Annotation of embedaddon/pcre/testdata/testoutput15, revision 1.1.1.4
1.1.1.2 misho 1: /-- This set of tests is for UTF-8 support, and is relevant only to the 8-bit
2: library. --/
3:
4: /X(\C{3})/8
5: X\x{1234}
6: 0: X\x{1234}
7: 1: \x{1234}
8:
9: /X(\C{4})/8
10: X\x{1234}YZ
11: 0: X\x{1234}Y
12: 1: \x{1234}Y
13:
14: /X\C*/8
15: XYZabcdce
16: 0: XYZabcdce
17:
18: /X\C*?/8
19: XYZabcde
20: 0: X
21:
22: /X\C{3,5}/8
23: Xabcdefg
24: 0: Xabcde
25: X\x{1234}
26: 0: X\x{1234}
27: X\x{1234}YZ
28: 0: X\x{1234}YZ
29: X\x{1234}\x{512}
30: 0: X\x{1234}\x{512}
31: X\x{1234}\x{512}YZ
32: 0: X\x{1234}\x{512}
33:
34: /X\C{3,5}?/8
35: Xabcdefg
36: 0: Xabc
37: X\x{1234}
38: 0: X\x{1234}
39: X\x{1234}YZ
40: 0: X\x{1234}
41: X\x{1234}\x{512}
42: 0: X\x{1234}
43:
44: /a\Cb/8
45: aXb
46: 0: aXb
47: a\nb
48: 0: a\x{0a}b
49:
50: /a\C\Cb/8
51: a\x{100}b
52: 0: a\x{100}b
53:
54: /ab\Cde/8
55: abXde
56: 0: abXde
57:
58: /a\C\Cb/8
59: a\x{100}b
60: 0: a\x{100}b
61: ** Failers
62: No match
63: a\x{12257}b
64: No match
65:
66: /[]/8
67: Failed: invalid UTF-8 string at offset 1
68:
69: //8
70: Failed: invalid UTF-8 string at offset 0
71:
72: /xxx/8
73: Failed: invalid UTF-8 string at offset 0
74:
75: /xxx/8?DZSS
76: ------------------------------------------------------------------
77: Bra
78: \X{c0}\X{c0}\X{c0}xxx
79: Ket
80: End
81: ------------------------------------------------------------------
1.1 misho 82: Capturing subpattern count = 0
1.1.1.2 misho 83: Options: utf no_utf_check
84: First char = \x{c3}
85: Need char = 'x'
86:
1.1.1.4 ! misho 87: /badutf/8
! 88: \xdf
1.1.1.2 misho 89: Error -10 (bad UTF-8 string) offset=0 reason=1
1.1.1.4 ! misho 90: \xef
! 91: Error -10 (bad UTF-8 string) offset=0 reason=2
! 92: \xef\x80
! 93: Error -10 (bad UTF-8 string) offset=0 reason=1
! 94: \xf7
! 95: Error -10 (bad UTF-8 string) offset=0 reason=3
! 96: \xf7\x80
! 97: Error -10 (bad UTF-8 string) offset=0 reason=2
! 98: \xf7\x80\x80
! 99: Error -10 (bad UTF-8 string) offset=0 reason=1
! 100: \xfb
! 101: Error -10 (bad UTF-8 string) offset=0 reason=4
! 102: \xfb\x80
! 103: Error -10 (bad UTF-8 string) offset=0 reason=3
! 104: \xfb\x80\x80
! 105: Error -10 (bad UTF-8 string) offset=0 reason=2
! 106: \xfb\x80\x80\x80
1.1.1.2 misho 107: Error -10 (bad UTF-8 string) offset=0 reason=1
1.1.1.4 ! misho 108: \xfd
! 109: Error -10 (bad UTF-8 string) offset=0 reason=5
! 110: \xfd\x80
! 111: Error -10 (bad UTF-8 string) offset=0 reason=4
! 112: \xfd\x80\x80
! 113: Error -10 (bad UTF-8 string) offset=0 reason=3
! 114: \xfd\x80\x80\x80
! 115: Error -10 (bad UTF-8 string) offset=0 reason=2
! 116: \xfd\x80\x80\x80\x80
1.1.1.2 misho 117: Error -10 (bad UTF-8 string) offset=0 reason=1
1.1.1.4 ! misho 118: \xdf\x7f
! 119: Error -10 (bad UTF-8 string) offset=0 reason=6
! 120: \xef\x7f\x80
! 121: Error -10 (bad UTF-8 string) offset=0 reason=6
! 122: \xef\x80\x7f
! 123: Error -10 (bad UTF-8 string) offset=0 reason=7
! 124: \xf7\x7f\x80\x80
! 125: Error -10 (bad UTF-8 string) offset=0 reason=6
! 126: \xf7\x80\x7f\x80
! 127: Error -10 (bad UTF-8 string) offset=0 reason=7
! 128: \xf7\x80\x80\x7f
! 129: Error -10 (bad UTF-8 string) offset=0 reason=8
! 130: \xfb\x7f\x80\x80\x80
! 131: Error -10 (bad UTF-8 string) offset=0 reason=6
! 132: \xfb\x80\x7f\x80\x80
! 133: Error -10 (bad UTF-8 string) offset=0 reason=7
! 134: \xfb\x80\x80\x7f\x80
! 135: Error -10 (bad UTF-8 string) offset=0 reason=8
! 136: \xfb\x80\x80\x80\x7f
! 137: Error -10 (bad UTF-8 string) offset=0 reason=9
! 138: \xfd\x7f\x80\x80\x80\x80
! 139: Error -10 (bad UTF-8 string) offset=0 reason=6
! 140: \xfd\x80\x7f\x80\x80\x80
