/[pcre]/code/trunk/pcre_exec.c
ViewVC logotype

Diff of /code/trunk/pcre_exec.c

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

revision 211 by ph10, Thu Aug 9 09:52:43 2007 UTC revision 231 by ph10, Tue Sep 11 11:15:33 2007 UTC
# Line 211  variable instead of being passed in the Line 211  variable instead of being passed in the
211  ****************************************************************************  ****************************************************************************
212  ***************************************************************************/  ***************************************************************************/
213    
214    /* Numbers for RMATCH calls. When this list is changed, the code at HEAP_RETURN
215  /* Numbers for RMATCH calls */  below must be updated in sync.  */
216    
217  enum { RM1=1, RM2,  RM3,  RM4,  RM5,  RM6,  RM7,  RM8,  RM9,  RM10,  enum { RM1=1, RM2,  RM3,  RM4,  RM5,  RM6,  RM7,  RM8,  RM9,  RM10,
218         RM11,  RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20,         RM11,  RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20,
219         RM21,  RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30,         RM21,  RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30,
220         RM31,  RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40,         RM31,  RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40,
221         RM41,  RM42, RM43, RM44, RM45, RM46, RM47, RM48, RM49, RM50,         RM41,  RM42, RM43, RM44, RM45, RM46, RM47, RM48, RM49, RM50,
222         RM51,  RM52, RM53 };         RM51,  RM52, RM53, RM54 };
   
223    
224  /* These versions of the macros use the stack, as normal. There are debugging  /* These versions of the macros use the stack, as normal. There are debugging
225  versions and production versions. Note that the "rw" argument of RMATCH isn't  versions and production versions. Note that the "rw" argument of RMATCH isn't
# Line 622  for (;;) Line 621  for (;;)
621    switch(op)    switch(op)
622      {      {
623      case OP_FAIL:      case OP_FAIL:
624      return MATCH_NOMATCH;      RRETURN(MATCH_NOMATCH);
625    
626      case OP_PRUNE:      case OP_PRUNE:
627      RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,      RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,
628        ims, eptrb, flags, RM51);        ims, eptrb, flags, RM51);
629      if (rrc != MATCH_NOMATCH) RRETURN(rrc);      if (rrc != MATCH_NOMATCH) RRETURN(rrc);
630      return MATCH_PRUNE;      RRETURN(MATCH_PRUNE);
631    
632      case OP_COMMIT:      case OP_COMMIT:
633      RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,      RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,
634        ims, eptrb, flags, RM52);        ims, eptrb, flags, RM52);
635      if (rrc != MATCH_NOMATCH) RRETURN(rrc);      if (rrc != MATCH_NOMATCH) RRETURN(rrc);
636      return MATCH_COMMIT;      RRETURN(MATCH_COMMIT);
637    
638      case OP_SKIP:      case OP_SKIP:
639      RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,      RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,
640        ims, eptrb, flags, RM53);        ims, eptrb, flags, RM53);
641      if (rrc != MATCH_NOMATCH) RRETURN(rrc);      if (rrc != MATCH_NOMATCH) RRETURN(rrc);
642      md->start_match_ptr = eptr;   /* Pass back current position */      md->start_match_ptr = eptr;   /* Pass back current position */
643      return MATCH_SKIP;      RRETURN(MATCH_SKIP);
644    
645      case OP_THEN:      case OP_THEN:
646      RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,      RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md,
647        ims, eptrb, flags, RM53);        ims, eptrb, flags, RM54);
648      if (rrc != MATCH_NOMATCH) RRETURN(rrc);      if (rrc != MATCH_NOMATCH) RRETURN(rrc);
649      return MATCH_THEN;      RRETURN(MATCH_THEN);
650    
651      /* Handle a capturing bracket. If there is space in the offset vector, save      /* Handle a capturing bracket. If there is space in the offset vector, save
652      the current subject position in the working slot at the top of the vector.      the current subject position in the working slot at the top of the vector.
