/[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 298 by ph10, Thu Jan 10 17:09:12 2008 UTC revision 371 by ph10, Mon Aug 25 18:28:05 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, set the length to be longer than the amount        /* If the reference is unset, there are two possibilities:
1760        of subject left; this ensures that every attempt at a match fails. We  
1761        can't just fail here, because of the possibility of quantifiers with zero        (a) In the default, Perl-compatible state, set the length to be longer
1762        minima. */        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        length = (offset >= offset_top || md->offset_vector[offset] < 0)?        quantifiers with zero minima.
1765          md->end_subject - eptr + 1 :  
1766          md->offset_vector[offset+1] - md->offset_vector[offset];        (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 (offset >= offset_top || md->offset_vector[offset] < 0)
1773            length = (md->jscript_compat)? 0 : md->end_subject - eptr + 1;
1774          else
1775            length = 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 2569  for (;;) Line 2609  for (;;)
2609              {              {
2610              RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM28);              RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM28);
2611              if (rrc != MATCH_NOMATCH) RRETURN(rrc);              if (rrc != MATCH_NOMATCH) RRETURN(rrc);
2612                if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
2613              GETCHARINC(d, eptr);              GETCHARINC(d, eptr);
2614              if (d < 256) d = md->lcc[d];              if (d < 256) d = md->lcc[d];
2615              if (fi >= max || eptr >= md->end_subject || fc == d)              if (fc == d) RRETURN(MATCH_NOMATCH);
2616                RRETURN(MATCH_NOMATCH);  
2617              }              }
2618            }            }
2619          else          else
# Line 2678  for (;;) Line 2719  for (;;)
2719              {              {
2720              RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM32);              RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM32);
2721              if (rrc != MATCH_NOMATCH) RRETURN(rrc);              if (rrc != MATCH_NOMATCH) RRETURN(rrc);
2722                if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
2723              GETCHARINC(d, eptr);              GETCHARINC(d, eptr);
2724              if (fi >= max || eptr >= md->end_subject || fc == d)              if (fc == d) RRETURN(MATCH_NOMATCH);
               RRETURN(MATCH_NOMATCH);  
2725              }              }
2726            }            }
2727          else          else
# Line 2854  for (;;) Line 2895  for (;;)
2895              {              {
2896              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
2897              GETCHARINCTEST(c, eptr);              GETCHARINCTEST(c, eptr);
2898              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_chartype = UCD_CHARTYPE(c);
2899              if ((prop_chartype == ucp_Lu ||              if ((prop_chartype == ucp_Lu ||
2900                   prop_chartype == ucp_Ll ||                   prop_chartype == ucp_Ll ||
2901                   prop_chartype == ucp_Lt) == prop_fail_result)                   prop_chartype == ucp_Lt) == prop_fail_result)
# Line 2867  for (;;) Line 2908  for (;;)
2908              {              {
2909              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
2910              GETCHARINCTEST(c, eptr);              GETCHARINCTEST(c, eptr);
2911              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
2912              if ((prop_category == prop_value) == prop_fail_result)              if ((prop_category == prop_value) == prop_fail_result)
2913                RRETURN(MATCH_NOMATCH);                RRETURN(MATCH_NOMATCH);
2914              }              }
# Line 2878  for (;;) Line 2919  for (;;)
2919              {              {
2920              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
2921              GETCHARINCTEST(c, eptr);              GETCHARINCTEST(c, eptr);
2922              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_chartype = UCD_CHARTYPE(c);
2923              if ((prop_chartype == prop_value) == prop_fail_result)              if ((prop_chartype == prop_value) == prop_fail_result)
2924                RRETURN(MATCH_NOMATCH);                RRETURN(MATCH_NOMATCH);
2925              }              }
# Line 2889  for (;;) Line 2930  for (;;)
2930              {              {
2931              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
2932              GETCHARINCTEST(c, eptr);              GETCHARINCTEST(c, eptr);
2933              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_script = UCD_SCRIPT(c);
2934              if ((prop_script == prop_value) == prop_fail_result)              if ((prop_script == prop_value) == prop_fail_result)
2935                RRETURN(MATCH_NOMATCH);                RRETURN(MATCH_NOMATCH);
2936              }              }
# Line 2908  for (;;) Line 2949  for (;;)
2949          for (i = 1; i <= min; i++)          for (i = 1; i <= min; i++)
