/[pcre]/code/trunk/pcre_internal.h
ViewVC logotype

Diff of /code/trunk/pcre_internal.h

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 461 by ph10, Mon Oct 5 10:59:35 2009 UTC revision 602 by ph10, Wed May 25 08:29:03 2011 UTC
# Line 7  Line 7 
7  and semantics are as close as possible to those of the Perl 5 language.  and semantics are as close as possible to those of the Perl 5 language.
8    
9                         Written by Philip Hazel                         Written by Philip Hazel
10             Copyright (c) 1997-2009 University of Cambridge             Copyright (c) 1997-2010 University of Cambridge
11    
12  -----------------------------------------------------------------------------  -----------------------------------------------------------------------------
13  Redistribution and use in source and binary forms, with or without  Redistribution and use in source and binary forms, with or without
# Line 45  functions whose names all begin with "_p Line 45  functions whose names all begin with "_p
45  #ifndef PCRE_INTERNAL_H  #ifndef PCRE_INTERNAL_H
46  #define PCRE_INTERNAL_H  #define PCRE_INTERNAL_H
47    
48  /* Define DEBUG to get debugging output on stdout. */  /* Define PCRE_DEBUG to get debugging output on stdout. */
49    
50  #if 0  #if 0
51  #define DEBUG  #define PCRE_DEBUG
52  #endif  #endif
53    
54  /* We do not support both EBCDIC and UTF-8 at the same time. The "configure"  /* We do not support both EBCDIC and UTF-8 at the same time. The "configure"
# Line 74  It turns out that the Mac Debugging.h he Line 74  It turns out that the Mac Debugging.h he
74  be absolutely sure we get our version. */  be absolutely sure we get our version. */
75    
76  #undef DPRINTF  #undef DPRINTF
77  #ifdef DEBUG  #ifdef PCRE_DEBUG
78  #define DPRINTF(p) printf p  #define DPRINTF(p) printf p
79  #else  #else
80  #define DPRINTF(p) /* Nothing */  #define DPRINTF(p) /* Nothing */
# Line 86  setjmp and stdarg are used is when NO_RE Line 86  setjmp and stdarg are used is when NO_RE
86    
87  #include <ctype.h>  #include <ctype.h>
88  #include <limits.h>  #include <limits.h>
 #include <setjmp.h>  
 #include <stdarg.h>  
89  #include <stddef.h>  #include <stddef.h>
90  #include <stdio.h>  #include <stdio.h>
91  #include <stdlib.h>  #include <stdlib.h>
# Line 186  preprocessor time in standard C environm Line 184  preprocessor time in standard C environm
184    #error Cannot determine a type for 32-bit unsigned integers    #error Cannot determine a type for 32-bit unsigned integers
185  #endif  #endif
186    
187    /* When checking for integer overflow in pcre_compile(), we need to handle
188    large integers. If a 64-bit integer type is available, we can use that.
189    Otherwise we have to cast to double, which of course requires floating point
190    arithmetic. Handle this by defining a macro for the appropriate type. If
191    stdint.h is available, include it; it may define INT64_MAX. Systems that do not
192    have stdint.h (e.g. Solaris) may have inttypes.h. The macro int64_t may be set
193    by "configure". */
194    
195    #if HAVE_STDINT_H
196    #include <stdint.h>
197    #elif HAVE_INTTYPES_H
198    #include <inttypes.h>
199    #endif
200    
201    #if defined INT64_MAX || defined int64_t
202    #define INT64_OR_DOUBLE int64_t
203    #else
204    #define INT64_OR_DOUBLE double
205    #endif
206    
207  /* All character handling must be done as unsigned characters. Otherwise there  /* All character handling must be done as unsigned characters. Otherwise there
208  are problems with top-bit-set characters and functions such as isspace().  are problems with top-bit-set characters and functions such as isspace().
209  However, we leave the interface to the outside world as char *, because that  However, we leave the interface to the outside world as char *, because that
# Line 390  capturing parenthesis numbers in back re Line 408  capturing parenthesis numbers in back re
408    
409  /* When UTF-8 encoding is being used, a character is no longer just a single  /* When UTF-8 encoding is being used, a character is no longer just a single
410  byte. The macros for character handling generate simple sequences when used in  byte. The macros for character handling generate simple sequences when used in
411  byte-mode, and more complicated ones for UTF-8 characters. BACKCHAR should  byte-mode, and more complicated ones for UTF-8 characters. GETCHARLENTEST is
412  never be called in byte mode. To make sure it can never even appear when UTF-8  not used when UTF-8 is not supported, so it is not defined, and BACKCHAR should
413  support is omitted, we don't even define it. */  never be called in byte mode. To make sure they can never even appear when
414    UTF-8 support is omitted, we don't even define them. */
415    
416  #ifndef SUPPORT_UTF8  #ifndef SUPPORT_UTF8
417  #define GETCHAR(c, eptr) c = *eptr;  #define GETCHAR(c, eptr) c = *eptr;
# Line 400  support is omitted, we don't even define Line 419  support is omitted, we don't even define
419  #define GETCHARINC(c, eptr) c = *eptr++;  #define GETCHARINC(c, eptr) c = *eptr++;
420  #define GETCHARINCTEST(c, eptr) c = *eptr++;  #define GETCHARINCTEST(c, eptr) c = *eptr++;
421  #define GETCHARLEN(c, eptr, len) c = *eptr;  #define GETCHARLEN(c, eptr, len) c = *eptr;
422    /* #define GETCHARLENTEST(c, eptr, len) */
423  /* #define BACKCHAR(eptr) */  /* #define BACKCHAR(eptr) */
424    
425  #else   /* SUPPORT_UTF8 */  #else   /* SUPPORT_UTF8 */
426    
427    /* These macros were originally written in the form of loops that used data
428    from the tables whose names start with _pcre_utf8_table. They were rewritten by
429    a user so as not to use loops, because in some environments this gives a
430    significant performance advantage, and it seems never to do any harm. */
431    
432    /* Base macro to pick up the remaining bytes of a UTF-8 character, not
433    advancing the pointer. */
434    
435    #define GETUTF8(c, eptr) \
436        { \
437        if ((c & 0x20) == 0) \
438          c = ((c & 0x1f) << 6) | (eptr[1] & 0x3f); \
439        else if ((c & 0x10) == 0) \
440          c = ((c & 0x0f) << 12) | ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \
441        else if ((c & 0x08) == 0) \
442          c = ((c & 0x07) << 18) | ((eptr[1] & 0x3f) << 12) | \
443          ((eptr[2] & 0x3f) << 6) | (eptr[3] & 0x3f); \
444        else if ((c & 0x04) == 0) \
445          c = ((c & 0x03) << 24) | ((eptr[1] & 0x3f) << 18) | \
446              ((eptr[2] & 0x3f) << 12) | ((eptr[3] & 0x3f) << 6) | \
447              (eptr[4] & 0x3f); \
448        else \
449          c = ((c & 0x01) << 30) | ((eptr[1] & 0x3f) << 24) | \
450              ((eptr[2] & 0x3f) << 18) | ((eptr[3] & 0x3f) << 12) | \
451              ((eptr[4] & 0x3f) << 6) | (eptr[5] & 0x3f); \
452        }
453    
454  /* Get the next UTF-8 character, not advancing the pointer. This is called when  /* Get the next UTF-8 character, not advancing the pointer. This is called when
455  we know we are in UTF-8 mode. */  we know we are in UTF-8 mode. */
456    
457  #define GETCHAR(c, eptr) \  #define GETCHAR(c, eptr) \
458    c = *eptr; \    c = *eptr; \
459    if (c >= 0xc0) \    if (c >= 0xc0) GETUTF8(c, eptr);
     { \  
     int gcii; \  
     int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \  
     int gcss = 6*gcaa; \  
     c = (c & _pcre_utf8_table3[gcaa]) << gcss; \  
     for (gcii = 1; gcii <= gcaa; gcii++) \  
       { \  
