Merge branch 'dt/cache-tree-repair'

Add a few more places in "commit" and "checkout" that make sure
that the cache-tree is fully populated in the index.

* dt/cache-tree-repair:
  cache-tree: do not try to use an invalidated subtree info to build a tree
  cache-tree: Write updated cache-tree after commit
  cache-tree: subdirectory tests
  test-dump-cache-tree: invalid trees are not errors
  cache-tree: create/update cache-tree on checkout

6 files changed, 184 insertions, 22 deletions

diff --git a/builtin/checkout.c b/builtin/checkout.c
index f71e74531d..8afdf2b5c4 100644
--- a/builtin/checkout.c
+++ b/builtin/checkout.c
@@ -552,6 +552,12 @@ static int merge_working_tree(const struct checkout_opts *opts,
 		}
 	}
 
+	if (!active_cache_tree)
+		active_cache_tree = cache_tree();
+
+	if (!cache_tree_fully_valid(active_cache_tree))
+		cache_tree_update(&the_index, WRITE_TREE_SILENT | WRITE_TREE_REPAIR);
+
 	if (write_locked_index(&the_index, lock_file, COMMIT_LOCK))
 		die(_("unable to write new index file"));
 
diff --git a/builtin/commit.c b/builtin/commit.c
index 5911447486..41f481bd03 100644
--- a/builtin/commit.c
+++ b/builtin/commit.c
@@ -353,6 +353,13 @@ static char *prepare_index(int argc, const char **argv, const char *prefix,
 
 		discard_cache();
 		read_cache_from(index_lock.filename);
+		if (update_main_cache_tree(WRITE_TREE_SILENT) == 0) {
+			if (reopen_lock_file(&index_lock) < 0)
+				die(_("unable to write index file"));
+			if (write_locked_index(&the_index, &index_lock, CLOSE_LOCK))
+				die(_("unable to update temporary index"));
+		} else
+			warning(_("Failed to update main cache tree"));
 
 		commit_style = COMMIT_NORMAL;
 		return index_lock.filename;
@@ -393,8 +400,12 @@ static char *prepare_index(int argc, const char **argv, const char *prefix,
 	if (!only && !pathspec.nr) {
 		hold_locked_index(&index_lock, 1);
 		refresh_cache_or_die(refresh_flags);
-		if (active_cache_changed) {
+		if (active_cache_changed
+		    || !cache_tree_fully_valid(active_cache_tree)) {
 			update_main_cache_tree(WRITE_TREE_SILENT);
+			active_cache_changed = 1;
+		}
+		if (active_cache_changed) {
 			if (write_locked_index(&the_index, &index_lock,
 					       COMMIT_LOCK))
 				die(_("unable to write new_index file"));
@@ -444,6 +455,7 @@ static char *prepare_index(int argc, const char **argv, const char *prefix,
 	hold_locked_index(&index_lock, 1);
 	add_remove_files(&partial);
 	refresh_cache(REFRESH_QUIET);
+	update_main_cache_tree(WRITE_TREE_SILENT);
 	if (write_locked_index(&the_index, &index_lock, CLOSE_LOCK))
 		die(_("unable to write new_index file"));
 
diff --git a/cache-tree.c b/cache-tree.c
index c53f7de2b1..75a54fdc72 100644
--- a/cache-tree.c
+++ b/cache-tree.c
@@ -246,9 +246,12 @@ static int update_one(struct cache_tree *it,
 	struct strbuf buffer;
 	int missing_ok = flags & WRITE_TREE_MISSING_OK;
 	int dryrun = flags & WRITE_TREE_DRY_RUN;
+	int repair = flags & WRITE_TREE_REPAIR;
 	int to_invalidate = 0;
 	int i;
 
+	assert(!(dryrun && repair));
+
 	*skip_count = 0;
 
 	if (0 <= it->entry_count && has_sha1_file(it->sha1))
@@ -320,6 +323,7 @@ static int update_one(struct cache_tree *it,
 		int pathlen, entlen;
 		const unsigned char *sha1;
 		unsigned mode;
+		int expected_missing = 0;
 
 		path = ce->name;
 		pathlen = ce_namelen(ce);
@@ -336,8 +340,10 @@ static int update_one(struct cache_tree *it,
 			i += sub->count;
 			sha1 = sub->cache_tree->sha1;
 			mode = S_IFDIR;
-			if (sub->cache_tree->entry_count < 0)
+			if (sub->cache_tree->entry_count < 0) {
 				to_invalidate = 1;
+				expected_missing = 1;
+			}
 		}
 		else {
 			sha1 = ce->sha1;
@@ -347,6 +353,8 @@ static int update_one(struct cache_tree *it,
 		}
 		if (mode != S_IFGITLINK && !missing_ok && !has_sha1_file(sha1)) {
 			strbuf_release(&buffer);
+			if (expected_missing)
+				return -1;
 			return error("invalid object %06o %s for '%.*s'",
 				mode, sha1_to_hex(sha1), entlen+baselen, path);
 		}
@@ -381,7 +389,14 @@ static int update_one(struct cache_tree *it,
 #endif
 	}
 
