Merge branch 'jc/diffcore'

* jc/diffcore:
  diffcore-delta.c: Ignore CR in CRLF for text files
  diffcore-delta.c: update the comment on the algorithm.
  diffcore_filespec: add is_binary
  diffcore_count_changes: pass diffcore_filespec

6 files changed, 76 insertions, 23 deletions

diff --git a/diff.c b/diff.c
index e0edb9884..93eca79c1 100644
--- a/diff.c
+++ b/diff.c
@@ -3005,6 +3005,22 @@ void diffcore_std(struct diff_options *options)
 {
 	if (options->quiet)
 		return;
+
+	/*
+	 * break/rename count similarity differently depending on
+	 * the binary-ness.
+	 */
+	if ((options->break_opt != -1) || (options->detect_rename)) {
+		struct diff_queue_struct *q = &diff_queued_diff;
+		int i;
+
+		for (i = 0; i < q->nr; i++) {
+			struct diff_filepair *p = q->queue[i];
+			p->one->is_binary = file_is_binary(p->one);
+			p->two->is_binary = file_is_binary(p->two);
+		}
+	}
+
 	if (options->break_opt != -1)
 		diffcore_break(options->break_opt);
 	if (options->detect_rename)
diff --git a/diffcore-break.c b/diffcore-break.c
index 9c19b8cab..ae8a7d03e 100644
--- a/diffcore-break.c
+++ b/diffcore-break.c
@@ -66,8 +66,7 @@ static int should_break(struct diff_filespec *src,
 	if (base_size < MINIMUM_BREAK_SIZE)
 		return 0; /* we do not break too small filepair */
 
-	if (diffcore_count_changes(src->data, src->size,
-				   dst->data, dst->size,
+	if (diffcore_count_changes(src, dst,
 				   NULL, NULL,
 				   0,
 				   &src_copied, &literal_added))
diff --git a/diffcore-delta.c b/diffcore-delta.c
index 7338a40c5..a038b166c 100644
--- a/diffcore-delta.c
+++ b/diffcore-delta.c
@@ -5,23 +5,20 @@
 /*
  * 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 */
@@ -125,11 +122,14 @@ static struct spanhash_top *add_spanhash(struct spanhash_top *top,
 	}
 }
 
-static struct spanhash_top *hash_chars(unsigned char *buf, unsigned int sz)
+static struct spanhash_top *hash_chars(struct diff_filespec *one)
 {
 	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 = !one->is_binary;
 
 	i = INITIAL_HASH_SIZE;
 	hash = xmalloc(sizeof(*hash) + sizeof(struct spanhash) * (1<<i));
@@ -143,6 +143,11 @@ static struct spanhash_top *hash_chars(unsigned char *buf, unsigned int sz)
 		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;
@@ -156,8 +161,8 @@ static struct spanhash_top *hash_chars(unsigned char *buf, unsigned int sz)
 	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,
@@ -172,14 +177,14 @@ int diffcore_count_changes(void *src, unsigned long src_size,
 	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;
 	}
diff --git a/diffcore-rename.c b/diffcore-rename.c
index e0a89f379..6bde4396f 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -190,8 +190,7 @@ static int estimate_similarity(struct diff_filespec *src,
 
 	delta_limit = (unsigned long)
 		(base_size * (MAX_SCORE-minimum_score) / MAX_SCORE);
-	if (diffcore_count_changes(src->data, src->size,
-				   dst->data, dst->size,
+	if (diffcore_count_changes(src, dst,
 				   &src->cnt_data, &dst->cnt_data,
 				   delta_limit,
 				   &src_copied, &literal_added))
diff --git a/diffcore.h b/diffcore.h
index 7b9294eab..0c8abb5b9 100644
--- a/diffcore.h
+++ b/diffcore.h
@@ -37,6 +37,7 @@ struct diff_filespec {
 #define DIFF_FILE_VALID(spec) (((spec)->mode) != 0)
 	unsigned should_free : 1; /* data should be free()'ed */
 	unsigned should_munmap : 1; /* data should be munmap()'ed */
+	unsigned is_binary : 1; /* data should be considered "binary" */
 };
 
 extern struct diff_filespec *alloc_filespec(const char *);
@@ -103,8 +104,8 @@ void diff_debug_queue(const char *, struct diff_queue_struct *);
 #define diff_debug_queue(a,b) do {} while(0)
 #endif
 
-extern int diffcore_count_changes(void *src, unsigned long src_size,
-				  void *dst, unsigned long dst_size,
+extern int diffcore_count_changes(struct diff_filespec *src,
+				  struct diff_filespec *dst,
 				  void **src_count_p,
 				  void **dst_count_p,
 				  unsigned long delta_limit,
diff --git a/t/t0022-crlf-rename.sh b/t/t0022-crlf-rename.sh
new file mode 100755
index 000000000..430a1d1d3
--- /dev/null
+++ b/t/t0022-crlf-rename.sh
@@ -0,0 +1,33 @@
+#!/bin/sh
+
+test_description='ignore CR in CRLF sequence while computing similiarity'
+
+. ./test-lib.sh
+
+test_expect_success setup '
+
+	cat ../t0022-crlf-rename.sh >sample &&
+	git add sample &&
+
+	test_tick &&
+	git commit -m Initial &&
+
+	sed -e "s/\$/
/" ../t0022-crlf-rename.sh >elpmas &&
+	git add elpmas &&
+	rm -f sample &&
+
+	test_tick &&
+	git commit -a -m Second
+
+'
+
+test_expect_success 'diff -M' '
+
+	git diff-tree -M -r --name-status HEAD^ HEAD |
+	sed -e "s/R[0-9]*/RNUM/" >actual &&
+	echo "RNUM	sample	elpmas" >expect &&
+	diff -u expect actual
+
+'
+
+test_done