File:  [ELWIX - Embedded LightWeight unIX -] / embedaddon / pcre / testdata / testoutput15
Revision 1.1.1.2 (vendor branch): download - view: text, annotated - select for diffs - revision graph
Tue Feb 21 23:50:25 2012 UTC (12 years, 5 months ago) by misho
Branches: pcre, MAIN
CVS tags: v8_30, HEAD
pcre

    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: ------------------------------------------------------------------
   82: Capturing subpattern count = 0
   83: Options: utf no_utf_check
   84: First char = \x{c3}
   85: Need char = 'x'
   86: 
   87: /abc/8
   88:     ]
   89: Error -10 (bad UTF-8 string) offset=0 reason=6
   90:     
   91: Error -10 (bad UTF-8 string) offset=0 reason=1
   92:     
   93: Error -10 (bad UTF-8 string) offset=0 reason=6
   94:     \?
   95: No match
   96:     \xe1\x88 
   97: Error -10 (bad UTF-8 string) offset=0 reason=1
   98:     \P\xe1\x88 
   99: Error -10 (bad UTF-8 string) offset=0 reason=1
  100:     \P\P\xe1\x88 
  101: Error -25 (short UTF-8 string) offset=0 reason=1
  102:     XX\xea
  103: Error -10 (bad UTF-8 string) offset=2 reason=2
  104:     \O0XX\xea
  105: Error -10 (bad UTF-8 string)
  106:     \O1XX\xea
  107: Error -10 (bad UTF-8 string)
  108:     \O2XX\xea
  109: Error -10 (bad UTF-8 string) offset=2 reason=2
  110:     XX\xf1
  111: Error -10 (bad UTF-8 string) offset=2 reason=3
  112:     XX\xf8  
  113: Error -10 (bad UTF-8 string) offset=2 reason=4
  114:     XX\xfc
  115: Error -10 (bad UTF-8 string) offset=2 reason=5
  116:     ZZ\xea\xaf\x20YY
  117: Error -10 (bad UTF-8 string) offset=2 reason=7
  118:     ZZ\xfd\xbf\xbf\x2f\xbf\xbfYY  
  119: Error -10 (bad UTF-8 string) offset=2 reason=8
  120:     ZZ\xfd\xbf\xbf\xbf\x2f\xbfYY  
  121: Error -10 (bad UTF-8 string) offset=2 reason=9
  122:     ZZ\xfd\xbf\xbf\xbf\xbf\x2fYY  
  123: Error -10 (bad UTF-8 string) offset=2 reason=10
  124:     ZZ\xffYY
  125: Error -10 (bad UTF-8 string) offset=2 reason=21
  126:     ZZ\xfeYY  
  127: Error -10 (bad UTF-8 string) offset=2 reason=21
  128: 
  129: /anything/8
  130:     \xc0\x80
  131: Error -10 (bad UTF-8 string) offset=0 reason=15
  132:     \xc1\x8f 
  133: Error -10 (bad UTF-8 string) offset=0 reason=15
  134:     \xe0\x9f\x80
  135: Error -10 (bad UTF-8 string) offset=0 reason=16
  136:     \xf0\x8f\x80\x80 
  137: Error -10 (bad UTF-8 string) offset=0 reason=17
  138:     \xf8\x87\x80\x80\x80  
  139: Error -10 (bad UTF-8 string) offset=0 reason=18
  140:     \xfc\x83\x80\x80\x80\x80
  141: Error -10 (bad UTF-8 string) offset=0 reason=19
  142:     \xfe\x80\x80\x80\x80\x80  
  143: Error -10 (bad UTF-8 string) offset=0 reason=21
  144:     \xff\x80\x80\x80\x80\x80  
  145: Error -10 (bad UTF-8 string) offset=0 reason=21
  146:     \xc3\x8f
  147: No match
  148:     \xe0\xaf\x80
  149: No match
  150:     \xe1\x80\x80
  151: No match
  152:     \xf0\x9f\x80\x80 
  153: No match
  154:     \xf1\x8f\x80\x80 
  155: No match
  156:     \xf8\x88\x80\x80\x80  
  157: Error -10 (bad UTF-8 string) offset=0 reason=11
  158:     \xf9\x87\x80\x80\x80  
  159: Error -10 (bad UTF-8 string) offset=0 reason=11
  160:     \xfc\x84\x80\x80\x80\x80
  161: Error -10 (bad UTF-8 string) offset=0 reason=12
  162:     \xfd\x83\x80\x80\x80\x80
  163: Error -10 (bad UTF-8 string) offset=0 reason=12
  164:     \?\xf8\x88\x80\x80\x80  
  165: No match
  166:     \?\xf9\x87\x80\x80\x80  
  167: No match
  168:     \?\xfc\x84\x80\x80\x80\x80
  169: No match
  170:     \?\xfd\x83\x80\x80\x80\x80
  171: No match
  172: 
  173: /\x{100}/8DZ
  174: ------------------------------------------------------------------
  175:         Bra
  176:         \x{100}
  177:         Ket
  178:         End
  179: ------------------------------------------------------------------
  180: Capturing subpattern count = 0
  181: Options: utf
  182: First char = \x{c4}
  183: Need char = \x{80}
  184: 
  185: /\x{1000}/8DZ
