pcre_compile.c

很好用的网络封装库,不熟悉网络编程的人也可以使用。使用风格良好的标准c++编写。

a table. A non-zero result is something that can be returned immediately.
Otherwise further processing may be required. */

#ifndef EBCDIC  /* ASCII coding */
else if (c < '0' || c > 'z') {}                           /* Not alphameric */
else if ((i = escapes[c - '0']) != 0) c = i;

#else           /* EBCDIC coding */
else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {}   /* Not alphameric */
else if ((i = escapes[c - 0x48]) != 0)  c = i;
#endif

/* Escapes that need further processing, or are illegal. */

else
  {
  const uschar *oldptr;
  BOOL braced, negated;

  switch (c)
    {
    /* A number of Perl escapes are not handled by PCRE. We give an explicit
    error. */

    case 'l':
    case 'L':
    case 'N':
    case 'u':
    case 'U':
    *errorcodeptr = ERR37;
    break;

    /* \g must be followed by a number, either plain or braced. If positive, it
    is an absolute backreference. If negative, it is a relative backreference.
    This is a Perl 5.10 feature. */

    case 'g':
    if (ptr[1] == '{')
      {
      braced = TRUE;
      ptr++;
      }
    else braced = FALSE;

    if (ptr[1] == '-')
      {
      negated = TRUE;
      ptr++;
      }
    else negated = FALSE;

    c = 0;
    while ((digitab[ptr[1]] & ctype_digit) != 0)
      c = c * 10 + *(++ptr) - '0';

    if (c == 0 || (braced && *(++ptr) != '}'))
      {
      *errorcodeptr = ERR57;
      return 0;
      }

    if (negated)
      {
      if (c > bracount)
        {
        *errorcodeptr = ERR15;
        return 0;
        }
      c = bracount - (c - 1);
      }

    c = -(ESC_REF + c);
    break;

    /* The handling of escape sequences consisting of a string of digits
    starting with one that is not zero is not straightforward. By experiment,
    the way Perl works seems to be as follows:

    Outside a character class, the digits are read as a decimal number. If the
    number is less than 10, or if there are that many previous extracting
    left brackets, then it is a back reference. Otherwise, up to three octal
    digits are read to form an escaped byte. Thus \123 is likely to be octal
    123 (cf \0123, which is octal 012 followed by the literal 3). If the octal
    value is greater than 377, the least significant 8 bits are taken. Inside a
    character class, \ followed by a digit is always an octal number. */

    case '1': case '2': case '3': case '4': case '5':
    case '6': case '7': case '8': case '9':

    if (!isclass)
      {
      oldptr = ptr;
      c -= '0';
      while ((digitab[ptr[1]] & ctype_digit) != 0)
        c = c * 10 + *(++ptr) - '0';
      if (c < 10 || c <= bracount)
        {
        c = -(ESC_REF + c);
        break;
        }
      ptr = oldptr;      /* Put the pointer back and fall through */
      }

    /* Handle an octal number following \. If the first digit is 8 or 9, Perl
    generates a binary zero byte and treats the digit as a following literal.
    Thus we have to pull back the pointer by one. */

    if ((c = *ptr) >= '8')
      {
      ptr--;
      c = 0;
      break;
      }

    /* \0 always starts an octal number, but we may drop through to here with a
    larger first octal digit. The original code used just to take the least
    significant 8 bits of octal numbers (I think this is what early Perls used
    to do). Nowadays we allow for larger numbers in UTF-8 mode, but no more
    than 3 octal digits. */

    case '0':
    c -= '0';
    while(i++ < 2 && ptr[1] >= '0' && ptr[1] <= '7')
        c = c * 8 + *(++ptr) - '0';
    if (!utf8 && c > 255) *errorcodeptr = ERR51;
    break;

