/[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 243 by ph10, Thu Sep 13 09:28:14 2007 UTC revision 365 by ph10, Fri Jul 11 17:06:55 2008 UTC
# Line 6  Line 6 
6  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.
7    
8                         Written by Philip Hazel                         Written by Philip Hazel
9             Copyright (c) 1997-2007 University of Cambridge             Copyright (c) 1997-2008 University of Cambridge
10    
11  -----------------------------------------------------------------------------  -----------------------------------------------------------------------------
12  Redistribution and use in source and binary forms, with or without  Redistribution and use in source and binary forms, with or without
# Line 158  printf("\n"); Line 158  printf("\n");
158    
159  if (length > md->end_subject - eptr) return FALSE;  if (length > md->end_subject - eptr) return FALSE;
160    
161  /* Separate the caselesss case for speed */  /* Separate the caseless case for speed. In UTF-8 mode we can only do this
162    properly if Unicode properties are supported. Otherwise, we can check only
163    ASCII characters. */
164    
165  if ((ims & PCRE_CASELESS) != 0)  if ((ims & PCRE_CASELESS) != 0)
166    {    {
167    #ifdef SUPPORT_UTF8
168    #ifdef SUPPORT_UCP
169      if (md->utf8)
170        {
171        USPTR endptr = eptr + length;
172        while (eptr < endptr)
173          {
174          int c, d;
175          GETCHARINC(c, eptr);
176          GETCHARINC(d, p);
177          if (c != d && c != UCD_OTHERCASE(d)) return FALSE;
178          }
179        }
180      else
181    #endif
182    #endif
183    
184      /* The same code works when not in UTF-8 mode and in UTF-8 mode when there
185      is no UCP support. */
186    
187    while (length-- > 0)    while (length-- > 0)
188      if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE;      { if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE; }
189    }    }
190    
191    /* In the caseful case, we can just compare the bytes, whether or not we
192    are in UTF-8 mode. */
193    
194  else  else
195    { while (length-- > 0) if (*p++ != *eptr++) return FALSE; }    { while (length-- > 0) if (*p++ != *eptr++) return FALSE; }
196    
# Line 1148  for (;;) Line 1174  for (;;)
1174      do ecode += GET(ecode,1); while (*ecode == OP_ALT);      do ecode += GET(ecode,1); while (*ecode == OP_ALT);
1175      break;      break;
1176    
1177      /* BRAZERO and BRAMINZERO occur just before a bracket group, indicating      /* BRAZERO, BRAMINZERO and SKIPZERO occur just before a bracket group,
1178      that it may occur zero times. It may repeat infinitely, or not at all -      indicating that it may occur zero times. It may repeat infinitely, or not
1179      i.e. it could be ()* or ()? in the pattern. Brackets with fixed upper      at all - i.e. it could be ()* or ()? or even (){0} in the pattern. Brackets
1180      repeat limits are compiled as a number of copies, with the optional ones      with fixed upper repeat limits are compiled as a number of copies, with the
1181      preceded by BRAZERO or BRAMINZERO. */      optional ones preceded by BRAZERO or BRAMINZERO. */
1182    
1183      case OP_BRAZERO:      case OP_BRAZERO:
1184        {        {
# Line 1174  for (;;) Line 1200  for (;;)
1200        }        }
1201      break;      break;
1202    
1203        case OP_SKIPZERO:
1204          {
1205          next = ecode+1;
1206          do next += GET(next,1); while (*next == OP_ALT);
1207          ecode = next + 1 + LINK_SIZE;
1208          }
1209        break;
1210    
1211      /* End of a group, repeated or non-repeating. */      /* End of a group, repeated or non-repeating. */
1212    
1213      case OP_KET:      case OP_KET:
# Line 1421  for (;;) Line 1455  for (;;)
1455      /* Match a single character type; inline for speed */      /* Match a single character type; inline for speed */
1456    
1457      case OP_ANY:      case OP_ANY:
1458      if ((ims & PCRE_DOTALL) == 0)      if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH);
1459        {      /* Fall through */
1460        if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH);  
1461        }      case OP_ALLANY:
