#include <stdlib.h>
#include <string.h>
+#include <zlib.h>
#include "delta.h"
-struct index {
+/* block size: min = 16, max = 64k, power of 2 */
+#define BLK_SIZE 16
+
+/* maximum hash entry list for the same hash bucket */
+#define HASH_LIMIT 64
+
+#define GR_PRIME 0x9e370001
+#define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift))
+
+struct index_entry {
const unsigned char *ptr;
- struct index *next;
+ unsigned int val;
+ struct index_entry *next;
};
-static struct index ** delta_index(const unsigned char *buf,
- unsigned long bufsize,
- unsigned long trg_bufsize)
+struct delta_index {
+ const void *src_buf;
+ unsigned long src_size;
+ unsigned int hash_shift;
+ struct index_entry *hash[0];
+};
+
+struct delta_index * create_delta_index(const void *buf, unsigned long bufsize)
{
- unsigned long hsize;
- unsigned int i, hshift, hlimit, *hash_count;
- const unsigned char *data;
- struct index *entry, **hash;
+ unsigned int i, hsize, hshift, entries, *hash_count;
+ const unsigned char *data, *buffer = buf;
+ struct delta_index *index;
+ struct index_entry *entry, **hash;
void *mem;
+ if (!buf || !bufsize)
+ return NULL;
+
/* 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;
- /*
- * Allocate lookup index. Note the first hash pointer
- * is used to store the hash shift value.
- */
- mem = malloc((1 + hsize) * sizeof(*hash) + bufsize * sizeof(*entry));
+ /* allocate lookup index */
+ mem = malloc(sizeof(*index) +
+ sizeof(*hash) * hsize +
+ sizeof(*entry) * entries);
if (!mem)
return NULL;
+ index = mem;
+ mem = index + 1;
hash = mem;
- *hash++ = (void *)hshift;
- entry = mem + (1 + hsize) * sizeof(*hash);
+ mem = hash + hsize;
+ entry = mem;
+
+ index->src_buf = buf;
+ index->src_size = bufsize;
+ index->hash_shift = hshift;
memset(hash, 0, hsize * sizeof(*hash));
/* allocate an array to count hash entries */
hash_count = calloc(hsize, sizeof(*hash_count));
if (!hash_count) {
- free(hash);
+ free(index);
return NULL;
}
/* then populate the index */
- data = buf + bufsize - 2;
- while (data > buf) {
- entry->ptr = --data;
- i = data[0] ^ ((data[1] ^ (data[2] << hshift)) << hshift);
+ data = buffer + entries * BLK_SIZE - BLK_SIZE;
+ while (data >= buffer) {
+ 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;
}
/*
* bucket that would bring us to O(m*n) computing costs (m and n
* corresponding to reference and target buffer sizes).
*
- * The more the target buffer is large, the more it is important to
- * have small entry lists for each hash buckets. With such a limit
- * the cost is bounded to something more like O(m+n).
- */
- hlimit = (1 << 26) / trg_bufsize;
- if (hlimit < 16)
- hlimit = 16;
-
- /*
- * Now make sure none of the hash buckets has more entries than
- * we're willing to test. Otherwise we short-circuit the entry
- * list uniformly to still preserve a good repartition across
+ * Make sure none of the hash buckets has more entries than
+ * 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++) {
- if (hash_count[i] < hlimit)
+ if (hash_count[i] < HASH_LIMIT)
continue;
entry = hash[i];
do {
- struct index *keep = entry;
- int skip = hash_count[i] / hlimit / 2;
+ struct index_entry *keep = entry;
+ int skip = hash_count[i] / HASH_LIMIT / 2;
do {
entry = entry->next;
} while(--skip && entry);
}
free(hash_count);
- return hash-1;
+ return index;
+}
+
+void free_delta_index(struct delta_index *index)
+{
+ free(index);
}
/* provide the size of the copy opcode given the block offset and size */
/* the maximum size for any opcode */
#define MAX_OP_SIZE COPYOP_SIZE(0xffffffff, 0xffffffff)
-void *diff_delta(void *from_buf, unsigned long from_size,
- void *to_buf, unsigned long to_size,
- unsigned long *delta_size,
- unsigned long max_size,
- void **from_index)
+void *
+create_delta(const struct delta_index *index,
+ const void *trg_buf, unsigned long trg_size,
+ 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;
- if (!from_size || !to_size)
+ if (!trg_buf || !trg_size)
return NULL;
- if (from_index && *from_index) {
- hash = *from_index;
- } else {
- hash = delta_index(from_buf, from_size, to_size);
- if (!hash)
- return NULL;
- if (from_index)
- *from_index = hash;
- }
- hash_shift = (unsigned int)(*hash++);
outpos = 0;
outsize = 8192;
if (max_size && outsize >= max_size)
outsize = max_size + MAX_OP_SIZE + 1;
out = malloc(outsize);
- if (!out) {
- if (!from_index)
- free(hash-1);
+ if (!out)
return NULL;
- }
-
- ref_data = from_buf;
- ref_top = from_buf + from_size;
- data = to_buf;
- top = to_buf + to_size;
/* store reference buffer size */
- out[outpos++] = from_size;
- from_size >>= 7;
- while (from_size) {
- out[outpos - 1] |= 0x80;
- out[outpos++] = from_size;
- from_size >>= 7;
+ i = index->src_size;
+ while (i >= 0x80) {
+ out[outpos++] = i | 0x80;
+ i >>= 7;
}
+ out[outpos++] = i;
/* store target buffer size */
- out[outpos++] = to_size;
- to_size >>= 7;
- while (to_size) {
- out[outpos - 1] |= 0x80;
- out[outpos++] = to_size;
- to_size >>= 7;
+ i = trg_size;
+ while (i >= 0x80) {
+ out[outpos++] = i | 0x80;
+ i >>= 7;
}
+ out[outpos++] = i;
+ ref_data = index->src_buf;
+ ref_top = ref_data + index->src_size;
+ data = trg_buf;
+ top = trg_buf + trg_size;
+ hash_shift = index->hash_shift;
inscnt = 0;
while (data < top) {
unsigned int moff = 0, msize = 0;
- if (data + 3 <= top) {
- i = data[0] ^ ((data[1] ^ (data[2] << hash_shift)) << 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 (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);
- if (msize < ref - entry->ptr) {
- /* this is our best match so far */
- msize = ref - entry->ptr;
- moff = entry->ptr - ref_data;
- }
+ struct index_entry *entry;
+ unsigned int val = adler32(0, data, BLK_SIZE);
+ i = HASH(val, hash_shift);
+ for (entry = index->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;
+ while (ref_size-- && *src++ == *ref)
+ ref++;
+ if (msize < ref - entry->ptr) {
+ /* this is our best match so far */
+ msize = ref - entry->ptr;
+ moff = entry->ptr - ref_data;
}
}
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;
}
out = realloc(out, outsize);
if (!out) {
free(tmp);
- if (!from_index)
- free(hash-1);
return NULL;
}
}
if (inscnt)
out[outpos - inscnt - 1] = inscnt;
- if (!from_index)
- free(hash-1);
*delta_size = outpos;
return out;
}