[PATCH] Add -B flag to diff-* brothers.

A new diffcore transformation, diffcore-break.c, is introduced.

When the -B flag is given, a patch that represents a complete
rewrite is broken into a deletion followed by a creation.  This
makes it easier to review such a complete rewrite patch.

The -B flag takes the same syntax as the -M and -C flags to
specify the minimum amount of non-source material the resulting
file needs to have to be considered a complete rewrite, and
defaults to 99% if not specified.

As the new test t4008-diff-break-rewrite.sh demonstrates, if a
file is a complete rewrite, it is broken into a delete/create
pair, which can further be subjected to the usual rename
detection if -M or -C is used.  For example, if file0 gets
completely rewritten to make it as if it were rather based on
file1 which itself disappeared, the following happens:

    The original change looks like this:

	file0     --> file0' (quite different from file0)
	file1     --> /dev/null

    After diffcore-break runs, it would become this:

	file0     --> /dev/null
	/dev/null --> file0'
	file1     --> /dev/null

    Then diffcore-rename matches them up:

	file1     --> file0'

The internal score values are finer grained now.  Earlier
maximum of 10000 has been raised to 60000; there is no user
visible changes but there is no reason to waste available bits.

Signed-off-by: Junio C Hamano <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: Junio C Hamano

Documentation/git-diff-cache.txt

@@ -9,7 +9,7 @@ git-diff-cache - Compares content and mode of blobs between the cache and reposi
 
 SYNOPSIS
 --------
-'git-diff-cache' [-p] [-r] [-z] [-m] [-M] [-R] [-C] [-S<string>] [--pickaxe-all] [--cached] <tree-ish> [<path>...]
+'git-diff-cache' [-p] [-r] [-z] [-m] [-B] [-M] [-R] [-C] [-S<string>] [--pickaxe-all] [--cached] <tree-ish> [<path>...]
 
 DESCRIPTION
 -----------
@@ -35,6 +35,9 @@ OPTIONS
 -z::
 	\0 line termination on output
 
+-B::
+	Break complete rewrite changes into pairs of delete and create.
+
 -M::
 	Detect renames.
 

Documentation/git-diff-files.txt

@@ -9,7 +9,7 @@ git-diff-files - Compares files in the working tree and the cache
 
 SYNOPSIS
 --------
-'git-diff-files' [-p] [-q] [-r] [-z] [-M] [-C] [-R] [-S<string>] [--pickaxe-all] [<pattern>...]
+'git-diff-files' [-p] [-q] [-r] [-z] [-B] [-M] [-C] [-R] [-S<string>] [--pickaxe-all] [<pattern>...]
 
 DESCRIPTION
 -----------
@@ -29,6 +29,9 @@ OPTIONS
 -R::
 	Output diff in reverse.
 
+-B::
+	Break complete rewrite changes into pairs of delete and create.
+
 -M::
 	Detect renames.
 

Documentation/git-diff-tree.txt

@@ -9,7 +9,7 @@ git-diff-tree - Compares the content and mode of blobs found via two tree object
 
 SYNOPSIS
 --------
-'git-diff-tree' [-p] [-r] [-z] [--stdin] [-M] [-R] [-C] [-S<string>] [--pickaxe-all] [-m] [-s] [-v] [-t] <tree-ish> <tree-ish> [<pattern>]\*
+'git-diff-tree' [-p] [-r] [-z] [--stdin] [-B] [-M] [-R] [-C] [-S<string>] [--pickaxe-all] [-m] [-s] [-v] [-t] <tree-ish> <tree-ish> [<pattern>]\*
 
 DESCRIPTION
 -----------
@@ -33,6 +33,9 @@ OPTIONS
 	generate patch (see section on generating patches).  For
 	git-diff-tree, this flag implies '-r' as well.
 
+-B::
+	Break complete rewrite changes into pairs of delete and create.
+
 -M::
 	Detect renames.
 

