#include <stdlib.h>
#include <string.h>
+#include <zlib.h>
#include "delta.h"
+/* block size: min = 16, max = 64k, power of 2 */
+#define BLK_SIZE 16
+
+#define MIN(a, b) ((a) < (b) ? (a) : (b))
+
+#define GR_PRIME 0x9e370001
+#define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift))
+
struct index {
const unsigned char *ptr;
+ unsigned int val;
struct index *next;
};
unsigned long trg_bufsize,
unsigned int *hash_shift)
{
- unsigned long hsize;
- unsigned int i, hshift, hlimit, *hash_count;
+ unsigned int i, hsize, hshift, hlimit, entries, *hash_count;
const unsigned char *data;
struct index *entry, **hash;
void *mem;
/* determine index hash size */
- hsize = bufsize / 4;
- for (i = 8; (1 << i) < hsize && i < 24; i += 2);
+ entries = bufsize / BLK_SIZE;
+ hsize = entries / 4;
+ for (i = 4; (1 << i) < hsize && i < 31; i++);
hsize = 1 << i;
- hshift = (i - 8) / 2;
+ hshift = 32 - i;
*hash_shift = hshift;
/* allocate lookup index */
- mem = malloc(hsize * sizeof(*hash) + bufsize * sizeof(*entry));
+ mem = malloc(hsize * sizeof(*hash) + entries * sizeof(*entry));
if (!mem)
return NULL;
hash = mem;
}
/* then populate the index */
- data = buf + bufsize - 2;
- while (data > buf) {
- entry->ptr = --data;
- i = data[0] ^ ((data[1] ^ (data[2] << hshift)) << hshift);
+ data = buf + entries * BLK_SIZE - BLK_SIZE;
+ while (data >= buf) {
+ unsigned int val = adler32(0, data, BLK_SIZE);
+ i = HASH(val, hshift);
+ entry->ptr = data;
+ entry->val = val;
entry->next = hash[i];
hash[i] = entry++;
hash_count[i]++;
+ data -= BLK_SIZE;
}
/*
* the cost is bounded to something more like O(m+n).
*/
hlimit = (1 << 26) / trg_bufsize;
- if (hlimit < 16)
- hlimit = 16;
+ if (hlimit < 4*BLK_SIZE)
+ hlimit = 4*BLK_SIZE;
/*
* Now make sure none of the hash buckets has more entries than
- * we're willing to test. Otherwise we cull the entry list to
- * limit identical three byte prefixes to still preserve a good
- * repartition across the reference buffer.
+ * we're willing to test. Otherwise we cull the entry list
+ * uniformly to still preserve a good repartition across
+ * the reference buffer.
*/
for (i = 0; i < hsize; i++) {
- struct index **list, *bucket, *remaining;
- int cnt;
if (hash_count[i] < hlimit)
continue;
-
- bucket = NULL;
- list = &bucket;
- remaining = hash[i];
- cnt = 0;
- while (cnt < hlimit && remaining) {
- struct index *this = remaining, *that;
- remaining = remaining->next;
- for (that = bucket; that; that = that->next) {
- if (!memcmp(that->ptr, this->ptr, 3))
- break;
- }
- if (that)
- continue; /* discard */
- cnt++;
- *list = this;
- list = &(this->next);
- this->next = NULL;
- }
- hash[i] = bucket;
+ entry = hash[i];
+ do {
+ struct index *keep = entry;
+ int skip = hash_count[i] / hlimit / 2;
+ do {
+ entry = entry->next;
+ } while(--skip && entry);
+ keep->next = entry;
+ } while(entry);
}
free(hash_count);
unsigned long *delta_size,
unsigned long max_size)
{
- unsigned int i, outpos, outsize, inscnt, hash_shift;
+ unsigned int i, outpos, outsize, hash_shift;
+ int inscnt;
const unsigned char *ref_data, *ref_top, *data, *top;
unsigned char *out;
struct index *entry, **hash;
while (data < top) {
unsigned int moff = 0, msize = 0;
- if (data + 3 <= top) {
- i = data[0] ^ ((data[1] ^ (data[2] << hash_shift)) << hash_shift);
+ if (data + BLK_SIZE <= top) {
+ unsigned int val = adler32(0, data, BLK_SIZE);
+ i = HASH(val, hash_shift);
for (entry = hash[i]; entry; entry = entry->next) {
const unsigned char *ref = entry->ptr;
const unsigned char *src = data;
unsigned int ref_size = ref_top - ref;
+ if (entry->val != val)
+ continue;
if (ref_size > top - src)
ref_size = top - src;
if (ref_size > 0x10000)
ref_size = 0x10000;
if (ref_size <= msize)
break;
- if (*ref != *src)
- continue;
- while (ref_size-- && *++src == *++ref);
+ while (ref_size-- && *src++ == *ref)
+ ref++;
if (msize < ref - entry->ptr) {
/* this is our best match so far */
msize = ref - entry->ptr;
unsigned char *op;
if (inscnt) {
+ while (moff && ref_data[moff-1] == data[-1]) {
+ if (msize == 0x10000)
+ break;
+ /* we can match one byte back */
+ msize++;
+ moff--;
+ data--;
+ outpos--;
+ if (--inscnt)
+ continue;
+ outpos--; /* remove count slot */
+ inscnt--; /* make it -1 */
+ break;
+ }
out[outpos - inscnt - 1] = inscnt;
inscnt = 0;
}