Merge branch 'jc/cache-tree'

* jc/cache-tree:
  Avoid "diff-index --cached" optimization under --find-copies-harder
  Optimize "diff-index --cached" using cache-tree
  t4007: modernize the style
  cache-tree.c::cache_tree_find(): simplify internal API
  write-tree --ignore-cache-tree

7 files changed, 117 insertions, 44 deletions

diff --git a/builtin-write-tree.c b/builtin-write-tree.c
index 9d640508d..3a24ce815 100644
--- a/builtin-write-tree.c
+++ b/builtin-write-tree.c
@@ -13,7 +13,7 @@ static const char write_tree_usage[] =
 
 int cmd_write_tree(int argc, const char **argv, const char *unused_prefix)
 {
-	int missing_ok = 0, ret;
+	int flags = 0, ret;
 	const char *prefix = NULL;
 	unsigned char sha1[20];
 	const char *me = "git-write-tree";
@@ -22,9 +22,15 @@ int cmd_write_tree(int argc, const char **argv, const char *unused_prefix)
 	while (1 < argc) {
 		const char *arg = argv[1];
 		if (!strcmp(arg, "--missing-ok"))
-			missing_ok = 1;
+			flags |= WRITE_TREE_MISSING_OK;
 		else if (!prefixcmp(arg, "--prefix="))
 			prefix = arg + 9;
+		else if (!prefixcmp(arg, "--ignore-cache-tree"))
+			/*
+			 * This is only useful for debugging, so I
+			 * do not bother documenting it.
+			 */
+			flags |= WRITE_TREE_IGNORE_CACHE_TREE;
 		else
 			usage(write_tree_usage);
 		argc--; argv++;
@@ -33,7 +39,7 @@ int cmd_write_tree(int argc, const char **argv, const char *unused_prefix)
 	if (argc > 2)
 		die("too many options");
 
-	ret = write_cache_as_tree(sha1, missing_ok, prefix);
+	ret = write_cache_as_tree(sha1, flags, prefix);
 	switch (ret) {
 	case 0:
 		printf("%s\n", sha1_to_hex(sha1));
diff --git a/cache-tree.c b/cache-tree.c
index 37bf35e63..16a65dfac 100644
--- a/cache-tree.c
+++ b/cache-tree.c
@@ -514,6 +514,8 @@ struct cache_tree *cache_tree_read(const char *buffer, unsigned long size)
 
 static struct cache_tree *cache_tree_find(struct cache_tree *it, const char *path)
 {
+	if (!it)
+		return NULL;
 	while (*path) {
 		const char *slash;
 		struct cache_tree_sub *sub;
@@ -538,28 +540,32 @@ static struct cache_tree *cache_tree_find(struct cache_tree *it, const char *pat
 	return it;
 }
 
-int write_cache_as_tree(unsigned char *sha1, int missing_ok, const char *prefix)
+int write_cache_as_tree(unsigned char *sha1, int flags, const char *prefix)
 {
 	int entries, was_valid, newfd;
+	struct lock_file *lock_file;
 
 	/*
 	 * We can't free this memory, it becomes part of a linked list
 	 * parsed atexit()
 	 */
-	struct lock_file *lock_file = xcalloc(1, sizeof(struct lock_file));
+	lock_file = xcalloc(1, sizeof(struct lock_file));
 
 	newfd = hold_locked_index(lock_file, 1);
 
 	entries = read_cache();
 	if (entries < 0)
 		return WRITE_TREE_UNREADABLE_INDEX;
+	if (flags & WRITE_TREE_IGNORE_CACHE_TREE)
+		cache_tree_free(&(active_cache_tree));
 
 	if (!active_cache_tree)
 		active_cache_tree = cache_tree();
 