  186: ------------------------------------------------------------------
  187:         Bra
  188:         \x{1000}
  189:         Ket
  190:         End
  191: ------------------------------------------------------------------
  192: Capturing subpattern count = 0
  193: Options: utf
  194: First char = \x{e1}
  195: Need char = \x{80}
  196: 
  197: /\x{10000}/8DZ
  198: ------------------------------------------------------------------
  199:         Bra
  200:         \x{10000}
  201:         Ket
  202:         End
  203: ------------------------------------------------------------------
  204: Capturing subpattern count = 0
  205: Options: utf
  206: First char = \x{f0}
  207: Need char = \x{80}
  208: 
  209: /\x{100000}/8DZ
  210: ------------------------------------------------------------------
  211:         Bra
  212:         \x{100000}
  213:         Ket
  214:         End
  215: ------------------------------------------------------------------
  216: Capturing subpattern count = 0
  217: Options: utf
  218: First char = \x{f4}
  219: Need char = \x{80}
  220: 
  221: /\x{10ffff}/8DZ
  222: ------------------------------------------------------------------
  223:         Bra
  224:         \x{10ffff}
  225:         Ket
  226:         End
  227: ------------------------------------------------------------------
  228: Capturing subpattern count = 0
  229: Options: utf
  230: First char = \x{f4}
  231: Need char = \x{bf}
  232: 
  233: /[\x{ff}]/8DZ
  234: ------------------------------------------------------------------
  235:         Bra
  236:         \x{ff}
  237:         Ket
  238:         End
  239: ------------------------------------------------------------------
  240: Capturing subpattern count = 0
  241: Options: utf
  242: First char = \x{c3}
  243: Need char = \x{bf}
  244: 
  245: /[\x{100}]/8DZ
  246: ------------------------------------------------------------------
  247:         Bra
  248:         \x{100}
  249:         Ket
  250:         End
  251: ------------------------------------------------------------------
  252: Capturing subpattern count = 0
  253: Options: utf
  254: First char = \x{c4}
  255: Need char = \x{80}
  256: 
  257: /\x80/8DZ
  258: ------------------------------------------------------------------
  259:         Bra
  260:         \x{80}
  261:         Ket
  262:         End
  263: ------------------------------------------------------------------
  264: Capturing subpattern count = 0
  265: Options: utf
  266: First char = \x{c2}
  267: Need char = \x{80}
  268: 
  269: /\xff/8DZ
  270: ------------------------------------------------------------------
  271:         Bra
  272:         \x{ff}
  273:         Ket
  274:         End
  275: ------------------------------------------------------------------
  276: Capturing subpattern count = 0
  277: Options: utf
  278: First char = \x{c3}
  279: Need char = \x{bf}
  280: 
  281: /\x{D55c}\x{ad6d}\x{C5B4}/DZ8 
  282: ------------------------------------------------------------------
  283:         Bra
  284:         \x{d55c}\x{ad6d}\x{c5b4}
  285:         Ket
  286:         End
  287: ------------------------------------------------------------------
  288: Capturing subpattern count = 0
  289: Options: utf
  290: First char = \x{ed}
  291: Need char = \x{b4}
  292:     \x{D55c}\x{ad6d}\x{C5B4} 
  293:  0: \x{d55c}\x{ad6d}\x{c5b4}
  294: 
  295: /\x{65e5}\x{672c}\x{8a9e}/DZ8
  296: ------------------------------------------------------------------
  297:         Bra
  298:         \x{65e5}\x{672c}\x{8a9e}
  299:         Ket
  300:         End
  301: ------------------------------------------------------------------
  302: Capturing subpattern count = 0
  303: Options: utf
  304: First char = \x{e6}
  305: Need char = \x{9e}
  306:     \x{65e5}\x{672c}\x{8a9e}
  307:  0: \x{65e5}\x{672c}\x{8a9e}
  308: 
  309: /\x{80}/DZ8
  310: ------------------------------------------------------------------