       gcss -= 6; \  
       c |= (eptr[gcii] & 0x3f) << gcss; \  
       } \  
     }  
460    
461  /* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the  /* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the
462  pointer. */  pointer. */
463    
464  #define GETCHARTEST(c, eptr) \  #define GETCHARTEST(c, eptr) \
465    c = *eptr; \    c = *eptr; \
466    if (utf8 && c >= 0xc0) \    if (utf8 && c >= 0xc0) GETUTF8(c, eptr);
467    
468    /* Base macro to pick up the remaining bytes of a UTF-8 character, advancing
469    the pointer. */
470    
471    #define GETUTF8INC(c, eptr) \
472      { \      { \
473      int gcii; \      if ((c & 0x20) == 0) \
474      int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \        c = ((c & 0x1f) << 6) | (*eptr++ & 0x3f); \
475      int gcss = 6*gcaa; \      else if ((c & 0x10) == 0) \
476      c = (c & _pcre_utf8_table3[gcaa]) << gcss; \        { \
477      for (gcii = 1; gcii <= gcaa; gcii++) \        c = ((c & 0x0f) << 12) | ((*eptr & 0x3f) << 6) | (eptr[1] & 0x3f); \
478          eptr += 2; \
479          } \
480        else if ((c & 0x08) == 0) \
481          { \
482          c = ((c & 0x07) << 18) | ((*eptr & 0x3f) << 12) | \
483              ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \
484          eptr += 3; \
485          } \
486        else if ((c & 0x04) == 0) \
487          { \
488          c = ((c & 0x03) << 24) | ((*eptr & 0x3f) << 18) | \
489              ((eptr[1] & 0x3f) << 12) | ((eptr[2] & 0x3f) << 6) | \
490              (eptr[3] & 0x3f); \
491          eptr += 4; \
492          } \
493        else \
494        { \        { \
495        gcss -= 6; \        c = ((c & 0x01) << 30) | ((*eptr & 0x3f) << 24) | \
496        c |= (eptr[gcii] & 0x3f) << gcss; \            ((eptr[1] & 0x3f) << 18) | ((eptr[2] & 0x3f) << 12) | \
497              ((eptr[3] & 0x3f) << 6) | (eptr[4] & 0x3f); \
498          eptr += 5; \
499        } \        } \
500      }      }
501    
# Line 445  know we are in UTF-8 mode. */ Line 504  know we are in UTF-8 mode. */
504    
505  #define GETCHARINC(c, eptr) \  #define GETCHARINC(c, eptr) \
506    c = *eptr++; \    c = *eptr++; \
507    if (c >= 0xc0) \    if (c >= 0xc0) GETUTF8INC(c, eptr);
     { \  
     int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \  
     int gcss = 6*gcaa; \  
     c = (c & _pcre_utf8_table3[gcaa]) << gcss; \  
     while (gcaa-- > 0) \  
       { \  
       gcss -= 6; \  
       c |= (*eptr++ & 0x3f) << gcss; \  
       } \  
     }  
508    
509  /* Get the next character, testing for UTF-8 mode, and advancing the pointer */  /* Get the next character, testing for UTF-8 mode, and advancing the pointer.
510    This is called when we don't know if we are in UTF-8 mode. */
511    
512  #define GETCHARINCTEST(c, eptr) \  #define GETCHARINCTEST(c, eptr) \
513    c = *eptr++; \    c = *eptr++; \
514    if (utf8 && c >= 0xc0) \    if (utf8 && c >= 0xc0) GETUTF8INC(c, eptr);
515    
516    /* Base macro to pick up the remaining bytes of a UTF-8 character, not
517    advancing the pointer, incrementing the length. */
518    
519    #define GETUTF8LEN(c, eptr, len) \
520      { \      { \
521      int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \      if ((c & 0x20) == 0) \
     int gcss = 6*gcaa; \  
     c = (c & _pcre_utf8_table3[gcaa]) << gcss; \  
     while (gcaa-- > 0) \  
522        { \        { \
523        gcss -= 6; \        c = ((c & 0x1f) << 6) | (eptr[1] & 0x3f); \
524        c |= (*eptr++ & 0x3f) << gcss; \        len++; \
525          } \
526        else if ((c & 0x10)  == 0) \
527          { \
528          c = ((c & 0x0f) << 12) | ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \
529          len += 2; \
530          } \
531        else if ((c & 0x08)  == 0) \
532          {\
533          c = ((c & 0x07) << 18) | ((eptr[1] & 0x3f) << 12) | \
534              ((eptr[2] & 0x3f) << 6) | (eptr[3] & 0x3f); \
535          len += 3; \
536          } \
537        else if ((c & 0x04)  == 0) \
538          { \
539          c = ((c & 0x03) << 24) | ((eptr[1] & 0x3f) << 18) | \
540              ((eptr[2] & 0x3f) << 12) | ((eptr[3] & 0x3f) << 6) | \
541              (eptr[4] & 0x3f); \
542          len += 4; \
543          } \
544        else \
545          {\
546          c = ((c & 0x01) << 30) | ((eptr[1] & 0x3f) << 24) | \
547              ((eptr[2] & 0x3f) << 18) | ((eptr[3] & 0x3f) << 12) | \
548              ((eptr[4] & 0x3f) << 6) | (eptr[5] & 0x3f); \
549          len += 5; \
550        } \        } \
551      }      }
552    
# Line 478  if there are extra bytes. This is called Line 555  if there are extra bytes. This is called
555    
556  #define GETCHARLEN(c, eptr, len) \  #define GETCHARLEN(c, eptr, len) \
557    c = *eptr; \    c = *eptr; \
558    if (c >= 0xc0) \    if (c >= 0xc0) GETUTF8LEN(c, eptr, len);
     { \  
     int gcii; \  
     int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \  
     int gcss = 6*gcaa; \  
     c = (c & _pcre_utf8_table3[gcaa]) << gcss; \  
     for (gcii = 1; gcii <= gcaa; gcii++) \  
       { \  
       gcss -= 6; \  
       c |= (eptr[gcii] & 0x3f) << gcss; \  
       } \  
     len += gcaa; \  
     }  
559    
560  /* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the  /* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the
561  pointer, incrementing length if there are extra bytes. This is called when we  pointer, incrementing length if there are extra bytes. This is called when we
562  know we are in UTF-8 mode. */  do not know if we are in UTF-8 mode. */
563    
564  #define GETCHARLENTEST(c, eptr, len) \  #define GETCHARLENTEST(c, eptr, len) \
565    c = *eptr; \    c = *eptr; \
566    if (utf8 && c >= 0xc0) \    if (utf8 && c >= 0xc0) GETUTF8LEN(c, eptr, len);
     { \  
     int gcii; \  
     int gcaa = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */ \  
     int gcss = 6*gcaa; \  
     c = (c & _pcre_utf8_table3[gcaa]) << gcss; \  
     for (gcii = 1; gcii <= gcaa; gcii++) \  
       { \  
       gcss -= 6; \  
       c |= (eptr[gcii] & 0x3f) << gcss; \  
       } \  
     len += gcaa; \  
     }  
567    
568  /* If the pointer is not at the start of a character, move it back until  /* If the pointer is not at the start of a character, move it back until
569  it is. This is called only in UTF-8 mode - we don't put a test within the macro  it is. This is called only in UTF-8 mode - we don't put a test within the macro
# Line 518  because almost all calls are already wit Line 571  because almost all calls are already wit
571    
572  #define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--  #define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--
573    
574  #endif  #endif  /* SUPPORT_UTF8 */
575    
576    
577  /* In case there is no definition of offsetof() provided - though any proper  /* In case there is no definition of offsetof() provided - though any proper
# Line 562  time, run time, or study time, respectiv Line 615  time, run time, or study time, respectiv
615     PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \     PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \
616     PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \     PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \
617     PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \     PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \
618     PCRE_JAVASCRIPT_COMPAT)     PCRE_JAVASCRIPT_COMPAT|PCRE_UCP|PCRE_NO_START_OPTIMIZE)
619    