! 141: Error -10 (bad UTF-8 string) offset=0 reason=7
! 142: \xfd\x80\x80\x7f\x80\x80
! 143: Error -10 (bad UTF-8 string) offset=0 reason=8
! 144: \xfd\x80\x80\x80\x7f\x80
! 145: Error -10 (bad UTF-8 string) offset=0 reason=9
! 146: \xfd\x80\x80\x80\x80\x7f
! 147: Error -10 (bad UTF-8 string) offset=0 reason=10
! 148: \xed\xa0\x80
! 149: Error -10 (bad UTF-8 string) offset=0 reason=14
! 150: \xc0\x8f
! 151: Error -10 (bad UTF-8 string) offset=0 reason=15
! 152: \xe0\x80\x8f
! 153: Error -10 (bad UTF-8 string) offset=0 reason=16
! 154: \xf0\x80\x80\x8f
! 155: Error -10 (bad UTF-8 string) offset=0 reason=17
! 156: \xf8\x80\x80\x80\x8f
! 157: Error -10 (bad UTF-8 string) offset=0 reason=18
! 158: \xfc\x80\x80\x80\x80\x8f
! 159: Error -10 (bad UTF-8 string) offset=0 reason=19
! 160: \x80
! 161: Error -10 (bad UTF-8 string) offset=0 reason=20
! 162: \xfe
! 163: Error -10 (bad UTF-8 string) offset=0 reason=21
! 164: \xff
! 165: Error -10 (bad UTF-8 string) offset=0 reason=21
! 166:
! 167: /badutf/8
! 168: \xfb\x80\x80\x80\x80
! 169: Error -10 (bad UTF-8 string) offset=0 reason=11
! 170: \xfd\x80\x80\x80\x80\x80
! 171: Error -10 (bad UTF-8 string) offset=0 reason=12
! 172: \xf7\xbf\xbf\xbf
! 173: Error -10 (bad UTF-8 string) offset=0 reason=13
! 174:
! 175: /shortutf/8
! 176: \P\P\xdf
! 177: Error -25 (short UTF-8 string) offset=0 reason=1
! 178: \P\P\xef
! 179: Error -25 (short UTF-8 string) offset=0 reason=2
! 180: \P\P\xef\x80
! 181: Error -25 (short UTF-8 string) offset=0 reason=1
! 182: \P\P\xf7
! 183: Error -25 (short UTF-8 string) offset=0 reason=3
! 184: \P\P\xf7\x80
! 185: Error -25 (short UTF-8 string) offset=0 reason=2
! 186: \P\P\xf7\x80\x80
! 187: Error -25 (short UTF-8 string) offset=0 reason=1
! 188: \P\P\xfb
! 189: Error -25 (short UTF-8 string) offset=0 reason=4
! 190: \P\P\xfb\x80
! 191: Error -25 (short UTF-8 string) offset=0 reason=3
! 192: \P\P\xfb\x80\x80
! 193: Error -25 (short UTF-8 string) offset=0 reason=2
! 194: \P\P\xfb\x80\x80\x80
! 195: Error -25 (short UTF-8 string) offset=0 reason=1
! 196: \P\P\xfd
! 197: Error -25 (short UTF-8 string) offset=0 reason=5
! 198: \P\P\xfd\x80
! 199: Error -25 (short UTF-8 string) offset=0 reason=4
! 200: \P\P\xfd\x80\x80
! 201: Error -25 (short UTF-8 string) offset=0 reason=3
! 202: \P\P\xfd\x80\x80\x80
! 203: Error -25 (short UTF-8 string) offset=0 reason=2
! 204: \P\P\xfd\x80\x80\x80\x80
1.1.1.2 misho 205: Error -25 (short UTF-8 string) offset=0 reason=1
206:
207: /anything/8
208: \xc0\x80
209: Error -10 (bad UTF-8 string) offset=0 reason=15
210: \xc1\x8f
211: Error -10 (bad UTF-8 string) offset=0 reason=15
212: \xe0\x9f\x80
213: Error -10 (bad UTF-8 string) offset=0 reason=16
214: \xf0\x8f\x80\x80
215: Error -10 (bad UTF-8 string) offset=0 reason=17
216: \xf8\x87\x80\x80\x80
217: Error -10 (bad UTF-8 string) offset=0 reason=18
218: \xfc\x83\x80\x80\x80\x80
219: Error -10 (bad UTF-8 string) offset=0 reason=19
220: \xfe\x80\x80\x80\x80\x80
221: Error -10 (bad UTF-8 string) offset=0 reason=21
222: \xff\x80\x80\x80\x80\x80
223: Error -10 (bad UTF-8 string) offset=0 reason=21
224: \xc3\x8f
225: No match
226: \xe0\xaf\x80
227: No match
228: \xe1\x80\x80
229: No match
230: \xf0\x9f\x80\x80
231: No match
232: \xf1\x8f\x80\x80
233: No match
234: \xf8\x88\x80\x80\x80
235: Error -10 (bad UTF-8 string) offset=0 reason=11
236: \xf9\x87\x80\x80\x80
237: Error -10 (bad UTF-8 string) offset=0 reason=11
238: \xfc\x84\x80\x80\x80\x80
239: Error -10 (bad UTF-8 string) offset=0 reason=12
240: \xfd\x83\x80\x80\x80\x80
241: Error -10 (bad UTF-8 string) offset=0 reason=12
242: \?\xf8\x88\x80\x80\x80
243: No match
