Back to index

glibc  2.9
Defines | Functions
str-two-way.h File Reference
#include <limits.h>
#include <stdint.h>
This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Defines

#define LONG_NEEDLE_THRESHOLD   32U
#define MAX(a, b)   ((a < b) ? (b) : (a))
#define CANON_ELEMENT(c)   c
#define CMP_FUNC   memcmp

Functions

static size_t critical_factorization (const unsigned char *needle, size_t needle_len, size_t *period)
static RETURN_TYPE two_way_short_needle (const unsigned char *haystack, size_t haystack_len, const unsigned char *needle, size_t needle_len)
static RETURN_TYPE two_way_long_needle (const unsigned char *haystack, size_t haystack_len, const unsigned char *needle, size_t needle_len)

Define Documentation

#define CANON_ELEMENT (   c)    c

Definition at line 76 of file str-two-way.h.

#define CMP_FUNC   memcmp

Definition at line 79 of file str-two-way.h.

#define LONG_NEEDLE_THRESHOLD   32U

Definition at line 66 of file str-two-way.h.

#define MAX (   a,
  b 
)    ((a < b) ? (b) : (a))

Definition at line 72 of file str-two-way.h.


Function Documentation

static size_t critical_factorization ( const unsigned char *  needle,
size_t  needle_len,
size_t period 
) [static]

Definition at line 106 of file str-two-way.h.

{
  /* Index of last byte of left half, or SIZE_MAX.  */
  size_t max_suffix, max_suffix_rev;
  size_t j; /* Index into NEEDLE for current candidate suffix.  */
  size_t k; /* Offset into current period.  */
  size_t p; /* Intermediate period.  */
  unsigned char a, b; /* Current comparison bytes.  */

  /* Invariants:
     0 <= j < NEEDLE_LEN - 1
     -1 <= max_suffix{,_rev} < j (treating SIZE_MAX as if it were signed)
     min(max_suffix, max_suffix_rev) < global period of NEEDLE
     1 <= p <= global period of NEEDLE
     p == global period of the substring NEEDLE[max_suffix{,_rev}+1...j]
     1 <= k <= p
  */

  /* Perform lexicographic search.  */
  max_suffix = SIZE_MAX;
  j = 0;
  k = p = 1;
  while (j + k < needle_len)
    {
      a = CANON_ELEMENT (needle[j + k]);
      b = CANON_ELEMENT (needle[max_suffix + k]);
      if (a < b)
       {
         /* Suffix is smaller, period is entire prefix so far.  */
         j += k;
         k = 1;
         p = j - max_suffix;
       }
      else if (a == b)
       {
         /* Advance through repetition of the current period.  */
         if (k != p)
           ++k;
         else
           {
             j += p;
             k = 1;
           }
       }
      else /* b < a */
       {
         /* Suffix is larger, start over from current location.  */
         max_suffix = j++;
         k = p = 1;
       }
    }
  *period = p;

  /* Perform reverse lexicographic search.  */
  max_suffix_rev = SIZE_MAX;
  j = 0;
  k = p = 1;
  while (j + k < needle_len)
    {
      a = CANON_ELEMENT (needle[j + k]);
      b = CANON_ELEMENT (needle[max_suffix_rev + k]);
      if (b < a)
       {
         /* Suffix is smaller, period is entire prefix so far.  */
         j += k;
         k = 1;
         p = j - max_suffix_rev;
       }
      else if (a == b)
       {
         /* Advance through repetition of the current period.  */
         if (k != p)
           ++k;
         else
           {
             j += p;
             k = 1;
           }
       }
      else /* a < b */
       {
         /* Suffix is larger, start over from current location.  */
         max_suffix_rev = j++;
         k = p = 1;
       }
    }

  /* Choose the longer suffix.  Return the first byte of the right
     half, rather than the last byte of the left half.  */
  if (max_suffix_rev + 1 < max_suffix + 1)
    return max_suffix + 1;
  *period = p;
  return max_suffix_rev + 1;
}

Here is the caller graph for this function:

static RETURN_TYPE two_way_long_needle ( const unsigned char *  haystack,
size_t  haystack_len,
const unsigned char *  needle,
size_t  needle_len 
) [static]

Definition at line 307 of file str-two-way.h.

{
  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;
         if (needle_len - 1 <= 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.  */
      size_t shift;
      period = MAX (suffix, needle_len - suffix) + 1;
      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)
           {
             j += shift;
             continue;
           }
         /* Scan for matches in right half.  The last byte has
            already been matched, by virtue of the shift table.  */
         i = suffix;
         while (i < needle_len - 1 && (CANON_ELEMENT (needle[i])
                                   == CANON_ELEMENT (haystack[i + j])))
           ++i;
         if (needle_len - 1 <= i)
           {
             /* Scan for matches in left half.  */
             i = suffix - 1;
             while (i != SIZE_MAX && (CANON_ELEMENT (needle[i])
                                   == CANON_ELEMENT (haystack[i + j])))
              --i;
             if (i == SIZE_MAX)
              return (RETURN_TYPE) (haystack + j);
             j += period;
           }
         else
           j += i - suffix + 1;
       }
    }
  return NULL;
}

Here is the call graph for this function:

Here is the caller graph for this function:

static RETURN_TYPE two_way_short_needle ( const unsigned char *  haystack,
size_t  haystack_len,
const unsigned char *  needle,
size_t  needle_len 
) [static]

Definition at line 213 of file str-two-way.h.

{
  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))
       {
         /* Scan for matches in right half.  */
         i = suffix;
         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 (i != SIZE_MAX && (CANON_ELEMENT (needle[i])
                                   == CANON_ELEMENT (haystack[i + j])))
              --i;
             if (i == SIZE_MAX)
              return (RETURN_TYPE) (haystack + j);
             j += period;
           }
         else
           j += i - suffix + 1;
       }
    }
  return NULL;
}

Here is the call graph for this function:

Here is the caller graph for this function: