diffcore-rename: split out the delta counting code.

This is to rework diffcore break/rename/copy detection code
so that it does not affected when deltifier code gets improved.

Signed-off-by: Junio C Hamano <junkio@cox.net>

5 files changed, 61 insertions, 40 deletions

diff --git a/Makefile b/Makefile
index 19578fc..a5eb0c4 100644
--- a/Makefile
+++ b/Makefile
@@ -196,7 +196,8 @@ LIB_H = \
 
 DIFF_OBJS = \
 	diff.o diffcore-break.o diffcore-order.o diffcore-pathspec.o \
-	diffcore-pickaxe.o diffcore-rename.o tree-diff.o combine-diff.o
+	diffcore-pickaxe.o diffcore-rename.o tree-diff.o combine-diff.o \
+	diffcore-delta.o
 
 LIB_OBJS = \
 	blob.o commit.o connect.o count-delta.o csum-file.o \
diff --git a/diffcore-break.c b/diffcore-break.c
index 95b5eb4..0fc2b86 100644
--- a/diffcore-break.c
+++ b/diffcore-break.c
@@ -4,8 +4,6 @@
 #include "cache.h"
 #include "diff.h"
 #include "diffcore.h"
-#include "delta.h"
-#include "count-delta.h"
 
 static int should_break(struct diff_filespec *src,
 			struct diff_filespec *dst,
@@ -47,7 +45,6 @@ static int should_break(struct diff_filespec *src,
 	 * The value we return is 1 if we want the pair to be broken,
 	 * or 0 if we do not.
 	 */
-	void *delta;
 	unsigned long delta_size, base_size, src_copied, literal_added;
 	int to_break = 0;
 
@@ -69,19 +66,11 @@ static int should_break(struct diff_filespec *src,
 	if (base_size < MINIMUM_BREAK_SIZE)
 		return 0; /* we do not break too small filepair */
 
-	delta = diff_delta(src->data, src->size,
-			   dst->data, dst->size,
-			   &delta_size, 0);
-	if (!delta)
-		return 0; /* error but caught downstream */
-
-	/* Estimate the edit size by interpreting delta. */
-	if (count_delta(delta, delta_size,
-			&src_copied, &literal_added)) {
-		free(delta);
-		return 0; /* we cannot tell */
-	}
-	free(delta);
+	if (diffcore_count_changes(src->data, src->size,
+				   dst->data, dst->size,
+				   0,
+				   &src_copied, &literal_added))
+		return 0;
 
 	/* Compute merge-score, which is "how much is removed
 	 * from the source material".  The clean-up stage will
diff --git a/diffcore-delta.c b/diffcore-delta.c
new file mode 100644
index 0000000..1e6a691
--- /dev/null
+++ b/diffcore-delta.c
@@ -0,0 +1,43 @@
+#include "cache.h"
+#include "diff.h"
+#include "diffcore.h"
+#include "delta.h"
+#include "count-delta.h"
+
+static int diffcore_count_changes_1(void *src, unsigned long src_size,
+				    void *dst, unsigned long dst_size,
+				    unsigned long delta_limit,
+				    unsigned long *src_copied,
+				    unsigned long *literal_added)
+{
+	void *delta;
+	unsigned long delta_size;
+
+	delta = diff_delta(src, src_size,
+			   dst, dst_size,
+			   &delta_size, delta_limit);
+	if (!delta)
+		/* If delta_limit is exceeded, we have too much differences */
+		return -1;
+
+	/* Estimate the edit size by interpreting delta. */
+	if (count_delta(delta, delta_size, src_copied, literal_added)) {
+		free(delta);
+		return -1;
+	}
+	free(delta);
+	return 0;
+}
+
+int diffcore_count_changes(void *src, unsigned long src_size,
+			   void *dst, unsigned long dst_size,
+			   unsigned long delta_limit,
+			   unsigned long *src_copied,
+			   unsigned long *literal_added)
+{
+	return diffcore_count_changes_1(src, src_size,
+					dst, dst_size,
+					delta_limit,
+					src_copied,
+					literal_added);
+}
diff --git a/diffcore-rename.c b/diffcore-rename.c
index ffd126a..55cf1c3 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -4,8 +4,6 @@
 #include "cache.h"
 #include "diff.h"
 #include "diffcore.h"
-#include "delta.h"
-#include "count-delta.h"
 
 /* Table of rename/copy destinations */
 
@@ -135,7 +133,6 @@ static int estimate_similarity(struct diff_filespec *src,
 	 * match than anything else; the destination does not even
 	 * call into this function in that case.
 	 */
-	void *delta;
 	unsigned long delta_size, base_size, src_copied, literal_added;
 	unsigned long delta_limit;
 	int score;
@@ -165,28 +162,13 @@ static int estimate_similarity(struct diff_filespec *src,
 	if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
 		return 0; /* error but caught downstream */
 
-	delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE;
-	delta = diff_delta(src->data, src->size,
-			   dst->data, dst->size,
-			   &delta_size, delta_limit);
-	if (!delta)
-		/* If delta_limit is exceeded, we have too much differences */
-		return 0;
-
-	/* A delta that has a lot of literal additions would have
-	 * big delta_size no matter what else it does.
-	 */
-	if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE) {
-		free(delta);
-		return 0;
-	}
 
-	/* Estimate the edit size by interpreting delta. */
-	if (count_delta(delta, delta_size, &src_copied, &literal_added)) {
-		free(delta);
+	delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE;
+	if (diffcore_count_changes(src->data, src->size,
+				   dst->data, dst->size,
+				   delta_limit,
+				   &src_copied, &literal_added))
 		return 0;
-	}
-	free(delta);
 
 	/* Extent of damage */
 	if (src->size + literal_added < src_copied)
diff --git a/diffcore.h b/diffcore.h
index 12cd816..dba4f17 100644
--- a/diffcore.h
+++ b/diffcore.h
@@ -101,4 +101,10 @@ 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,
+				  unsigned long delta_limit,
+				  unsigned long *src_copied,
+				  unsigned long *literal_added);
+
 #endif