/*
* Routines to provide a memory-efficient hashtable.
*
- * Copyright (C) 2007-2015 Wayne Davison
+ * Copyright (C) 2007-2022 Wayne Davison
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
size *= 2;
}
- if (!(tbl = new(struct hashtable))
- || !(tbl->nodes = new_array0(char, size * node_size)))
- out_of_memory("hashtable_create");
+ tbl = new(struct hashtable);
+ tbl->nodes = new_array0(char, size * node_size);
tbl->size = size;
tbl->entries = 0;
tbl->node_size = node_size;
free(tbl);
}
-/* This returns the node for the indicated key, either newly created or
- * already existing. Returns NULL if not allocating and not found. */
-void *hashtable_find(struct hashtable *tbl, int64 key, int allocate_if_missing)
+/* Returns the node that holds the indicated key if it exists. When it does not
+ * exist, it returns either NULL (when data_when_new is NULL), or it returns a
+ * new node with its node->data set to the indicated value.
+ *
+ * If your code doesn't know the data value for a new node in advance (usually
+ * because it doesn't know if a node is new or not) you should pass in a unique
+ * (non-0) value that you can use to check if the returned node is new. You can
+ * then overwrite the data with any value you want (even 0) since it only needs
+ * to be different than whatever data_when_new value you use later on.
+ *
+ * This return is a void* just because it might be pointing at a ht_int32_node
+ * or a ht_int64_node, and that makes the caller's assignment a little easier. */
+void *hashtable_find(struct hashtable *tbl, int64 key, void *data_when_new)
{
int key64 = tbl->key64;
struct ht_int32_node *node;
exit_cleanup(RERR_MESSAGEIO);
}
- if (allocate_if_missing && tbl->entries > HASH_LOAD_LIMIT(tbl->size)) {
+ if (data_when_new && tbl->entries > HASH_LOAD_LIMIT(tbl->size)) {
void *old_nodes = tbl->nodes;
int size = tbl->size * 2;
int i;
- if (!(tbl->nodes = new_array0(char, size * tbl->node_size)))
- out_of_memory("hashtable_node");
+ tbl->nodes = new_array0(char, size * tbl->node_size);
tbl->size = size;
tbl->entries = 0;
int64 move_key = HT_KEY(move_node, key64);
if (move_key == 0)
continue;
- node = hashtable_find(tbl, move_key, 1);
- node->data = move_node->data;
+ if (move_node->data)
+ hashtable_find(tbl, move_key, move_node->data);
+ else {
+ node = hashtable_find(tbl, move_key, "");
+ node->data = 0;
+ }
}
free(old_nodes);
if (nkey == key)
return node;
if (nkey == 0) {
- if (!allocate_if_missing)
+ if (!data_when_new)
return NULL;
break;
}
((struct ht_int64_node*)node)->key = key;
else
node->key = (int32)key;
+ node->data = data_when_new;
tbl->entries++;
return node;
}
-------------------------------------------------------------------------------
*/
+#define NON_ZERO_32(x) ((x) ? (x) : (uint32_t)1)
+#define NON_ZERO_64(x, y) ((x) || (y) ? (y) | (int64)(x) << 32 | (y) : (int64)1)
+
uint32_t hashlittle(const void *key, size_t length)
{
uint32_t a,b,c; /* internal state */
case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */
case 2 : a+=((uint32_t)k8[1])<<8; /* fall through */
case 1 : a+=k8[0]; break;
- case 0 : return c;
+ case 0 : return NON_ZERO_32(c);
+ }
+ } else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0)) {
+ const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */
+ const uint8_t *k8;
+
+ /*--------------- all but last block: aligned reads and different mixing */
+ while (length > 12)
+ {
+ a += k[0] + (((uint32_t)k[1])<<16);
+ b += k[2] + (((uint32_t)k[3])<<16);
+ c += k[4] + (((uint32_t)k[5])<<16);
+ mix(a,b,c);
+ length -= 12;
+ k += 6;
+ }
+
+ /*----------------------------- handle the last (probably partial) block */
+ k8 = (const uint8_t *)k;
+ switch(length)
+ {
+ case 12: c+=k[4]+(((uint32_t)k[5])<<16);
+ b+=k[2]+(((uint32_t)k[3])<<16);
+ a+=k[0]+(((uint32_t)k[1])<<16);
+ break;
+ case 11: c+=((uint32_t)k8[10])<<16; /* fall through */
+ case 10: c+=k[4];
+ b+=k[2]+(((uint32_t)k[3])<<16);
+ a+=k[0]+(((uint32_t)k[1])<<16);
+ break;
+ case 9 : c+=k8[8]; /* fall through */
+ case 8 : b+=k[2]+(((uint32_t)k[3])<<16);
+ a+=k[0]+(((uint32_t)k[1])<<16);
+ break;
+ case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */
+ case 6 : b+=k[2];
+ a+=k[0]+(((uint32_t)k[1])<<16);
+ break;
+ case 5 : b+=k8[4]; /* fall through */
+ case 4 : a+=k[0]+(((uint32_t)k[1])<<16);
+ break;
+ case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */
+ case 2 : a+=k[0];
+ break;
+ case 1 : a+=k8[0];
+ break;
+ case 0 : return NON_ZERO_32(c); /* zero length requires no mixing */