2950            {            {
2951            GETCHARINCTEST(c, eptr);            GETCHARINCTEST(c, eptr);
2952            prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);            prop_category = UCD_CATEGORY(c);
2953            if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH);            if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH);
2954            while (eptr < md->end_subject)            while (eptr < md->end_subject)
2955              {              {
# Line 2917  for (;;) Line 2958  for (;;)
2958                {                {
2959                GETCHARLEN(c, eptr, len);                GETCHARLEN(c, eptr, len);
2960                }                }
2961              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
2962              if (prop_category != ucp_M) break;              if (prop_category != ucp_M) break;
2963              eptr += len;              eptr += len;
2964              }              }
# Line 2935  for (;;) Line 2976  for (;;)
2976          case OP_ANY:          case OP_ANY:
2977          for (i = 1; i <= min; i++)          for (i = 1; i <= min; i++)
2978            {            {
2979            if (eptr >= md->end_subject ||            if (eptr >= md->end_subject || IS_NEWLINE(eptr))
                ((ims & PCRE_DOTALL) == 0 && IS_NEWLINE(eptr)))  
2980              RRETURN(MATCH_NOMATCH);              RRETURN(MATCH_NOMATCH);
2981            eptr++;            eptr++;
2982            while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;            while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;
2983            }            }
2984          break;          break;
2985    
2986            case OP_ALLANY:
2987            for (i = 1; i <= min; i++)
2988              {
2989              if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
2990              eptr++;
2991              while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;
2992              }
2993            break;
2994    
2995          case OP_ANYBYTE:          case OP_ANYBYTE:
2996          eptr += min;          eptr += min;
2997          break;          break;
# Line 3151  for (;;) Line 3200  for (;;)
3200        switch(ctype)        switch(ctype)
3201          {          {
3202          case OP_ANY:          case OP_ANY:
3203          if ((ims & PCRE_DOTALL) == 0)          for (i = 1; i <= min; i++)
3204            {            {
3205            for (i = 1; i <= min; i++)            if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH);
3206              {            eptr++;
             if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH);  
             eptr++;  
             }  
3207            }            }
3208          else eptr += min;          break;
3209    
3210            case OP_ALLANY:
3211            eptr += min;
3212          break;          break;
3213    
3214          case OP_ANYBYTE:          case OP_ANYBYTE:
# Line 3325  for (;;) Line 3374  for (;;)
3374              if (rrc != MATCH_NOMATCH) RRETURN(rrc);              if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3375              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
3376              GETCHARINC(c, eptr);              GETCHARINC(c, eptr);
3377              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_chartype = UCD_CHARTYPE(c);
3378              if ((prop_chartype == ucp_Lu ||              if ((prop_chartype == ucp_Lu ||
3379                   prop_chartype == ucp_Ll ||                   prop_chartype == ucp_Ll ||
3380                   prop_chartype == ucp_Lt) == prop_fail_result)                   prop_chartype == ucp_Lt) == prop_fail_result)
# Line 3340  for (;;) Line 3389  for (;;)
3389              if (rrc != MATCH_NOMATCH) RRETURN(rrc);              if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3390              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
3391              GETCHARINC(c, eptr);              GETCHARINC(c, eptr);
3392              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
3393              if ((prop_category == prop_value) == prop_fail_result)              if ((prop_category == prop_value) == prop_fail_result)
3394                RRETURN(MATCH_NOMATCH);                RRETURN(MATCH_NOMATCH);
3395              }              }
# Line 3353  for (;;) Line 3402  for (;;)
3402              if (rrc != MATCH_NOMATCH) RRETURN(rrc);              if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3403              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
3404              GETCHARINC(c, eptr);              GETCHARINC(c, eptr);
3405              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_chartype = UCD_CHARTYPE(c);
3406              if ((prop_chartype == prop_value) == prop_fail_result)              if ((prop_chartype == prop_value) == prop_fail_result)
3407                RRETURN(MATCH_NOMATCH);                RRETURN(MATCH_NOMATCH);
3408              }              }
# Line 3366  for (;;) Line 3415  for (;;)
3415              if (rrc != MATCH_NOMATCH) RRETURN(rrc);              if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3416              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);              if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