# Line 1527  for (;;) Line 1526  for (;;)
1526        case 0x000d:        case 0x000d:
1527        if (eptr < md->end_subject && *eptr == 0x0a) eptr++;        if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
1528        break;        break;
1529    
1530        case 0x000a:        case 0x000a:
1531          break;
1532    
1533        case 0x000b:        case 0x000b:
1534        case 0x000c:        case 0x000c:
1535        case 0x0085:        case 0x0085:
1536        case 0x2028:        case 0x2028:
1537        case 0x2029:        case 0x2029:
1538          if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
1539        break;        break;
1540        }        }
1541      ecode++;      ecode++;
# Line 2089  for (;;) Line 2092  for (;;)
2092            RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM21);            RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM21);
2093            if (rrc != MATCH_NOMATCH) RRETURN(rrc);            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
2094            if (eptr-- == pp) break;        /* Stop if tried at original pos */            if (eptr-- == pp) break;        /* Stop if tried at original pos */
2095            BACKCHAR(eptr);            if (utf8) BACKCHAR(eptr);
2096            }            }
2097          RRETURN(MATCH_NOMATCH);          RRETURN(MATCH_NOMATCH);
2098          }          }
# Line 2955  for (;;) Line 2958  for (;;)
2958              case 0x000d:              case 0x000d:
2959              if (eptr < md->end_subject && *eptr == 0x0a) eptr++;              if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
2960              break;              break;
2961    
2962              case 0x000a:              case 0x000a:
2963                break;
2964    
2965              case 0x000b:              case 0x000b:
2966              case 0x000c:              case 0x000c:
2967              case 0x0085:              case 0x0085:
2968              case 0x2028:              case 0x2028:
2969              case 0x2029:              case 0x2029:
2970                if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
2971              break;              break;
2972              }              }
2973            }            }
# Line 3094  for (;;) Line 3101  for (;;)
3101          for (i = 1; i <= min; i++)          for (i = 1; i <= min; i++)
3102            {            {
3103            if (eptr >= md->end_subject ||            if (eptr >= md->end_subject ||
3104               (*eptr < 128 && (md->ctypes[*eptr++] & ctype_space) != 0))               (*eptr < 128 && (md->ctypes[*eptr] & ctype_space) != 0))
3105              RRETURN(MATCH_NOMATCH);              RRETURN(MATCH_NOMATCH);
3106            while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;            while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80);
3107            }            }
3108          break;          break;
3109    
# Line 3114  for (;;) Line 3121  for (;;)
3121          for (i = 1; i <= min; i++)          for (i = 1; i <= min; i++)
3122            {            {
3123            if (eptr >= md->end_subject ||            if (eptr >= md->end_subject ||
3124               (*eptr < 128 && (md->ctypes[*eptr++] & ctype_word) != 0))               (*eptr < 128 && (md->ctypes[*eptr] & ctype_word) != 0))
3125              RRETURN(MATCH_NOMATCH);              RRETURN(MATCH_NOMATCH);
3126            while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;            while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80);
3127            }            }
3128          break;          break;
3129    
# Line 3173  for (;;) Line 3180  for (;;)
3180              if (eptr < md->end_subject && *eptr == 0x0a) eptr++;              if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
3181              break;              break;
3182              case 0x000a:              case 0x000a:
3183                break;
3184    
3185              case 0x000b:              case 0x000b:
3186              case 0x000c:              case 0x000c:
3187              case 0x0085:              case 0x0085:
3188                if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
3189              break;              break;
3190              }              }
3191            }            }
# Line 3427  for (;;) Line 3437  for (;;)
3437                if (eptr < md->end_subject && *eptr == 0x0a) eptr++;                if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
