pcre_dfa_exec.c

SDL文件。SDL_ERROwenjian.....

          case 0x2002:    /* EN SPACE */
          case 0x2003:    /* EM SPACE */
          case 0x2004:    /* THREE-PER-EM SPACE */
          case 0x2005:    /* FOUR-PER-EM SPACE */
          case 0x2006:    /* SIX-PER-EM SPACE */
          case 0x2007:    /* FIGURE SPACE */
          case 0x2008:    /* PUNCTUATION SPACE */
          case 0x2009:    /* THIN SPACE */
          case 0x200A:    /* HAIR SPACE */
          case 0x202f:    /* NARROW NO-BREAK SPACE */
          case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
          case 0x3000:    /* IDEOGRAPHIC SPACE */
          OK = TRUE;
          break;

          default:
          OK = FALSE;
          break;
          }

        if (OK == (d == OP_HSPACE))
          {
          if (codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSUPTO)
            {
            active_count--;           /* Remove non-match possibility */
            next_active_state--;
            }
          if (++count >= GET2(code, 1))
            { ADD_NEW_DATA(-(state_offset + 4), 0, 0); }
          else
            { ADD_NEW_DATA(-state_offset, count, 0); }
          }
        }
      break;

/* ========================================================================== */
      /* These opcodes are followed by a character that is usually compared
      to the current subject character; it is loaded into d. We still get
      here even if there is no subject character, because in some cases zero
      repetitions are permitted. */

      /*-----------------------------------------------------------------*/
      case OP_CHAR:
      if (clen > 0 && c == d) { ADD_NEW(state_offset + dlen + 1, 0); }
      break;

      /*-----------------------------------------------------------------*/
      case OP_CHARNC:
      if (clen == 0) break;

#ifdef SUPPORT_UTF8
      if (utf8)
        {
        if (c == d) { ADD_NEW(state_offset + dlen + 1, 0); } else
          {
          unsigned int othercase;
          if (c < 128) othercase = fcc[c]; else

          /* If we have Unicode property support, we can use it to test the
          other case of the character. */

#ifdef SUPPORT_UCP
          othercase = _pcre_ucp_othercase(c);
#else
          othercase = NOTACHAR;
#endif

          if (d == othercase) { ADD_NEW(state_offset + dlen + 1, 0); }
          }
        }
      else
#endif  /* SUPPORT_UTF8 */

      /* Non-UTF-8 mode */
        {
        if (lcc[c] == lcc[d]) { ADD_NEW(state_offset + 2, 0); }
        }
      break;


#ifdef SUPPORT_UCP
      /*-----------------------------------------------------------------*/
      /* This is a tricky one because it can match more than one character.
      Find out how many characters to skip, and then set up a negative state
      to wait for them to pass before continuing. */

      case OP_EXTUNI:
      if (clen > 0 && _pcre_ucp_findprop(c, &chartype, &script) != ucp_M)
        {
        const uschar *nptr = ptr + clen;
        int ncount = 0;
        while (nptr < end_subject)
          {
          int nclen = 1;
          GETCHARLEN(c, nptr, nclen);
          if (_pcre_ucp_findprop(c, &chartype, &script) != ucp_M) break;
          ncount++;
          nptr += nclen;
          }
        ADD_NEW_DATA(-(state_offset + 1), 0, ncount);
        }
      break;
#endif

      /*-----------------------------------------------------------------*/
      /* This is a tricky like EXTUNI because it too can match more than one
      character (when CR is followed by LF). In this case, set up a negative
      state to wait for one character to pass before continuing. */

      case OP_ANYNL:
      if (clen > 0) switch(c)
        {
        case 0x000b:
        case 0x000c:
        case 0x0085:
        case 0x2028:
        case 0x2029:
        if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break;

        case 0x000a:
        ADD_NEW(state_offset + 1, 0);
        break;

        case 0x000d:
        if (ptr + 1 < end_subject && ptr[1] == 0x0a)
          {
          ADD_NEW_DATA(-(state_offset + 1), 0, 1);
          }
        else
          {
          ADD_NEW(state_offset + 1, 0);
          }
        break;
        }
      break;