3417              GETCHARINC(c, eptr);              GETCHARINC(c, eptr);
3418              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_script = UCD_SCRIPT(c);
3419              if ((prop_script == prop_value) == prop_fail_result)              if ((prop_script == prop_value) == prop_fail_result)
3420                RRETURN(MATCH_NOMATCH);                RRETURN(MATCH_NOMATCH);
3421              }              }
# Line 3388  for (;;) Line 3437  for (;;)
3437            if (rrc != MATCH_NOMATCH) RRETURN(rrc);            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3438            if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);            if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
3439            GETCHARINCTEST(c, eptr);            GETCHARINCTEST(c, eptr);
3440            prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);            prop_category = UCD_CATEGORY(c);
3441            if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH);            if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH);
3442            while (eptr < md->end_subject)            while (eptr < md->end_subject)
3443              {              {
# Line 3397  for (;;) Line 3446  for (;;)
3446                {                {
3447                GETCHARLEN(c, eptr, len);                GETCHARLEN(c, eptr, len);
3448                }                }
3449              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
3450              if (prop_category != ucp_M) break;              if (prop_category != ucp_M) break;
3451              eptr += len;              eptr += len;
3452              }              }
# Line 3416  for (;;) Line 3465  for (;;)
3465            RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM42);            RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM42);
3466            if (rrc != MATCH_NOMATCH) RRETURN(rrc);            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3467            if (fi >= max || eptr >= md->end_subject ||            if (fi >= max || eptr >= md->end_subject ||
3468                 (ctype == OP_ANY && (ims & PCRE_DOTALL) == 0 &&                 (ctype == OP_ANY && IS_NEWLINE(eptr)))
                 IS_NEWLINE(eptr)))  
3469              RRETURN(MATCH_NOMATCH);              RRETURN(MATCH_NOMATCH);
3470    
3471            GETCHARINC(c, eptr);            GETCHARINC(c, eptr);
3472            switch(ctype)            switch(ctype)
3473              {              {
3474              case OP_ANY:        /* This is the DOTALL case */              case OP_ANY:        /* This is the non-NL case */
3475              break;              case OP_ALLANY:
   
3476              case OP_ANYBYTE:              case OP_ANYBYTE:
3477              break;              break;
3478    
# Line 3577  for (;;) Line 3624  for (;;)
3624            RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM43);            RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM43);
3625            if (rrc != MATCH_NOMATCH) RRETURN(rrc);            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
3626            if (fi >= max || eptr >= md->end_subject ||            if (fi >= max || eptr >= md->end_subject ||
3627                 ((ims & PCRE_DOTALL) == 0 && IS_NEWLINE(eptr)))                 (ctype == OP_ANY && IS_NEWLINE(eptr)))
3628              RRETURN(MATCH_NOMATCH);              RRETURN(MATCH_NOMATCH);
3629    
3630            c = *eptr++;            c = *eptr++;
3631            switch(ctype)            switch(ctype)
3632              {              {
3633              case OP_ANY:   /* This is the DOTALL case */              case OP_ANY:     /* This is the non-NL case */
3634              break;              case OP_ALLANY:
   
3635              case OP_ANYBYTE:              case OP_ANYBYTE:
3636              break;              break;
3637    
# Line 3718  for (;;) Line 3764  for (;;)
3764              int len = 1;              int len = 1;
3765              if (eptr >= md->end_subject) break;              if (eptr >= md->end_subject) break;
3766              GETCHARLEN(c, eptr, len);              GETCHARLEN(c, eptr, len);
3767              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_chartype = UCD_CHARTYPE(c);
3768              if ((prop_chartype == ucp_Lu ||              if ((prop_chartype == ucp_Lu ||
3769                   prop_chartype == ucp_Ll ||                   prop_chartype == ucp_Ll ||
3770                   prop_chartype == ucp_Lt) == prop_fail_result)                   prop_chartype == ucp_Lt) == prop_fail_result)
# Line 3733  for (;;) Line 3779  for (;;)
3779              int len = 1;              int len = 1;
3780              if (eptr >= md->end_subject) break;              if (eptr >= md->end_subject) break;
3781              GETCHARLEN(c, eptr, len);              GETCHARLEN(c, eptr, len);
3782              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
3783              if ((prop_category == prop_value) == prop_fail_result)              if ((prop_category == prop_value) == prop_fail_result)
3784                break;                break;
3785              eptr+= len;              eptr+= len;
