Merge branch 'np/delta' into next

* np/delta:
  count-delta: tweak counting of copied source material.
  diff-delta: produce optimal pack data

2 files changed, 101 insertions, 53 deletions

diff --git a/count-delta.c b/count-delta.c
index 058a2aadb..4e4d2f4fc 100644
--- a/count-delta.c
+++ b/count-delta.c
@@ -3,11 +3,74 @@
  * The delta-parsing part is almost straight copy of patch-delta.c
  * which is (C) 2005 Nicolas Pitre <nico@cam.org>.
  */
+#include "cache.h"
+#include "delta.h"
+#include "count-delta.h"
 #include <stdlib.h>
 #include <string.h>
 #include <limits.h>
-#include "delta.h"
-#include "count-delta.h"
+
+struct span {
+	struct span *next;
+	unsigned long ofs;
+	unsigned long end;
+};
+
+static void touch_range(struct span **span,
+			unsigned long ofs, unsigned long end)
+{
+	struct span *e = *span;
+	struct span *p = NULL;
+
+	while (e && e->ofs <= ofs) {
+		again:
+		if (ofs < e->end) {
+			while (e->end < end) {
+				if (e->next) {
+					e->end = e->next->ofs;
+					e = e->next;
+				}
+				else {
+					e->end = end;
+					return;
+				}
+			}
+			return;
+		}
+		p = e;
+		e = e->next;
+	}
+	if (e && e->ofs <= end) {
+		e->ofs = ofs;
+		goto again;
+	}
+	else {
+		e = xmalloc(sizeof(*e));
+		e->ofs = ofs;
+		e->end = end;
+		if (p) {
+			e->next = p->next;
+			p->next = e;
+		}
+		else {
+			e->next = *span;
+			*span = e;
+		}
+	}
+}
+
+static unsigned long count_range(struct span *s)
+{
+	struct span *t;
+	unsigned long sz = 0;
+	while (s) {
+		t = s;
+		sz += s->end - s->ofs;
+		s = s->next;
+		free(t);
+	}
+	return sz;
+}
 
 /*
  * NOTE.  We do not _interpret_ delta fully.  As an approximation, we
@@ -21,10 +84,11 @@
 int count_delta(void *delta_buf, unsigned long delta_size,
 		unsigned long *src_copied, unsigned long *literal_added)
 {
-	unsigned long copied_from_source, added_literal;
+	unsigned long added_literal;
 	const unsigned char *data, *top;
 	unsigned char cmd;
 	unsigned long src_size, dst_size, out;
+	struct span *span = NULL;
 
 	if (delta_size < DELTA_SIZE_MIN)
 		return -1;
@@ -35,7 +99,7 @@ int count_delta(void *delta_buf, unsigned long delta_size,
 	src_size = get_delta_hdr_size(&data);
 	dst_size = get_delta_hdr_size(&data);
 
-	added_literal = copied_from_source = out = 0;
+	added_literal = out = 0;
 	while (data < top) {
 		cmd = *data++;
 		if (cmd & 0x80) {
@@ -49,7 +113,7 @@ int count_delta(void *delta_buf, unsigned long delta_size,
 			if (cmd & 0x40) cp_size |= (*data++ << 16);
 			if (cp_size == 0) cp_size = 0x10000;
 
-			copied_from_source += cp_size;
+			touch_range(&span, cp_off, cp_off+cp_size);
 			out += cp_size;
 		} else {
 			/* write literal into dst */
@@ -59,6 +123,8 @@ int count_delta(void *delta_buf, unsigned long delta_size,
 		}
 	}
 
+	*src_copied = count_range(span);
+
 	/* sanity check */
 	if (data != top || out != dst_size)
 		return -1;
@@ -66,7 +132,6 @@ int count_delta(void *delta_buf, unsigned long delta_size,
 	/* delete size is what was _not_ copied from source.
 	 * edit size is that and literal additions.
 	 */
-	*src_copied = copied_from_source;
 	*literal_added = added_literal;
 	return 0;
 }
diff --git a/diff-delta.c b/diff-delta.c
index 2ed5984b1..27f83a085 100644
--- a/diff-delta.c
+++ b/diff-delta.c
@@ -20,21 +20,11 @@
 
 #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;
 };
 
@@ -42,21 +32,21 @@ static struct index ** delta_index(const unsigned char *buf,
 				   unsigned long bufsize,
 				   unsigned int *hash_shift)
 {
-	unsigned int hsize, hshift, entries, blksize, i;
+	unsigned long hsize;
+	unsigned int hshift, i;
 	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 < 16; i++);
 	hsize = 1 << i;
-	hshift = 32 - i;
+	hshift = i - 8;
 	*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;
@@ -64,17 +54,12 @@ static struct index ** delta_index(const unsigned char *buf,
 	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;
+	data = buf + bufsize - 2;
+	while (data > buf) {
+		entry->ptr = --data;
+		i = data[0] ^ data[1] ^ (data[2] << hshift);
 		entry->next = hash[i];
 		hash[i] = entry++;
-		blksize = BLK_SIZE;
-		data -= BLK_SIZE;
  	}
 
 	return hash;
@@ -141,29 +126,27 @@ 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 + 2 < top) {
+			i = data[0] ^ data[1] ^ (data[2] << 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;
+				while (ref_size && *src++ == *ref) {
+					ref++;
+					ref_size--;
+				}
+				ref_size = ref - entry->ptr;
+				if (msize < ref - entry->ptr) {
+					/* this is our best match so far */
+					msize = ref - entry->ptr;
+					moff = entry->ptr - ref_data;
 				}
 			}
 		}