Makefile

@@ -48,7 +48,7 @@ LIB_OBJS += strbuf.o
 
 LIB_H += diff.h count-delta.h
 LIB_OBJS += diff.o diffcore-rename.o diffcore-pickaxe.o diffcore-pathspec.o \
-	count-delta.o
+	count-delta.o diffcore-break.o
 
 LIB_OBJS += gitenv.o
 
@@ -130,6 +130,7 @@ diff.o: $(LIB_H) diffcore.h
 diffcore-rename.o : $(LIB_H) diffcore.h
 diffcore-pathspec.o : $(LIB_H) diffcore.h
 diffcore-pickaxe.o : $(LIB_H) diffcore.h
+diffcore-break.o : $(LIB_H) diffcore.h
 
 test: all
 	$(MAKE) -C t/ all

diff-cache.c

@@ -9,6 +9,7 @@ static int diff_setup_opt = 0;
 static int diff_score_opt = 0;
 static const char *pickaxe = NULL;
 static int pickaxe_opts = 0;
+static int diff_break_opt = -1;
 
 /* A file entry went away or appeared */
 static void show_file(const char *prefix, struct cache_entry *ce, unsigned char *sha1, unsigned int mode)
@@ -188,6 +189,10 @@ int main(int argc, const char **argv)
 			diff_output_format = DIFF_FORMAT_PATCH;
 			continue;
 		}
+		if (!strncmp(arg, "-B", 2)) {
+			diff_break_opt = diff_scoreopt_parse(arg);
+			continue;
+		}
 		if (!strncmp(arg, "-M", 2)) {
 			detect_rename = DIFF_DETECT_RENAME;
 			diff_score_opt = diff_scoreopt_parse(arg);
@@ -240,9 +245,11 @@ int main(int argc, const char **argv)
 		die("unable to read tree object %s", tree_name);
 
 	ret = diff_cache(active_cache, active_nr);
-	diffcore_std(pathspec,
+
+	diffcore_std(pathspec ? : NULL,
 		     detect_rename, diff_score_opt,
-		     pickaxe, pickaxe_opts);
+		     pickaxe, pickaxe_opts,
+		     diff_break_opt);
 	diff_flush(diff_output_format, 1);
 	return ret;
 }

diff-files.c

@@ -15,6 +15,7 @@ static int diff_setup_opt = 0;
 static int diff_score_opt = 0;
 static const char *pickaxe = NULL;
 static int pickaxe_opts = 0;
+static int diff_break_opt = -1;
 static int silent = 0;
 
 static void show_unmerge(const char *path)
@@ -57,6 +58,8 @@ int main(int argc, const char **argv)
 			pickaxe = argv[1] + 2;
 		else if (!strcmp(argv[1], "--pickaxe-all"))
 			pickaxe_opts = DIFF_PICKAXE_ALL;
+		else if (!strncmp(argv[1], "-B", 2))
+			diff_break_opt = diff_scoreopt_parse(argv[1]);
 		else if (!strncmp(argv[1], "-M", 2)) {
 			diff_score_opt = diff_scoreopt_parse(argv[1]);
 			detect_rename = DIFF_DETECT_RENAME;
@@ -116,9 +119,10 @@ int main(int argc, const char **argv)
 		show_modified(oldmode, mode, ce->sha1, null_sha1,
 			      ce->name);
 	}
-	diffcore_std(argv + 1,
+	diffcore_std((1 < argc) ? argv + 1 : NULL,
 		     detect_rename, diff_score_opt,
-		     pickaxe, pickaxe_opts);
+		     pickaxe, pickaxe_opts,
+		     diff_break_opt);
 	diff_flush(diff_output_format, 1);
 	return 0;
 }

diff-tree.c

@@ -14,6 +14,7 @@ static int diff_setup_opt = 0;
 static int diff_score_opt = 0;
 static const char *pickaxe = NULL;
 static int pickaxe_opts = 0;
+static int diff_break_opt = -1;
 static const char *header = NULL;
 static const char *header_prefix = "";
 
