1 |
/-- These tests for Unicode property support test PCRE's API and show some of
|
2 |
the compiled code. They are not Perl-compatible. --/
|
3 |
|
4 |
/[\p{L}]/DZ
|
5 |
------------------------------------------------------------------
|
6 |
Bra
|
7 |
[\p{L}]
|
8 |
Ket
|
9 |
End
|
10 |
------------------------------------------------------------------
|
11 |
Capturing subpattern count = 0
|
12 |
No options
|
13 |
No first char
|
14 |
No need char
|
15 |
|
16 |
/[\p{^L}]/DZ
|
17 |
------------------------------------------------------------------
|
18 |
Bra
|
19 |
[\P{L}]
|
20 |
Ket
|
21 |
End
|
22 |
------------------------------------------------------------------
|
23 |
Capturing subpattern count = 0
|
24 |
No options
|
25 |
No first char
|
26 |
No need char
|
27 |
|
28 |
/[\P{L}]/DZ
|
29 |
------------------------------------------------------------------
|
30 |
Bra
|
31 |
[\P{L}]
|
32 |
Ket
|
33 |
End
|
34 |
------------------------------------------------------------------
|
35 |
Capturing subpattern count = 0
|
36 |
No options
|
37 |
No first char
|
38 |
No need char
|
39 |
|
40 |
/[\P{^L}]/DZ
|
41 |
------------------------------------------------------------------
|
42 |
Bra
|
43 |
[\p{L}]
|
44 |
Ket
|
45 |
End
|
46 |
------------------------------------------------------------------
|
47 |
Capturing subpattern count = 0
|
48 |
No options
|
49 |
No first char
|
50 |
No need char
|
51 |
|
52 |
/[abc\p{L}\x{0660}]/8DZ
|
53 |
------------------------------------------------------------------
|
54 |
Bra
|
55 |
[a-c\p{L}\x{660}]
|
56 |
Ket
|
57 |
End
|
58 |
------------------------------------------------------------------
|
59 |
Capturing subpattern count = 0
|
60 |
Options: utf8
|
61 |
No first char
|
62 |
No need char
|
63 |
|
64 |
/[\p{Nd}]/8DZ
|
65 |
------------------------------------------------------------------
|
66 |
Bra
|
67 |
[\p{Nd}]
|
68 |
Ket
|
69 |
End
|
70 |
------------------------------------------------------------------
|
71 |
Capturing subpattern count = 0
|
72 |
Options: utf8
|
73 |
No first char
|
74 |
No need char
|
75 |
1234
|
76 |
0: 1
|
77 |
|
78 |
/[\p{Nd}+-]+/8DZ
|
79 |
------------------------------------------------------------------
|
80 |
Bra
|
81 |
[+\-\p{Nd}]+
|
82 |
Ket
|
83 |
End
|
84 |
------------------------------------------------------------------
|
85 |
Capturing subpattern count = 0
|
86 |
Options: utf8
|
87 |
No first char
|
88 |
No need char
|
89 |
1234
|
90 |
0: 1234
|
91 |
12-34
|
92 |
0: 12-34
|
93 |
12+\x{661}-34
|
94 |
0: 12+\x{661}-34
|
95 |
** Failers
|
96 |
No match
|
97 |
abcd
|
98 |
No match
|
99 |
|
100 |
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iDZ
|
101 |
------------------------------------------------------------------
|
102 |
Bra
|
103 |
NC A\x{391}\x{10427}\x{ff3a}\x{1fb0}
|
104 |
Ket
|
105 |
End
|
106 |
------------------------------------------------------------------
