/*!
* ptaRemoveDupsByHash()
*
* Input: ptas (assumed to be integer values)
* &ptad (<return> unique set of pts; duplicates removed)
* &dahash (<optional return> dnahash used for lookup)
* Return: 0 if OK, 1 on error
*
* Notes:
* (1) Generates a pta with unique values.
* (2) The dnahash is built up with ptad to assure uniqueness.
* It can be used to find if a point is in the set:
* ptaFindPtByHash(ptad, dahash, x, y, &index)
* (3) The hash of the (x,y) location is simple and fast. It scales
* up with the number of buckets to insure a fairly random
* bucket selection for adjacent points.
* (4) A Dna is used rather than a Numa because we need accurate
* representation of 32-bit integers that are indices into ptas.
* Integer --> float --> integer conversion makes errors for
* integers larger than 10M.
* (5) This is faster than ptaRemoveDupsByAset(), because the
* bucket lookup is O(n), although there is a double-loop
* lookup within the dna in each bucket.
*/
l_int32
ptaRemoveDupsByHash(PTA *ptas,
PTA **pptad,
L_DNAHASH **pdahash)
{
l_int32 i, n, index, items, x, y;
l_uint32 nsize;
l_uint64 key;
l_float64 val;
PTA *ptad;
L_DNAHASH *dahash;
PROCNAME("ptaRemoveDupsByHash");
if (pdahash) *pdahash = NULL;
if (!pptad)
return ERROR_INT("&ptad not defined", procName, 1);
*pptad = NULL;
if (!ptas)
return ERROR_INT("ptas not defined", procName, 1);
n = ptaGetCount(ptas);
findNextLargerPrime(n / 20, &nsize); /* buckets in hash table */
dahash = l_dnaHashCreate(nsize, 8);
ptad = ptaCreate(n);
*pptad = ptad;
for (i = 0, items = 0; i < n; i++) {
ptaGetIPt(ptas, i, &x, &y);
ptaFindPtByHash(ptad, dahash, x, y, &index);
if (index < 0) { /* not found */
l_hashPtToUint64Fast(nsize, x, y, &key);
l_dnaHashAdd(dahash, key, (l_float64)items);
ptaAddPt(ptad, x, y);
items++;
}
}
if (pdahash)
*pdahash = dahash;
else
l_dnaHashDestroy(&dahash);
return 0;
}
/*!
* \brief sarrayRemoveDupsByHash()
*
* \param[in] sas
* \param[out] psad unique set of strings; duplicates removed
* \param[out] pdahash [optional] dnahash used for lookup
* \return 0 if OK, 1 on error
*
* <pre>
* Notes:
* (1) Generates a sarray with unique values.
* (2) The dnahash is built up with sad to assure uniqueness.
* It can be used to find if a string is in the set:
* sarrayFindValByHash(sad, dahash, str, \&index)
* (3) The hash of the string location is simple and fast. It scales
* up with the number of buckets to insure a fairly random
* bucket selection input strings.
* (4) This is faster than sarrayRemoveDupsByAset(), because the
* bucket lookup is O(n), although there is a double-loop
* lookup within the dna in each bucket.
* </pre>
*/
l_int32
sarrayRemoveDupsByHash(SARRAY *sas,
SARRAY **psad,
L_DNAHASH **pdahash)
{
char *str;
l_int32 i, n, index, items;
l_uint32 nsize;
l_uint64 key;
SARRAY *sad;
L_DNAHASH *dahash;
PROCNAME("sarrayRemoveDupsByHash");
if (pdahash) *pdahash = NULL;
if (!psad)
return ERROR_INT("&sad not defined", procName, 1);
*psad = NULL;
if (!sas)
return ERROR_INT("sas not defined", procName, 1);
n = sarrayGetCount(sas);
findNextLargerPrime(n / 20, &nsize); /* buckets in hash table */
dahash = l_dnaHashCreate(nsize, 8);
sad = sarrayCreate(n);
*psad = sad;
for (i = 0, items = 0; i < n; i++) {
str = sarrayGetString(sas, i, L_NOCOPY);
sarrayFindStringByHash(sad, dahash, str, &index);
if (index < 0) { /* not found */
l_hashStringToUint64(str, &key);
l_dnaHashAdd(dahash, key, (l_float64)items);
sarrayAddString(sad, str, L_COPY);
items++;
}
}
if (pdahash)
*pdahash = dahash;
else
l_dnaHashDestroy(&dahash);
return 0;
}