# Line 3746  for (;;) Line 3792  for (;;)
3792              int len = 1;              int len = 1;
3793              if (eptr >= md->end_subject) break;              if (eptr >= md->end_subject) break;
3794              GETCHARLEN(c, eptr, len);              GETCHARLEN(c, eptr, len);
3795              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_chartype = UCD_CHARTYPE(c);
3796              if ((prop_chartype == prop_value) == prop_fail_result)              if ((prop_chartype == prop_value) == prop_fail_result)
3797                break;                break;
3798              eptr+= len;              eptr+= len;
# Line 3759  for (;;) Line 3805  for (;;)
3805              int len = 1;              int len = 1;
3806              if (eptr >= md->end_subject) break;              if (eptr >= md->end_subject) break;
3807              GETCHARLEN(c, eptr, len);              GETCHARLEN(c, eptr, len);
3808              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_script = UCD_SCRIPT(c);
3809              if ((prop_script == prop_value) == prop_fail_result)              if ((prop_script == prop_value) == prop_fail_result)
3810                break;                break;
3811              eptr+= len;              eptr+= len;
# Line 3788  for (;;) Line 3834  for (;;)
3834            {            {
3835            if (eptr >= md->end_subject) break;            if (eptr >= md->end_subject) break;
3836            GETCHARINCTEST(c, eptr);            GETCHARINCTEST(c, eptr);
3837            prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);            prop_category = UCD_CATEGORY(c);
3838            if (prop_category == ucp_M) break;            if (prop_category == ucp_M) break;
3839            while (eptr < md->end_subject)            while (eptr < md->end_subject)
3840              {              {
# Line 3797  for (;;) Line 3843  for (;;)
3843                {                {
3844                GETCHARLEN(c, eptr, len);                GETCHARLEN(c, eptr, len);
3845                }                }
3846              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
3847              if (prop_category != ucp_M) break;              if (prop_category != ucp_M) break;
3848              eptr += len;              eptr += len;
3849              }              }
# Line 3819  for (;;) Line 3865  for (;;)
3865                BACKCHAR(eptr);                BACKCHAR(eptr);
3866                GETCHARLEN(c, eptr, len);                GETCHARLEN(c, eptr, len);
3867                }                }
3868              prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);              prop_category = UCD_CATEGORY(c);
3869              if (prop_category != ucp_M) break;              if (prop_category != ucp_M) break;
3870              eptr--;              eptr--;
3871              }              }
# Line 3839  for (;;) Line 3885  for (;;)
3885            case OP_ANY:            case OP_ANY:
3886            if (max < INT_MAX)            if (max < INT_MAX)
3887              {              {
3888              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  
3889                {                {
3890                for (i = min; i < max; i++)                if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break;
3891                  {                eptr++;
3892                  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++;  
                 }  
3893                }                }
3894              }              }
3895    
# Line 3863  for (;;) Line 3897  for (;;)
3897    
3898            else            else
3899              {              {
3900              if ((ims & PCRE_DOTALL) == 0)              for (i = min; i < max; i++)
3901                {                {
3902                for (i = min; i < max; i++)                if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break;
3903                  {                eptr++;
3904                  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++;  
                 }  
3905                }                }
3906              else              }
3907              break;
3908    
3909              case OP_ALLANY:
3910              if (max < INT_MAX)
3911                {
3912                for (i = min; i < max; i++)
3913                {                {
3914                eptr = md->end_subject;                if (eptr >= md->end_subject) break;
3915                  eptr++;
3916                  while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++;
3917                }                }
3918              }              }
3919              else eptr = md->end_subject;   /* Unlimited UTF-8 repeat */
3920            break;            break;
3921    
3922            /* The byte case is the same as non-UTF8 */            /* The byte case is the same as non-UTF8 */
# Line 4064  for (;;) Line 4104  for (;;)
4104          switch(ctype)          switch(ctype)
4105            {            {
4106            case OP_ANY:            case OP_ANY:
4107            if ((ims & PCRE_DOTALL) == 0)            for (i = min; i < max; i++)
4108              {              {
4109              for (i = min; i < max; i++)              if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break;