620  #define PUBLIC_EXEC_OPTIONS \  #define PUBLIC_EXEC_OPTIONS \
621    (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NOTEMPTY_ATSTART| \    (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NOTEMPTY_ATSTART| \
# Line 857  so that PCRE works on both ASCII and EBC Line 910  so that PCRE works on both ASCII and EBC
910  #define STRING_COMMIT0              "COMMIT\0"  #define STRING_COMMIT0              "COMMIT\0"
911  #define STRING_F0                   "F\0"  #define STRING_F0                   "F\0"
912  #define STRING_FAIL0                "FAIL\0"  #define STRING_FAIL0                "FAIL\0"
913    #define STRING_MARK0                "MARK\0"
914  #define STRING_PRUNE0               "PRUNE\0"  #define STRING_PRUNE0               "PRUNE\0"
915  #define STRING_SKIP0                "SKIP\0"  #define STRING_SKIP0                "SKIP\0"
916  #define STRING_THEN                 "THEN"  #define STRING_THEN                 "THEN"
# Line 878  so that PCRE works on both ASCII and EBC Line 932  so that PCRE works on both ASCII and EBC
932    
933  #define STRING_DEFINE               "DEFINE"  #define STRING_DEFINE               "DEFINE"
934    
935  #define STRING_CR_RIGHTPAR          "CR)"  #define STRING_CR_RIGHTPAR             "CR)"
936  #define STRING_LF_RIGHTPAR          "LF)"  #define STRING_LF_RIGHTPAR             "LF)"
937  #define STRING_CRLF_RIGHTPAR        "CRLF)"  #define STRING_CRLF_RIGHTPAR           "CRLF)"
938  #define STRING_ANY_RIGHTPAR         "ANY)"  #define STRING_ANY_RIGHTPAR            "ANY)"
939  #define STRING_ANYCRLF_RIGHTPAR     "ANYCRLF)"  #define STRING_ANYCRLF_RIGHTPAR        "ANYCRLF)"
940  #define STRING_BSR_ANYCRLF_RIGHTPAR "BSR_ANYCRLF)"  #define STRING_BSR_ANYCRLF_RIGHTPAR    "BSR_ANYCRLF)"
941  #define STRING_BSR_UNICODE_RIGHTPAR "BSR_UNICODE)"  #define STRING_BSR_UNICODE_RIGHTPAR    "BSR_UNICODE)"
942  #define STRING_UTF8_RIGHTPAR        "UTF8)"  #define STRING_UTF8_RIGHTPAR           "UTF8)"
943    #define STRING_UCP_RIGHTPAR            "UCP)"
944    #define STRING_NO_START_OPT_RIGHTPAR   "NO_START_OPT)"
945    
946  #else  /* SUPPORT_UTF8 */  #else  /* SUPPORT_UTF8 */
947    
# Line 1109  only. */ Line 1165  only. */
1165  #define STRING_COMMIT0              STR_C STR_O STR_M STR_M STR_I STR_T "\0"  #define STRING_COMMIT0              STR_C STR_O STR_M STR_M STR_I STR_T "\0"
1166  #define STRING_F0                   STR_F "\0"  #define STRING_F0                   STR_F "\0"
1167  #define STRING_FAIL0                STR_F STR_A STR_I STR_L "\0"  #define STRING_FAIL0                STR_F STR_A STR_I STR_L "\0"
1168    #define STRING_MARK0                STR_M STR_A STR_R STR_K "\0"
1169  #define STRING_PRUNE0               STR_P STR_R STR_U STR_N STR_E "\0"  #define STRING_PRUNE0               STR_P STR_R STR_U STR_N STR_E "\0"
1170  #define STRING_SKIP0                STR_S STR_K STR_I STR_P "\0"  #define STRING_SKIP0                STR_S STR_K STR_I STR_P "\0"
1171  #define STRING_THEN                 STR_T STR_H STR_E STR_N  #define STRING_THEN                 STR_T STR_H STR_E STR_N
# Line 1130  only. */ Line 1187  only. */
1187    
1188  #define STRING_DEFINE               STR_D STR_E STR_F STR_I STR_N STR_E  #define STRING_DEFINE               STR_D STR_E STR_F STR_I STR_N STR_E
1189    
1190  #define STRING_CR_RIGHTPAR          STR_C STR_R STR_RIGHT_PARENTHESIS  #define STRING_CR_RIGHTPAR             STR_C STR_R STR_RIGHT_PARENTHESIS
1191  #define STRING_LF_RIGHTPAR          STR_L STR_F STR_RIGHT_PARENTHESIS  #define STRING_LF_RIGHTPAR             STR_L STR_F STR_RIGHT_PARENTHESIS
1192  #define STRING_CRLF_RIGHTPAR        STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS  #define STRING_CRLF_RIGHTPAR           STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS
1193  #define STRING_ANY_RIGHTPAR         STR_A STR_N STR_Y STR_RIGHT_PARENTHESIS  #define STRING_ANY_RIGHTPAR            STR_A STR_N STR_Y STR_RIGHT_PARENTHESIS
1194  #define STRING_ANYCRLF_RIGHTPAR     STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS  #define STRING_ANYCRLF_RIGHTPAR        STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS
1195  #define STRING_BSR_ANYCRLF_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS  #define STRING_BSR_ANYCRLF_RIGHTPAR    STR_B STR_S STR_R STR_UNDERSCORE STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS
1196  #define STRING_BSR_UNICODE_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_U STR_N STR_I STR_C STR_O STR_D STR_E STR_RIGHT_PARENTHESIS  #define STRING_BSR_UNICODE_RIGHTPAR    STR_B STR_S STR_R STR_UNDERSCORE STR_U STR_N STR_I STR_C STR_O STR_D STR_E STR_RIGHT_PARENTHESIS
1197  #define STRING_UTF8_RIGHTPAR        STR_U STR_T STR_F STR_8 STR_RIGHT_PARENTHESIS  #define STRING_UTF8_RIGHTPAR           STR_U STR_T STR_F STR_8 STR_RIGHT_PARENTHESIS
1198    #define STRING_UCP_RIGHTPAR            STR_U STR_C STR_P STR_RIGHT_PARENTHESIS
1199    #define STRING_NO_START_OPT_RIGHTPAR   STR_N STR_O STR_UNDERSCORE STR_S STR_T STR_A STR_R STR_T STR_UNDERSCORE STR_O STR_P STR_T STR_RIGHT_PARENTHESIS
1200    
1201  #endif  /* SUPPORT_UTF8 */  #endif  /* SUPPORT_UTF8 */
1202    
# Line 1170  only. */ Line 1229  only. */
1229    
1230  #define PT_ANY        0    /* Any property - matches all chars */  #define PT_ANY        0    /* Any property - matches all chars */
1231  #define PT_LAMP       1    /* L& - the union of Lu, Ll, Lt */  #define PT_LAMP       1    /* L& - the union of Lu, Ll, Lt */
1232  #define PT_GC         2    /* General characteristic (e.g. L) */  #define PT_GC         2    /* Specified general characteristic (e.g. L) */
1233  #define PT_PC         3    /* Particular characteristic (e.g. Lu) */  #define PT_PC         3    /* Specified particular characteristic (e.g. Lu) */
1234  #define PT_SC         4    /* Script (e.g. Han) */  #define PT_SC         4    /* Script (e.g. Han) */
1235    #define PT_ALNUM      5    /* Alphanumeric - the union of L and N */
1236    #define PT_SPACE      6    /* Perl space - Z plus 9,10,12,13 */
1237    #define PT_PXSPACE    7    /* POSIX space - Z plus 9,10,11,12,13 */
1238    #define PT_WORD       8    /* Word - L plus N plus underscore */
1239    
1240  /* Flag bits and data types for the extended class (OP_XCLASS) for classes that  /* Flag bits and data types for the extended class (OP_XCLASS) for classes that
1241  contain UTF-8 characters with values greater than 255. */  contain UTF-8 characters with values greater than 255. */
# Line 1189  contain UTF-8 characters with values gre Line 1252  contain UTF-8 characters with values gre
1252  /* These are escaped items that aren't just an encoding of a particular data  /* These are escaped items that aren't just an encoding of a particular data
1253  value such as \n. They must have non-zero values, as check_escape() returns  value such as \n. They must have non-zero values, as check_escape() returns
1254  their negation. Also, they must appear in the same order as in the opcode  their negation. Also, they must appear in the same order as in the opcode
1255  definitions below, up to ESC_z. There's a dummy for OP_ANY because it  definitions below, up to ESC_z. There's a dummy for OP_ALLANY because it
1256  corresponds to "." rather than an escape sequence, and another for OP_ALLANY  corresponds to "." in DOTALL mode rather than an escape sequence. It is also
1257  (which is used for [^] in JavaScript compatibility mode).  used for [^] in JavaScript compatibility mode. In non-DOTALL mode, "." behaves
1258    like \N.
