Function sarrayRemoveDupsByAset

deps/leptonica/src/sarray2.c:276–306

! * \brief sarrayRemoveDupsByAset() * * \param[in] sas * \return sad with duplicates removed, or NULL on error * * * Notes: * (1) This is O(nlogn), considerably slower than * sarrayRemoveDupsByHash() for large string arrays. * (2) The key for each string is a 64-bit hash. * (3) Build a set, using hashed strings as keys. As the set is * buil

 * </pre>
 */
SARRAY *
sarrayRemoveDupsByAset(SARRAY  *sas)
{
char     *str;
l_int32   i, n;
l_uint64  hash;
L_ASET   *set;
RB_TYPE   key;
SARRAY   *sad;

    PROCNAME("sarrayRemoveDupsByAset");

    if (!sas)
        return (SARRAY *)ERROR_PTR("sas not defined", procName, NULL);

    set = l_asetCreate(L_UINT_TYPE);
    sad = sarrayCreate(0);
    n = sarrayGetCount(sas);
    for (i = 0; i < n; i++) {
        str = sarrayGetString(sas, i, L_NOCOPY);
        l_hashStringToUint64(str, &hash);
        key.utype = hash;
        if (!l_asetFind(set, key)) {
            sarrayAddString(sad, str, L_COPY);
            l_asetInsert(set, key);
        }
    }

    l_asetDestroy(&set);
    return sad;
}


/*!