244: \?\xf9\x87\x80\x80\x80
245: No match
246: \?\xfc\x84\x80\x80\x80\x80
247: No match
248: \?\xfd\x83\x80\x80\x80\x80
249: No match
250:
251: /\x{100}/8DZ
252: ------------------------------------------------------------------
253: Bra
254: \x{100}
255: Ket
256: End
257: ------------------------------------------------------------------
258: Capturing subpattern count = 0
259: Options: utf
260: First char = \x{c4}
261: Need char = \x{80}
262:
263: /\x{1000}/8DZ
264: ------------------------------------------------------------------
265: Bra
266: \x{1000}
267: Ket
268: End
269: ------------------------------------------------------------------
270: Capturing subpattern count = 0
271: Options: utf
272: First char = \x{e1}
273: Need char = \x{80}
274:
275: /\x{10000}/8DZ
276: ------------------------------------------------------------------
277: Bra
278: \x{10000}
279: Ket
280: End
281: ------------------------------------------------------------------
282: Capturing subpattern count = 0
283: Options: utf
284: First char = \x{f0}
285: Need char = \x{80}
286:
287: /\x{100000}/8DZ
288: ------------------------------------------------------------------
289: Bra
290: \x{100000}
291: Ket
292: End
293: ------------------------------------------------------------------
294: Capturing subpattern count = 0
295: Options: utf
296: First char = \x{f4}
297: Need char = \x{80}
298:
299: /\x{10ffff}/8DZ
300: ------------------------------------------------------------------
301: Bra
302: \x{10ffff}
303: Ket
304: End
305: ------------------------------------------------------------------
306: Capturing subpattern count = 0
307: Options: utf
308: First char = \x{f4}
309: Need char = \x{bf}
310:
311: /[\x{ff}]/8DZ
312: ------------------------------------------------------------------
313: Bra
314: \x{ff}
315: Ket
316: End
317: ------------------------------------------------------------------
318: Capturing subpattern count = 0
319: Options: utf
320: First char = \x{c3}
321: Need char = \x{bf}
322:
323: /[\x{100}]/8DZ
324: ------------------------------------------------------------------
325: Bra
326: \x{100}
327: Ket
328: End
329: ------------------------------------------------------------------
330: Capturing subpattern count = 0
331: Options: utf
332: First char = \x{c4}
333: Need char = \x{80}
334:
335: /\x80/8DZ
336: ------------------------------------------------------------------
337: Bra
338: \x{80}
339: Ket
340: End
341: ------------------------------------------------------------------
342: Capturing subpattern count = 0
343: Options: utf
344: First char = \x{c2}
345: Need char = \x{80}
346:
347: /\xff/8DZ
348: ------------------------------------------------------------------
349: Bra
350: \x{ff}
351: Ket
352: End
353: ------------------------------------------------------------------
354: Capturing subpattern count = 0
355: Options: utf
356: First char = \x{c3}
357: Need char = \x{bf}
358:
359: /\x{D55c}\x{ad6d}\x{C5B4}/DZ8
360: ------------------------------------------------------------------
361: Bra
362: \x{d55c}\x{ad6d}\x{c5b4}
363: Ket
364: End
365: ------------------------------------------------------------------
366: Capturing subpattern count = 0
367: Options: utf
368: First char = \x{ed}
369: Need char = \x{b4}
370: \x{D55c}\x{ad6d}\x{C5B4}
371: 0: \x{d55c}\x{ad6d}\x{c5b4}
372:
373: /\x{65e5}\x{672c}\x{8a9e}/DZ8
374: ------------------------------------------------------------------
375: Bra
376: \x{65e5}\x{672c}\x{8a9e}
377: Ket
378: End
379: ------------------------------------------------------------------