-	if (dryrun)
+	if (repair) {
+		unsigned char sha1[20];
+		hash_sha1_file(buffer.buf, buffer.len, tree_type, sha1);
+		if (has_sha1_file(sha1))
+			hashcpy(it->sha1, sha1);
+		else
+			to_invalidate = 1;
+	} else if (dryrun)
 		hash_sha1_file(buffer.buf, buffer.len, tree_type, it->sha1);
 	else if (write_sha1_file(buffer.buf, buffer.len, tree_type, it->sha1)) {
 		strbuf_release(&buffer);
diff --git a/cache-tree.h b/cache-tree.h
index b47ccec7f6..aa7b3e4a0a 100644
--- a/cache-tree.h
+++ b/cache-tree.h
@@ -39,6 +39,7 @@ int update_main_cache_tree(int);
 #define WRITE_TREE_IGNORE_CACHE_TREE 2
 #define WRITE_TREE_DRY_RUN 4
 #define WRITE_TREE_SILENT 8
+#define WRITE_TREE_REPAIR 16
 
 /* error return codes */
 #define WRITE_TREE_UNREADABLE_INDEX (-1)
diff --git a/t/t0090-cache-tree.sh b/t/t0090-cache-tree.sh
index 6c33e28ee8..f9648a8642 100755
--- a/t/t0090-cache-tree.sh
+++ b/t/t0090-cache-tree.sh
@@ -8,7 +8,7 @@ cache-tree extension.
  . ./test-lib.sh
 
 cmp_cache_tree () {
-	test-dump-cache-tree >actual &&
+	test-dump-cache-tree | sed -e '/#(ref)/d' >actual &&
 	sed "s/$_x40/SHA/" <actual >filtered &&
 	test_cmp "$1" filtered
 }
@@ -16,15 +16,40 @@ cmp_cache_tree () {
 # We don't bother with actually checking the SHA1:
 # test-dump-cache-tree already verifies that all existing data is
 # correct.
-test_shallow_cache_tree () {
-	printf "SHA  (%d entries, 0 subtrees)\n" $(git ls-files|wc -l) >expect &&
+generate_expected_cache_tree_rec () {
+	dir="$1${1:+/}" &&
+	parent="$2" &&
+	# ls-files might have foo/bar, foo/bar/baz, and foo/bar/quux
+	# We want to count only foo because it's the only direct child
+	subtrees=$(git ls-files|grep /|cut -d / -f 1|uniq) &&
+	subtree_count=$(echo "$subtrees"|awk '$1 {++c} END {print c}') &&
+	entries=$(git ls-files|wc -l) &&
+	printf "SHA $dir (%d entries, %d subtrees)\n" "$entries" "$subtree_count" &&
+	for subtree in $subtrees
+	do
+		cd "$subtree"
+		generate_expected_cache_tree_rec "$dir$subtree" "$dir" || return 1
+		cd ..
+	done &&
+	dir=$parent
+}
+
+generate_expected_cache_tree () {
+	(
+		generate_expected_cache_tree_rec
+	)
+}
+
+test_cache_tree () {
+	generate_expected_cache_tree >expect &&
 	cmp_cache_tree expect
 }
 
 test_invalid_cache_tree () {
-	echo "invalid                                   (0 subtrees)" >expect &&
-	printf "SHA #(ref)  (%d entries, 0 subtrees)\n" $(git ls-files|wc -l) >>expect &&
-	cmp_cache_tree expect
+	printf "invalid                                  %s ()\n" "" "$@" >expect &&
+	test-dump-cache-tree |
+	sed -n -e "s/[0-9]* subtrees//" -e '/#(ref)/d' -e '/^invalid /p' >actual &&
+	test_cmp expect actual
 }
 
 test_no_cache_tree () {
@@ -32,26 +57,59 @@ test_no_cache_tree () {
 	cmp_cache_tree expect
 }
 
-test_expect_failure 'initial commit has cache-tree' '
+test_expect_success 'initial commit has cache-tree' '
 	test_commit foo &&
-	test_shallow_cache_tree
+	test_cache_tree
 '
 
 test_expect_success 'read-tree HEAD establishes cache-tree' '
 	git read-tree HEAD &&
-	test_shallow_cache_tree
+	test_cache_tree
 '
 
 test_expect_success 'git-add invalidates cache-tree' '
 	test_when_finished "git reset --hard; git read-tree HEAD" &&
-	echo "I changed this file" > foo &&
+	echo "I changed this file" >foo &&
 	git add foo &&
 	test_invalid_cache_tree
 '
 