1259    
1260    The special values ESC_DU, ESC_du, etc. are used instead of ESC_D, ESC_d, etc.
1261    when PCRE_UCP is set, when replacement of \d etc by \p sequences is required.
1262    They must be contiguous, and remain in order so that the replacements can be
1263    looked up from a table.
1264    
1265  The final escape must be ESC_REF as subsequent values are used for  The final escape must be ESC_REF as subsequent values are used for
1266  backreferences (\1, \2, \3, etc). There are two tests in the code for an escape  backreferences (\1, \2, \3, etc). There are two tests in the code for an escape
# Line 1201  put in between that don't consume a char Line 1270  put in between that don't consume a char
1270  */  */
1271    
1272  enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s,  enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s,
1273         ESC_W, ESC_w, ESC_dum1, ESC_dum2, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H,         ESC_W, ESC_w, ESC_N, ESC_dum, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H,
1274         ESC_h, ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z, ESC_E, ESC_Q, ESC_g, ESC_k,         ESC_h, ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z,
1275           ESC_E, ESC_Q, ESC_g, ESC_k,
1276           ESC_DU, ESC_du, ESC_SU, ESC_su, ESC_WU, ESC_wu,
1277         ESC_REF };         ESC_REF };
1278    
   
1279  /* Opcode table: Starting from 1 (i.e. after OP_END), the values up to  /* Opcode table: Starting from 1 (i.e. after OP_END), the values up to
1280  OP_EOD must correspond in order to the list of escapes immediately above.  OP_EOD must correspond in order to the list of escapes immediately above.
1281    
1282  *** NOTE NOTE NOTE *** Whenever this list is updated, the two macro definitions  *** NOTE NOTE NOTE *** Whenever this list is updated, the two macro definitions
1283  that follow must also be updated to match. There is also a table called  that follow must also be updated to match. There are also tables called
1284  "coptable" in pcre_dfa_exec.c that must be updated. */  "coptable" and "poptable" in pcre_dfa_exec.c that must be updated. */
1285    
1286  enum {  enum {
1287    OP_END,            /* 0 End of pattern */    OP_END,            /* 0 End of pattern */
# Line 1229  enum { Line 1299  enum {
1299    OP_WHITESPACE,         /*  9 \s */    OP_WHITESPACE,         /*  9 \s */
1300    OP_NOT_WORDCHAR,       /* 10 \W */    OP_NOT_WORDCHAR,       /* 10 \W */
1301    OP_WORDCHAR,           /* 11 \w */    OP_WORDCHAR,           /* 11 \w */
1302    OP_ANY,            /* 12 Match any character (subject to DOTALL) */  
1303    OP_ALLANY,         /* 13 Match any character (not subject to DOTALL) */    OP_ANY,            /* 12 Match any character except newline */
1304      OP_ALLANY,         /* 13 Match any character */
1305    OP_ANYBYTE,        /* 14 Match any byte (\C); different to OP_ANY for UTF-8 */    OP_ANYBYTE,        /* 14 Match any byte (\C); different to OP_ANY for UTF-8 */
1306    OP_NOTPROP,        /* 15 \P (not Unicode property) */    OP_NOTPROP,        /* 15 \P (not Unicode property) */
1307    OP_PROP,           /* 16 \p (Unicode property) */    OP_PROP,           /* 16 \p (Unicode property) */
# Line 1243  enum { Line 1314  enum {
1314    OP_EODN,           /* 23 End of data or \n at end of data: \Z. */    OP_EODN,           /* 23 End of data or \n at end of data: \Z. */
1315    OP_EOD,            /* 24 End of data: \z */    OP_EOD,            /* 24 End of data: \z */
1316    
1317    OP_OPT,            /* 25 Set runtime options */    OP_CIRC,           /* 25 Start of line - not multiline */
1318    OP_CIRC,           /* 26 Start of line - varies with multiline switch */    OP_CIRCM,          /* 26 Start of line - multiline */
1319    OP_DOLL,           /* 27 End of line - varies with multiline switch */    OP_DOLL,           /* 27 End of line - not multiline */
1320    OP_CHAR,           /* 28 Match one character, casefully */    OP_DOLLM,          /* 28 End of line - multiline */
1321    OP_CHARNC,         /* 29 Match one character, caselessly */    OP_CHAR,           /* 29 Match one character, casefully */
1322    OP_NOT,            /* 30 Match one character, not the following one */    OP_CHARI,          /* 30 Match one character, caselessly */
1323      OP_NOT,            /* 31 Match one character, not the given one, casefully */
1324    OP_STAR,           /* 31 The maximizing and minimizing versions of */    OP_NOTI,           /* 32 Match one character, not the given one, caselessly */
1325    OP_MINSTAR,        /* 32 these six opcodes must come in pairs, with */  
1326    OP_PLUS,           /* 33 the minimizing one second. */    /* The following sets of 13 opcodes must always be kept in step because
1327    OP_MINPLUS,        /* 34 This first set applies to single characters.*/    the offset from the first one is used to generate the others. */
1328    OP_QUERY,          /* 35 */  
1329    OP_MINQUERY,       /* 36 */    /**** Single characters, caseful, must precede the caseless ones ****/
1330    
1331    OP_UPTO,           /* 37 From 0 to n matches */    OP_STAR,           /* 33 The maximizing and minimizing versions of */
1332    OP_MINUPTO,        /* 38 */    OP_MINSTAR,        /* 34 these six opcodes must come in pairs, with */
1333    OP_EXACT,          /* 39 Exactly n matches */    OP_PLUS,           /* 35 the minimizing one second. */
1334      OP_MINPLUS,        /* 36 */
1335    OP_POSSTAR,        /* 40 Possessified star */    OP_QUERY,          /* 37 */
1336    OP_POSPLUS,        /* 41 Possessified plus */    OP_MINQUERY,       /* 38 */
1337    OP_POSQUERY,       /* 42 Posesssified query */  
1338    OP_POSUPTO,        /* 43 Possessified upto */    OP_UPTO,           /* 39 From 0 to n matches of one character, caseful*/
1339      OP_MINUPTO,        /* 40 */
1340    OP_NOTSTAR,        /* 44 The maximizing and minimizing versions of */    OP_EXACT,          /* 41 Exactly n matches */
1341    OP_NOTMINSTAR,     /* 45 these six opcodes must come in pairs, with */  
1342    OP_NOTPLUS,        /* 46 the minimizing one second. They must be in */    OP_POSSTAR,        /* 42 Possessified star, caseful */
1343    OP_NOTMINPLUS,     /* 47 exactly the same order as those above. */    OP_POSPLUS,        /* 43 Possessified plus, caseful */
1344    OP_NOTQUERY,       /* 48 This set applies to "not" single characters. */    OP_POSQUERY,       /* 44 Posesssified query, caseful */
1345    OP_NOTMINQUERY,    /* 49 */    OP_POSUPTO,        /* 45 Possessified upto, caseful */
1346    
1347    OP_NOTUPTO,        /* 50 From 0 to n matches */    /**** Single characters, caseless, must follow the caseful ones */
1348    OP_NOTMINUPTO,     /* 51 */  
1349    OP_NOTEXACT,       /* 52 Exactly n matches */    OP_STARI,          /* 46 */
1350      OP_MINSTARI,       /* 47 */
1351    OP_NOTPOSSTAR,     /* 53 Possessified versions */    OP_PLUSI,          /* 48 */
1352    OP_NOTPOSPLUS,     /* 54 */    OP_MINPLUSI,       /* 49 */
1353    OP_NOTPOSQUERY,    /* 55 */    OP_QUERYI,         /* 50 */
1354    OP_NOTPOSUPTO,     /* 56 */    OP_MINQUERYI,      /* 51 */
1355    
1356    OP_TYPESTAR,       /* 57 The maximizing and minimizing versions of */    OP_UPTOI,          /* 52 From 0 to n matches of one character, caseless */
1357    OP_TYPEMINSTAR,    /* 58 these six opcodes must come in pairs, with */    OP_MINUPTOI,       /* 53 */
1358    OP_TYPEPLUS,       /* 59 the minimizing one second. These codes must */    OP_EXACTI,         /* 54 */
1359    OP_TYPEMINPLUS,    /* 60 be in exactly the same order as those above. */  