380: Capturing subpattern count = 0
381: Options: utf
382: First char = \x{e6}
383: Need char = \x{9e}
384: \x{65e5}\x{672c}\x{8a9e}
385: 0: \x{65e5}\x{672c}\x{8a9e}
386:
387: /\x{80}/DZ8
388: ------------------------------------------------------------------
389: Bra
390: \x{80}
391: Ket
392: End
393: ------------------------------------------------------------------
394: Capturing subpattern count = 0
395: Options: utf
396: First char = \x{c2}
397: Need char = \x{80}
398:
399: /\x{084}/DZ8
400: ------------------------------------------------------------------
401: Bra
402: \x{84}
403: Ket
404: End
405: ------------------------------------------------------------------
406: Capturing subpattern count = 0
407: Options: utf
408: First char = \x{c2}
409: Need char = \x{84}
410:
411: /\x{104}/DZ8
412: ------------------------------------------------------------------
413: Bra
414: \x{104}
415: Ket
416: End
417: ------------------------------------------------------------------
418: Capturing subpattern count = 0
419: Options: utf
420: First char = \x{c4}
421: Need char = \x{84}
422:
423: /\x{861}/DZ8
424: ------------------------------------------------------------------
425: Bra
426: \x{861}
427: Ket
428: End
429: ------------------------------------------------------------------
430: Capturing subpattern count = 0
431: Options: utf
432: First char = \x{e0}
433: Need char = \x{a1}
434:
435: /\x{212ab}/DZ8
436: ------------------------------------------------------------------
437: Bra
438: \x{212ab}
439: Ket
440: End
441: ------------------------------------------------------------------
442: Capturing subpattern count = 0
443: Options: utf
444: First char = \x{f0}
445: Need char = \x{ab}
446:
447: /-- This one is here not because it's different to Perl, but because the way
448: the captured single-byte is displayed. (In Perl it becomes a character, and you
449: can't tell the difference.) --/
450:
451: /X(\C)(.*)/8
452: X\x{1234}
453: 0: X\x{1234}
454: 1: \x{e1}
455: 2: \x{88}\x{b4}
456: X\nabc
457: 0: X\x{0a}abc
458: 1: \x{0a}
459: 2: abc
460:
461: /-- This one is here because Perl gives out a grumbly error message (quite
462: correctly, but that messes up comparisons). --/
463:
464: /a\Cb/8
465: *** Failers
466: No match
467: a\x{100}b
468: No match
469:
470: /[^ab\xC0-\xF0]/8SDZ
471: ------------------------------------------------------------------
472: Bra
473: [\x00-`c-\xbf\xf1-\xff] (neg)
474: Ket
475: End
476: ------------------------------------------------------------------
477: Capturing subpattern count = 0
478: Options: utf
479: No first char
480: No need char
481: Subject length lower bound = 1
482: Starting byte set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a
483: \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19
484: \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4
485: 5 6 7 8 9 : ; < = > ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y
486: Z [ \ ] ^ _ ` c d e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f
487: \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0
488: \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd \xde \xdf
489: \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec \xed \xee
490: \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd
491: \xfe \xff
492: \x{f1}
493: 0: \x{f1}
494: \x{bf}
495: 0: \x{bf}
496: \x{100}
497: 0: \x{100}
498: \x{1000}
499: 0: \x{1000}
500: *** Failers
501: 0: *
502: \x{c0}
503: No match
504: \x{f0}
505: No match
506:
507: /Ā{3,4}/8SDZ
508: ------------------------------------------------------------------
509: Bra
510: \x{100}{3}
511: \x{100}?