    /* \x is complicated. \x{ddd} is a character number which can be greater
    than 0xff in utf8 mode, but only if the ddd are hex digits. If not, { is
    treated as a data character. */

    case 'x':
    if (ptr[1] == '{')
      {
      const uschar *pt = ptr + 2;
      int count = 0;

      c = 0;
      while ((digitab[*pt] & ctype_xdigit) != 0)
        {
        register int cc = *pt++;
        if (c == 0 && cc == '0') continue;     /* Leading zeroes */
        count++;

#ifndef EBCDIC  /* ASCII coding */
        if (cc >= 'a') cc -= 32;               /* Convert to upper case */
        c = (c << 4) + cc - ((cc < 'A')? '0' : ('A' - 10));
#else           /* EBCDIC coding */
        if (cc >= 'a' && cc <= 'z') cc += 64;  /* Convert to upper case */
        c = (c << 4) + cc - ((cc >= '0')? '0' : ('A' - 10));
#endif
        }

      if (*pt == '}')
        {
        if (c < 0 || count > (utf8? 8 : 2)) *errorcodeptr = ERR34;
        ptr = pt;
        break;
        }

      /* If the sequence of hex digits does not end with '}', then we don't
      recognize this construct; fall through to the normal \x handling. */
      }

    /* Read just a single-byte hex-defined char */

    c = 0;
    while (i++ < 2 && (digitab[ptr[1]] & ctype_xdigit) != 0)
      {
      int cc;                               /* Some compilers don't like ++ */
      cc = *(++ptr);                        /* in initializers */
#ifndef EBCDIC  /* ASCII coding */
      if (cc >= 'a') cc -= 32;              /* Convert to upper case */
      c = c * 16 + cc - ((cc < 'A')? '0' : ('A' - 10));
#else           /* EBCDIC coding */
      if (cc <= 'z') cc += 64;              /* Convert to upper case */
      c = c * 16 + cc - ((cc >= '0')? '0' : ('A' - 10));
#endif
      }
    break;

    /* For \c, a following letter is upper-cased; then the 0x40 bit is flipped.
    This coding is ASCII-specific, but then the whole concept of \cx is
    ASCII-specific. (However, an EBCDIC equivalent has now been added.) */

    case 'c':
    c = *(++ptr);
    if (c == 0)
      {
      *errorcodeptr = ERR2;
      return 0;
      }

#ifndef EBCDIC  /* ASCII coding */
    if (c >= 'a' && c <= 'z') c -= 32;
    c ^= 0x40;
#else           /* EBCDIC coding */
    if (c >= 'a' && c <= 'z') c += 64;
    c ^= 0xC0;
#endif
    break;

    /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any
    other alphameric following \ is an error if PCRE_EXTRA was set; otherwise,
    for Perl compatibility, it is a literal. This code looks a bit odd, but
    there used to be some cases other than the default, and there may be again
    in future, so I haven't "optimized" it. */

    default:
    if ((options & PCRE_EXTRA) != 0) switch(c)
      {
      default:
      *errorcodeptr = ERR3;
      break;
      }
    break;
    }
  }

*ptrptr = ptr;
return c;
}



#ifdef SUPPORT_UCP
/*************************************************
*               Handle \P and \p                 *
*************************************************/

/* This function is called after \P or \p has been encountered, provided that
PCRE is compiled with support for Unicode properties. On entry, ptrptr is
pointing at the P or p. On exit, it is pointing at the final character of the
escape sequence.

