+12345)"); |
320 | is(Unicode::UCD::_getcode('123x'), undef, "_getcode(123x)"); |
321 | is(Unicode::UCD::_getcode('x123'), undef, "_getcode(x123)"); |
322 | is(Unicode::UCD::_getcode('0x123x'), undef, "_getcode(x123)"); |
323 | is(Unicode::UCD::_getcode('U+123x'), undef, "_getcode(x123)"); |
741297c1 |
324 | |
325 | { |
326 | my $r1 = charscript('Latin'); |
327 | my $n1 = @$r1; |
98fbe989 |
328 | is($n1, 35, "number of ranges in Latin script (Unicode 5.0.0)"); |
741297c1 |
329 | shift @$r1 while @$r1; |
330 | my $r2 = charscript('Latin'); |
331 | is(@$r2, $n1, "modifying results should not mess up internal caches"); |
332 | } |
333 | |
c5a29f40 |
334 | { |
335 | is(charinfo(0xdeadbeef), undef, "[perl #23273] warnings in Unicode::UCD"); |
2d3cf3ee |
336 | } |
a2bd7410 |
337 | |
338 | use Unicode::UCD qw(namedseq); |
339 | |
340 | is(namedseq("KATAKANA LETTER AINU P"), "\x{31F7}\x{309A}", "namedseq"); |
341 | is(namedseq("KATAKANA LETTER AINU Q"), undef); |
342 | is(namedseq(), undef); |
343 | is(namedseq(qw(foo bar)), undef); |
344 | my @ns = namedseq("KATAKANA LETTER AINU P"); |
345 | is(scalar @ns, 2); |
346 | is($ns[0], 0x31F7); |
347 | is($ns[1], 0x309A); |
348 | my %ns = namedseq(); |
349 | is($ns{"KATAKANA LETTER AINU P"}, "\x{31F7}\x{309A}"); |
350 | @ns = namedseq(42); |
351 | is(@ns, 0); |
352 | |