3438                break;                break;
3439                case 0x000a:                case 0x000a:
3440                  break;
3441    
3442                case 0x000b:                case 0x000b:
3443                case 0x000c:                case 0x000c:
3444                case 0x0085:                case 0x0085:
3445                case 0x2028:                case 0x2028:
3446                case 0x2029:                case 0x2029:
3447                  if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
3448                break;                break;
3449                }                }
3450              break;              break;
# Line 3583  for (;;) Line 3596  for (;;)
3596                case 0x000d:                case 0x000d:
3597                if (eptr < md->end_subject && *eptr == 0x0a) eptr++;                if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
3598                break;                break;
3599    
3600                case 0x000a:                case 0x000a:
3601                  break;
3602    
3603                case 0x000b:                case 0x000b:
3604                case 0x000c:                case 0x000c:
3605                case 0x0085:                case 0x0085:
3606                  if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
3607                break;                break;
3608                }                }
3609              break;              break;
# Line 3884  for (;;) Line 3901  for (;;)
3901                }                }
3902              else              else
3903                {                {
3904                if (c != 0x000a && c != 0x000b && c != 0x000c &&                if (c != 0x000a &&
3905                    c != 0x0085 && c != 0x2028 && c != 0x2029)                    (md->bsr_anycrlf ||
3906                       (c != 0x000b && c != 0x000c &&
3907                        c != 0x0085 && c != 0x2028 && c != 0x2029)))
3908                  break;                  break;
3909                eptr += len;                eptr += len;
3910                }                }
# Line 4075  for (;;) Line 4094  for (;;)
4094                }                }
4095              else              else
4096                {                {
4097                if (c != 0x000a && c != 0x000b && c != 0x000c && c != 0x0085)                if (c != 0x000a &&
4098                      (md->bsr_anycrlf ||
4099                        (c != 0x000b && c != 0x000c && c != 0x0085)))
4100                  break;                  break;
4101                eptr++;                eptr++;
4102                }                }
# Line 4229  switch (frame->Xwhere) Line 4250  switch (frame->Xwhere)
4250    LBL(17) LBL(18) LBL(19) LBL(20) LBL(21) LBL(22) LBL(23) LBL(24)    LBL(17) LBL(18) LBL(19) LBL(20) LBL(21) LBL(22) LBL(23) LBL(24)
4251    LBL(25) LBL(26) LBL(27) LBL(28) LBL(29) LBL(30) LBL(31) LBL(32)    LBL(25) LBL(26) LBL(27) LBL(28) LBL(29) LBL(30) LBL(31) LBL(32)
4252    LBL(33) LBL(34) LBL(35) LBL(36) LBL(37) LBL(38) LBL(39) LBL(40)    LBL(33) LBL(34) LBL(35) LBL(36) LBL(37) LBL(38) LBL(39) LBL(40)
4253    LBL(41) LBL(42) LBL(43) LBL(44) LBL(45) LBL(46) LBL(47)    LBL(41) LBL(42) LBL(43) LBL(44) LBL(45) LBL(46) LBL(47) LBL(48)
4254      LBL(49) LBL(50) LBL(51) LBL(52) LBL(53) LBL(54)
4255    default:    default:
4256    DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere));    DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere));
4257    return PCRE_ERROR_INTERNAL;    return PCRE_ERROR_INTERNAL;
# Line 4408  if (re->magic_number != MAGIC_NUMBER) Line 4430  if (re->magic_number != MAGIC_NUMBER)
4430  /* Set up other data */  /* Set up other data */
4431    
4432  anchored = ((re->options | options) & PCRE_ANCHORED) != 0;  anchored = ((re->options | options) & PCRE_ANCHORED) != 0;
4433  startline = (re->options & PCRE_STARTLINE) != 0;  startline = (re->flags & PCRE_STARTLINE) != 0;
4434  firstline = (re->options & PCRE_FIRSTLINE) != 0;  firstline = (re->options & PCRE_FIRSTLINE) != 0;
4435    
4436  /* The code starts after the real_pcre block and the capture name table. */  /* The code starts after the real_pcre block and the capture name table. */
# Line 4435  md->recursive = NULL; Line 4457  md->recursive = NULL;
4457  md->lcc = tables + lcc_offset;  md->lcc = tables + lcc_offset;
4458  md->ctypes = tables + ctypes_offset;  md->ctypes = tables + ctypes_offset;
4459    