|
107 |
Capturing subpattern count = 0
|
108 |
Options: caseless utf8
|
109 |
First char = 'A' (caseless)
|
110 |
No need char
|
111 |
|
112 |
/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8DZ
|
113 |
------------------------------------------------------------------
|
114 |
Bra
|
115 |
A\x{391}\x{10427}\x{ff3a}\x{1fb0}
|
116 |
Ket
|
117 |
End
|
118 |
------------------------------------------------------------------
|
119 |
Capturing subpattern count = 0
|
120 |
Options: utf8
|
121 |
First char = 'A'
|
122 |
Need char = 176
|
123 |
|
124 |
/AB\x{1fb0}/8DZ
|
125 |
------------------------------------------------------------------
|
126 |
Bra
|
127 |
AB\x{1fb0}
|
128 |
Ket
|
129 |
End
|
130 |
------------------------------------------------------------------
|
131 |
Capturing subpattern count = 0
|
132 |
Options: utf8
|
133 |
First char = 'A'
|
134 |
Need char = 176
|
135 |
|
136 |
/AB\x{1fb0}/8DZi
|
137 |
------------------------------------------------------------------
|
138 |
Bra
|
139 |
NC AB\x{1fb0}
|
140 |
Ket
|
141 |
End
|
142 |
------------------------------------------------------------------
|
143 |
Capturing subpattern count = 0
|
144 |
Options: caseless utf8
|
145 |
First char = 'A' (caseless)
|
146 |
Need char = 'B' (caseless)
|
147 |
|
148 |
/[\x{105}-\x{109}]/8iDZ
|
149 |
------------------------------------------------------------------
|
150 |
Bra
|
151 |
[\x{104}-\x{109}]
|
152 |
Ket
|
153 |
End
|
154 |
------------------------------------------------------------------
|
155 |
Capturing subpattern count = 0
|
156 |
Options: caseless utf8
|
157 |
No first char
|
158 |
No need char
|
159 |
\x{104}
|
160 |
0: \x{104}
|
161 |
\x{105}
|
162 |
0: \x{105}
|
163 |
\x{109}
|
164 |
0: \x{109}
|
165 |
** Failers
|
166 |
No match
|
167 |
\x{100}
|
168 |
No match
|
169 |
\x{10a}
|
170 |
No match
|
171 |
|
172 |
/[z-\x{100}]/8iDZ
|
173 |
------------------------------------------------------------------
|
174 |
Bra
|
175 |
[Z\x{39c}\x{178}z-\x{101}]
|
176 |
Ket
|
177 |
End
|
178 |
------------------------------------------------------------------
|
179 |
Capturing subpattern count = 0
|
180 |
Options: caseless utf8
|
181 |
No first char
|
182 |
No need char
|
183 |
Z
|
184 |
0: Z
|
185 |
z
|
186 |
0: z
|
187 |
\x{39c}
|
188 |
0: \x{39c}
|
189 |
\x{178}
|
190 |
0: \x{178}
|
191 |
|
|
192 |
0: |
|
193 |
\x{80}
|
194 |
0: \x{80}
|
195 |
\x{ff}
|
196 |
0: \x{ff}
|
197 |
\x{100}
|
198 |
0: \x{100}
|
199 |
\x{101}
|
200 |
0: \x{101}
|
201 |
** Failers
|
202 |
No match
|
203 |
\x{102}
|
204 |
No match
|
205 |
Y
|
206 |
No match
|
207 |
y
|
208 |
No match
|
209 |
|
210 |
/[z-\x{100}]/8DZi
|
211 |
------------------------------------------------------------------
|
212 |
Bra
|
213 |
[Z\x{39c}\x{178}z-\x{101}]
|
214 |
Ket
|
215 |
End
|
216 |
------------------------------------------------------------------