1360    OP_TYPEQUERY,      /* 61 This set applies to character types such as \d */    OP_POSSTARI,       /* 55 Possessified star, caseless */
1361    OP_TYPEMINQUERY,   /* 62 */    OP_POSPLUSI,       /* 56 Possessified plus, caseless */
1362      OP_POSQUERYI,      /* 57 Posesssified query, caseless */
1363    OP_TYPEUPTO,       /* 63 From 0 to n matches */    OP_POSUPTOI,       /* 58 Possessified upto, caseless */
1364    OP_TYPEMINUPTO,    /* 64 */  
1365    OP_TYPEEXACT,      /* 65 Exactly n matches */    /**** The negated ones must follow the non-negated ones, and match them ****/
1366      /**** Negated single character, caseful; must precede the caseless ones ****/
1367    OP_TYPEPOSSTAR,    /* 66 Possessified versions */  
1368    OP_TYPEPOSPLUS,    /* 67 */    OP_NOTSTAR,        /* 59 The maximizing and minimizing versions of */
1369    OP_TYPEPOSQUERY,   /* 68 */    OP_NOTMINSTAR,     /* 60 these six opcodes must come in pairs, with */
1370    OP_TYPEPOSUPTO,    /* 69 */    OP_NOTPLUS,        /* 61 the minimizing one second. They must be in */
1371      OP_NOTMINPLUS,     /* 62 exactly the same order as those above. */
1372    OP_CRSTAR,         /* 70 The maximizing and minimizing versions of */    OP_NOTQUERY,       /* 63 */
1373    OP_CRMINSTAR,      /* 71 all these opcodes must come in pairs, with */    OP_NOTMINQUERY,    /* 64 */
1374    OP_CRPLUS,         /* 72 the minimizing one second. These codes must */  
1375    OP_CRMINPLUS,      /* 73 be in exactly the same order as those above. */    OP_NOTUPTO,        /* 65 From 0 to n matches, caseful */
1376    OP_CRQUERY,        /* 74 These are for character classes and back refs */    OP_NOTMINUPTO,     /* 66 */
1377    OP_CRMINQUERY,     /* 75 */    OP_NOTEXACT,       /* 67 Exactly n matches */
1378    OP_CRRANGE,        /* 76 These are different to the three sets above. */  
1379    OP_CRMINRANGE,     /* 77 */    OP_NOTPOSSTAR,     /* 68 Possessified versions, caseful */
1380      OP_NOTPOSPLUS,     /* 69 */
1381    OP_CLASS,          /* 78 Match a character class, chars < 256 only */    OP_NOTPOSQUERY,    /* 70 */
1382    OP_NCLASS,         /* 79 Same, but the bitmap was created from a negative    OP_NOTPOSUPTO,     /* 71 */
1383                             class - the difference is relevant only when a UTF-8  
1384                             character > 255 is encountered. */    /**** Negated single character, caseless; must follow the caseful ones ****/
1385    
1386    OP_XCLASS,         /* 80 Extended class for handling UTF-8 chars within the    OP_NOTSTARI,       /* 72 */
1387                             class. This does both positive and negative. */    OP_NOTMINSTARI,    /* 73 */
1388      OP_NOTPLUSI,       /* 74 */
1389    OP_REF,            /* 81 Match a back reference */    OP_NOTMINPLUSI,    /* 75 */
1390    OP_RECURSE,        /* 82 Match a numbered subpattern (possibly recursive) */    OP_NOTQUERYI,      /* 76 */
1391    OP_CALLOUT,        /* 83 Call out to external function if provided */    OP_NOTMINQUERYI,   /* 77 */
1392    
1393    OP_ALT,            /* 84 Start of alternation */    OP_NOTUPTOI,       /* 78 From 0 to n matches, caseless */
1394    OP_KET,            /* 85 End of group that doesn't have an unbounded repeat */    OP_NOTMINUPTOI,    /* 79 */
1395    OP_KETRMAX,        /* 86 These two must remain together and in this */    OP_NOTEXACTI,      /* 80 Exactly n matches */
1396    OP_KETRMIN,        /* 87 order. They are for groups the repeat for ever. */  
1397      OP_NOTPOSSTARI,    /* 81 Possessified versions, caseless */
1398      OP_NOTPOSPLUSI,    /* 82 */
1399      OP_NOTPOSQUERYI,   /* 83 */
1400      OP_NOTPOSUPTOI,    /* 84 */
1401    
1402      /**** Character types ****/
1403    
1404      OP_TYPESTAR,       /* 85 The maximizing and minimizing versions of */
1405      OP_TYPEMINSTAR,    /* 86 these six opcodes must come in pairs, with */
1406      OP_TYPEPLUS,       /* 87 the minimizing one second. These codes must */
1407      OP_TYPEMINPLUS,    /* 88 be in exactly the same order as those above. */
1408      OP_TYPEQUERY,      /* 89 */
1409      OP_TYPEMINQUERY,   /* 90 */
1410    
1411      OP_TYPEUPTO,       /* 91 From 0 to n matches */
1412      OP_TYPEMINUPTO,    /* 92 */
1413      OP_TYPEEXACT,      /* 93 Exactly n matches */
1414    
1415      OP_TYPEPOSSTAR,    /* 94 Possessified versions */
1416      OP_TYPEPOSPLUS,    /* 95 */
1417      OP_TYPEPOSQUERY,   /* 96 */
1418      OP_TYPEPOSUPTO,    /* 97 */
1419    
1420      /* These are used for character classes and back references; only the
1421      first six are the same as the sets above. */
1422    
1423      OP_CRSTAR,         /* 98 The maximizing and minimizing versions of */
1424      OP_CRMINSTAR,      /* 99 all these opcodes must come in pairs, with */
1425      OP_CRPLUS,         /* 100 the minimizing one second. These codes must */
1426      OP_CRMINPLUS,      /* 101 be in exactly the same order as those above. */
1427      OP_CRQUERY,        /* 102 */
1428      OP_CRMINQUERY,     /* 103 */
1429    
1430      OP_CRRANGE,        /* 104 These are different to the three sets above. */
1431      OP_CRMINRANGE,     /* 105 */
1432    
1433      /* End of quantifier opcodes */
1434    
1435      OP_CLASS,          /* 106 Match a character class, chars < 256 only */
1436      OP_NCLASS,         /* 107 Same, but the bitmap was created from a negative
1437                                  class - the difference is relevant only when a
1438                                  UTF-8 character > 255 is encountered. */
1439      OP_XCLASS,         /* 108 Extended class for handling UTF-8 chars within the
1440                                  class. This does both positive and negative. */
1441      OP_REF,            /* 109 Match a back reference, casefully */
1442      OP_REFI,           /* 110 Match a back reference, caselessly */
1443      OP_RECURSE,        /* 111 Match a numbered subpattern (possibly recursive) */
1444      OP_CALLOUT,        /* 112 Call out to external function if provided */
1445    
1446      OP_ALT,            /* 113 Start of alternation */
1447      OP_KET,            /* 114 End of group that doesn't have an unbounded repeat */
1448      OP_KETRMAX,        /* 115 These two must remain together and in this */
1449      OP_KETRMIN,        /* 116 order. They are for groups the repeat for ever. */
1450    
1451    /* The assertions must come before BRA, CBRA, ONCE, and COND.*/    /* The assertions must come before BRA, CBRA, ONCE, and COND.*/
1452    
1453    OP_ASSERT,         /* 88 Positive lookahead */    OP_ASSERT,         /* 117 Positive lookahead */
1454    OP_ASSERT_NOT,     /* 89 Negative lookahead */    OP_ASSERT_NOT,     /* 118 Negative lookahead */
1455    OP_ASSERTBACK,     /* 90 Positive lookbehind */    OP_ASSERTBACK,     /* 119 Positive lookbehind */
1456    OP_ASSERTBACK_NOT, /* 91 Negative lookbehind */    OP_ASSERTBACK_NOT, /* 120 Negative lookbehind */
1457    OP_REVERSE,        /* 92 Move pointer back - used in lookbehind assertions */    OP_REVERSE,        /* 121 Move pointer back - used in lookbehind assertions */
1458    
1459    /* ONCE, BRA, CBRA, and COND must come after the assertions, with ONCE first,    /* ONCE, BRA, CBRA, and COND must come after the assertions, with ONCE first,
1460    as there's a test for >= ONCE for a subpattern that isn't an assertion. */    as there's a test for >= ONCE for a subpattern that isn't an assertion. */
1461    
1462    OP_ONCE,           /* 93 Atomic group */    OP_ONCE,           /* 122 Atomic group */
1463    OP_BRA,            /* 94 Start of non-capturing bracket */    OP_BRA,            /* 123 Start of non-capturing bracket */
