Merge part of np/delta

diff --git a/diff-delta.c b/diff-delta.c
index 2ed5984..0730b24 100644 (file)
--- a/diff-delta.c
+++ b/diff-delta.c
@@ -20,63 +20,93 @@
 
 #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;
 };
 
 static struct index ** delta_index(const unsigned char *buf,
                                   unsigned long bufsize,
+                                  unsigned long trg_bufsize,
                                   unsigned int *hash_shift)
 {
-       unsigned int hsize, hshift, entries, blksize, i;
+       unsigned long hsize;
+       unsigned int i, hshift, hlimit, *hash_count;
        const unsigned char *data;
        struct index *entry, **hash;
        void *mem;
 
        /* determine index hash size */
-       entries = (bufsize + BLK_SIZE - 1) / BLK_SIZE;
-       hsize = entries / 4;
-       for (i = 4; (1 << i) < hsize && i < 16; i++);
+       hsize = bufsize / 4;
+       for (i = 8; (1 << i) < hsize && i < 24; i += 2);
        hsize = 1 << i;
-       hshift = 32 - i;
+       hshift = (i - 8) / 2;
        *hash_shift = hshift;
 
        /* allocate lookup index */
-       mem = malloc(hsize * sizeof(*hash) + entries * sizeof(*entry));
+       mem = malloc(hsize * sizeof(*hash) + bufsize * sizeof(*entry));
        if (!mem)
                return NULL;
        hash = mem;
        entry = mem + hsize * sizeof(*hash);
        memset(hash, 0, hsize * sizeof(*hash));
 
-       /* then populate it */
-       data = buf + entries * BLK_SIZE - BLK_SIZE;
-       blksize = bufsize - (data - buf);
-       while (data >= buf) {
-               unsigned int val = adler32(0, data, blksize);
-               i = HASH(val, hshift);
-               entry->ptr = data;
-               entry->val = val;
+       /* allocate an array to count hash entries */
+       hash_count = calloc(hsize, sizeof(*hash_count));
+       if (!hash_count) {
+               free(hash);
+               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);
                entry->next = hash[i];
                hash[i] = entry++;
-               blksize = BLK_SIZE;
-               data -= BLK_SIZE;
+               hash_count[i]++;
        }
 
+       /*
+        * Determine a limit on the number of entries in the same hash
+        * bucket.  This guard us against patological data sets causing
+        * really bad hash distribution with most entries in the same hash
+        * 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
+        * the reference buffer.
+        */
+       for (i = 0; i < hsize; i++) {
+               if (hash_count[i] < hlimit)
+                       continue;
+               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);
+
        return hash;
 }
 
@@ -100,7 +130,7 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 
        if (!from_size || !to_size)
                return NULL;
-       hash = delta_index(from_buf, from_size, &hash_shift);
+       hash = delta_index(from_buf, from_size, to_size, &hash_shift);
        if (!hash)
                return NULL;
 
@@ -141,29 +171,25 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 
        while (data < top) {
                unsigned int moff = 0, msize = 0;
-               unsigned int blksize = MIN(top - data, BLK_SIZE);
-               unsigned int val = adler32(0, data, blksize);
-               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;
-                       while (ref_size && *src++ == *ref) {
-                               ref++;
-                               ref_size--;
-                       }
-                       ref_size = ref - entry->ptr;
-                       if (ref_size > msize) {
-                               /* this is our best match so far */
-                               moff = entry->ptr - ref_data;
-                               msize = ref_size;
-                               if (msize >= 0x10000) {
-                                       msize = 0x10000;
+               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;
                                }
                        }
                }