Function two_way_short_needle

numexpr3/string_functions.hpp:225–305

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 NEEDLE_LEN < LONG_NEEDLE_THRESHOLD. Performance is guaranteed to be linear, with an initialization cost of 2 * NEEDLE_LEN comparisons. If AVAILABLE does not modify HAYSTACK_LEN (as in memmem), then at most 2 * HAYSTACK_LEN -

   If AVAILABLE modifies HAYSTACK_LEN (as in strstr), then at most 3 *
   HAYSTACK_LEN - NEEDLE_LEN comparisons occur in searching.  */
static RETURN_TYPE
two_way_short_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.  */

  /* 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);

  /* 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;
      j = 0;
      while (AVAILABLE (haystack, haystack_len, j, needle_len))
	{
	  /* Scan for matches in right half.  */
	  i = MAX (suffix, memory);
	  while (i < needle_len && (CANON_ELEMENT (needle[i])
				    == CANON_ELEMENT (haystack[i + j])))
	    ++i;
	  if (needle_len <= i)
	    {
	      /* Scan for matches in left half.  */
	      i = suffix - 1;
	      while (memory < i + 1 && (CANON_ELEMENT (needle[i])
					== CANON_ELEMENT (haystack[i + j])))
		--i;
	      if (i + 1 < memory + 1)
		return (RETURN_TYPE) (haystack + j);
	      /* No match, so remember how many repetitions of period
		 on the right half were scanned.  */
	      j += period;
	      memory = needle_len - period;
	    }
	  else
	    {
	      j += i - suffix + 1;
	      memory = 0;
	    }
	}
    }
  else
    {
      /* The two halves of needle are distinct; no extra memory is
	 required, and any mismatch results in a maximal shift.  */
      period = MAX (suffix, needle_len - suffix) + 1;
      j = 0;
      while (AVAILABLE (haystack, haystack_len, j, needle_len))