      /*-----------------------------------------------------------------*/
      case OP_NOT_VSPACE:
      if (clen > 0) switch(c)
        {
        case 0x000a:
        case 0x000b:
        case 0x000c:
        case 0x000d:
        case 0x0085:
        case 0x2028:
        case 0x2029:
        break;

        default:
        ADD_NEW(state_offset + 1, 0);
        break;
        }
      break;

      /*-----------------------------------------------------------------*/
      case OP_VSPACE:
      if (clen > 0) switch(c)
        {
        case 0x000a:
        case 0x000b:
        case 0x000c:
        case 0x000d:
        case 0x0085:
        case 0x2028:
        case 0x2029:
        ADD_NEW(state_offset + 1, 0);
        break;

        default: break;
        }
      break;

      /*-----------------------------------------------------------------*/
      case OP_NOT_HSPACE:
      if (clen > 0) switch(c)
        {
        case 0x09:      /* HT */
        case 0x20:      /* SPACE */
        case 0xa0:      /* NBSP */
        case 0x1680:    /* OGHAM SPACE MARK */
        case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
        case 0x2000:    /* EN QUAD */
        case 0x2001:    /* EM QUAD */
        case 0x2002:    /* EN SPACE */
        case 0x2003:    /* EM SPACE */
        case 0x2004:    /* THREE-PER-EM SPACE */
        case 0x2005:    /* FOUR-PER-EM SPACE */
        case 0x2006:    /* SIX-PER-EM SPACE */
        case 0x2007:    /* FIGURE SPACE */
        case 0x2008:    /* PUNCTUATION SPACE */
        case 0x2009:    /* THIN SPACE */
        case 0x200A:    /* HAIR SPACE */
        case 0x202f:    /* NARROW NO-BREAK SPACE */
        case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
        case 0x3000:    /* IDEOGRAPHIC SPACE */
        break;

        default:
        ADD_NEW(state_offset + 1, 0);
        break;
        }
      break;

      /*-----------------------------------------------------------------*/
      case OP_HSPACE:
      if (clen > 0) switch(c)
        {
        case 0x09:      /* HT */
        case 0x20:      /* SPACE */
        case 0xa0:      /* NBSP */
        case 0x1680:    /* OGHAM SPACE MARK */
        case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
        case 0x2000:    /* EN QUAD */
        case 0x2001:    /* EM QUAD */
        case 0x2002:    /* EN SPACE */
        case 0x2003:    /* EM SPACE */
        case 0x2004:    /* THREE-PER-EM SPACE */
        case 0x2005:    /* FOUR-PER-EM SPACE */
        case 0x2006:    /* SIX-PER-EM SPACE */
        case 0x2007:    /* FIGURE SPACE */
        case 0x2008:    /* PUNCTUATION SPACE */
        case 0x2009:    /* THIN SPACE */
        case 0x200A:    /* HAIR SPACE */
        case 0x202f:    /* NARROW NO-BREAK SPACE */
        case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
        case 0x3000:    /* IDEOGRAPHIC SPACE */
        ADD_NEW(state_offset + 1, 0);
        break;
        }
      break;

      /*-----------------------------------------------------------------*/
      /* Match a negated single character. This is only used for one-byte
      characters, that is, we know that d < 256. The character we are
      checking (c) can be multibyte. */

      case OP_NOT:
      if (clen > 0)
        {
        unsigned int otherd = ((ims & PCRE_CASELESS) != 0)? fcc[d] : d;
        if (c != d && c != otherd) { ADD_NEW(state_offset + dlen + 1, 0); }
        }
      break;

      /*-----------------------------------------------------------------*/
      case OP_PLUS:
      case OP_MINPLUS:
      case OP_POSPLUS:
      case OP_NOTPLUS:
      case OP_NOTMINPLUS:
      case OP_NOTPOSPLUS:
      count = current_state->count;  /* Already matched */
      if (count > 0) { ADD_ACTIVE(state_offset + dlen + 1, 0); }
      if (clen > 0)
        {
        unsigned int otherd = NOTACHAR;
        if ((ims & PCRE_CASELESS) != 0)
          {
#ifdef SUPPORT_UTF8
          if (utf8 && d >= 128)
            {
#ifdef SUPPORT_UCP
            otherd = _pcre_ucp_othercase(d);
#endif  /* SUPPORT_UCP */
            }
          else
#endif  /* SUPPORT_UTF8 */
          otherd = fcc[d];
          }
        if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR))
          {
          if (count > 0 &&
              (codevalue == OP_POSPLUS || codevalue == OP_NOTPOSPLUS))
            {
            active_count--;             /* Remove non-match possibility */
            next_active_state--;
            }
          count++;
          ADD_NEW(state_offset, count);
          }
        }
      break;

