/*
* Idea here is very simple.
*
- * We have total of (sz-N+1) N-byte overlapping sequences in buf whose
- * size is sz. If the same N-byte sequence appears in both source and
- * destination, we say the byte that starts that sequence is shared
- * between them (i.e. copied from source to destination).
+ * Almost all data we are interested in are text, but sometimes we have
+ * to deal with binary data. So we cut them into chunks delimited by
+ * LF byte, or 64-byte sequence, whichever comes first, and hash them.
*
- * For each possible N-byte sequence, if the source buffer has more
- * instances of it than the destination buffer, that means the
- * difference are the number of bytes not copied from source to
- * destination. If the counts are the same, everything was copied
- * from source to destination. If the destination has more,
- * everything was copied, and destination added more.
+ * For those chunks, if the source buffer has more instances of it
+ * than the destination buffer, that means the difference are the
+ * number of bytes not copied from source to destination. If the
+ * counts are the same, everything was copied from source to
+ * destination. If the destination has more, everything was copied,
+ * and destination added more.
*
* We are doing an approximation so we do not really have to waste
* memory by actually storing the sequence. We just hash them into
* somewhere around 2^16 hashbuckets and count the occurrences.
- *
- * The length of the sequence is arbitrarily set to 8 for now.
*/
/* Wild guess at the initial hash size */
-#define INITIAL_HASH_SIZE 10
-#define HASHBASE 65537 /* next_prime(2^16) */
+#define INITIAL_HASH_SIZE 9
+
+/* We leave more room in smaller hash but do not let it
+ * grow to have unused hole too much.
+ */
+#define INITIAL_FREE(sz_log2) ((1<<(sz_log2))*(sz_log2-3)/(sz_log2))
+
+/* A prime rather carefully chosen between 2^16..2^17, so that
+ * HASHBASE < INITIAL_FREE(17). We want to keep the maximum hashtable
+ * size under the current 2<<17 maximum, which can hold this many
+ * different values before overflowing to hashtable of size 2<<18.
+ */
+#define HASHBASE 107927
struct spanhash {
- unsigned long hashval;
- unsigned long cnt;
+ unsigned int hashval;
+ unsigned int cnt;
};
struct spanhash_top {
int alloc_log2;
struct spanhash data[FLEX_ARRAY];
};
-static struct spanhash *spanhash_find(struct spanhash_top *top, unsigned long hashval)
+static struct spanhash *spanhash_find(struct spanhash_top *top,
+ unsigned int hashval)
{
int sz = 1 << top->alloc_log2;
int bucket = hashval & (sz - 1);
new = xmalloc(sizeof(*orig) + sizeof(struct spanhash) * sz);
new->alloc_log2 = orig->alloc_log2 + 1;
- new->free = osz;
+ new->free = INITIAL_FREE(new->alloc_log2);
memset(new->data, 0, sizeof(struct spanhash) * sz);
for (i = 0; i < osz; i++) {
struct spanhash *o = &(orig->data[i]);
}
static struct spanhash_top *add_spanhash(struct spanhash_top *top,
- unsigned long hashval)
+ unsigned int hashval, int cnt)
{
int bucket, lim;
struct spanhash *h;
h = &(top->data[bucket++]);
if (!h->cnt) {
h->hashval = hashval;
- h->cnt = 1;
+ h->cnt = cnt;
top->free--;
if (top->free < 0)
return spanhash_rehash(top);
return top;
}
if (h->hashval == hashval) {
- h->cnt++;
+ h->cnt += cnt;
return top;
}
if (lim <= bucket)
}
}
-static struct spanhash_top *hash_chars(unsigned char *buf, unsigned long sz)
+static struct spanhash_top *hash_chars(struct diff_filespec *one)
{
- int i;
- unsigned long accum1, accum2, hashval;
+ int i, n;
+ unsigned int accum1, accum2, hashval;
struct spanhash_top *hash;
+ unsigned char *buf = one->data;
+ unsigned int sz = one->size;
+ int is_text = !diff_filespec_is_binary(one);
i = INITIAL_HASH_SIZE;
hash = xmalloc(sizeof(*hash) + sizeof(struct spanhash) * (1<<i));
hash->alloc_log2 = i;
- hash->free = (1<<i)/2;
+ hash->free = INITIAL_FREE(i);
memset(hash->data, 0, sizeof(struct spanhash) * (1<<i));
- /* an 8-byte shift register made of accum1 and accum2. New
- * bytes come at LSB of accum2, and shifted up to accum1
- */
- for (i = accum1 = accum2 = 0; i < 7; i++, sz--) {
- accum1 = (accum1 << 8) | (accum2 >> 24);
- accum2 = (accum2 << 8) | *buf++;
- }
+ n = 0;
+ accum1 = accum2 = 0;
while (sz) {
- accum1 = (accum1 << 8) | (accum2 >> 24);
- accum2 = (accum2 << 8) | *buf++;
- hashval = (accum1 + accum2 * 0x61) % HASHBASE;
- hash = add_spanhash(hash, hashval);
+ unsigned int c = *buf++;
+ unsigned int old_1 = accum1;
sz--;
+
+ /* Ignore CR in CRLF sequence if text */
+ if (is_text && c == '\r' && sz && *buf == '\n')
+ continue;
+
+ accum1 = (accum1 << 7) ^ (accum2 >> 25);
+ accum2 = (accum2 << 7) ^ (old_1 >> 25);
+ accum1 += c;
+ if (++n < 64 && c != '\n')
+ continue;
+ hashval = (accum1 + accum2 * 0x61) % HASHBASE;
+ hash = add_spanhash(hash, hashval, n);
+ n = 0;
+ accum1 = accum2 = 0;
}
return hash;
}
-int diffcore_count_changes(void *src, unsigned long src_size,
- void *dst, unsigned long dst_size,
+int diffcore_count_changes(struct diff_filespec *src,
+ struct diff_filespec *dst,
void **src_count_p,
void **dst_count_p,
unsigned long delta_limit,
struct spanhash_top *src_count, *dst_count;
unsigned long sc, la;
- if (src_size < 8 || dst_size < 8)
- return -1;
-
src_count = dst_count = NULL;
if (src_count_p)
src_count = *src_count_p;
if (!src_count) {
- src_count = hash_chars(src, src_size);
+ src_count = hash_chars(src);
if (src_count_p)
*src_count_p = src_count;
}
if (dst_count_p)
dst_count = *dst_count_p;
if (!dst_count) {
- dst_count = hash_chars(dst, dst_size);
+ dst_count = hash_chars(dst);
if (dst_count_p)
*dst_count_p = dst_count;
}