  311:         Bra
  312:         \x{80}
  313:         Ket
  314:         End
  315: ------------------------------------------------------------------
  316: Capturing subpattern count = 0
  317: Options: utf
  318: First char = \x{c2}
  319: Need char = \x{80}
  320: 
  321: /\x{084}/DZ8
  322: ------------------------------------------------------------------
  323:         Bra
  324:         \x{84}
  325:         Ket
  326:         End
  327: ------------------------------------------------------------------
  328: Capturing subpattern count = 0
  329: Options: utf
  330: First char = \x{c2}
  331: Need char = \x{84}
  332: 
  333: /\x{104}/DZ8
  334: ------------------------------------------------------------------
  335:         Bra
  336:         \x{104}
  337:         Ket
  338:         End
  339: ------------------------------------------------------------------
  340: Capturing subpattern count = 0
  341: Options: utf
  342: First char = \x{c4}
  343: Need char = \x{84}
  344: 
  345: /\x{861}/DZ8
  346: ------------------------------------------------------------------
  347:         Bra
  348:         \x{861}
  349:         Ket
  350:         End
  351: ------------------------------------------------------------------
  352: Capturing subpattern count = 0
  353: Options: utf
  354: First char = \x{e0}
  355: Need char = \x{a1}
  356: 
  357: /\x{212ab}/DZ8
  358: ------------------------------------------------------------------
  359:         Bra
  360:         \x{212ab}
  361:         Ket
  362:         End
  363: ------------------------------------------------------------------
  364: Capturing subpattern count = 0
  365: Options: utf
  366: First char = \x{f0}
  367: Need char = \x{ab}
  368: 
  369: /-- This one is here not because it's different to Perl, but because the way
  370: the captured single-byte is displayed. (In Perl it becomes a character, and you
  371: can't tell the difference.) --/
  372:     
  373: /X(\C)(.*)/8
  374:     X\x{1234}
  375:  0: X\x{1234}
  376:  1: \x{e1}
  377:  2: \x{88}\x{b4}
  378:     X\nabc 
  379:  0: X\x{0a}abc
  380:  1: \x{0a}
  381:  2: abc
  382: 
  383: /-- This one is here because Perl gives out a grumbly error message (quite 
  384: correctly, but that messes up comparisons). --/
  385:     
  386: /a\Cb/8
  387:     *** Failers 
  388: No match
  389:     a\x{100}b 
  390: No match
  391:     
  392: /[^ab\xC0-\xF0]/8SDZ
  393: ------------------------------------------------------------------
  394:         Bra
  395:         [\x00-`c-\xbf\xf1-\xff] (neg)
  396:         Ket
  397:         End
  398: ------------------------------------------------------------------
  399: Capturing subpattern count = 0
  400: Options: utf
  401: No first char
  402: No need char
  403: Subject length lower bound = 1
  404: Starting byte set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
  405:   \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 
  406:   \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 
  407:   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 
  408:   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 
  409:   \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 
  410:   \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd \xde \xdf 
  411:   \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec \xed \xee 
  412:   \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd 
  413:   \xfe \xff 
  414:     \x{f1}
  415:  0: \x{f1}
  416:     \x{bf}
  417:  0: \x{bf}
  418:     \x{100}
  419:  0: \x{100}
  420:     \x{1000}   
  421:  0: \x{1000}
  422:     *** Failers
  423:  0: *
  424:     \x{c0} 
  425: No match
  426:     \x{f0} 
  427: No match
  428: 
  429: /Ā{3,4}/8SDZ
  430: ------------------------------------------------------------------
  431:         Bra
  432:         \x{100}{3}
  433:         \x{100}?