@@ -263,7 +264,8 @@ static int call_diff_flush(void)
 {
 	diffcore_std(0,
 		     detect_rename, diff_score_opt,
-		     pickaxe, pickaxe_opts);
+		     pickaxe, pickaxe_opts,
+		     diff_break_opt);
 	if (diff_queue_is_empty()) {
 		diff_flush(DIFF_FORMAT_NO_OUTPUT, 0);
 		return 0;
@@ -523,6 +525,10 @@ int main(int argc, const char **argv)
 			diff_score_opt = diff_scoreopt_parse(arg);
 			continue;
 		}
+		if (!strncmp(arg, "-B", 2)) {
+			diff_break_opt = diff_scoreopt_parse(arg);
+			continue;
+		}
 		if (!strcmp(arg, "-z")) {
 			diff_output_format = DIFF_FORMAT_MACHINE;
 			continue;

diff.c

@@ -603,6 +603,7 @@ struct diff_filepair *diff_queue(struct diff_queue_struct *queue,
 	dp->two = two;
 	dp->score = 0;
 	dp->source_stays = 0;
+	dp->broken_pair = 0;
 	diff_q(queue, dp);
 	return dp;
 }
@@ -637,6 +638,16 @@ static void diff_flush_raw(struct diff_filepair *p,
 		sprintf(status, "%c%03d", p->status,
 			(int)(0.5 + p->score * 100.0/MAX_SCORE));
 		break;
+	case 'N': case 'D':
+		two_paths = 0;
+		if (p->score)
+			sprintf(status, "%c%03d", p->status,
+				(int)(0.5 + p->score * 100.0/MAX_SCORE));
+		else {
+			status[0] = p->status;
+			status[1] = 0;
+		}
+		break;
 	default:
 		two_paths = 0;
 		status[0] = p->status;
@@ -760,8 +771,9 @@ void diff_debug_filepair(const struct diff_filepair *p, int i)
 {
 	diff_debug_filespec(p->one, i, "one");
 	diff_debug_filespec(p->two, i, "two");
-	fprintf(stderr, "score %d, status %c source_stays %d\n",
-		p->score, p->status ? : '?', p->source_stays);
+	fprintf(stderr, "score %d, status %c stays %d broken %d\n",
+		p->score, p->status ? : '?',
+		p->source_stays, p->broken_pair);
 }
 
 void diff_debug_queue(const char *msg, struct diff_queue_struct *q)
@@ -875,10 +887,13 @@ void diff_flush(int diff_output_style, int resolve_rename_copy)
 
 void diffcore_std(const char **paths,
 		  int detect_rename, int rename_score,
-		  const char *pickaxe, int pickaxe_opts)
+		  const char *pickaxe, int pickaxe_opts,
+		  int break_opt)
 {
 	if (paths && paths[0])
 		diffcore_pathspec(paths);
+	if (0 <= break_opt)
+		diffcore_break(break_opt);
 	if (detect_rename)
 		diffcore_rename(detect_rename, rename_score);
 	if (pickaxe)

diff.h

@@ -43,9 +43,12 @@ extern void diffcore_pickaxe(const char *needle, int opts);
 
 extern void diffcore_pathspec(const char **pathspec);
 
+extern void diffcore_break(int);
+
 extern void diffcore_std(const char **paths,
 			 int detect_rename, int rename_score,
-			 const char *pickaxe, int pickaxe_opts);
+			 const char *pickaxe, int pickaxe_opts,
+			 int break_opt);
 
 extern int diff_queue_is_empty(void);
 