|
217 |
Capturing subpattern count = 0
|
218 |
Options: caseless utf8
|
219 |
No first char
|
220 |
No need char
|
221 |
|
222 |
/(?:[\PPa*]*){8,}/
|
223 |
|
224 |
/[\P{Any}]/BZ
|
225 |
------------------------------------------------------------------
|
226 |
Bra
|
227 |
[\P{Any}]
|
228 |
Ket
|
229 |
End
|
230 |
------------------------------------------------------------------
|
231 |
|
232 |
/[\P{Any}\E]/BZ
|
233 |
------------------------------------------------------------------
|
234 |
Bra
|
235 |
[\P{Any}]
|
236 |
Ket
|
237 |
End
|
238 |
------------------------------------------------------------------
|
239 |
|
240 |
/(\P{Yi}+\277)/
|
241 |
|
242 |
/(\P{Yi}+\277)?/
|
243 |
|
244 |
/(?<=\P{Yi}{3}A)X/
|
245 |
|
246 |
/\p{Yi}+(\P{Yi}+)(?1)/
|
247 |
|
248 |
/(\P{Yi}{2}\277)?/
|
249 |
|
250 |
/[\P{Yi}A]/
|
251 |
|
252 |
/[\P{Yi}\P{Yi}\P{Yi}A]/
|
253 |
|
254 |
/[^\P{Yi}A]/
|
255 |
|
256 |
/[^\P{Yi}\P{Yi}\P{Yi}A]/
|
257 |
|
258 |
/(\P{Yi}*\277)*/
|
259 |
|
260 |
/(\P{Yi}*?\277)*/
|
261 |
|
262 |
/(\p{Yi}*+\277)*/
|
263 |
|
264 |
/(\P{Yi}?\277)*/
|
265 |
|
266 |
/(\P{Yi}??\277)*/
|
267 |
|
268 |
/(\p{Yi}?+\277)*/
|
269 |
|
270 |
/(\P{Yi}{0,3}\277)*/
|
271 |
|
272 |
/(\P{Yi}{0,3}?\277)*/
|
273 |
|
274 |
/(\p{Yi}{0,3}+\277)*/
|
275 |
|
276 |
/\p{Zl}{2,3}+/8BZ
|
277 |
------------------------------------------------------------------
|
278 |
Bra
|
279 |
prop Zl {2}
|
280 |
prop Zl ?+
|
281 |
Ket
|
282 |
End
|
283 |
------------------------------------------------------------------
|
284 |
\xe2\x80\xa8\xe2\x80\xa8
|
285 |
0: \x{2028}\x{2028}
|
286 |
\x{2028}\x{2028}\x{2028}
|
287 |
0: \x{2028}\x{2028}\x{2028}
|
288 |
|
289 |
/\p{Zl}/8BZ
|
290 |
------------------------------------------------------------------
|
291 |
Bra
|
292 |
prop Zl
|
293 |
Ket
|
294 |
End
|
295 |
------------------------------------------------------------------
|
296 |
|
297 |
/\p{Lu}{3}+/8BZ
|
298 |
------------------------------------------------------------------
|
299 |
Bra
|
300 |
prop Lu {3}
|
301 |
Ket
|
302 |
End
|
303 |
------------------------------------------------------------------
|
304 |
|
305 |
/\pL{2}+/8BZ
|
306 |
------------------------------------------------------------------
|
307 |
Bra
|
308 |
prop L {2}
|
309 |
Ket
|
310 |
End
|
311 |
------------------------------------------------------------------
|
312 |
|
313 |
/\p{Cc}{2}+/8BZ
|
314 |
------------------------------------------------------------------
|
315 |
Bra
|
316 |
prop Cc {2}
|
317 |
Ket
|
318 |
End
|
319 |
------------------------------------------------------------------
|
320 |
|
321 |
/^\p{Cs}/8
|
322 |
\?\x{dfff}
|
323 |
0: \x{dfff}
|
324 |
** Failers
|
325 |
No match
|
326 |
\x{09f}
|
327 |
No match
|
328 |
|
329 |
/^\p{Sc}+/8
|
330 |
$\x{a2}\x{a3}\x{a4}\x{a5}\x{a6}
|
331 |
0: $\x{a2}\x{a3}\x{a4}\x{a5}
|
332 |
\x{9f2}
|
333 |
0: \x{9f2}
|
334 |
** Failers
|