      /*-----------------------------------------------------------------*/
      case OP_QUERY:
      case OP_MINQUERY:
      case OP_POSQUERY:
      case OP_NOTQUERY:
      case OP_NOTMINQUERY:
      case OP_NOTPOSQUERY:
      ADD_ACTIVE(state_offset + dlen + 1, 0);
      if (clen > 0)
        {
        unsigned int otherd = NOTACHAR;
        if ((ims & PCRE_CASELESS) != 0)
          {
#ifdef SUPPORT_UTF8
          if (utf8 && d >= 128)
            {
#ifdef SUPPORT_UCP
            otherd = _pcre_ucp_othercase(d);
#endif  /* SUPPORT_UCP */
            }
          else
#endif  /* SUPPORT_UTF8 */
          otherd = fcc[d];
          }
        if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR))
          {
          if (codevalue == OP_POSQUERY || codevalue == OP_NOTPOSQUERY)
            {
            active_count--;            /* Remove non-match possibility */
            next_active_state--;
            }
          ADD_NEW(state_offset + dlen + 1, 0);
          }
        }
      break;

      /*-----------------------------------------------------------------*/
      case OP_STAR:
      case OP_MINSTAR:
      case OP_POSSTAR:
      case OP_NOTSTAR:
      case OP_NOTMINSTAR:
      case OP_NOTPOSSTAR:
      ADD_ACTIVE(state_offset + dlen + 1, 0);
      if (clen > 0)
        {
        unsigned int otherd = NOTACHAR;
        if ((ims & PCRE_CASELESS) != 0)
          {
#ifdef SUPPORT_UTF8
          if (utf8 && d >= 128)
            {
#ifdef SUPPORT_UCP
            otherd = _pcre_ucp_othercase(d);
#endif  /* SUPPORT_UCP */
            }
          else
#endif  /* SUPPORT_UTF8 */
          otherd = fcc[d];
          }
        if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR))
          {
          if (codevalue == OP_POSSTAR || codevalue == OP_NOTPOSSTAR)
            {
            active_count--;            /* Remove non-match possibility */
            next_active_state--;
            }
          ADD_NEW(state_offset, 0);
          }
        }
      break;

      /*-----------------------------------------------------------------*/
      case OP_EXACT:
      case OP_NOTEXACT:
      count = current_state->count;  /* Number already matched */
      if (clen > 0)
        {
        unsigned int otherd = NOTACHAR;
        if ((ims & PCRE_CASELESS) != 0)
          {
#ifdef SUPPORT_UTF8
          if (utf8 && d >= 128)
            {
#ifdef SUPPORT_UCP
            otherd = _pcre_ucp_othercase(d);
#endif  /* SUPPORT_UCP */
            }
          else
#endif  /* SUPPORT_UTF8 */
          otherd = fcc[d];
          }
        if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR))
          {
          if (++count >= GET2(code, 1))
            { ADD_NEW(state_offset + dlen + 3, 0); }
          else
            { ADD_NEW(state_offset, count); }
          }
        }
      break;

      /*-----------------------------------------------------------------*/
      case OP_UPTO:
      case OP_MINUPTO:
      case OP_POSUPTO:
      case OP_NOTUPTO:
      case OP_NOTMINUPTO:
      case OP_NOTPOSUPTO:
      ADD_ACTIVE(state_offset + dlen + 3, 0);
      count = current_state->count;  /* Number already matched */
      if (clen > 0)
        {
        unsigned int otherd = NOTACHAR;
        if ((ims & PCRE_CASELESS) != 0)
          {
#ifdef SUPPORT_UTF8
          if (utf8 && d >= 128)
            {
#ifdef SUPPORT_UCP
            otherd = _pcre_ucp_othercase(d);
#endif  /* SUPPORT_UCP */
            }
          else
#endif  /* SUPPORT_UTF8 */
          otherd = fcc[d];