512: Ket
513: End
514: ------------------------------------------------------------------
515: Capturing subpattern count = 0
516: Options: utf
517: First char = \x{c4}
518: Need char = \x{80}
1.1 misho 519: Subject length lower bound = 3
520: No set of starting bytes
1.1.1.2 misho 521: \x{100}\x{100}\x{100}\x{100\x{100}
522: 0: \x{100}\x{100}\x{100}
523:
524: /(\x{100}+|x)/8SDZ
525: ------------------------------------------------------------------
526: Bra
527: CBra 1
528: \x{100}+
529: Alt
530: x
531: Ket
532: Ket
533: End
534: ------------------------------------------------------------------
535: Capturing subpattern count = 1
536: Options: utf
537: No first char
538: No need char
539: Subject length lower bound = 1
540: Starting byte set: x \xc4
541:
542: /(\x{100}*a|x)/8SDZ
543: ------------------------------------------------------------------
544: Bra
545: CBra 1
546: \x{100}*+
547: a
548: Alt
549: x
550: Ket
551: Ket
552: End
553: ------------------------------------------------------------------
554: Capturing subpattern count = 1
555: Options: utf
556: No first char
557: No need char
558: Subject length lower bound = 1
559: Starting byte set: a x \xc4
560:
561: /(\x{100}{0,2}a|x)/8SDZ
562: ------------------------------------------------------------------
563: Bra
564: CBra 1
565: \x{100}{0,2}
566: a
567: Alt
568: x
569: Ket
570: Ket
571: End
572: ------------------------------------------------------------------
573: Capturing subpattern count = 1
574: Options: utf
575: No first char
576: No need char
577: Subject length lower bound = 1
578: Starting byte set: a x \xc4
579:
580: /(\x{100}{1,2}a|x)/8SDZ
581: ------------------------------------------------------------------
582: Bra
583: CBra 1
584: \x{100}
585: \x{100}{0,1}
586: a
587: Alt
588: x
589: Ket
590: Ket
591: End
592: ------------------------------------------------------------------
593: Capturing subpattern count = 1
594: Options: utf
595: No first char
596: No need char
597: Subject length lower bound = 1
598: Starting byte set: x \xc4
599:
600: /\x{100}/8DZ
601: ------------------------------------------------------------------
602: Bra
603: \x{100}
604: Ket
605: End
606: ------------------------------------------------------------------
607: Capturing subpattern count = 0
608: Options: utf
609: First char = \x{c4}
610: Need char = \x{80}
611:
612: /a\x{100}\x{101}*/8DZ
613: ------------------------------------------------------------------
614: Bra
615: a\x{100}
616: \x{101}*
617: Ket
618: End
619: ------------------------------------------------------------------
620: Capturing subpattern count = 0
621: Options: utf
622: First char = 'a'
623: Need char = \x{80}
624:
625: /a\x{100}\x{101}+/8DZ
626: ------------------------------------------------------------------
627: Bra
628: a\x{100}
629: \x{101}+
630: Ket
631: End
632: ------------------------------------------------------------------
633: Capturing subpattern count = 0
634: Options: utf
635: First char = 'a'
636: Need char = \x{81}
1.1 misho 637:
1.1.1.2 misho 638: /[^\x{c4}]/DZ
639: ------------------------------------------------------------------
640: Bra
1.1.1.4 ! misho 641: [^\x{c4}]
1.1.1.2 misho 642: Ket
643: End
644: ------------------------------------------------------------------
1.1 misho 645: Capturing subpattern count = 0
646: No options
647: No first char
648: No need char
1.1.1.2 misho 649:
650: /[\x{100}]/8DZ
651: ------------------------------------------------------------------
652: Bra
653: \x{100}
654: Ket
655: End
656: ------------------------------------------------------------------
657: Capturing subpattern count = 0
658: Options: utf
659: First char = \x{c4}
660: Need char = \x{80}
661: \x{100}
662: 0: \x{100}
663: Z\x{100}
664: 0: \x{100}
665: \x{100}Z
666: 0: \x{100}
667: *** Failers
668: No match
669:
670: /[\xff]/DZ8
671: ------------------------------------------------------------------