  434:         Ket
  435:         End
  436: ------------------------------------------------------------------
  437: Capturing subpattern count = 0
  438: Options: utf
  439: First char = \x{c4}
  440: Need char = \x{80}
  441: Subject length lower bound = 3
  442: No set of starting bytes
  443:   \x{100}\x{100}\x{100}\x{100\x{100}
  444:  0: \x{100}\x{100}\x{100}
  445: 
  446: /(\x{100}+|x)/8SDZ
  447: ------------------------------------------------------------------
  448:         Bra
  449:         CBra 1
  450:         \x{100}+
  451:         Alt
  452:         x
  453:         Ket
  454:         Ket
  455:         End
  456: ------------------------------------------------------------------
  457: Capturing subpattern count = 1
  458: Options: utf
  459: No first char
  460: No need char
  461: Subject length lower bound = 1
  462: Starting byte set: x \xc4 
  463: 
  464: /(\x{100}*a|x)/8SDZ
  465: ------------------------------------------------------------------
  466:         Bra
  467:         CBra 1
  468:         \x{100}*+
  469:         a
  470:         Alt
  471:         x
  472:         Ket
  473:         Ket
  474:         End
  475: ------------------------------------------------------------------
  476: Capturing subpattern count = 1
  477: Options: utf
  478: No first char
  479: No need char
  480: Subject length lower bound = 1
  481: Starting byte set: a x \xc4 
  482: 
  483: /(\x{100}{0,2}a|x)/8SDZ
  484: ------------------------------------------------------------------
  485:         Bra
  486:         CBra 1
  487:         \x{100}{0,2}
  488:         a
  489:         Alt
  490:         x
  491:         Ket
  492:         Ket
  493:         End
  494: ------------------------------------------------------------------
  495: Capturing subpattern count = 1
  496: Options: utf
  497: No first char
  498: No need char
  499: Subject length lower bound = 1
  500: Starting byte set: a x \xc4 
  501: 
  502: /(\x{100}{1,2}a|x)/8SDZ
  503: ------------------------------------------------------------------
  504:         Bra
  505:         CBra 1
  506:         \x{100}
  507:         \x{100}{0,1}
  508:         a
  509:         Alt
  510:         x
  511:         Ket
  512:         Ket
  513:         End
  514: ------------------------------------------------------------------
  515: Capturing subpattern count = 1
  516: Options: utf
  517: No first char
  518: No need char
  519: Subject length lower bound = 1
  520: Starting byte set: x \xc4 
  521: 
  522: /\x{100}/8DZ
  523: ------------------------------------------------------------------
  524:         Bra
  525:         \x{100}
  526:         Ket
  527:         End
  528: ------------------------------------------------------------------
  529: Capturing subpattern count = 0
  530: Options: utf
  531: First char = \x{c4}
  532: Need char = \x{80}
  533: 
  534: /a\x{100}\x{101}*/8DZ
  535: ------------------------------------------------------------------
  536:         Bra
  537:         a\x{100}
  538:         \x{101}*
  539:         Ket
  540:         End
  541: ------------------------------------------------------------------
  542: Capturing subpattern count = 0
  543: Options: utf
  544: First char = 'a'
  545: Need char = \x{80}
  546: 
  547: /a\x{100}\x{101}+/8DZ
  548: ------------------------------------------------------------------
  549:         Bra
  550:         a\x{100}
  551:         \x{101}+
  552:         Ket
  553:         End
  554: ------------------------------------------------------------------
  555: Capturing subpattern count = 0