1464    OP_CBRA,           /* 95 Start of capturing bracket */    OP_CBRA,           /* 124 Start of capturing bracket */
1465    OP_COND,           /* 96 Conditional group */    OP_COND,           /* 125 Conditional group */
1466    
1467    /* These three must follow the previous three, in the same order. There's a    /* These three must follow the previous three, in the same order. There's a
1468    check for >= SBRA to distinguish the two sets. */    check for >= SBRA to distinguish the two sets. */
1469    
1470    OP_SBRA,           /* 97 Start of non-capturing bracket, check empty  */    OP_SBRA,           /* 126 Start of non-capturing bracket, check empty  */
1471    OP_SCBRA,          /* 98 Start of capturing bracket, check empty */    OP_SCBRA,          /* 127 Start of capturing bracket, check empty */
1472    OP_SCOND,          /* 99 Conditional group, check empty */    OP_SCOND,          /* 128 Conditional group, check empty */
1473    
1474    /* The next two pairs must (respectively) be kept together. */    /* The next two pairs must (respectively) be kept together. */
1475    
1476    OP_CREF,           /* 100 Used to hold a capture number as condition */    OP_CREF,           /* 129 Used to hold a capture number as condition */
1477    OP_NCREF,          /* 101 Same, but generaged by a name reference*/    OP_NCREF,          /* 130 Same, but generated by a name reference*/
1478    OP_RREF,           /* 102 Used to hold a recursion number as condition */    OP_RREF,           /* 131 Used to hold a recursion number as condition */
1479    OP_NRREF,          /* 103 Same, but generaged by a name reference*/    OP_NRREF,          /* 132 Same, but generated by a name reference*/
1480    OP_DEF,            /* 104 The DEFINE condition */    OP_DEF,            /* 133 The DEFINE condition */
1481    
1482    OP_BRAZERO,        /* 105 These two must remain together and in this */    OP_BRAZERO,        /* 134 These two must remain together and in this */
1483    OP_BRAMINZERO,     /* 106 order. */    OP_BRAMINZERO,     /* 135 order. */
1484    
1485    /* These are backtracking control verbs */    /* These are backtracking control verbs */
1486    
1487    OP_PRUNE,          /* 107 */    OP_MARK,           /* 136 always has an argument */
1488    OP_SKIP,           /* 108 */    OP_PRUNE,          /* 137 */
1489    OP_THEN,           /* 109 */    OP_PRUNE_ARG,      /* 138 same, but with argument */
1490    OP_COMMIT,         /* 110 */    OP_SKIP,           /* 139 */
1491      OP_SKIP_ARG,       /* 140 same, but with argument */
1492      OP_THEN,           /* 141 */
1493      OP_THEN_ARG,       /* 142 same, but with argument */
1494      OP_COMMIT,         /* 143 */
1495    
1496    /* These are forced failure and success verbs */    /* These are forced failure and success verbs */
1497    
1498    OP_FAIL,           /* 111 */    OP_FAIL,           /* 144 */
1499    OP_ACCEPT,         /* 112 */    OP_ACCEPT,         /* 145 */
1500    OP_CLOSE,          /* 113 Used before OP_ACCEPT to close open captures */    OP_CLOSE,          /* 146 Used before OP_ACCEPT to close open captures */
1501    
1502    /* This is used to skip a subpattern with a {0} quantifier */    /* This is used to skip a subpattern with a {0} quantifier */
1503    
1504    OP_SKIPZERO        /* 114 */    OP_SKIPZERO,       /* 147 */
1505    
1506      /* This is not an opcode, but is used to check that tables indexed by opcode
1507      are the correct length, in order to catch updating errors - there have been
1508      some in the past. */
1509    
1510      OP_TABLE_LENGTH
1511  };  };
1512    
1513    /* *** NOTE NOTE NOTE *** Whenever the list above is updated, the two macro
1514    definitions that follow must also be updated to match. There are also tables
1515    called "coptable" and "poptable" in pcre_dfa_exec.c that must be updated. */
1516    
1517    
1518  /* This macro defines textual names for all the opcodes. These are used only  /* This macro defines textual names for all the opcodes. These are used only
1519  for debugging. The macro is referenced only in pcre_printint.c. */  for debugging, and some of them are only partial names. The macro is referenced
1520    only in pcre_printint.c, which fills out the full names in many cases (and in
1521    some cases doesn't actually use these names at all). */
1522    
1523  #define OP_NAME_LIST \  #define OP_NAME_LIST \
1524    "End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d",         \    "End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d",         \
1525    "\\S", "\\s", "\\W", "\\w", "Any", "AllAny", "Anybyte",         \    "\\S", "\\s", "\\W", "\\w", "Any", "AllAny", "Anybyte",         \
1526    "notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v",           \    "notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v",           \
1527    "extuni",  "\\Z", "\\z",                                        \    "extuni",  "\\Z", "\\z",                                        \
1528    "Opt", "^", "$", "char", "charnc", "not",                       \    "^", "^", "$", "$", "char", "chari", "not", "noti",             \
1529    "*", "*?", "+", "+?", "?", "??", "{", "{", "{",                 \    "*", "*?", "+", "+?", "?", "??",                                \
1530      "{", "{", "{",                                                  \
1531    "*+","++", "?+", "{",                                           \    "*+","++", "?+", "{",                                           \
1532    "*", "*?", "+", "+?", "?", "??", "{", "{", "{",                 \    "*", "*?", "+", "+?", "?", "??",                                \
1533      "{", "{", "{",                                                  \
1534      "*+","++", "?+", "{",                                           \
1535      "*", "*?", "+", "+?", "?", "??",                                \
1536      "{", "{", "{",                                                  \
1537      "*+","++", "?+", "{",                                           \
1538      "*", "*?", "+", "+?", "?", "??",                                \
1539      "{", "{", "{",                                                  \
1540    "*+","++", "?+", "{",                                           \    "*+","++", "?+", "{",                                           \
1541    "*", "*?", "+", "+?", "?", "??", "{", "{", "{",                 \    "*", "*?", "+", "+?", "?", "??", "{", "{", "{",                 \
1542    "*+","++", "?+", "{",                                           \    "*+","++", "?+", "{",                                           \
1543    "*", "*?", "+", "+?", "?", "??", "{", "{",                      \    "*", "*?", "+", "+?", "?", "??", "{", "{",                      \
1544    "class", "nclass", "xclass", "Ref", "Recurse", "Callout",       \    "class", "nclass", "xclass", "Ref", "Refi",                     \
1545      "Recurse", "Callout",                                           \
1546    "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not",     \    "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not",     \
1547    "AssertB", "AssertB not", "Reverse",                            \    "AssertB", "AssertB not", "Reverse",                            \
1548    "Once", "Bra", "CBra", "Cond", "SBra", "SCBra", "SCond",        \    "Once", "Bra", "CBra", "Cond", "SBra", "SCBra", "SCond",        \
1549    "Cond ref", "Cond nref", "Cond rec", "Cond nrec", "Cond def",   \    "Cond ref", "Cond nref", "Cond rec", "Cond nrec", "Cond def",   \
1550    "Brazero", "Braminzero",                                        \    "Brazero", "Braminzero",                                        \