672: Bra
673: \x{ff}
674: Ket
675: End
676: ------------------------------------------------------------------
677: Capturing subpattern count = 0
678: Options: utf
679: First char = \x{c3}
680: Need char = \x{bf}
681: >\x{ff}<
682: 0: \x{ff}
683:
684: /[^\xff]/8DZ
685: ------------------------------------------------------------------
686: Bra
1.1.1.3 misho 687: [^\x{ff}]
1.1.1.2 misho 688: Ket
689: End
690: ------------------------------------------------------------------
691: Capturing subpattern count = 0
692: Options: utf
693: No first char
694: No need char
695:
696: /\x{100}abc(xyz(?1))/8DZ
697: ------------------------------------------------------------------
698: Bra
699: \x{100}abc
700: CBra 1
701: xyz
702: Recurse
703: Ket
704: Ket
705: End
706: ------------------------------------------------------------------
707: Capturing subpattern count = 1
708: Options: utf
709: First char = \x{c4}
710: Need char = 'z'
711:
712: /a\x{1234}b/P8
713: a\x{1234}b
714: 0: a\x{1234}b
715:
716: /\777/8I
717: Capturing subpattern count = 0
718: Options: utf
719: First char = \x{c7}
720: Need char = \x{bf}
721: \x{1ff}
722: 0: \x{1ff}
723: \777
724: 0: \x{1ff}
725:
726: /\x{100}+\x{200}/8DZ
727: ------------------------------------------------------------------
728: Bra
729: \x{100}++
730: \x{200}
731: Ket
732: End
733: ------------------------------------------------------------------
734: Capturing subpattern count = 0
735: Options: utf
736: First char = \x{c4}
737: Need char = \x{80}
738:
739: /\x{100}+X/8DZ
740: ------------------------------------------------------------------
741: Bra
742: \x{100}++
743: X
744: Ket
745: End
746: ------------------------------------------------------------------
747: Capturing subpattern count = 0
748: Options: utf
749: First char = \x{c4}
750: Need char = 'X'
751:
752: /^[\QĀ\E-\QŐ\E/BZ8
753: Failed: missing terminating ] for character class at offset 15
754:
755: /-- This tests the stricter UTF-8 check according to RFC 3629. --/
756:
757: /X/8
758: \x{d800}
759: Error -10 (bad UTF-8 string) offset=0 reason=14
760: \x{d800}\?
761: No match
762: \x{da00}
763: Error -10 (bad UTF-8 string) offset=0 reason=14
764: \x{da00}\?
765: No match
766: \x{dfff}
767: Error -10 (bad UTF-8 string) offset=0 reason=14
768: \x{dfff}\?
769: No match
770: \x{110000}
771: Error -10 (bad UTF-8 string) offset=0 reason=13
772: \x{110000}\?
773: No match
774: \x{2000000}
775: Error -10 (bad UTF-8 string) offset=0 reason=11
776: \x{2000000}\?
777: No match
778: \x{7fffffff}
779: Error -10 (bad UTF-8 string) offset=0 reason=12
780: \x{7fffffff}\?
781: No match
782:
783: /(*UTF8)\x{1234}/
784: abcd\x{1234}pqr
785: 0: \x{1234}
786:
1.1.1.4 ! misho 787: /(*CRLF)(*UTF)(*BSR_UNICODE)a\Rb/I
1.1.1.2 misho 788: Capturing subpattern count = 0
789: Options: bsr_unicode utf
790: Forced newline sequence: CRLF
791: First char = 'a'
792: Need char = 'b'
793:
794: /\h/SI8
795: Capturing subpattern count = 0
796: Options: utf
797: No first char
798: No need char
799: Subject length lower bound = 1
800: Starting byte set: \x09 \x20 \xc2 \xe1 \xe2 \xe3
801: ABC\x{09}
802: 0: \x{09}
803: ABC\x{20}
804: 0:
805: ABC\x{a0}
806: 0: \x{a0}
807: ABC\x{1680}
808: 0: \x{1680}
809: ABC\x{180e}
810: 0: \x{180e}
811: ABC\x{2000}
812: 0: \x{2000}
813: ABC\x{202f}
814: 0: \x{202f}
815: ABC\x{205f}
816: 0: \x{205f}
817: ABC\x{3000}
818: 0: \x{3000}
819:
820: /\v/SI8
821: Capturing subpattern count = 0
822: Options: utf
823: No first char
824: No need char
825: Subject length lower bound = 1
826: Starting byte set: \x0a \x0b \x0c \x0d \xc2 \xe2
827: ABC\x{0a}
828: 0: \x{0a}
829: ABC\x{0b}
830: 0: \x{0b}
831: ABC\x{0c}
832: 0: \x{0c}
833: ABC\x{0d}
834: 0: \x{0d}
835: ABC\x{85}
836: 0: \x{85}
837: ABC\x{2028}
838: 0: \x{2028}
839:
840: /\h*A/SI8
841: Capturing subpattern count = 0
842: Options: utf
843: No first char
844: Need char = 'A'
845: Subject length lower bound = 1