1462      if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH);      if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH);
1463      if (utf8)      if (utf8) while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;
       while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;  
1464      ecode++;      ecode++;
1465      break;      break;
1466    
# Line 1646  for (;;) Line 1679  for (;;)
1679      if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);      if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
1680      GETCHARINCTEST(c, eptr);      GETCHARINCTEST(c, eptr);
1681        {        {
1682        int chartype, script;        const ucd_record * prop = GET_UCD(c);
       int category = _pcre_ucp_findprop(c, &chartype, &script);  
1683    
1684        switch(ecode[1])        switch(ecode[1])
1685          {          {
# Line 1656  for (;;) Line 1688  for (;;)
1688          break;          break;
1689    
1690          case PT_LAMP:          case PT_LAMP:
1691          if ((chartype == ucp_Lu ||          if ((prop->chartype == ucp_Lu ||
1692               chartype == ucp_Ll ||               prop->chartype == ucp_Ll ||
1693               chartype == ucp_Lt) == (op == OP_NOTPROP))               prop->chartype == ucp_Lt) == (op == OP_NOTPROP))
1694            RRETURN(MATCH_NOMATCH);            RRETURN(MATCH_NOMATCH);
1695           break;           break;
1696    
1697          case PT_GC:          case PT_GC:
1698          if ((ecode[2] != category) == (op == OP_PROP))          if ((ecode[2] != _pcre_ucp_gentype[prop->chartype]) == (op == OP_PROP))
1699            RRETURN(MATCH_NOMATCH);            RRETURN(MATCH_NOMATCH);
1700          break;          break;
1701    
1702          case PT_PC:          case PT_PC:
1703          if ((ecode[2] != chartype) == (op == OP_PROP))          if ((ecode[2] != prop->chartype) == (op == OP_PROP))
1704            RRETURN(MATCH_NOMATCH);            RRETURN(MATCH_NOMATCH);
1705          break;          break;
1706    
1707          case PT_SC:          case PT_SC:
1708          if ((ecode[2] != script) == (op == OP_PROP))          if ((ecode[2] != prop->script) == (op == OP_PROP))
1709            RRETURN(MATCH_NOMATCH);            RRETURN(MATCH_NOMATCH);
1710          break;          break;
1711    
# Line 1692  for (;;) Line 1724  for (;;)
1724      if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);      if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
1725      GETCHARINCTEST(c, eptr);      GETCHARINCTEST(c, eptr);
1726        {        {
1727        int chartype, script;        int category = UCD_CATEGORY(c);
       int category = _pcre_ucp_findprop(c, &chartype, &script);  
1728        if (category == ucp_M) RRETURN(MATCH_NOMATCH);        if (category == ucp_M) RRETURN(MATCH_NOMATCH);
1729        while (eptr < md->end_subject)        while (eptr < md->end_subject)
1730          {          {
# Line 1702  for (;;) Line 1733  for (;;)
1733            {            {
1734            GETCHARLEN(c, eptr, len);            GETCHARLEN(c, eptr, len);
1735            }            }
1736          category = _pcre_ucp_findprop(c, &chartype, &script);          category = UCD_CATEGORY(c);
1737          if (category != ucp_M) break;          if (category != ucp_M) break;
1738          eptr += len;          eptr += len;
1739          }          }
# Line 1723  for (;;) Line 1754  for (;;)
1754      case OP_REF:      case OP_REF:
1755        {        {
1756        offset = GET2(ecode, 1) << 1;               /* Doubled ref number */        offset = GET2(ecode, 1) << 1;               /* Doubled ref number */
1757        ecode += 3;                                 /* Advance past item */        ecode += 3;
1758    
1759          /* If the reference is unset, there are two possibilities:
1760    
1761          (a) In the default, Perl-compatible state, set the length to be longer
1762          than the amount of subject left; this ensures that every attempt at a
1763          match fails. We can't just fail here, because of the possibility of
1764          quantifiers with zero minima.
1765    
1766          (b) If the JavaScript compatibility flag is set, set the length to zero
1767          so that the back reference matches an empty string.
