[PATCH] Make -C less eager.

Like diff-tree, this patch makes -C option for diff-* brothers
to use only pre-image of modified files as rename/copy detection
by default.  Give --find-copies-harder to use unmodified files
to find copies from as well.

This also fixes "diff-files -C" problem earlier noticed by
Linus.  It was feeding the null sha1 even when the file in the
work tree was known to match what is in the index file.  This
resulted in diff-files showing everything in the project.

Signed-off-by: Junio C Hamano <junkio@cox.net>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

8 files changed, 37 insertions, 18 deletions

diff --git a/diff-cache.c b/diff-cache.c
index 13baaa3721..603a6b7774 100644
--- a/diff-cache.c
+++ b/diff-cache.c
@@ -5,6 +5,7 @@ static int cached_only = 0;
 static int diff_output_format = DIFF_FORMAT_HUMAN;
 static int match_nonexisting = 0;
 static int detect_rename = 0;
+static int find_copies_harder = 0;
 static int diff_setup_opt = 0;
 static int diff_score_opt = 0;
 static const char *pickaxe = NULL;
@@ -75,7 +76,7 @@ static int show_modified(struct cache_entry *old,
 
 	oldmode = old->ce_mode;
 	if (mode == oldmode && !memcmp(sha1, old->sha1, 20) &&
-	    detect_rename < DIFF_DETECT_COPY)
+	    !find_copies_harder)
 		return 0;
 
 	mode = ntohl(mode);
@@ -158,7 +159,7 @@ static void mark_merge_entries(void)
 }
 
 static char *diff_cache_usage =
-"git-diff-cache [-p] [-r] [-z] [-m] [-M] [-C] [-R] [-S<string>] [-O<orderfile>] [--cached] <tree-ish> [<path>...]";
+"git-diff-cache [-p] [-r] [-z] [-m] [--cached] [-R] [-B] [-M] [-C] [--find-copies-harder] [-O<orderfile>] [-S<string>] [--pickaxe-all] <tree-ish> [<path>...]";
 
 int main(int argc, const char **argv)
 {
@@ -213,6 +214,10 @@ int main(int argc, const char **argv)
 				usage(diff_cache_usage);
 			continue;
 		}
+		if (!strcmp(arg, "--find-copies-harder")) {
+			find_copies_harder = 1;
+			continue;
+		}
 		if (!strcmp(arg, "-z")) {
 			diff_output_format = DIFF_FORMAT_MACHINE;
 			continue;
@@ -248,6 +253,9 @@ int main(int argc, const char **argv)
 		usage(diff_cache_usage);
 	}
 
+	if (find_copies_harder && detect_rename != DIFF_DETECT_COPY)
+		usage(diff_cache_usage);
+
 	if (!tree_name || get_sha1(tree_name, sha1))
 		usage(diff_cache_usage);
 
diff --git a/diff-files.c b/diff-files.c
index b6d972e062..4d60017e46 100644
--- a/diff-files.c
+++ b/diff-files.c
@@ -7,10 +7,11 @@
 #include "diff.h"
 
 static const char *diff_files_usage =
-"git-diff-files [-p] [-q] [-r] [-z] [-M] [-C] [-R] [-S<string>] [-O<orderfile>] [paths...]";
+"git-diff-files [-p] [-q] [-r] [-z] [-R] [-B] [-M] [-C] [--find-copies-harder] [-O<orderfile>] [-S<string>] [--pickaxe-all] [<path>...]";
 
 static int diff_output_format = DIFF_FORMAT_HUMAN;
 static int detect_rename = 0;
+static int find_copies_harder = 0;
 static int diff_setup_opt = 0;
 static int diff_score_opt = 0;
 static const char *pickaxe = NULL;
@@ -81,11 +82,16 @@ int main(int argc, const char **argv)
 				usage(diff_files_usage);
 			detect_rename = DIFF_DETECT_COPY;
 		}
+		else if (!strcmp(argv[1], "--find-copies-harder"))
+			find_copies_harder = 1;
 		else
 			usage(diff_files_usage);
 		argv++; argc--;
 	}
 