1551    "*PRUNE", "*SKIP", "*THEN", "*COMMIT", "*FAIL", "*ACCEPT",      \    "*MARK", "*PRUNE", "*PRUNE", "*SKIP", "*SKIP",                  \
1552      "*THEN", "*THEN", "*COMMIT", "*FAIL", "*ACCEPT",                \
1553    "Close", "Skip zero"    "Close", "Skip zero"
1554    
1555    
# Line 1417  in UTF-8 mode. The code that uses this t Line 1567  in UTF-8 mode. The code that uses this t
1567    1, 1, 1, 1, 1,                 /* \A, \G, \K, \B, \b                     */ \    1, 1, 1, 1, 1,                 /* \A, \G, \K, \B, \b                     */ \
1568    1, 1, 1, 1, 1, 1,              /* \D, \d, \S, \s, \W, \w                 */ \    1, 1, 1, 1, 1, 1,              /* \D, \d, \S, \s, \W, \w                 */ \
1569    1, 1, 1,                       /* Any, AllAny, Anybyte                   */ \    1, 1, 1,                       /* Any, AllAny, Anybyte                   */ \
1570    3, 3, 1,                       /* NOTPROP, PROP, EXTUNI                  */ \    3, 3,                          /* \P, \p                                 */ \
1571    1, 1, 1, 1, 1,                 /* \R, \H, \h, \V, \v                     */ \    1, 1, 1, 1, 1,                 /* \R, \H, \h, \V, \v                     */ \
1572    1, 1, 2, 1, 1,                 /* \Z, \z, Opt, ^, $                      */ \    1,                             /* \X                                     */ \
1573      1, 1, 1, 1, 1, 1,              /* \Z, \z, ^, ^M, $, $M                   */ \
1574    2,                             /* Char  - the minimum length             */ \    2,                             /* Char  - the minimum length             */ \
1575    2,                             /* Charnc  - the minimum length           */ \    2,                             /* Chari  - the minimum length            */ \
1576    2,                             /* not                                    */ \    2,                             /* not                                    */ \
1577    /* Positive single-char repeats                            ** These are  */ \    2,                             /* noti                                   */ \
1578    2, 2, 2, 2, 2, 2,              /* *, *?, +, +?, ?, ??      ** minima in  */ \    /* Positive single-char repeats                             ** These are */ \
1579    4, 4, 4,                       /* upto, minupto, exact     ** UTF-8 mode */ \    2, 2, 2, 2, 2, 2,              /* *, *?, +, +?, ?, ??       ** minima in */ \
1580      4, 4, 4,                       /* upto, minupto, exact      ** mode      */ \
1581    2, 2, 2, 4,                    /* *+, ++, ?+, upto+                      */ \    2, 2, 2, 4,                    /* *+, ++, ?+, upto+                      */ \
1582      2, 2, 2, 2, 2, 2,              /* *I, *?I, +I, +?I, ?I, ??I ** UTF-8     */ \
1583      4, 4, 4,                       /* upto I, minupto I, exact I             */ \
1584      2, 2, 2, 4,                    /* *+I, ++I, ?+I, upto+I                  */ \
1585    /* Negative single-char repeats - only for chars < 256                   */ \    /* Negative single-char repeats - only for chars < 256                   */ \
1586    2, 2, 2, 2, 2, 2,              /* NOT *, *?, +, +?, ?, ??                */ \    2, 2, 2, 2, 2, 2,              /* NOT *, *?, +, +?, ?, ??                */ \
1587    4, 4, 4,                       /* NOT upto, minupto, exact               */ \    4, 4, 4,                       /* NOT upto, minupto, exact               */ \
1588    2, 2, 2, 4,                    /* Possessive *, +, ?, upto               */ \    2, 2, 2, 4,                    /* Possessive NOT *, +, ?, upto           */ \
1589      2, 2, 2, 2, 2, 2,              /* NOT *I, *?I, +I, +?I, ?I, ??I          */ \
1590      4, 4, 4,                       /* NOT upto I, minupto I, exact I         */ \
1591      2, 2, 2, 4,                    /* Possessive NOT *I, +I, ?I, upto I      */ \
1592    /* Positive type repeats                                                 */ \    /* Positive type repeats                                                 */ \
1593    2, 2, 2, 2, 2, 2,              /* Type *, *?, +, +?, ?, ??               */ \    2, 2, 2, 2, 2, 2,              /* Type *, *?, +, +?, ?, ??               */ \
1594    4, 4, 4,                       /* Type upto, minupto, exact              */ \    4, 4, 4,                       /* Type upto, minupto, exact              */ \
# Line 1442  in UTF-8 mode. The code that uses this t Line 1600  in UTF-8 mode. The code that uses this t
1600   33,                             /* NCLASS                                 */ \   33,                             /* NCLASS                                 */ \
1601    0,                             /* XCLASS - variable length               */ \    0,                             /* XCLASS - variable length               */ \
1602    3,                             /* REF                                    */ \    3,                             /* REF                                    */ \
1603      3,                             /* REFI                                   */ \
1604    1+LINK_SIZE,                   /* RECURSE                                */ \    1+LINK_SIZE,                   /* RECURSE                                */ \
1605    2+2*LINK_SIZE,                 /* CALLOUT                                */ \    2+2*LINK_SIZE,                 /* CALLOUT                                */ \
1606    1+LINK_SIZE,                   /* Alt                                    */ \    1+LINK_SIZE,                   /* Alt                                    */ \
# Line 1464  in UTF-8 mode. The code that uses this t Line 1623  in UTF-8 mode. The code that uses this t
1623    3, 3,                          /* RREF, NRREF                            */ \    3, 3,                          /* RREF, NRREF                            */ \
1624    1,                             /* DEF                                    */ \    1,                             /* DEF                                    */ \
1625    1, 1,                          /* BRAZERO, BRAMINZERO                    */ \    1, 1,                          /* BRAZERO, BRAMINZERO                    */ \
1626    1, 1, 1, 1,                    /* PRUNE, SKIP, THEN, COMMIT,             */ \    3, 1, 3,                       /* MARK, PRUNE, PRUNE_ARG                 */ \
1627    1, 1, 3, 1                     /* FAIL, ACCEPT, CLOSE, SKIPZERO          */    1, 3,                          /* SKIP, SKIP_ARG                         */ \
1628      1+LINK_SIZE, 3+LINK_SIZE,      /* THEN, THEN_ARG                         */ \
1629      1, 1, 1, 3, 1                  /* COMMIT, FAIL, ACCEPT, CLOSE, SKIPZERO  */ \
1630    
1631  /* A magic value for OP_RREF and OP_NRREF to indicate the "any recursion"  /* A magic value for OP_RREF and OP_NRREF to indicate the "any recursion"
1632  condition. */  condition. */
1633    
1634  #define RREF_ANY  0xffff  #define RREF_ANY  0xffff
1635    
1636  /* Error code numbers. They are given names so that they can more easily be  /* Compile time error code numbers. They are given names so that they can more
1637  tracked. */  easily be tracked. When a new number is added, the table called eint in
1638    pcreposix.c must be updated. */
1639    
1640  enum { ERR0,  ERR1,  ERR2,  ERR3,  ERR4,  ERR5,  ERR6,  ERR7,  ERR8,  ERR9,  enum { ERR0,  ERR1,  ERR2,  ERR3,  ERR4,  ERR5,  ERR6,  ERR7,  ERR8,  ERR9,
1641         ERR10, ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19,         ERR10, ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19,