1768    
1769          Otherwise, set the length to the length of what was matched by the
1770          referenced subpattern. */
1771    
1772        /* If the reference is unset, set the length to be longer than the amount        if (offset >= offset_top || md->offset_vector[offset] < 0)
1773        of subject left; this ensures that every attempt at a match fails. We          length = (md->jscript_compat)? 0 : md->end_subject - eptr + 1;
1774        can't just fail here, because of the possibility of quantifiers with zero        else
1775        minima. */          length = md->offset_vector[offset+1] - md->offset_vector[offset];
   
       length = (offset >= offset_top || md->offset_vector[offset] < 0)?  
         md->end_subject - eptr + 1 :  
         md->offset_vector[offset+1] - md->offset_vector[offset];  
1776    
1777        /* Set up for repetition, or handle the non-repeated case */        /* Set up for repetition, or handle the non-repeated case */
1778    
# Line 2158  for (;;) Line 2198  for (;;)
2198          if (fc != dc)          if (fc != dc)
2199            {            {
2200  #ifdef SUPPORT_UCP  #ifdef SUPPORT_UCP
2201            if (dc != _pcre_ucp_othercase(fc))            if (dc != UCD_OTHERCASE(fc))
2202  #endif  #endif
2203              RRETURN(MATCH_NOMATCH);              RRETURN(MATCH_NOMATCH);
2204            }            }
# Line 2249  for (;;) Line 2289  for (;;)
2289  #ifdef SUPPORT_UCP  #ifdef SUPPORT_UCP
2290          unsigned int othercase;          unsigned int othercase;
2291          if ((ims & PCRE_CASELESS) != 0 &&          if ((ims & PCRE_CASELESS) != 0 &&
2292              (othercase = _pcre_ucp_othercase(fc)) != NOTACHAR)              (othercase = UCD_OTHERCASE(fc)) != fc)
2293            oclength = _pcre_ord2utf8(othercase, occhars);            oclength = _pcre_ord2utf8(othercase, occhars);
2294          else oclength = 0;          else oclength = 0;
2295  #endif  /* SUPPORT_UCP */  #endif  /* SUPPORT_UCP */
# Line 2854  for (;;) Line 2894  for (;;)
2894              {              {
2895              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
2896              GETCHARINCTEST(c, eptr);              GETCHARINCTEST(c, eptr);
2897              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_chartype = UCD_CHARTYPE(c);
2898              if ((prop_chartype == ucp_Lu ||              if ((prop_chartype == ucp_Lu ||
2899                   prop_chartype == ucp_Ll ||                   prop_chartype == ucp_Ll ||
2900                   prop_chartype == ucp_Lt) == prop_fail_result)                   prop_chartype == ucp_Lt) == prop_fail_result)
# Line 2867  for (;;) Line 2907  for (;;)
2907              {              {
2908              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
2909              GETCHARINCTEST(c, eptr);              GETCHARINCTEST(c, eptr);
2910              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
2911              if ((prop_category == prop_value) == prop_fail_result)              if ((prop_category == prop_value) == prop_fail_result)
2912                RRETURN(MATCH_NOMATCH);                RRETURN(MATCH_NOMATCH);
2913              }              }
# Line 2878  for (;;) Line 2918  for (;;)
2918              {              {
2919              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
2920              GETCHARINCTEST(c, eptr);              GETCHARINCTEST(c, eptr);
2921              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_chartype = UCD_CHARTYPE(c);
2922              if ((prop_chartype == prop_value) == prop_fail_result)              if ((prop_chartype == prop_value) == prop_fail_result)
2923                RRETURN(MATCH_NOMATCH);                RRETURN(MATCH_NOMATCH);
2924              }              }
# Line 2889  for (;;) Line 2929  for (;;)
2929              {              {
2930              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
2931              GETCHARINCTEST(c, eptr);              GETCHARINCTEST(c, eptr);
2932              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_script = UCD_SCRIPT(c);
2933              if ((prop_script == prop_value) == prop_fail_result)              if ((prop_script == prop_value) == prop_fail_result)
2934                RRETURN(MATCH_NOMATCH);                RRETURN(MATCH_NOMATCH);
2935              }              }
# Line 2908  for (;;) Line 2948  for (;;)
2948          for (i = 1; i <= min; i++)          for (i = 1; i <= min; i++)
2949            {            {
2950            GETCHARINCTEST(c, eptr);            GETCHARINCTEST(c, eptr);
2951            prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);            prop_category = UCD_CATEGORY(c);
