Merge branch 'jc/diff' into next

diff --git a/diff-delta.c b/diff-delta.c
index 0730b24df8fe679d16e1cd03d066b4d7f33e73cd..aaee7be4d20dade99d351f6bdd70632cf249230e 100644 (file)
--- a/diff-delta.c
+++ b/diff-delta.c
@@ -20,11 +20,21 @@
 
 #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;
 };
 
@@ -33,21 +43,21 @@ static struct index ** delta_index(const unsigned char *buf,
                                   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;
@@ -62,13 +72,16 @@ static struct index ** delta_index(const unsigned char *buf,
        }
 
        /* 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;
        }
 
        /*
@@ -83,13 +96,13 @@ static struct index ** delta_index(const unsigned char *buf,
         * 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 short-circuit the entry
-        * list uniformly to still preserve a good repartition across
+        * 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++) {
@@ -171,21 +184,23 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 
        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;