335 |
No match
|
336 |
X
|
337 |
No match
|
338 |
\x{2c2}
|
339 |
No match
|
340 |
|
341 |
/^\p{Zs}/8
|
342 |
\ \
|
343 |
0:
|
344 |
\x{a0}
|
345 |
0: \x{a0}
|
346 |
\x{1680}
|
347 |
0: \x{1680}
|
348 |
\x{180e}
|
349 |
0: \x{180e}
|
350 |
\x{2000}
|
351 |
0: \x{2000}
|
352 |
\x{2001}
|
353 |
0: \x{2001}
|
354 |
** Failers
|
355 |
No match
|
356 |
\x{2028}
|
357 |
No match
|
358 |
\x{200d}
|
359 |
No match
|
360 |
|
361 |
/-- These four are here rather than in test 6 because Perl has problems with
|
362 |
the negative versions of the properties. --/
|
363 |
|
364 |
/\p{^Lu}/8i
|
365 |
1234
|
366 |
0: 1
|
367 |
** Failers
|
368 |
0: *
|
369 |
ABC
|
370 |
No match
|
371 |
|
372 |
/\P{Lu}/8i
|
373 |
1234
|
374 |
0: 1
|
375 |
** Failers
|
376 |
0: *
|
377 |
ABC
|
378 |
No match
|
379 |
|
380 |
/\p{Ll}/8i
|
381 |
a
|
382 |
0: a
|
383 |
Az
|
384 |
0: z
|
385 |
** Failers
|
386 |
0: a
|
387 |
ABC
|
388 |
No match
|
389 |
|
390 |
/\p{Lu}/8i
|
391 |
A
|
392 |
0: A
|
393 |
a\x{10a0}B
|
394 |
0: \x{10a0}
|
395 |
** Failers
|
396 |
0: F
|
397 |
a
|
398 |
No match
|
399 |
\x{1d00}
|
400 |
No match
|
401 |
|
402 |
/[\x{c0}\x{391}]/8i
|
403 |
\x{c0}
|
404 |
0: \x{c0}
|
405 |
\x{e0}
|
406 |
0: \x{e0}
|
407 |
|
408 |
/-- The next two are special cases where the lengths of the different cases of
|
409 |
the same character differ. The first went wrong with heap frame storage; the
|
410 |
second was broken in all cases. --/
|
411 |
|
412 |
/^\x{023a}+?(\x{0130}+)/8i
|
413 |
\x{023a}\x{2c65}\x{0130}
|
414 |
0: \x{23a}\x{2c65}\x{130}
|
415 |
1: \x{130}
|
416 |
|
417 |
/^\x{023a}+([^X])/8i
|
418 |
\x{023a}\x{2c65}X
|
419 |
0: \x{23a}\x{2c65}
|
420 |
1: \x{2c65}
|
421 |
|
422 |
/\x{c0}+\x{116}+/8i
|
423 |
\x{c0}\x{e0}\x{116}\x{117}
|
424 |
0: \x{c0}\x{e0}\x{116}\x{117}
|
425 |
|
426 |
/[\x{c0}\x{116}]+/8i
|
427 |
\x{c0}\x{e0}\x{116}\x{117}
|
428 |
0: \x{c0}\x{e0}\x{116}\x{117}
|
429 |
|
430 |
/(\x{de})\1/8i
|
431 |
\x{de}\x{de}
|
432 |
0: \x{de}\x{de}
|
433 |
1: \x{de}
|
434 |
\x{de}\x{fe}
|
435 |
0: \x{de}\x{fe}
|
436 |
1: \x{de}
|
437 |
\x{fe}\x{fe}
|
438 |
0: \x{fe}\x{fe}
|
439 |
1: \x{fe}
|
440 |
\x{fe}\x{de}
|
441 |
0: \x{fe}\x{de}
|
442 |
1: \x{fe}
|
443 |
|
444 |
/^\x{c0}$/8i
|
445 |
\x{c0}
|
446 |
0: \x{c0}
|
447 |
\x{e0}
|
448 |
0: \x{e0}
|
449 |
|
450 |
/^\x{e0}$/8i
|
451 |
\x{c0}
|
452 |
0: \x{c0}
|
453 |
\x{e0}
|
454 |
0: \x{e0}
|
455 |
|
456 |
/-- The next two should be Perl-compatible, but it fails to match \x{e0}. PCRE
|
457 |
will match it only with UCP support, because without that it has no notion
|
458 |
of case for anything other than the ASCII letters. --/
|
459 |
|
460 |
/((?i)[\x{c0}])/8
|
461 |
\x{c0}
|
462 |
0: \x{c0}
|
463 |
1: \x{c0}
|
464 |
\x{e0}
|
465 |
0: \x{e0}
|
466 |
1: \x{e0}
|
467 |
|
468 |
/(?i:[\x{c0}])/8
|
469 |
\x{c0}
|
470 |
0: \x{c0}
|
471 |
\x{e0}
|
472 |
0: \x{e0}
|
473 |
|
474 |
/-- End of testinput12 --/
|