2952            if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH);            if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH);
2953            while (eptr < md->end_subject)            while (eptr < md->end_subject)
2954              {              {
# Line 2917  for (;;) Line 2957  for (;;)
2957                {                {
2958                GETCHARLEN(c, eptr, len);                GETCHARLEN(c, eptr, len);
2959                }                }
2960              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
2961              if (prop_category != ucp_M) break;              if (prop_category != ucp_M) break;
2962              eptr += len;              eptr += len;
2963              }              }
# Line 2935  for (;;) Line 2975  for (;;)
2975          case OP_ANY:          case OP_ANY:
2976          for (i = 1; i <= min; i++)          for (i = 1; i <= min; i++)
2977            {            {
2978            if (eptr >= md->end_subject ||            if (eptr >= md->end_subject || IS_NEWLINE(eptr))
                ((ims & PCRE_DOTALL) == 0 && IS_NEWLINE(eptr)))  
2979              RRETURN(MATCH_NOMATCH);              RRETURN(MATCH_NOMATCH);
2980            eptr++;            eptr++;
2981            while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;            while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;
2982            }            }
2983          break;          break;
2984    
2985            case OP_ALLANY:
2986            for (i = 1; i <= min; i++)
2987              {
2988              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
2989              eptr++;
2990              while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;
2991              }
2992            break;
2993    
2994          case OP_ANYBYTE:          case OP_ANYBYTE:
2995          eptr += min;          eptr += min;
2996          break;          break;
# Line 3151  for (;;) Line 3199  for (;;)
3199        switch(ctype)        switch(ctype)
3200          {          {
3201          case OP_ANY:          case OP_ANY:
3202          if ((ims & PCRE_DOTALL) == 0)          for (i = 1; i <= min; i++)
3203            {            {
3204            for (i = 1; i <= min; i++)            if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH);
3205              {            eptr++;
             if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH);  
             eptr++;  
             }  
3206            }            }
3207          else eptr += min;          break;
3208    
3209            case OP_ALLANY:
3210            eptr += min;
3211          break;          break;
3212    
3213          case OP_ANYBYTE:          case OP_ANYBYTE:
# Line 3325  for (;;) Line 3373  for (;;)
3373              if (rrc != MATCH_NOMATCH) RRETURN(rrc);              if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3374              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
3375              GETCHARINC(c, eptr);              GETCHARINC(c, eptr);
3376              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_chartype = UCD_CHARTYPE(c);
3377              if ((prop_chartype == ucp_Lu ||              if ((prop_chartype == ucp_Lu ||
3378                   prop_chartype == ucp_Ll ||                   prop_chartype == ucp_Ll ||
3379                   prop_chartype == ucp_Lt) == prop_fail_result)                   prop_chartype == ucp_Lt) == prop_fail_result)
# Line 3340  for (;;) Line 3388  for (;;)
3388              if (rrc != MATCH_NOMATCH) RRETURN(rrc);              if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3389              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
3390              GETCHARINC(c, eptr);              GETCHARINC(c, eptr);
3391              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
3392              if ((prop_category == prop_value) == prop_fail_result)              if ((prop_category == prop_value) == prop_fail_result)
3393                RRETURN(MATCH_NOMATCH);                RRETURN(MATCH_NOMATCH);
3394              }              }
# Line 3353  for (;;) Line 3401  for (;;)
3401              if (rrc != MATCH_NOMATCH) RRETURN(rrc);              if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3402              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
3403              GETCHARINC(c, eptr);              GETCHARINC(c, eptr);
3404              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_chartype = UCD_CHARTYPE(c);
3405              if ((prop_chartype == prop_value) == prop_fail_result)              if ((prop_chartype == prop_value) == prop_fail_result)