+	if (find_copies_harder && detect_rename != DIFF_DETECT_COPY)
+		usage(diff_files_usage);
+
 	/* At this point, if argc == 1, then we are doing everything.
 	 * Otherwise argv[1] .. argv[argc-1] have the explicit paths.
 	 */
@@ -122,12 +128,11 @@ int main(int argc, const char **argv)
 			continue;
 		}
 		changed = ce_match_stat(ce, &st);
-		if (!changed && detect_rename < DIFF_DETECT_COPY)
+		if (!changed && !find_copies_harder)
 			continue;
-
 		oldmode = ntohl(ce->ce_mode);
 		show_modified(oldmode, DIFF_FILE_CANON_MODE(st.st_mode),
-			      ce->sha1, null_sha1,
+			      ce->sha1, (changed ? null_sha1 : ce->sha1),
 			      ce->name);
 	}
 	diffcore_std((1 < argc) ? argv + 1 : NULL,
diff --git a/diff-stages.c b/diff-stages.c
index 4b87c8ef7b..f0998149cf 100644
--- a/diff-stages.c
+++ b/diff-stages.c
@@ -7,6 +7,7 @@
 
 static int diff_output_format = DIFF_FORMAT_HUMAN;
 static int detect_rename = 0;
+static int find_copies_harder = 0;
 static int diff_setup_opt = 0;
 static int diff_score_opt = 0;
 static const char *pickaxe = NULL;
@@ -16,7 +17,7 @@ static const char *orderfile = NULL;
 static const char *diff_filter = NULL;
 
 static char *diff_stages_usage =
-"git-diff-stages [-p] [-r] [-z] [-M] [-C] [-R] [-S<string>] [-O<orderfile>] <stage1> <stage2> [<path>...]";
+"git-diff-stages [-p] [-r] [-z] [-R] [-B] [-M] [-C] [--find-copies-harder] [-O<orderfile>] [-S<string>] [--pickaxe-all] <stage1> <stage2> [<path>...]";
 
 static void diff_stages(int stage1, int stage2)
 {
@@ -50,9 +51,10 @@ static void diff_stages(int stage1, int stage2)
 			diff_addremove('-', ntohl(one->ce_mode),
 				       one->sha1, name, NULL);
 		else if (memcmp(one->sha1, two->sha1, 20) ||
-			 (one->ce_mode != two->ce_mode))
-			 diff_change(ntohl(one->ce_mode), ntohl(two->ce_mode),
-				     one->sha1, two->sha1, name, NULL);
+			 (one->ce_mode != two->ce_mode) ||
+			 find_copies_harder)
+			diff_change(ntohl(one->ce_mode), ntohl(two->ce_mode),
+				    one->sha1, two->sha1, name, NULL);
 	}
 }
 
@@ -81,6 +83,8 @@ int main(int ac, const char **av)
 			if ((diff_score_opt = diff_scoreopt_parse(arg)) == -1)
 				usage(diff_stages_usage);
 		}
+		else if (!strcmp(arg, "--find-copies-harder"))
+			find_copies_harder = 1;
 		else if (!strcmp(arg, "-z"))
 			diff_output_format = DIFF_FORMAT_MACHINE;
 		else if (!strcmp(arg, "-R"))
@@ -102,7 +106,8 @@ int main(int ac, const char **av)
 	    sscanf(av[1], "%d", &stage1) != 1 ||
 	    ! (0 <= stage1 && stage1 <= 3) ||
 	    sscanf(av[2], "%d", &stage2) != 1 ||
-	    ! (0 <= stage2 && stage2 <= 3))
+	    ! (0 <= stage2 && stage2 <= 3) ||
+	    find_copies_harder && detect_rename != DIFF_DETECT_COPY)
 		usage(diff_stages_usage);
 
 	av += 3; /* The rest from av[0] are for paths restriction. */
diff --git a/diff-tree.c b/diff-tree.c
index 2075715350..7446e09af4 100644
--- a/diff-tree.c
+++ b/diff-tree.c
@@ -201,7 +201,7 @@ static int interesting(void *tree, unsigned long size, const char *base)
 static void show_tree(const char *prefix, void *tree, unsigned long size, const char *base)
 {
 	while (size) {
-		if (find_copies_harder || interesting(tree, size, base))
+		if (interesting(tree, size, base))
 			show_file(prefix, tree, size, base);
 		update_tree_entry(&tree, &size);
 	}
@@ -269,7 +269,7 @@ static void call_diff_setup(void)
 
