polynomial. In Tim's experiments the current scheme ran faster, produced
equally good collision statistics, needed less code & used less memory.
-Theoretical Python 2.5 headache: hash codes are only C "long", but
-sizeof(Py_ssize_t) > sizeof(long) may be possible. In that case, and if a
-dict is genuinely huge, then only the slots directly reachable via indexing
-by a C long can be the first slot in a probe sequence. The probe sequence
-will still eventually reach every slot in the table, but the collision rate
-on initial probes may be much higher than this scheme was designed for.
-Getting a hash code as fat as Py_ssize_t is the only real cure. But in
-practice, this probably won't make a lick of difference for many years (at
-which point everyone will have terabytes of RAM on 64-bit boxes).
*/
/* Object used as dummy key to fill deleted entries */
{
PyObject *old_value;
register PyDictEntry *ep;
- typedef PyDictEntry *(*lookupfunc)(PyDictObject *, PyObject *, long);
+ typedef PyDictEntry *(*lookupfunc)(PyDictObject *, PyObject *, Py_hash_t);
assert(mp->ma_lookup != NULL);
ep = mp->ma_lookup(mp, key, hash);
set_insert_key(register PySetObject *so, PyObject *key, Py_hash_t hash)
{
register setentry *entry;
- typedef setentry *(*lookupfunc)(PySetObject *, PyObject *, long);
+ typedef setentry *(*lookupfunc)(PySetObject *, PyObject *, Py_hash_t);
assert(so->lookup != NULL);
entry = so->lookup(so, key, hash);
if (key != NULL &&
key != dummy) {
Py_INCREF(key);
- if (set_insert_key(so, key, (long) entry->hash) == -1) {
+ if (set_insert_key(so, key, entry->hash) == -1) {
Py_DECREF(key);
return -1;
}
if (so->hash != -1)
return so->hash;
- hash *= (long) PySet_GET_SIZE(self) + 1;
+ hash *= PySet_GET_SIZE(self) + 1;
while (set_next(so, &pos, &entry)) {
/* Work to increase the bit dispersion for closely spaced hash
values. The is important because some use cases have many
combinations of a small number of elements with nearby
hashes so that many distinct combinations collapse to only
a handful of distinct hash values. */
- h = (long) entry->hash;
+ h = entry->hash;
hash ^= (h ^ (h << 16) ^ 89869747L) * 3644798167u;
}
hash = hash * 69069L + 907133923L;
setentry *u;
setentry *(*f)(PySetObject *so, PyObject *key, Py_ssize_t hash);
setentry tab[PySet_MINSIZE];
- long h;
+ Py_hash_t h;
t = a->fill; a->fill = b->fill; b->fill = t;
t = a->used; a->used = b->used; b->used = t;
setentry entrycopy;
entrycopy.hash = entry->hash;
entrycopy.key = entry->key;
- if (!_PyDict_Contains(other, entry->key, (long) entry->hash)) {
+ if (!_PyDict_Contains(other, entry->key, entry->hash)) {
if (set_add_entry((PySetObject *)result, &entrycopy) == -1) {
Py_DECREF(result);
return NULL;