3406                RRETURN(MATCH_NOMATCH);                RRETURN(MATCH_NOMATCH);
3407              }              }
# Line 3366  for (;;) Line 3414  for (;;)
3414              if (rrc != MATCH_NOMATCH) RRETURN(rrc);              if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3415              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
3416              GETCHARINC(c, eptr);              GETCHARINC(c, eptr);
3417              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_script = UCD_SCRIPT(c);
3418              if ((prop_script == prop_value) == prop_fail_result)              if ((prop_script == prop_value) == prop_fail_result)
3419                RRETURN(MATCH_NOMATCH);                RRETURN(MATCH_NOMATCH);
3420              }              }
# Line 3388  for (;;) Line 3436  for (;;)
3436            if (rrc != MATCH_NOMATCH) RRETURN(rrc);            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3437            if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);            if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
3438            GETCHARINCTEST(c, eptr);            GETCHARINCTEST(c, eptr);
3439            prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);            prop_category = UCD_CATEGORY(c);
3440            if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH);            if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH);
3441            while (eptr < md->end_subject)            while (eptr < md->end_subject)
3442              {              {
# Line 3397  for (;;) Line 3445  for (;;)
3445                {                {
3446                GETCHARLEN(c, eptr, len);                GETCHARLEN(c, eptr, len);
3447                }                }
3448              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
3449              if (prop_category != ucp_M) break;              if (prop_category != ucp_M) break;
3450              eptr += len;              eptr += len;
3451              }              }
# Line 3416  for (;;) Line 3464  for (;;)
3464            RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM42);            RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM42);
3465            if (rrc != MATCH_NOMATCH) RRETURN(rrc);            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3466            if (fi >= max || eptr >= md->end_subject ||            if (fi >= max || eptr >= md->end_subject ||
3467                 (ctype == OP_ANY && (ims & PCRE_DOTALL) == 0 &&                 (ctype == OP_ANY && IS_NEWLINE(eptr)))
                 IS_NEWLINE(eptr)))  
3468              RRETURN(MATCH_NOMATCH);              RRETURN(MATCH_NOMATCH);
3469    
3470            GETCHARINC(c, eptr);            GETCHARINC(c, eptr);
3471            switch(ctype)            switch(ctype)
3472              {              {
3473              case OP_ANY:        /* This is the DOTALL case */              case OP_ANY:        /* This is the non-NL case */
3474              break;              case OP_ALLANY:
   
3475              case OP_ANYBYTE:              case OP_ANYBYTE:
3476              break;              break;
3477    
# Line 3577  for (;;) Line 3623  for (;;)
3623            RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM43);            RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM43);
3624            if (rrc != MATCH_NOMATCH) RRETURN(rrc);            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3625            if (fi >= max || eptr >= md->end_subject ||            if (fi >= max || eptr >= md->end_subject ||
3626                 ((ims & PCRE_DOTALL) == 0 && IS_NEWLINE(eptr)))                 (ctype == OP_ANY && IS_NEWLINE(eptr)))
3627              RRETURN(MATCH_NOMATCH);              RRETURN(MATCH_NOMATCH);
3628    
3629            c = *eptr++;            c = *eptr++;
3630            switch(ctype)            switch(ctype)
3631              {              {
3632              case OP_ANY:   /* This is the DOTALL case */              case OP_ANY:     /* This is the non-NL case */
3633              break;              case OP_ALLANY:
   
3634              case OP_ANYBYTE:              case OP_ANYBYTE:
3635              break;              break;
3636    
# Line 3718  for (;;) Line 3763  for (;;)
3763              int len = 1;              int len = 1;
3764              if (eptr >= md->end_subject) break;              if (eptr >= md->end_subject) break;
3765              GETCHARLEN(c, eptr, len);              GETCHARLEN(c, eptr, len);
3766              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_chartype = UCD_CHARTYPE(c);
