Function two_way_long_needle

numexpr3/string_functions.hpp:319–437

Return the first location of non-empty NEEDLE within HAYSTACK, or NULL. HAYSTACK_LEN is the minimum known length of HAYSTACK. This method is optimized for LONG_NEEDLE_THRESHOLD <= NEEDLE_LEN. Performance is guaranteed to be linear, with an initialization cost of 3 * NEEDLE_LEN + (1 << CHAR_BIT) operations. If AVAILABLE does not modify HAYSTACK_LEN (as in memmem), then at most

   HAYSTACK_LEN - NEEDLE_LEN comparisons occur in searching, and
   sublinear performance is not possible.  */
static RETURN_TYPE
two_way_long_needle (const unsigned char *haystack, size_t haystack_len,
		     const unsigned char *needle, size_t needle_len)
{
  size_t i; /* Index into current byte of NEEDLE.  */
  size_t j; /* Index into current window of HAYSTACK.  */
  size_t period; /* The period of the right half of needle.  */
  size_t suffix; /* The index of the right half of needle.  */
  size_t shift_table[1U << CHAR_BIT]; /* See below.  */

  /* Factor the needle into two halves, such that the left half is
     smaller than the global period, and the right half is
     periodic (with a period as large as NEEDLE_LEN - suffix).  */
  suffix = critical_factorization (needle, needle_len, &period);

  /* Populate shift_table.  For each possible byte value c,
     shift_table[c] is the distance from the last occurrence of c to
     the end of NEEDLE, or NEEDLE_LEN if c is absent from the NEEDLE.
     shift_table[NEEDLE[NEEDLE_LEN - 1]] contains the only 0.  */
  for (i = 0; i < 1U << CHAR_BIT; i++)
    shift_table[i] = needle_len;
  for (i = 0; i < needle_len; i++)
    shift_table[CANON_ELEMENT (needle[i])] = needle_len - i - 1;

  /* Perform the search.  Each iteration compares the right half
     first.  */
  if (CMP_FUNC (needle, needle + period, suffix) == 0)
    {
      /* Entire needle is periodic; a mismatch can only advance by the
	 period, so use memory to avoid rescanning known occurrences
	 of the period.  */
      size_t memory = 0;
      size_t shift;
      j = 0;
      while (AVAILABLE (haystack, haystack_len, j, needle_len))
	{
	  /* Check the last byte first; if it does not match, then
	     shift to the next possible match location.  */
	  shift = shift_table[CANON_ELEMENT (haystack[j + needle_len - 1])];
	  if (0 < shift)
	    {
	      if (memory && shift < period)
		{
		  /* Since needle is periodic, but the last period has
		     a byte out of place, there can be no match until
		     after the mismatch.  */
		  shift = needle_len - period;
		}
	      memory = 0;
	      j += shift;
	      continue;
	    }
	  /* Scan for matches in right half.  The last byte has
	     already been matched, by virtue of the shift table.  */
	  i = MAX (suffix, memory);
	  while (i < needle_len - 1 && (CANON_ELEMENT (needle[i])
					== CANON_ELEMENT (haystack[i + j])))
	    ++i;