4460    /* Handle different \R options. */
4461    
4462    switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE))
4463      {
4464      case 0:
4465      if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0)
4466        md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0;
4467      else
4468    #ifdef BSR_ANYCRLF
4469      md->bsr_anycrlf = TRUE;
4470    #else
4471      md->bsr_anycrlf = FALSE;
4472    #endif
4473      break;
4474    
4475      case PCRE_BSR_ANYCRLF:
4476      md->bsr_anycrlf = TRUE;
4477      break;
4478    
4479      case PCRE_BSR_UNICODE:
4480      md->bsr_anycrlf = FALSE;
4481      break;
4482    
4483      default: return PCRE_ERROR_BADNEWLINE;
4484      }
4485    
4486  /* Handle different types of newline. The three bits give eight cases. If  /* Handle different types of newline. The three bits give eight cases. If
4487  nothing is set at run time, whatever was used at compile time applies. */  nothing is set at run time, whatever was used at compile time applies. */
4488    
4489  switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) &  switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options :
4490         PCRE_NEWLINE_BITS)          (pcre_uint32)options) & PCRE_NEWLINE_BITS)
4491    {    {
4492    case 0: newline = NEWLINE; break;   /* Compile-time default */    case 0: newline = NEWLINE; break;   /* Compile-time default */
4493    case PCRE_NEWLINE_CR: newline = '\r'; break;    case PCRE_NEWLINE_CR: newline = '\r'; break;
# Line 4478  else Line 4526  else
4526  /* Partial matching is supported only for a restricted set of regexes at the  /* Partial matching is supported only for a restricted set of regexes at the
4527  moment. */  moment. */
4528    
4529  if (md->partial && (re->options & PCRE_NOPARTIAL) != 0)  if (md->partial && (re->flags & PCRE_NOPARTIAL) != 0)
4530    return PCRE_ERROR_BADPARTIAL;    return PCRE_ERROR_BADPARTIAL;
4531    
4532  /* Check a UTF-8 string if required. Unfortunately there's no way of passing  /* Check a UTF-8 string if required. Unfortunately there's no way of passing
# Line 4555  studied, there may be a bitmap of possib Line 4603  studied, there may be a bitmap of possib
4603    
4604  if (!anchored)  if (!anchored)
4605    {    {
4606    if ((re->options & PCRE_FIRSTSET) != 0)    if ((re->flags & PCRE_FIRSTSET) != 0)
4607      {      {
4608      first_byte = re->first_byte & 255;      first_byte = re->first_byte & 255;
4609      if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE)      if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE)
# Line 4570  if (!anchored) Line 4618  if (!anchored)
4618  /* For anchored or unanchored matches, there may be a "last known required  /* For anchored or unanchored matches, there may be a "last known required
4619  character" set. */  character" set. */
4620    
4621  if ((re->options & PCRE_REQCHSET) != 0)  if ((re->flags & PCRE_REQCHSET) != 0)
4622    {    {
4623    req_byte = re->req_byte & 255;    req_byte = re->req_byte & 255;
4624    req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0;    req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0;
# Line 4785  for(;;) Line 4833  for(;;)
4833    
4834    if (anchored || start_match > end_subject) break;    if (anchored || start_match > end_subject) break;
4835    
4836    /* If we have just passed a CR and the newline option is CRLF or ANY or    /* If we have just passed a CR and we are now at a LF, and the pattern does
4837    ANYCRLF, and we are now at a LF, advance the match position by one more    not contain any explicit matches for \r or \n, and the newline option is CRLF
4838    character. */    or ANY or ANYCRLF, advance the match position by one more character. */
4839    
4840    if (start_match[-1] == '\r' &&    if (start_match[-1] == '\r' &&
4841         (md->nltype == NLTYPE_ANY ||        start_match < end_subject &&
4842          md->nltype == NLTYPE_ANYCRLF ||        *start_match == '\n' &&
4843          md->nllen == 2) &&        (re->flags & PCRE_HASCRORLF) == 0 &&
4844         start_match < end_subject &&          (md->nltype == NLTYPE_ANY ||
4845         *start_match == '\n')           md->nltype == NLTYPE_ANYCRLF ||
4846             md->nllen == 2))
4847      start_match++;      start_match++;
4848    
4849    }   /* End of for(;;) "bumpalong" loop */    }   /* End of for(;;) "bumpalong" loop */

Legend:
Removed from v.211  
changed lines
  Added in v.231

  ViewVC Help
Powered by ViewVC 1.1.5