3767              if ((prop_chartype == ucp_Lu ||              if ((prop_chartype == ucp_Lu ||
3768                   prop_chartype == ucp_Ll ||                   prop_chartype == ucp_Ll ||
3769                   prop_chartype == ucp_Lt) == prop_fail_result)                   prop_chartype == ucp_Lt) == prop_fail_result)
# Line 3733  for (;;) Line 3778  for (;;)
3778              int len = 1;              int len = 1;
3779              if (eptr >= md->end_subject) break;              if (eptr >= md->end_subject) break;
3780              GETCHARLEN(c, eptr, len);              GETCHARLEN(c, eptr, len);
3781              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
3782              if ((prop_category == prop_value) == prop_fail_result)              if ((prop_category == prop_value) == prop_fail_result)
3783                break;                break;
3784              eptr+= len;              eptr+= len;
# Line 3746  for (;;) Line 3791  for (;;)
3791              int len = 1;              int len = 1;
3792              if (eptr >= md->end_subject) break;              if (eptr >= md->end_subject) break;
3793              GETCHARLEN(c, eptr, len);              GETCHARLEN(c, eptr, len);
3794              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_chartype = UCD_CHARTYPE(c);
3795              if ((prop_chartype == prop_value) == prop_fail_result)              if ((prop_chartype == prop_value) == prop_fail_result)
3796                break;                break;
3797              eptr+= len;              eptr+= len;
# Line 3759  for (;;) Line 3804  for (;;)
3804              int len = 1;              int len = 1;
3805              if (eptr >= md->end_subject) break;              if (eptr >= md->end_subject) break;
3806              GETCHARLEN(c, eptr, len);              GETCHARLEN(c, eptr, len);
3807              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_script = UCD_SCRIPT(c);
3808              if ((prop_script == prop_value) == prop_fail_result)              if ((prop_script == prop_value) == prop_fail_result)
3809                break;                break;
3810              eptr+= len;              eptr+= len;
# Line 3788  for (;;) Line 3833  for (;;)
3833            {            {
3834            if (eptr >= md->end_subject) break;            if (eptr >= md->end_subject) break;
3835            GETCHARINCTEST(c, eptr);            GETCHARINCTEST(c, eptr);
3836            prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);            prop_category = UCD_CATEGORY(c);
3837            if (prop_category == ucp_M) break;            if (prop_category == ucp_M) break;
3838            while (eptr < md->end_subject)            while (eptr < md->end_subject)
3839              {              {
# Line 3797  for (;;) Line 3842  for (;;)
3842                {                {
3843                GETCHARLEN(c, eptr, len);                GETCHARLEN(c, eptr, len);
3844                }                }
3845              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
3846              if (prop_category != ucp_M) break;              if (prop_category != ucp_M) break;
3847              eptr += len;              eptr += len;
3848              }              }
# Line 3819  for (;;) Line 3864  for (;;)
3864                BACKCHAR(eptr);                BACKCHAR(eptr);
3865                GETCHARLEN(c, eptr, len);                GETCHARLEN(c, eptr, len);
3866                }                }
3867              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
3868              if (prop_category != ucp_M) break;              if (prop_category != ucp_M) break;
3869              eptr--;              eptr--;
3870              }              }
# Line 3839  for (;;) Line 3884  for (;;)
3884            case OP_ANY:            case OP_ANY:
3885            if (max < INT_MAX)            if (max < INT_MAX)
3886              {              {
3887              if ((ims & PCRE_DOTALL) == 0)              for (i = min; i < max; i++)
               {  
               for (i = min; i < max; i++)  
                 {  
                 if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break;  
                 eptr++;  
                 while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;  
                 }  
               }  
             else  
3888                {                {
3889                for (i = min; i < max; i++)                if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break;
3890                  {                eptr++;
3891                  if (eptr >= md->end_subject) break;                while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;
                 eptr++;  