 	was_valid = cache_tree_fully_valid(active_cache_tree);
-
 	if (!was_valid) {
+		int missing_ok = flags & WRITE_TREE_MISSING_OK;
+
 		if (cache_tree_update(active_cache_tree,
 				      active_cache, active_nr,
 				      missing_ok, 0) < 0)
@@ -625,3 +631,35 @@ void prime_cache_tree(struct cache_tree **it, struct tree *tree)
 	*it = cache_tree();
 	prime_cache_tree_rec(*it, tree);
 }
+
+/*
+ * find the cache_tree that corresponds to the current level without
+ * exploding the full path into textual form.  The root of the
+ * cache tree is given as "root", and our current level is "info".
+ * (1) When at root level, info->prev is NULL, so it is "root" itself.
+ * (2) Otherwise, find the cache_tree that corresponds to one level
+ *     above us, and find ourselves in there.
+ */
+static struct cache_tree *find_cache_tree_from_traversal(struct cache_tree *root,
+							 struct traverse_info *info)
+{
+	struct cache_tree *our_parent;
+
+	if (!info->prev)
+		return root;
+	our_parent = find_cache_tree_from_traversal(root, info->prev);
+	return cache_tree_find(our_parent, info->name.path);
+}
+
+int cache_tree_matches_traversal(struct cache_tree *root,
+				 struct name_entry *ent,
+				 struct traverse_info *info)
+{
+	struct cache_tree *it;
+
+	it = find_cache_tree_from_traversal(root, info);
+	it = cache_tree_find(it, ent->path);
+	if (it && it->entry_count > 0 && !hashcmp(ent->sha1, it->sha1))
+		return it->entry_count;
+	return 0;
+}
diff --git a/cache-tree.h b/cache-tree.h
index e95883523..3df641f59 100644
--- a/cache-tree.h
+++ b/cache-tree.h
@@ -2,6 +2,7 @@
 #define CACHE_TREE_H
 
 #include "tree.h"
+#include "tree-walk.h"
 
 struct cache_tree;
 struct cache_tree_sub {
@@ -30,11 +31,18 @@ struct cache_tree *cache_tree_read(const char *buffer, unsigned long size);
 int cache_tree_fully_valid(struct cache_tree *);
 int cache_tree_update(struct cache_tree *, struct cache_entry **, int, int, int);
 
+/* bitmasks to write_cache_as_tree flags */
+#define WRITE_TREE_MISSING_OK 1
+#define WRITE_TREE_IGNORE_CACHE_TREE 2
+
+/* error return codes */
 #define WRITE_TREE_UNREADABLE_INDEX (-1)
 #define WRITE_TREE_UNMERGED_INDEX (-2)
 #define WRITE_TREE_PREFIX_ERROR (-3)
 
-int write_cache_as_tree(unsigned char *sha1, int missing_ok, const char *prefix);
+int write_cache_as_tree(unsigned char *sha1, int flags, const char *prefix);
 void prime_cache_tree(struct cache_tree **, struct tree *);
 
+extern int cache_tree_matches_traversal(struct cache_tree *, struct name_entry *ent, struct traverse_info *info);
+
 #endif
diff --git a/diff-lib.c b/diff-lib.c
index 0aba6cda3..ad2a4cde7 100644
--- a/diff-lib.c
+++ b/diff-lib.c
@@ -446,6 +446,8 @@ int run_diff_index(struct rev_info *revs, int cached)
 	memset(&opts, 0, sizeof(opts));
 	opts.head_idx = 1;
 	opts.index_only = cached;
+	opts.diff_index_cached = (cached &&
+				  !DIFF_OPT_TST(&revs->diffopt, FIND_COPIES_HARDER));
 	opts.merge = 1;
 	opts.fn = oneway_diff;
 	opts.unpack_data = revs;
@@ -502,6 +504,7 @@ int do_diff_cache(const unsigned char *tree_sha1, struct diff_options *opt)
 	memset(&opts, 0, sizeof(opts));
 	opts.head_idx = 1;
 	opts.index_only = 1;
+	opts.diff_index_cached = !DIFF_OPT_TST(opt, FIND_COPIES_HARDER);
 	opts.merge = 1;
 	opts.fn = oneway_diff;
 	opts.unpack_data = &revs;
diff --git a/t/t4007-rename-3.sh b/t/t4007-rename-3.sh
index 42072d724..11502b750 100755
--- a/t/t4007-rename-3.sh
+++ b/t/t4007-rename-3.sh
@@ -9,32 +9,36 @@ test_description='Rename interaction with pathspec.
 . ./test-lib.sh
 . "$TEST_DIRECTORY"/diff-lib.sh ;# test-lib chdir's into trash
 
-test_expect_success \
-    'prepare reference tree' \
-    'mkdir path0 path1 &&
-     cp "$TEST_DIRECTORY"/../COPYING path0/COPYING &&
-     git update-index --add path0/COPYING &&
-    tree=$(git write-tree) &&
-    echo $tree'
-
-test_expect_success \
-    'prepare work tree' \
-    'cp path0/COPYING path1/COPYING &&
-     git update-index --add --remove path0/COPYING path1/COPYING'
+test_expect_success 'prepare reference tree' '
+	mkdir path0 path1 &&
+	cp "$TEST_DIRECTORY"/../COPYING path0/COPYING &&
+	git update-index --add path0/COPYING &&
+	tree=$(git write-tree) &&
+	echo $tree
+'
+
+test_expect_success 'prepare work tree' '
+	cp path0/COPYING path1/COPYING &&
+	git update-index --add --remove path0/COPYING path1/COPYING
+'
 