  556: Options: utf
  557: First char = 'a'
  558: Need char = \x{81}
  559: 
  560: /[^\x{c4}]/DZ
  561: ------------------------------------------------------------------
  562:         Bra
  563:         [^\xc4]
  564:         Ket
  565:         End
  566: ------------------------------------------------------------------
  567: Capturing subpattern count = 0
  568: No options
  569: No first char
  570: No need char
  571: 
  572: /[\x{100}]/8DZ
  573: ------------------------------------------------------------------
  574:         Bra
  575:         \x{100}
  576:         Ket
  577:         End
  578: ------------------------------------------------------------------
  579: Capturing subpattern count = 0
  580: Options: utf
  581: First char = \x{c4}
  582: Need char = \x{80}
  583:     \x{100}
  584:  0: \x{100}
  585:     Z\x{100}
  586:  0: \x{100}
  587:     \x{100}Z
  588:  0: \x{100}
  589:     *** Failers 
  590: No match
  591: 
  592: /[\xff]/DZ8
  593: ------------------------------------------------------------------
  594:         Bra
  595:         \x{ff}
  596:         Ket
  597:         End
  598: ------------------------------------------------------------------
  599: Capturing subpattern count = 0
  600: Options: utf
  601: First char = \x{c3}
  602: Need char = \x{bf}
  603:     >\x{ff}<
  604:  0: \x{ff}
  605: 
  606: /[^\xff]/8DZ
  607: ------------------------------------------------------------------
  608:         Bra
  609:         [\x00-\xfe] (neg)
  610:         Ket
  611:         End
  612: ------------------------------------------------------------------
  613: Capturing subpattern count = 0
  614: Options: utf
  615: No first char
  616: No need char
  617: 
  618: /\x{100}abc(xyz(?1))/8DZ
  619: ------------------------------------------------------------------
  620:         Bra
  621:         \x{100}abc
  622:         CBra 1
  623:         xyz
  624:         Recurse
  625:         Ket
  626:         Ket
  627:         End
  628: ------------------------------------------------------------------
  629: Capturing subpattern count = 1
  630: Options: utf
  631: First char = \x{c4}
  632: Need char = 'z'
  633: 
  634: /a\x{1234}b/P8
  635:     a\x{1234}b
  636:  0: a\x{1234}b
  637: 
  638: /\777/8I
  639: Capturing subpattern count = 0
  640: Options: utf
  641: First char = \x{c7}
  642: Need char = \x{bf}
  643:   \x{1ff}
  644:  0: \x{1ff}
  645:   \777 
  646:  0: \x{1ff}
  647:   
  648: /\x{100}+\x{200}/8DZ
  649: ------------------------------------------------------------------
  650:         Bra
  651:         \x{100}++
  652:         \x{200}
  653:         Ket
  654:         End
  655: ------------------------------------------------------------------
  656: Capturing subpattern count = 0
  657: Options: utf
  658: First char = \x{c4}
  659: Need char = \x{80}
  660: 
  661: /\x{100}+X/8DZ
  662: ------------------------------------------------------------------
  663:         Bra
  664:         \x{100}++
  665:         X
  666:         Ket
  667:         End
  668: ------------------------------------------------------------------
  669: Capturing subpattern count = 0
  670: Options: utf
  671: First char = \x{c4}
  672: Need char = 'X'
  673: 
  674: /^[\QĀ\E-\QŐ\E/BZ8
  675: Failed: missing terminating ] for character class at offset 15
  676: 
  677: /-- This tests the stricter UTF-8 check according to RFC 3629. --/ 
  678:     
  679: /X/8
  680:     \x{0}\x{d7ff}\x{e000}\x{10ffff}
  681: No match
  682:     \x{d800}
  683: Error -10 (bad UTF-8 string) offset=0 reason=14
  684:     \x{d800}\?