                 while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;  
                 }  
3892                }                }
3893              }              }
3894    
# Line 3863  for (;;) Line 3896  for (;;)
3896    
3897            else            else
3898              {              {
3899              if ((ims & PCRE_DOTALL) == 0)              for (i = min; i < max; i++)
3900                {                {
3901                for (i = min; i < max; i++)                if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break;
3902                  {                eptr++;
3903                  if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break;                while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;
                 eptr++;  
                 while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;  
                 }  
3904                }                }
3905              else              }
3906              break;
3907    
3908              case OP_ALLANY:
3909              if (max < INT_MAX)
3910                {
3911                for (i = min; i < max; i++)
3912                {                {
3913                eptr = md->end_subject;                if (eptr >= md->end_subject) break;
3914                  eptr++;
3915                  while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;
3916                }                }
3917              }              }
3918              else eptr = md->end_subject;   /* Unlimited UTF-8 repeat */
3919            break;            break;
3920    
3921            /* The byte case is the same as non-UTF8 */            /* The byte case is the same as non-UTF8 */
# Line 4064  for (;;) Line 4103  for (;;)
4103          switch(ctype)          switch(ctype)
4104            {            {
4105            case OP_ANY:            case OP_ANY:
4106            if ((ims & PCRE_DOTALL) == 0)            for (i = min; i < max; i++)
4107              {              {
4108              for (i = min; i < max; i++)              if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break;
4109                {              eptr++;
               if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break;  
               eptr++;  
               }  
             break;  
4110              }              }
4111            /* For DOTALL case, fall through and treat as \C */            break;
4112    
4113              case OP_ALLANY:
4114            case OP_ANYBYTE:            case OP_ANYBYTE:
4115            c = max - min;            c = max - min;
4116            if (c > (unsigned int)(md->end_subject - eptr))            if (c > (unsigned int)(md->end_subject - eptr))
# Line 4246  HEAP_RETURN: Line 4282  HEAP_RETURN:
4282  switch (frame->Xwhere)  switch (frame->Xwhere)
4283    {    {
4284    LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8)    LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8)
4285    LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(16)    LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(17)
4286    LBL(17) LBL(18) LBL(19) LBL(20) LBL(21) LBL(22) LBL(23) LBL(24)    LBL(19) LBL(24) LBL(25) LBL(26) LBL(27) LBL(29) LBL(31) LBL(33)
4287    LBL(25) LBL(26) LBL(27) LBL(28) LBL(29) LBL(30) LBL(31) LBL(32)    LBL(35) LBL(43) LBL(47) LBL(48) LBL(49) LBL(50) LBL(51) LBL(52)
4288    LBL(33) LBL(34) LBL(35) LBL(36) LBL(37) LBL(38) LBL(39) LBL(40)    LBL(53) LBL(54)
4289    LBL(41) LBL(42) LBL(43) LBL(44) LBL(45) LBL(46) LBL(47) LBL(48)  #ifdef SUPPORT_UTF8
4290    LBL(49) LBL(50) LBL(51) LBL(52) LBL(53) LBL(54)    LBL(16) LBL(18) LBL(20) LBL(21) LBL(22) LBL(23) LBL(28) LBL(30)
4291      LBL(32) LBL(34) LBL(42) LBL(46)
4292    #ifdef SUPPORT_UCP
4293      LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) LBL(41) LBL(44) LBL(45)
4294    #endif  /* SUPPORT_UCP */
4295    #endif  /* SUPPORT_UTF8 */
4296    default:    default:
4297    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));
4298    return PCRE_ERROR_INTERNAL;    return PCRE_ERROR_INTERNAL;
# Line 4343  Returns: > 0 => success; value Line 4384  Returns: > 0 => success; value
4384                   < -1 => some kind of unexpected problem                   < -1 => some kind of unexpected problem
4385  */  */
4386    
4387  PCRE_EXP_DEFN int  PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
4388  pcre_exec(const pcre *argument_re, const pcre_extra *extra_data,  pcre_exec(const pcre *argument_re, const pcre_extra *extra_data,
4389    PCRE_SPTR subject, int length, int start_offset, int options, int *offsets,    PCRE_SPTR subject, int length, int start_offset, int options, int *offsets,