# Line 1482  enum { ERR0,  ERR1,  ERR2,  ERR3,  ERR4, Line 1643  enum { ERR0,  ERR1,  ERR2,  ERR3,  ERR4,
1643         ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39,         ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39,
1644         ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49,         ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49,
1645         ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59,         ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59,
1646         ERR60, ERR61, ERR62, ERR63, ERR64, ERR65 };         ERR60, ERR61, ERR62, ERR63, ERR64, ERR65, ERR66, ERR67, ERR68,
1647           ERRCOUNT };
1648    
1649  /* The real format of the start of the pcre block; the index of names and the  /* The real format of the start of the pcre block; the index of names and the
1650  code vector run on as long as necessary after the end. We store an explicit  code vector run on as long as necessary after the end. We store an explicit
# Line 1532  typedef struct pcre_study_data { Line 1694  typedef struct pcre_study_data {
1694    
1695  /* Structure for building a chain of open capturing subpatterns during  /* Structure for building a chain of open capturing subpatterns during
1696  compiling, so that instructions to close them can be compiled when (*ACCEPT) is  compiling, so that instructions to close them can be compiled when (*ACCEPT) is
1697  encountered. */  encountered. This is also used to identify subpatterns that contain recursive
1698    back references to themselves, so that they can be made atomic. */
1699    
1700  typedef struct open_capitem {  typedef struct open_capitem {
1701    struct open_capitem *next;    /* Chain link */    struct open_capitem *next;    /* Chain link */
1702    pcre_uint16 number;           /* Capture number */    pcre_uint16 number;           /* Capture number */
1703      pcre_uint16 flag;             /* Set TRUE if recursive back ref */
1704  } open_capitem;  } open_capitem;
1705    
1706  /* Structure for passing "static" information around between the functions  /* Structure for passing "static" information around between the functions
# Line 1575  branches, for testing for left recursion Line 1739  branches, for testing for left recursion
1739    
1740  typedef struct branch_chain {  typedef struct branch_chain {
1741    struct branch_chain *outer;    struct branch_chain *outer;
1742    uschar *current;    uschar *current_branch;
1743  } branch_chain;  } branch_chain;
1744    
1745  /* Structure for items in a linked list that represents an explicit recursive  /* Structure for items in a linked list that represents an explicit recursive
# Line 1585  typedef struct recursion_info { Line 1749  typedef struct recursion_info {
1749    struct recursion_info *prevrec; /* Previous recursion record (or NULL) */    struct recursion_info *prevrec; /* Previous recursion record (or NULL) */
1750    int group_num;                /* Number of group that was called */    int group_num;                /* Number of group that was called */
1751    const uschar *after_call;     /* "Return value": points after the call in the expr */    const uschar *after_call;     /* "Return value": points after the call in the expr */
   USPTR save_start;             /* Old value of mstart */  
1752    int *offset_save;             /* Pointer to start of saved offsets */    int *offset_save;             /* Pointer to start of saved offsets */
1753    int saved_max;                /* Number of saved offsets */    int saved_max;                /* Number of saved offsets */
1754    int save_offset_top;          /* Current value of offset_top */    int save_offset_top;          /* Current value of offset_top */
# Line 1624  typedef struct match_data { Line 1787  typedef struct match_data {
1787    BOOL   noteol;                /* NOTEOL flag */    BOOL   noteol;                /* NOTEOL flag */
1788    BOOL   utf8;                  /* UTF8 flag */    BOOL   utf8;                  /* UTF8 flag */
1789    BOOL   jscript_compat;        /* JAVASCRIPT_COMPAT flag */    BOOL   jscript_compat;        /* JAVASCRIPT_COMPAT flag */
1790      BOOL   use_ucp;               /* PCRE_UCP flag */
1791    BOOL   endonly;               /* Dollar not before final \n */    BOOL   endonly;               /* Dollar not before final \n */
1792    BOOL   notempty;              /* Empty string match not wanted */    BOOL   notempty;              /* Empty string match not wanted */
1793    BOOL   notempty_atstart;      /* Empty string match at start not wanted */    BOOL   notempty_atstart;      /* Empty string match at start not wanted */
# Line 1643  typedef struct match_data { Line 1807  typedef struct match_data {
1807    int    eptrn;                 /* Next free eptrblock */    int    eptrn;                 /* Next free eptrblock */
1808    recursion_info *recursive;    /* Linked list of recursion data */    recursion_info *recursive;    /* Linked list of recursion data */
1809    void  *callout_data;          /* To pass back to callouts */    void  *callout_data;          /* To pass back to callouts */
1810      const uschar *mark;           /* Mark pointer to pass back */
1811  } match_data;  } match_data;
1812    
1813  /* A similar structure is used for the same purpose by the DFA matching  /* A similar structure is used for the same purpose by the DFA matching
# Line 1734  one of the exported public functions. Th Line 1899  one of the exported public functions. Th
1899  sense, but are not part of the PCRE public API. */  sense, but are not part of the PCRE public API. */
1900    
1901  extern const uschar *_pcre_find_bracket(const uschar *, BOOL, int);  extern const uschar *_pcre_find_bracket(const uschar *, BOOL, int);
1902  extern BOOL          _pcre_is_newline(const uschar *, int, const uschar *,  extern BOOL          _pcre_is_newline(USPTR, int, USPTR, int *, BOOL);
                        int *, BOOL);  
1903  extern int           _pcre_ord2utf8(int, uschar *);  extern int           _pcre_ord2utf8(int, uschar *);
1904  extern real_pcre    *_pcre_try_flipped(const real_pcre *, real_pcre *,  extern real_pcre    *_pcre_try_flipped(const real_pcre *, real_pcre *,
1905                         const pcre_study_data *, pcre_study_data *);                         const pcre_study_data *, pcre_study_data *);
1906  extern int           _pcre_valid_utf8(const uschar *, int);  extern int           _pcre_valid_utf8(USPTR, int, int *);
1907  extern BOOL          _pcre_was_newline(const uschar *, int, const uschar *,  extern BOOL          _pcre_was_newline(USPTR, int, USPTR, int *, BOOL);
                        int *, BOOL);  
1908  extern BOOL          _pcre_xclass(int, const uschar *);  extern BOOL          _pcre_xclass(int, const uschar *);
1909    
1910    
# Line 1764  extern const int         _pcre_ucp_genty Line 1927  extern const int         _pcre_ucp_genty
1927  #define UCD_BLOCK_SIZE 128  #define UCD_BLOCK_SIZE 128
1928  #define GET_UCD(ch) (_pcre_ucd_records + \  #define GET_UCD(ch) (_pcre_ucd_records + \
1929          _pcre_ucd_stage2[_pcre_ucd_stage1[(ch) / UCD_BLOCK_SIZE] * \          _pcre_ucd_stage2[_pcre_ucd_stage1[(ch) / UCD_BLOCK_SIZE] * \
1930          UCD_BLOCK_SIZE + ch % UCD_BLOCK_SIZE])          UCD_BLOCK_SIZE + (ch) % UCD_BLOCK_SIZE])
1931    
1932  #define UCD_CHARTYPE(ch)  GET_UCD(ch)->chartype  #define UCD_CHARTYPE(ch)  GET_UCD(ch)->chartype
1933  #define UCD_SCRIPT(ch)    GET_UCD(ch)->script  #define UCD_SCRIPT(ch)    GET_UCD(ch)->script

Legend:
Removed from v.461  
changed lines
  Added in v.602

  ViewVC Help
Powered by ViewVC 1.1.5