  685: No match
  686:     \x{da00}
  687: Error -10 (bad UTF-8 string) offset=0 reason=14
  688:     \x{da00}\?
  689: No match
  690:     \x{dfff}
  691: Error -10 (bad UTF-8 string) offset=0 reason=14
  692:     \x{dfff}\?
  693: No match
  694:     \x{110000}    
  695: Error -10 (bad UTF-8 string) offset=0 reason=13
  696:     \x{110000}\?    
  697: No match
  698:     \x{2000000} 
  699: Error -10 (bad UTF-8 string) offset=0 reason=11
  700:     \x{2000000}\? 
  701: No match
  702:     \x{7fffffff} 
  703: Error -10 (bad UTF-8 string) offset=0 reason=12
  704:     \x{7fffffff}\? 
  705: No match
  706: 
  707: /(*UTF8)\x{1234}/
  708:   abcd\x{1234}pqr
  709:  0: \x{1234}
  710: 
  711: /(*CRLF)(*UTF8)(*BSR_UNICODE)a\Rb/I
  712: Capturing subpattern count = 0
  713: Options: bsr_unicode utf
  714: Forced newline sequence: CRLF
  715: First char = 'a'
  716: Need char = 'b'
  717: 
  718: /\h/SI8
  719: Capturing subpattern count = 0
  720: Options: utf
  721: No first char
  722: No need char
  723: Subject length lower bound = 1
  724: Starting byte set: \x09 \x20 \xc2 \xe1 \xe2 \xe3 
  725:     ABC\x{09}
  726:  0: \x{09}
  727:     ABC\x{20}
  728:  0:  
  729:     ABC\x{a0}
  730:  0: \x{a0}
  731:     ABC\x{1680}
  732:  0: \x{1680}
  733:     ABC\x{180e}
  734:  0: \x{180e}
  735:     ABC\x{2000}
  736:  0: \x{2000}
  737:     ABC\x{202f} 
  738:  0: \x{202f}
  739:     ABC\x{205f} 
  740:  0: \x{205f}
  741:     ABC\x{3000} 
  742:  0: \x{3000}
  743: 
  744: /\v/SI8
  745: Capturing subpattern count = 0
  746: Options: utf
  747: No first char
  748: No need char
  749: Subject length lower bound = 1
  750: Starting byte set: \x0a \x0b \x0c \x0d \xc2 \xe2 
  751:     ABC\x{0a}
  752:  0: \x{0a}
  753:     ABC\x{0b}
  754:  0: \x{0b}
  755:     ABC\x{0c}
  756:  0: \x{0c}
  757:     ABC\x{0d}
  758:  0: \x{0d}
  759:     ABC\x{85}
  760:  0: \x{85}
  761:     ABC\x{2028}
  762:  0: \x{2028}
  763: 
  764: /\h*A/SI8
  765: Capturing subpattern count = 0
  766: Options: utf
  767: No first char
  768: Need char = 'A'
  769: Subject length lower bound = 1
  770: Starting byte set: \x09 \x20 A \xc2 \xe1 \xe2 \xe3 
  771:     CDBABC
  772:  0: A
  773:     
  774: /\v+A/SI8
  775: Capturing subpattern count = 0
  776: Options: utf
  777: No first char
  778: Need char = 'A'
  779: Subject length lower bound = 2
  780: Starting byte set: \x0a \x0b \x0c \x0d \xc2 \xe2 
  781: 
  782: /\s?xxx\s/8SI
  783: Capturing subpattern count = 0
  784: Options: utf
  785: No first char
  786: Need char = 'x'
  787: Subject length lower bound = 4
  788: Starting byte set: \x09 \x0a \x0c \x0d \x20 x 
  789: 
  790: /\sxxx\s/I8ST1
  791: Capturing subpattern count = 0
  792: Options: utf
  793: No first char
  794: Need char = 'x'
  795: Subject length lower bound = 5
  796: Starting byte set: \x09 \x0a \x0c \x0d \x20 \xc2 
  797:     AB\x{85}xxx\x{a0}XYZ
  798:  0: \x{85}xxx\x{a0}
  799:     AB\x{a0}xxx\x{85}XYZ
  800:  0: \x{a0}xxx\x{85}
  801: 
  802: /\S \S/I8ST1
  803: Capturing subpattern count = 0
  804: Options: utf
  805: No first char
  806: Need char = ' '
  807: Subject length lower bound = 3
  808: Starting byte set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x0b \x0e 