4390    int offsetcount)    int offsetcount)
# Line 4445  end_subject = md->end_subject; Line 4486  end_subject = md->end_subject;
4486    
4487  md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0;  md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0;
4488  utf8 = md->utf8 = (re->options & PCRE_UTF8) != 0;  utf8 = md->utf8 = (re->options & PCRE_UTF8) != 0;
4489    md->jscript_compat = (re->options & PCRE_JAVASCRIPT_COMPAT) != 0;
4490    
4491  md->notbol = (options & PCRE_NOTBOL) != 0;  md->notbol = (options & PCRE_NOTBOL) != 0;
4492  md->noteol = (options & PCRE_NOTEOL) != 0;  md->noteol = (options & PCRE_NOTEOL) != 0;
# Line 4654  for(;;) Line 4696  for(;;)
4696    if (firstline)    if (firstline)
4697      {      {
4698      USPTR t = start_match;      USPTR t = start_match;
4699    #ifdef SUPPORT_UTF8
4700        if (utf8)
4701          {
4702          while (t < md->end_subject && !IS_NEWLINE(t))
4703            {
4704            t++;
4705            while (t < end_subject && (*t & 0xc0) == 0x80) t++;
4706            }
4707          }
4708        else
4709    #endif
4710      while (t < md->end_subject && !IS_NEWLINE(t)) t++;      while (t < md->end_subject && !IS_NEWLINE(t)) t++;
4711      end_subject = t;      end_subject = t;
4712      }      }
4713    
4714    /* Now test for a unique first byte */    /* Now advance to a unique first byte if there is one. */
4715    
4716    if (first_byte >= 0)    if (first_byte >= 0)
4717      {      {
4718      if (first_byte_caseless)      if (first_byte_caseless)
4719        while (start_match < end_subject &&        while (start_match < end_subject && md->lcc[*start_match] != first_byte)
              md->lcc[*start_match] != first_byte)  
4720          start_match++;          start_match++;
4721      else      else
4722        while (start_match < end_subject && *start_match != first_byte)        while (start_match < end_subject && *start_match != first_byte)
4723          start_match++;          start_match++;
4724      }      }
4725    
4726    /* Or to just after a linebreak for a multiline match if possible */    /* Or to just after a linebreak for a multiline match */
4727    
4728    else if (startline)    else if (startline)
4729      {      {
4730      if (start_match > md->start_subject + start_offset)      if (start_match > md->start_subject + start_offset)
4731        {        {
4732        while (start_match <= end_subject && !WAS_NEWLINE(start_match))  #ifdef SUPPORT_UTF8
4733          if (utf8)
4734            {
4735            while (start_match < end_subject && !WAS_NEWLINE(start_match))
4736              {
4737              start_match++;
4738              while(start_match < end_subject && (*start_match & 0xc0) == 0x80)
4739                start_match++;
4740              }
4741            }
4742          else
4743    #endif
4744          while (start_match < end_subject && !WAS_NEWLINE(start_match))
4745          start_match++;          start_match++;
4746    
4747        /* If we have just passed a CR and the newline option is ANY or ANYCRLF,        /* If we have just passed a CR and the newline option is ANY or ANYCRLF,
4748        and we are now at a LF, advance the match position by one more character.        and we are now at a LF, advance the match position by one more character.
4749        */        */
# Line 4692  for(;;) Line 4756  for(;;)
4756        }        }
4757      }      }
4758    
4759    /* Or to a non-unique first char after study */    /* Or to a non-unique first byte after study */
4760    
4761    else if (start_bits != NULL)    else if (start_bits != NULL)
4762      {      {
4763      while (start_match < end_subject)      while (start_match < end_subject)
4764        {        {
4765        register unsigned int c = *start_match;        register unsigned int c = *start_match;
4766        if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++; else break;        if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++;
4767            else break;
4768        }        }
4769      }      }
4770    
# Line 4774  for(;;) Line 4839  for(;;)
4839      }      }
4840    
4841    /* OK, we can now run the match. */    /* OK, we can now run the match. */
4842    
4843    md->start_match_ptr = start_match;    md->start_match_ptr = start_match;
4844    md->match_call_count = 0;    md->match_call_count = 0;
4845    rc = match(start_match, md->start_code, start_match, 2, md, ims, NULL, 0, 0);    rc = match(start_match, md->start_code, start_match, 2, md, ims, NULL, 0, 0);
Legend:
Removed from v.243  
changed lines
  Added in v.365
webmaster@exim.org
 ViewVC Help
Powered by ViewVC 1.1.12