+ }
+
+ } else { /* need to read the key one byte at a time */
+ const uint8_t *k = (const uint8_t *)key;
+
+ /*--------------- all but the last block: affect some 32 bits of (a,b,c) */
+ while (length > 12)
+ {
+ a += k[0];
+ a += ((uint32_t)k[1])<<8;
+ a += ((uint32_t)k[2])<<16;
+ a += ((uint32_t)k[3])<<24;
+ b += k[4];
+ b += ((uint32_t)k[5])<<8;
+ b += ((uint32_t)k[6])<<16;
+ b += ((uint32_t)k[7])<<24;
+ c += k[8];
+ c += ((uint32_t)k[9])<<8;
+ c += ((uint32_t)k[10])<<16;
+ c += ((uint32_t)k[11])<<24;
+ mix(a,b,c);
+ length -= 12;
+ k += 12;
+ }
+
+ /*-------------------------------- last block: affect all 32 bits of (c) */
+ switch(length) /* all the case statements fall through */
+ {
+ case 12: c+=((uint32_t)k[11])<<24;
+ /* FALLTHROUGH */
+ case 11: c+=((uint32_t)k[10])<<16;
+ /* FALLTHROUGH */
+ case 10: c+=((uint32_t)k[9])<<8;
+ /* FALLTHROUGH */
+ case 9 : c+=k[8];
+ /* FALLTHROUGH */
+ case 8 : b+=((uint32_t)k[7])<<24;
+ /* FALLTHROUGH */
+ case 7 : b+=((uint32_t)k[6])<<16;
+ /* FALLTHROUGH */
+ case 6 : b+=((uint32_t)k[5])<<8;
+ /* FALLTHROUGH */
+ case 5 : b+=k[4];
+ /* FALLTHROUGH */
+ case 4 : a+=((uint32_t)k[3])<<24;
+ /* FALLTHROUGH */
+ case 3 : a+=((uint32_t)k[2])<<16;
+ /* FALLTHROUGH */
+ case 2 : a+=((uint32_t)k[1])<<8;
+ /* FALLTHROUGH */
+ case 1 : a+=k[0];
+ break;
+ case 0 : return NON_ZERO_32(c);
+ }
+ }
+
+ final(a,b,c);
+ return NON_ZERO_32(c);
+}
+
+#if SIZEOF_INT64 >= 8
+/*
+ * hashlittle2: return 2 32-bit hash values joined into an int64.
+ *
+ * This is identical to hashlittle(), except it returns two 32-bit hash
+ * values instead of just one. This is good enough for hash table
+ * lookup with 2^^64 buckets, or if you want a second hash if you're not
+ * happy with the first, or if you want a probably-unique 64-bit ID for
+ * the key. *pc is better mixed than *pb, so use *pc first. If you want
+ * a 64-bit value do something like "*pc + (((uint64_t)*pb)<<32)".
+ */
+int64 hashlittle2(const void *key, size_t length)
+{
+ uint32_t a,b,c; /* internal state */
+ union { const void *ptr; size_t i; } u; /* needed for Mac Powerbook G4 */
+
+ /* Set up the internal state */
+ a = b = c = 0xdeadbeef + ((uint32_t)length);
+
+ u.ptr = key;
+ if (HASH_LITTLE_ENDIAN && ((u.i & 0x3) == 0)) {
+ const uint32_t *k = (const uint32_t *)key; /* read 32-bit chunks */
+ const uint8_t *k8;
+
+ /*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */
+ while (length > 12)
+ {
+ a += k[0];
+ b += k[1];
+ c += k[2];
+ mix(a,b,c);
+ length -= 12;
+ k += 3;
+ }
+
+ /*----------------------------- handle the last (probably partial) block */
+ k8 = (const uint8_t *)k;
+ switch(length)
+ {
+ case 12: c+=k[2]; b+=k[1]; a+=k[0]; break;
+ case 11: c+=((uint32_t)k8[10])<<16; /* fall through */
+ case 10: c+=((uint32_t)k8[9])<<8; /* fall through */
+ case 9 : c+=k8[8]; /* fall through */
+ case 8 : b+=k[1]; a+=k[0]; break;
+ case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */
+ case 6 : b+=((uint32_t)k8[5])<<8; /* fall through */
+ case 5 : b+=k8[4]; /* fall through */
+ case 4 : a+=k[0]; break;
+ case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */
+ case 2 : a+=((uint32_t)k8[1])<<8; /* fall through */
+ case 1 : a+=k8[0]; break;
+ case 0 : return NON_ZERO_64(b, c);
}
} else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0)) {
const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */
break;
case 1 : a+=k8[0];
break;
- case 0 : return c; /* zero length requires no mixing */
+ case 0 : return NON_ZERO_64(b, c); /* zero length strings require no mixing */
}
} else { /* need to read the key one byte at a time */
switch(length) /* all the case statements fall through */
{
case 12: c+=((uint32_t)k[11])<<24;
+ /* FALLTHROUGH */
case 11: c+=((uint32_t)k[10])<<16;
+ /* FALLTHROUGH */
case 10: c+=((uint32_t)k[9])<<8;
+ /* FALLTHROUGH */
case 9 : c+=k[8];
+ /* FALLTHROUGH */
case 8 : b+=((uint32_t)k[7])<<24;
+ /* FALLTHROUGH */
case 7 : b+=((uint32_t)k[6])<<16;
+ /* FALLTHROUGH */
case 6 : b+=((uint32_t)k[5])<<8;
+ /* FALLTHROUGH */
case 5 : b+=k[4];
+ /* FALLTHROUGH */
case 4 : a+=((uint32_t)k[3])<<24;
+ /* FALLTHROUGH */
case 3 : a+=((uint32_t)k[2])<<16;
+ /* FALLTHROUGH */
case 2 : a+=((uint32_t)k[1])<<8;
+ /* FALLTHROUGH */
case 1 : a+=k[0];
break;
- case 0 : return c;
+ case 0 : return NON_ZERO_64(b, c);
}
}
final(a,b,c);
- return c;
+ return NON_ZERO_64(b, c);
}
+#else
+#define hashlittle2(key, len) hashlittle(key, len)
+#endif
git.samba.org / rsync.git / blobdiff