 # In the tree, there is only path0/COPYING.  In the cache, path0 and
 # 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-index -C --find-copies-harder $tree >current
-
 cat >expected <<\EOF
 :100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 6ff87c4664981e4397625791c8ea3bbb5f2279a3 C100	path0/COPYING	path1/COPYING
 EOF
 
-test_expect_success \
-    'validate the result (#1)' \
-    'compare_diff_raw current expected'
+test_expect_success 'copy detection' '
+	git diff-index -C --find-copies-harder $tree >current &&
+	compare_diff_raw current expected
+'
+
+test_expect_success 'copy detection, cached' '
+	git diff-index -C --find-copies-harder --cached $tree >current &&
+	compare_diff_raw current expected
+'
 
 # In the tree, there is only path0/COPYING.  In the cache, path0 and
 # path1 both have COPYING and the latter is a copy of path0/COPYING.
@@ -42,49 +46,45 @@ test_expect_success \
 # path1/COPYING suddenly appearing from nowhere, not detected as
 # a copy from path0/COPYING.
 
-git diff-index -C $tree path1 >current
-
 cat >expected <<\EOF
 :000000 100644 0000000000000000000000000000000000000000 6ff87c4664981e4397625791c8ea3bbb5f2279a3 A	path1/COPYING
 EOF
 
-test_expect_success \
-    'validate the result (#2)' \
-    'compare_diff_raw current expected'
-
-test_expect_success \
-    'tweak work tree' \
-    'rm -f path0/COPYING &&
-     git update-index --remove path0/COPYING'
+test_expect_success 'copy, limited to a subtree' '
+	git diff-index -C --find-copies-harder $tree path1 >current &&
+	compare_diff_raw current expected
+'
 
+test_expect_success 'tweak work tree' '
+	rm -f path0/COPYING &&
+	git update-index --remove path0/COPYING
+'
 # In the tree, there is only path0/COPYING.  In the cache, path0 does
 # not have COPYING anymore and path1 has COPYING which is a copy of
 # path0/COPYING.  Showing the full tree with cache should tell us about
 # the rename.
 
-git diff-index -C $tree >current
-
 cat >expected <<\EOF
 :100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 6ff87c4664981e4397625791c8ea3bbb5f2279a3 R100	path0/COPYING	path1/COPYING
 EOF
 
-test_expect_success \
-    'validate the result (#3)' \
-    'compare_diff_raw current expected'
+test_expect_success 'rename detection' '
+	git diff-index -C --find-copies-harder $tree >current &&
+	compare_diff_raw current expected
+'
 
 # In the tree, there is only path0/COPYING.  In the cache, path0 does
 # not have COPYING anymore and path1 has COPYING which is a copy of
 # path0/COPYING.  When we say we care only about path1, we should just
 # see path1/COPYING appearing from nowhere.
 
-git diff-index -C $tree path1 >current
-
 cat >expected <<\EOF
 :000000 100644 0000000000000000000000000000000000000000 6ff87c4664981e4397625791c8ea3bbb5f2279a3 A	path1/COPYING
 EOF
 
-test_expect_success \
-    'validate the result (#4)' \
-    'compare_diff_raw current expected'
+test_expect_success 'rename, limited to a subtree' '
+	git diff-index -C --find-copies-harder $tree path1 >current &&
+	compare_diff_raw current expected
+'
 
 test_done
diff --git a/unpack-trees.c b/unpack-trees.c
index aaacaf101..8eb3ddb39 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -326,6 +326,23 @@ static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, str
 			if (src[0])
 				conflicts |= 1;
 		}
+
+		/* special case: "diff-index --cached" looking at a tree */
+		if (o->diff_index_cached &&
+		    n == 1 && dirmask == 1 && S_ISDIR(names->mode)) {
+			int matches;
+			matches = cache_tree_matches_traversal(o->src_index->cache_tree,
+							       names, info);
+			/*
+			 * Everything under the name matches.  Adjust o->pos to
+			 * skip the entire hierarchy.
+			 */
+			if (matches) {
+				o->pos += matches;
+				return mask;
+			}
+		}
+
 		if (traverse_trees_recursive(n, dirmask, conflicts,
 					     names, info) < 0)
 			return -1;
diff --git a/unpack-trees.h b/unpack-trees.h
index 0d26f3d73..1e0e2325f 100644
--- a/unpack-trees.h
+++ b/unpack-trees.h
@@ -27,6 +27,7 @@ struct unpack_trees_options {
 		     aggressive:1,
 		     skip_unmerged:1,
 		     initial_checkout:1,
+		     diff_index_cached:1,
 		     gently:1;
 	const char *prefix;
 	int pos;