4110                {              eptr++;
               if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break;  
               eptr++;  
               }  
             break;  
4111              }              }
4112            /* For DOTALL case, fall through and treat as \C */            break;
4113    
4114              case OP_ALLANY:
4115            case OP_ANYBYTE:            case OP_ANYBYTE:
4116            c = max - min;            c = max - min;
4117            if (c > (unsigned int)(md->end_subject - eptr))            if (c > (unsigned int)(md->end_subject - eptr))
# Line 4348  Returns:          > 0 => success; value Line 4385  Returns:          > 0 => success; value
4385                   < -1 => some kind of unexpected problem                   < -1 => some kind of unexpected problem
4386  */  */
4387    
4388  PCRE_EXP_DEFN int  PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
4389  pcre_exec(const pcre *argument_re, const pcre_extra *extra_data,  pcre_exec(const pcre *argument_re, const pcre_extra *extra_data,
4390    PCRE_SPTR subject, int length, int start_offset, int options, int *offsets,    PCRE_SPTR subject, int length, int start_offset, int options, int *offsets,
4391    int offsetcount)    int offsetcount)
# Line 4450  end_subject = md->end_subject; Line 4487  end_subject = md->end_subject;
4487    
4488  md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0;  md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0;
4489  utf8 = md->utf8 = (re->options & PCRE_UTF8) != 0;  utf8 = md->utf8 = (re->options & PCRE_UTF8) != 0;
4490    md->jscript_compat = (re->options & PCRE_JAVASCRIPT_COMPAT) != 0;
4491    
4492  md->notbol = (options & PCRE_NOTBOL) != 0;  md->notbol = (options & PCRE_NOTBOL) != 0;
4493  md->noteol = (options & PCRE_NOTEOL) != 0;  md->noteol = (options & PCRE_NOTEOL) != 0;
# Line 4659  for(;;) Line 4697  for(;;)
4697    if (firstline)    if (firstline)
4698      {      {
4699      USPTR t = start_match;      USPTR t = start_match;
4700    #ifdef SUPPORT_UTF8
4701        if (utf8)
4702          {
4703          while (t < md->end_subject && !IS_NEWLINE(t))
4704            {
4705            t++;
4706            while (t < end_subject && (*t & 0xc0) == 0x80) t++;
4707            }
4708          }
4709        else
4710    #endif
4711      while (t < md->end_subject && !IS_NEWLINE(t)) t++;      while (t < md->end_subject && !IS_NEWLINE(t)) t++;
4712      end_subject = t;      end_subject = t;
4713      }      }
4714    
4715    /* Now test for a unique first byte */    /* Now advance to a unique first byte if there is one. */
4716    
4717    if (first_byte >= 0)    if (first_byte >= 0)
4718      {      {
4719      if (first_byte_caseless)      if (first_byte_caseless)
4720        while (start_match < end_subject &&        while (start_match < end_subject && md->lcc[*start_match] != first_byte)
4721               md->lcc[*start_match] != first_byte)          start_match++;
         { NEXTCHAR(start_match); }  
4722      else      else
4723        while (start_match < end_subject && *start_match != first_byte)        while (start_match < end_subject && *start_match != first_byte)
4724          { NEXTCHAR(start_match); }          start_match++;
4725      }      }
4726    
4727    /* Or to just after a linebreak for a multiline match if possible */    /* Or to just after a linebreak for a multiline match */
4728    
4729    else if (startline)    else if (startline)
4730      {      {
4731      if (start_match > md->start_subject + start_offset)      if (start_match > md->start_subject + start_offset)
4732        {        {
4733        while (start_match <= end_subject && !WAS_NEWLINE(start_match))  #ifdef SUPPORT_UTF8
4734          { NEXTCHAR(start_match); }        if (utf8)
4735            {
4736            while (start_match < end_subject && !WAS_NEWLINE(start_match))
4737              {
4738              start_match++;
4739              while(start_match < end_subject && (*start_match & 0xc0) == 0x80)
4740                start_match++;
4741              }
4742            }
4743          else
4744    #endif
4745          while (start_match < end_subject && !WAS_NEWLINE(start_match))
4746            start_match++;
4747    
4748        /* 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,
4749        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.
# Line 4697  for(;;) Line 4757  for(;;)
4757        }        }
4758      }      }
4759    
4760    /* Or to a non-unique first char after study */    /* Or to a non-unique first byte after study */
4761    
4762    else if (start_bits != NULL)    else if (start_bits != NULL)
4763      {      {
4764      while (start_match < end_subject)      while (start_match < end_subject)
4765        {        {
4766        register unsigned int c = *start_match;        register unsigned int c = *start_match;
4767        if ((start_bits[c/8] & (1 << (c&7))) == 0)        if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++;
4768          { NEXTCHAR(start_match); }          else break;
       else break;  
4769        }        }
4770      }      }
4771    

Legend:
Removed from v.298  
changed lines
  Added in v.371

  ViewVC Help
Powered by ViewVC 1.1.5