846: Starting byte set: \x09 \x20 A \xc2 \xe1 \xe2 \xe3
847: CDBABC
848: 0: A
849:
850: /\v+A/SI8
851: Capturing subpattern count = 0
852: Options: utf
853: No first char
854: Need char = 'A'
855: Subject length lower bound = 2
856: Starting byte set: \x0a \x0b \x0c \x0d \xc2 \xe2
857:
858: /\s?xxx\s/8SI
859: Capturing subpattern count = 0
860: Options: utf
861: No first char
862: Need char = 'x'
863: Subject length lower bound = 4
864: Starting byte set: \x09 \x0a \x0c \x0d \x20 x
865:
866: /\sxxx\s/I8ST1
867: Capturing subpattern count = 0
868: Options: utf
869: No first char
870: Need char = 'x'
871: Subject length lower bound = 5
872: Starting byte set: \x09 \x0a \x0c \x0d \x20 \xc2
873: AB\x{85}xxx\x{a0}XYZ
874: 0: \x{85}xxx\x{a0}
875: AB\x{a0}xxx\x{85}XYZ
876: 0: \x{a0}xxx\x{85}
877:
878: /\S \S/I8ST1
879: Capturing subpattern count = 0
880: Options: utf
881: No first char
882: Need char = ' '
883: Subject length lower bound = 3
884: Starting byte set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0b \x0e
885: \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d
886: \x1e \x1f ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 9 : ; < = > ? @
887: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z [ \ ] ^ _ ` a b c d e
888: f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f \xc0 \xc1 \xc2 \xc3
889: \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 \xd1 \xd2
890: \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd \xde \xdf \xe0 \xe1
891: \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec \xed \xee \xef \xf0
892: \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd \xfe \xff
893: \x{a2} \x{84}
894: 0: \x{a2} \x{84}
895: A Z
896: 0: A Z
897:
898: /a+/8
899: a\x{123}aa\>1
900: 0: aa
901: a\x{123}aa\>2
902: Error -11 (bad UTF-8 offset)
903: a\x{123}aa\>3
904: 0: aa
905: a\x{123}aa\>4
906: 0: a
907: a\x{123}aa\>5
908: No match
909: a\x{123}aa\>6
910: Error -24 (bad offset value)
911:
912: /\x{1234}+/iS8I
913: Capturing subpattern count = 0
914: Options: caseless utf
915: No first char
916: No need char
917: Subject length lower bound = 1
918: Starting byte set: \xe1
919:
920: /\x{1234}+?/iS8I
921: Capturing subpattern count = 0
922: Options: caseless utf
923: No first char
924: No need char
925: Subject length lower bound = 1
926: Starting byte set: \xe1
927:
928: /\x{1234}++/iS8I
929: Capturing subpattern count = 0
930: Options: caseless utf
931: No first char
932: No need char
933: Subject length lower bound = 1
934: Starting byte set: \xe1
935:
936: /\x{1234}{2}/iS8I
937: Capturing subpattern count = 0
938: Options: caseless utf
939: No first char
940: No need char
941: Subject length lower bound = 2
942: Starting byte set: \xe1
943:
944: /[^\x{c4}]/8DZ
945: ------------------------------------------------------------------
946: Bra
1.1.1.3 misho 947: [^\x{c4}]
1.1.1.2 misho 948: Ket
949: End
950: ------------------------------------------------------------------
951: Capturing subpattern count = 0
952: Options: utf
953: No first char
954: No need char
955:
956: /X+\x{200}/8DZ
957: ------------------------------------------------------------------
958: Bra
959: X++
960: \x{200}
961: Ket
962: End
963: ------------------------------------------------------------------
964: Capturing subpattern count = 0
965: Options: utf
966: First char = 'X'
967: Need char = \x{80}
968:
969: /\R/SI8
970: Capturing subpattern count = 0
971: Options: utf
972: No first char
973: No need char
974: Subject length lower bound = 1
975: Starting byte set: \x0a \x0b \x0c \x0d \xc2 \xe2
976:
977: /\777/8DZ
978: ------------------------------------------------------------------
979: Bra
980: \x{1ff}
981: Ket
982: End
983: ------------------------------------------------------------------
984: Capturing subpattern count = 0
985: Options: utf
986: First char = \x{c7}
987: Need char = \x{bf}
1.1 misho 988:
1.1.1.3 misho 989: /\w+\x{C4}/8BZ