+test_expect_success 'git-add in subdir invalidates cache-tree' '
+	test_when_finished "git reset --hard; git read-tree HEAD" &&
+	mkdir dirx &&
+	echo "I changed this file" >dirx/foo &&
+	git add dirx/foo &&
+	test_invalid_cache_tree
+'
+
+cat >before <<\EOF
+SHA  (3 entries, 2 subtrees)
+SHA dir1/ (1 entries, 0 subtrees)
+SHA dir2/ (1 entries, 0 subtrees)
+EOF
+
+cat >expect <<\EOF
+invalid                                   (2 subtrees)
+invalid                                  dir1/ (0 subtrees)
+SHA dir2/ (1 entries, 0 subtrees)
+EOF
+
+test_expect_success 'git-add in subdir does not invalidate sibling cache-tree' '
+	git tag no-children &&
+	test_when_finished "git reset --hard no-children; git read-tree HEAD" &&
+	mkdir dir1 dir2 &&
+	test_commit dir1/a &&
+	test_commit dir2/b &&
+	echo "I changed this file" >dir1/a &&
+	cmp_cache_tree before &&
+	echo "I changed this file" >dir1/a &&
+	git add dir1/a &&
+	cmp_cache_tree expect
+'
+
 test_expect_success 'update-index invalidates cache-tree' '
 	test_when_finished "git reset --hard; git read-tree HEAD" &&
-	echo "I changed this file" > foo &&
+	echo "I changed this file" >foo &&
 	git update-index --add foo &&
 	test_invalid_cache_tree
 '
@@ -59,7 +117,7 @@ test_expect_success 'update-index invalidates cache-tree' '
 test_expect_success 'write-tree establishes cache-tree' '
 	test-scrap-cache-tree &&
 	git write-tree &&
-	test_shallow_cache_tree
+	test_cache_tree
 '
 
 test_expect_success 'test-scrap-cache-tree works' '
@@ -70,24 +128,94 @@ test_expect_success 'test-scrap-cache-tree works' '
 
 test_expect_success 'second commit has cache-tree' '
 	test_commit bar &&
-	test_shallow_cache_tree
+	test_cache_tree
+'
+
+test_expect_success 'commit --interactive gives cache-tree on partial commit' '
+	cat <<-\EOT >foo.c &&
+	int foo()
+	{
+		return 42;
+	}
+	int bar()
+	{
+		return 42;
+	}
+	EOT
+	git add foo.c &&
+	test_invalid_cache_tree &&
+	git commit -m "add a file" &&
+	test_cache_tree &&
+	cat <<-\EOT >foo.c &&
+	int foo()
+	{
+		return 43;
+	}
+	int bar()
+	{
+		return 44;
+	}
+	EOT
+	(echo p; echo 1; echo; echo s; echo n; echo y; echo q) |
+	git commit --interactive -m foo &&
+	test_cache_tree
+'
+
+test_expect_success 'commit in child dir has cache-tree' '
+	mkdir dir &&
+	>dir/child.t &&
+	git add dir/child.t &&
+	git commit -m dir/child.t &&
+	test_cache_tree
 '
 
 test_expect_success 'reset --hard gives cache-tree' '
 	test-scrap-cache-tree &&
 	git reset --hard &&
-	test_shallow_cache_tree
+	test_cache_tree
 '
 
 test_expect_success 'reset --hard without index gives cache-tree' '
 	rm -f .git/index &&
 	git reset --hard &&
-	test_shallow_cache_tree
+	test_cache_tree
 '
 
-test_expect_failure 'checkout gives cache-tree' '
+test_expect_success 'checkout gives cache-tree' '
+	git tag current &&
 	git checkout HEAD^ &&
-	test_shallow_cache_tree
+	test_cache_tree
+'
+
+test_expect_success 'checkout -b gives cache-tree' '
+	git checkout current &&
+	git checkout -b prev HEAD^ &&
+	test_cache_tree
+'
+
+test_expect_success 'checkout -B gives cache-tree' '
+	git checkout current &&
+	git checkout -B prev HEAD^ &&
+	test_cache_tree
+'
+
+test_expect_success 'partial commit gives cache-tree' '
+	git checkout -b partial no-children &&
+	test_commit one &&
+	test_commit two &&
+	echo "some change" >one.t &&
+	git add one.t &&
+	echo "some other change" >two.t &&
+	git commit two.t -m partial &&
+	test_cache_tree
+'
+
+test_expect_success 'no phantom error when switching trees' '
+	mkdir newdir &&
+	>newdir/one &&
+	git add newdir/one &&
+	git checkout 2>errors &&
+	! test -s errors
 '
 
 test_done
diff --git a/test-dump-cache-tree.c b/test-dump-cache-tree.c
index 330ba4f4dd..54c0872fcb 100644
--- a/test-dump-cache-tree.c
+++ b/test-dump-cache-tree.c
@@ -26,16 +26,16 @@ static int dump_cache_tree(struct cache_tree *it,
 		return 0;
 
 	if (it->entry_count < 0) {
+		/* invalid */
 		dump_one(it, pfx, "");
 		dump_one(ref, pfx, "#(ref) ");
-		if (it->subtree_nr != ref->subtree_nr)
-			errs = 1;
 	}
 	else {
 		dump_one(it, pfx, "");
 		if (hashcmp(it->sha1, ref->sha1) ||
 		    ref->entry_count != it->entry_count ||
 		    ref->subtree_nr != it->subtree_nr) {
+			/* claims to be valid but is lying */
 			dump_one(ref, pfx, "#(ref) ");
 			errs = 1;
 		}