Argument:
  ptrptr         points to the pattern position pointer
  negptr         points to a boolean that is set TRUE for negation else FALSE
  dptr           points to an int that is set to the detailed property value
  errorcodeptr   points to the error code variable

Returns:         type value from ucp_type_table, or -1 for an invalid type
*/

static int
get_ucp(const uschar **ptrptr, BOOL *negptr, int *dptr, int *errorcodeptr)
{
int c, i, bot, top;
const uschar *ptr = *ptrptr;
char name[32];

c = *(++ptr);
if (c == 0) goto ERROR_RETURN;

*negptr = FALSE;

/* \P or \p can be followed by a name in {}, optionally preceded by ^ for
negation. */

if (c == '{')
  {
  if (ptr[1] == '^')
    {
    *negptr = TRUE;
    ptr++;
    }
  for (i = 0; i < sizeof(name) - 1; i++)
    {
    c = *(++ptr);
    if (c == 0) goto ERROR_RETURN;
    if (c == '}') break;
    name[i] = c;
    }
  if (c !='}') goto ERROR_RETURN;
  name[i] = 0;
  }

/* Otherwise there is just one following character */

else
  {
  name[0] = c;
  name[1] = 0;
  }

*ptrptr = ptr;

/* Search for a recognized property name using binary chop */

bot = 0;
top = _pcre_utt_size;

while (bot < top)
  {
  i = (bot + top) >> 1;
  c = strcmp(name, _pcre_utt[i].name);
  if (c == 0)
    {
    *dptr = _pcre_utt[i].value;
    return _pcre_utt[i].type;
    }
  if (c > 0) bot = i + 1; else top = i;
  }

*errorcodeptr = ERR47;
*ptrptr = ptr;
return -1;

ERROR_RETURN:
*errorcodeptr = ERR46;
*ptrptr = ptr;
return -1;
}
#endif




/*************************************************
*            Check for counted repeat            *
*************************************************/

/* This function is called when a '{' is encountered in a place where it might
start a quantifier. It looks ahead to see if it really is a quantifier or not.
It is only a quantifier if it is one of the forms {ddd} {ddd,} or {ddd,ddd}
where the ddds are digits.

Arguments:
  p         pointer to the first char after '{'

Returns:    TRUE or FALSE
*/

static BOOL
is_counted_repeat(const uschar *p)
{
if ((digitab[*p++] & ctype_digit) == 0) return FALSE;
while ((digitab[*p] & ctype_digit) != 0) p++;
if (*p == '}') return TRUE;

if (*p++ != ',') return FALSE;
if (*p == '}') return TRUE;

if ((digitab[*p++] & ctype_digit) == 0) return FALSE;
while ((digitab[*p] & ctype_digit) != 0) p++;

return (*p == '}');
}



/*************************************************
*         Read repeat counts                     *
*************************************************/

/* Read an item of the form {n,m} and return the values. This is called only
after is_counted_repeat() has confirmed that a repeat-count quantifier exists,
so the syntax is guaranteed to be correct, but we need to check the values.

Arguments:
  p              pointer to first char after '{'
  minp           pointer to int for min
  maxp           pointer to int for max
                 returned as -1 if no max
  errorcodeptr   points to error code variable

Returns:         pointer to '}' on success;
                 current ptr on error, with errorcodeptr set non-zero
*/

static const uschar *
read_repeat_counts(const uschar *p, int *minp, int *maxp, int *errorcodeptr)
{
int min = 0;
int max = -1;

/* Read the minimum value and do a paranoid check: a negative value indicates
an integer overflow. */

while ((digitab[*p] & ctype_digit) != 0) min = min * 10 + *p++ - '0';
if (min < 0 || min > 65535)
  {
  *errorcodeptr = ERR5;
  return p;
  }

/* Read the maximum value if there is one, and again do a paranoid on its size.
Also, max must not be less than min. */

if (*p == '}') max = min; else
  {
  if (*(++p) != '}')
    {
    max = 0;
    while((digitab[*p] & ctype_digit) != 0) max = max * 10 + *p++ - '0';
    if (max < 0 || max > 65535)
      {
      *errorcodeptr = ERR5;
      return p;
      }
    if (max < min)
      {
      *errorcodeptr = ERR4;
      return p;
      }
    }
  }

/* Fill in the required variables, and pass back the pointer to the terminating
'}'. */

*minp = min;
*maxp = max;
return p;
}



/*************************************************
*       Find forward referenced subpattern       *