diffcore-break.c

@@ -0,0 +1,127 @@
+/*
+ * Copyright (C) 2005 Junio C Hamano
+ */
+#include "cache.h"
+#include "diff.h"
+#include "diffcore.h"
+#include "delta.h"
+#include "count-delta.h"
+
+static int very_different(struct diff_filespec *src,
+			  struct diff_filespec *dst,
+			  int min_score)
+{
+	/* dst is recorded as a modification of src.  Are they so
+	 * different that we are better off recording this as a pair
+	 * of delete and create?  min_score is the minimum amount of
+	 * new material that must exist in the dst and not in src for
+	 * the pair to be considered a complete rewrite, and recommended
+	 * to be set to a very high value, 99% or so.
+	 *
+	 * The value we return represents the amount of new material
+	 * that is in dst and not in src.  We return 0 when we do not
+	 * want to get the filepair broken.
+	 */
+	void *delta;
+	unsigned long delta_size, base_size;
+
+	if (!S_ISREG(src->mode) || !S_ISREG(dst->mode))
+		return 0; /* leave symlink rename alone */
+
+	if (diff_populate_filespec(src, 1) || diff_populate_filespec(dst, 1))
+		return 0; /* error but caught downstream */
+
+	delta_size = ((src->size < dst->size) ?
+		      (dst->size - src->size) : (src->size - dst->size));
+
+	/* Notice that we use max of src and dst as the base size,
+	 * unlike rename similarity detection.  This is so that we do
+	 * not mistake a large addition as a complete rewrite.
+	 */
+	base_size = ((src->size < dst->size) ? dst->size : src->size);
+
+	/*
+	 * If file size difference is too big compared to the
+	 * base_size, we declare this a complete rewrite.
+	 */
+	if (base_size * min_score < delta_size * MAX_SCORE)
+		return MAX_SCORE;
+
+	if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
+		return 0; /* error but caught downstream */
+
+	delta = diff_delta(src->data, src->size,
+			   dst->data, dst->size,
+			   &delta_size);
+
+	/* A delta that has a lot of literal additions would have
+	 * big delta_size no matter what else it does.
+	 */
+	if (base_size * min_score < delta_size * MAX_SCORE)
+		return MAX_SCORE;
+
+	/* Estimate the edit size by interpreting delta. */
+	delta_size = count_delta(delta, delta_size);
+	free(delta);
+	if (delta_size == UINT_MAX)
+		return 0; /* error in delta computation */
+
+	if (base_size < delta_size)
+		return MAX_SCORE;
+
+	return delta_size * MAX_SCORE / base_size; 
+}
+
+void diffcore_break(int min_score)
+{
+	struct diff_queue_struct *q = &diff_queued_diff;
+	struct diff_queue_struct outq;
+	int i;
+
+	if (!min_score)
+		min_score = DEFAULT_BREAK_SCORE;
+
+	outq.nr = outq.alloc = 0;
+	outq.queue = NULL;
+
+	for (i = 0; i < q->nr; i++) {
+		struct diff_filepair *p = q->queue[i];
+		int score;
+
+		/* We deal only with in-place edit of non directory.
+		 * We do not break anything else.
+		 */
+		if (DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two) &&
+		    !S_ISDIR(p->one->mode) && !S_ISDIR(p->two->mode) &&
+		    !strcmp(p->one->path, p->two->path)) {
+			score = very_different(p->one, p->two, min_score);
+			if (min_score <= score) {
+				/* Split this into delete and create */
+				struct diff_filespec *null_one, *null_two;
+				struct diff_filepair *dp;
+
+				/* deletion of one */
+				null_one = alloc_filespec(p->one->path);
+				dp = diff_queue(&outq, p->one, null_one);
+				dp->score = score;
+				dp->broken_pair = 1;
+
+				/* creation of two */
+				null_two = alloc_filespec(p->two->path);
+				dp = diff_queue(&outq, null_two, p->two);
+				dp->score = score;
+				dp->broken_pair = 1;
+
+				free(p); /* not diff_free_filepair(), we are
+					  * reusing one and two here.
+					  */
+				continue;
+			}
+		}
+		diff_q(&outq, p);
+	}
+	free(q->queue);
+	*q = outq;
+
+	return;
+}