 static int call_diff_flush(void)
 {
-	diffcore_std(find_copies_harder ? paths : 0,
+	diffcore_std(NULL,
 		     detect_rename, diff_score_opt,
 		     pickaxe, pickaxe_opts,
 		     diff_break_opt,
@@ -401,7 +401,7 @@ static int diff_tree_stdin(char *line)
 }
 
 static char *diff_tree_usage =
-"git-diff-tree [-p] [-r] [-z] [--stdin] [-M] [-C] [-R] [-S<string>] [-O<orderfile>] [-m] [-s] [-v] [--pretty] [-t] <tree-ish> <tree-ish>";
+"git-diff-tree [-p] [-r] [-z] [--stdin] [-m] [-s] [-v] [--pretty] [-t] [-R] [-B] [-M] [-C] [--find-copies-header] [-O<orderfile>] [-S<string>] [--pickaxe-all] <tree-ish> <tree-ish>";
 
 static enum cmit_fmt get_commit_format(const char *arg)
 {
diff --git a/t/t4003-diff-rename-1.sh b/t/t4003-diff-rename-1.sh
index 63a3103b4b..8e3091abb6 100644
--- a/t/t4003-diff-rename-1.sh
+++ b/t/t4003-diff-rename-1.sh
@@ -108,7 +108,8 @@ test_expect_success \
 # the diff-core.  Unchanged rezrov, although being fed to
 # git-diff-cache as well, should not be mentioned.
 
-GIT_DIFF_OPTS=--unified=0 git-diff-cache -C -p $tree >current
+GIT_DIFF_OPTS=--unified=0 \
+    git-diff-cache -C --find-copies-harder -p $tree >current
 cat >expected <<\EOF
 diff --git a/COPYING b/COPYING.1
 copy from COPYING
diff --git a/t/t4005-diff-rename-2.sh b/t/t4005-diff-rename-2.sh
index 1921299fbc..cee06e4c5d 100644
--- a/t/t4005-diff-rename-2.sh
+++ b/t/t4005-diff-rename-2.sh
@@ -136,7 +136,7 @@ test_expect_success \
     'cat ../../COPYING >COPYING &&
      git-update-cache --add --remove COPYING COPYING.1'
 
-git-diff-cache -C $tree >current
+git-diff-cache -C --find-copies-harder $tree >current
 cat >expected <<\EOF
 :100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 0603b3238a076dc6c8022aedc6648fa523a17178 C1234	COPYING	COPYING.1
 EOF
diff --git a/t/t4007-rename-3.sh b/t/t4007-rename-3.sh
index a55d6b65d1..ab83ea3b8a 100644
--- a/t/t4007-rename-3.sh
+++ b/t/t4007-rename-3.sh
@@ -26,7 +26,7 @@ test_expect_success \
 # path1 both have COPYING and the latter is a copy of path0/COPYING.
 # Comparing the full tree with cache should tell us so.
 
-git-diff-cache -C $tree >current
+git-diff-cache -C --find-copies-harder $tree >current
 
 cat >expected <<\EOF
 :100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 6ff87c4664981e4397625791c8ea3bbb5f2279a3 C100	path0/COPYING	path1/COPYING
diff --git a/t/t4009-diff-rename-4.sh b/t/t4009-diff-rename-4.sh
index 318915f447..6229a5bf1a 100644
--- a/t/t4009-diff-rename-4.sh
+++ b/t/t4009-diff-rename-4.sh
@@ -143,7 +143,7 @@ test_expect_success \
     'cat ../../COPYING >COPYING &&
      git-update-cache --add --remove COPYING COPYING.1'
 
-git-diff-cache -z -C $tree >current
+git-diff-cache -z -C --find-copies-harder $tree >current
 cat >expected <<\EOF
 :100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 0603b3238a076dc6c8022aedc6648fa523a17178 C1234
 COPYING