990: ------------------------------------------------------------------
991: Bra
992: \w++
993: \x{c4}
994: Ket
995: End
996: ------------------------------------------------------------------
997: a\x{C4}\x{C4}
998: 0: a\x{c4}
999:
1000: /\w+\x{C4}/8BZT1
1001: ------------------------------------------------------------------
1002: Bra
1003: \w+
1004: \x{c4}
1005: Ket
1006: End
1007: ------------------------------------------------------------------
1008: a\x{C4}\x{C4}
1009: 0: a\x{c4}\x{c4}
1010:
1011: /\W+\x{C4}/8BZ
1012: ------------------------------------------------------------------
1013: Bra
1014: \W+
1015: \x{c4}
1016: Ket
1017: End
1018: ------------------------------------------------------------------
1019: !\x{C4}
1020: 0: !\x{c4}
1021:
1022: /\W+\x{C4}/8BZT1
1023: ------------------------------------------------------------------
1024: Bra
1025: \W++
1026: \x{c4}
1027: Ket
1028: End
1029: ------------------------------------------------------------------
1030: !\x{C4}
1031: 0: !\x{c4}
1032:
1033: /\W+\x{A1}/8BZ
1034: ------------------------------------------------------------------
1035: Bra
1036: \W+
1037: \x{a1}
1038: Ket
1039: End
1040: ------------------------------------------------------------------
1041: !\x{A1}
1042: 0: !\x{a1}
1043:
1044: /\W+\x{A1}/8BZT1
1045: ------------------------------------------------------------------
1046: Bra
1047: \W+
1048: \x{a1}
1049: Ket
1050: End
1051: ------------------------------------------------------------------
1052: !\x{A1}
1053: 0: !\x{a1}
1054:
1055: /X\s+\x{A0}/8BZ
1056: ------------------------------------------------------------------
1057: Bra
1058: X
1059: \s++
1060: \x{a0}
1061: Ket
1062: End
1063: ------------------------------------------------------------------
1064: X\x20\x{A0}\x{A0}
1065: 0: X \x{a0}
1066:
1067: /X\s+\x{A0}/8BZT1
1068: ------------------------------------------------------------------
1069: Bra
1070: X
1071: \s+
1072: \x{a0}
1073: Ket
1074: End
1075: ------------------------------------------------------------------
1076: X\x20\x{A0}\x{A0}
1077: 0: X \x{a0}\x{a0}
1078:
1079: /\S+\x{A0}/8BZ
1080: ------------------------------------------------------------------
1081: Bra
1082: \S+
1083: \x{a0}
1084: Ket
1085: End
1086: ------------------------------------------------------------------
1087: X\x{A0}\x{A0}
1088: 0: X\x{a0}\x{a0}
1089:
1090: /\S+\x{A0}/8BZT1
1091: ------------------------------------------------------------------
1092: Bra
1093: \S++
1094: \x{a0}
1095: Ket
1096: End
1097: ------------------------------------------------------------------
1098: X\x{A0}\x{A0}
1099: 0: X\x{a0}
1100:
1101: /\x{a0}+\s!/8BZ
1102: ------------------------------------------------------------------
1103: Bra
1104: \x{a0}++
1105: \s
1106: !
1107: Ket
1108: End
1109: ------------------------------------------------------------------
1110: \x{a0}\x20!
1111: 0: \x{a0} !
1112:
1113: /\x{a0}+\s!/8BZT1
1114: ------------------------------------------------------------------
1115: Bra
1116: \x{a0}+
1117: \s
1118: !
1119: Ket
1120: End
1121: ------------------------------------------------------------------
1122: \x{a0}\x20!
1123: 0: \x{a0} !
1124:
1.1.1.4 ! misho 1125: /A/8
! 1126: \x{ff000041}
! 1127: ** Character \x{ff000041} is greater than 0x7fffffff and so cannot be converted to UTF-8
! 1128: \x{7f000041}
! 1129: Error -10 (bad UTF-8 string) offset=0 reason=12
! 1130:
! 1131: /(*UTF8)abc/9
! 1132: Failed: setting UTF is disabled by the application at offset 0
! 1133:
! 1134: /abc/89
! 1135: Failed: setting UTF is disabled by the application at offset 0
! 1136:
1.1 misho 1137: /-- End of testinput15 --/
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/icons/cvsweb/back.gif){kind=icon}
Return to testoutput15 CVS log ![[TXT]](/icons/cvsweb/text.gif){kind=icon}
![[DIR]](/icons/cvsweb/dir.gif){kind=icon}
Up to [ELWIX - Embedded LightWeight unIX -] / embedaddon / pcre / testdata