  809:   \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1a \x1b \x1c \x1d 
  810:   \x1e \x1f ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 9 : ; < = > ? @ 
  811:   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 
  812:   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 
  813:   \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 \xd1 \xd2 
  814:   \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd \xde \xdf \xe0 \xe1 
  815:   \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec \xed \xee \xef \xf0 
  816:   \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd \xfe \xff 
  817:     \x{a2} \x{84} 
  818:  0: \x{a2} \x{84}
  819:     A Z 
  820:  0: A Z
  821: 
  822: /a+/8
  823:     a\x{123}aa\>1
  824:  0: aa
  825:     a\x{123}aa\>2
  826: Error -11 (bad UTF-8 offset)
  827:     a\x{123}aa\>3
  828:  0: aa
  829:     a\x{123}aa\>4
  830:  0: a
  831:     a\x{123}aa\>5
  832: No match
  833:     a\x{123}aa\>6
  834: Error -24 (bad offset value)
  835: 
  836: /\x{1234}+/iS8I
  837: Capturing subpattern count = 0
  838: Options: caseless utf
  839: No first char
  840: No need char
  841: Subject length lower bound = 1
  842: Starting byte set: \xe1 
  843: 
  844: /\x{1234}+?/iS8I
  845: Capturing subpattern count = 0
  846: Options: caseless utf
  847: No first char
  848: No need char
  849: Subject length lower bound = 1
  850: Starting byte set: \xe1 
  851: 
  852: /\x{1234}++/iS8I
  853: Capturing subpattern count = 0
  854: Options: caseless utf
  855: No first char
  856: No need char
  857: Subject length lower bound = 1
  858: Starting byte set: \xe1 
  859: 
  860: /\x{1234}{2}/iS8I
  861: Capturing subpattern count = 0
  862: Options: caseless utf
  863: No first char
  864: No need char
  865: Subject length lower bound = 2
  866: Starting byte set: \xe1 
  867: 
  868: /[^\x{c4}]/8DZ
  869: ------------------------------------------------------------------
  870:         Bra
  871:         [\x00-\xc3\xc5-\xff] (neg)
  872:         Ket
  873:         End
  874: ------------------------------------------------------------------
  875: Capturing subpattern count = 0
  876: Options: utf
  877: No first char
  878: No need char
  879: 
  880: /X+\x{200}/8DZ
  881: ------------------------------------------------------------------
  882:         Bra
  883:         X++
  884:         \x{200}
  885:         Ket
  886:         End
  887: ------------------------------------------------------------------
  888: Capturing subpattern count = 0
  889: Options: utf
  890: First char = 'X'
  891: Need char = \x{80}
  892: 
  893: /\R/SI8
  894: Capturing subpattern count = 0
  895: Options: utf
  896: No first char
  897: No need char
  898: Subject length lower bound = 1
  899: Starting byte set: \x0a \x0b \x0c \x0d \xc2 \xe2 
  900: 
  901: /\777/8DZ
  902: ------------------------------------------------------------------
  903:         Bra
  904:         \x{1ff}
  905:         Ket
  906:         End
  907: ------------------------------------------------------------------
  908: Capturing subpattern count = 0
  909: Options: utf
  910: First char = \x{c7}
  911: Need char = \x{bf}
  912: 
  913: /-- End of testinput15 --/

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>