Merge branch 'ds/status-with-sparse-index'

"git status" codepath learned to work with sparsely populated index
without hydrating it fully.

* ds/status-with-sparse-index:
  t1092: document bad sparse-checkout behavior
  fsmonitor: integrate with sparse index
  wt-status: expand added sparse directory entries
  status: use sparse-index throughout
  status: skip sparse-checkout percentage with sparse-index
  diff-lib: handle index diffs with sparse dirs
  dir.c: accept a directory as part of cone-mode patterns
  unpack-trees: unpack sparse directory entries
  unpack-trees: rename unpack_nondirectories()
  unpack-trees: compare sparse directories correctly
  unpack-trees: preserve cache_bottom
  t1092: add tests for status/add and sparse files
  t1092: expand repository data shape
  t1092: replace incorrect 'echo' with 'cat'
  sparse-index: include EXTENDED flag when expanding
  sparse-index: skip indexes with unmerged entries

builtin/commit.c

@@ -1517,6 +1517,9 @@ int cmd_status(int argc, const char **argv, const char *prefix)
 	if (argc == 2 && !strcmp(argv[1], "-h"))
 		usage_with_options(builtin_status_usage, builtin_status_options);
 
+	prepare_repo_settings(the_repository);
+	the_repository->settings.command_requires_full_index = 0;
+
 	status_init_config(&s, git_status_config);
 	argc = parse_options(argc, argv, prefix,
 			     builtin_status_options,

diff-lib.c

@@ -325,6 +325,11 @@ static void show_new_file(struct rev_info *revs,
 	unsigned dirty_submodule = 0;
 	struct index_state *istate = revs->diffopt.repo->index;
 
+	if (new_file && S_ISSPARSEDIR(new_file->ce_mode)) {
+		diff_tree_oid(NULL, &new_file->oid, new_file->name, &revs->diffopt);
+		return;
+	}
+
 	/*
 	 * New file in the index: it might actually be different in
 	 * the working tree.
@@ -347,6 +352,20 @@ static int show_modified(struct rev_info *revs,
 	unsigned dirty_submodule = 0;
 	struct index_state *istate = revs->diffopt.repo->index;
 
+	assert(S_ISSPARSEDIR(old_entry->ce_mode) ==
+	       S_ISSPARSEDIR(new_entry->ce_mode));
+
+	/*
+	 * If both are sparse directory entries, then expand the
+	 * modifications to the file level. If only one was a sparse
+	 * directory, then they appear as an add and delete instead of
+	 * a modification.
+	 */
+	if (S_ISSPARSEDIR(new_entry->ce_mode)) {
+		diff_tree_oid(&old_entry->oid, &new_entry->oid, new_entry->name, &revs->diffopt);
+		return 0;
+	}
+
 	if (get_stat_data(istate, new_entry, &oid, &mode, cached, match_missing,
 			  &dirty_submodule, &revs->diffopt) < 0) {
 		if (report_missing)

dir.c

@@ -1380,7 +1380,7 @@ enum pattern_match_result path_matches_pattern_list(
 	struct path_pattern *pattern;
 	struct strbuf parent_pathname = STRBUF_INIT;
 	int result = NOT_MATCHED;
-	const char *slash_pos;
+	size_t slash_pos;
 
 	if (!pl->use_cone_patterns) {
 		pattern = last_matching_pattern_from_list(pathname, pathlen, basename,
@@ -1401,21 +1401,35 @@ enum pattern_match_result path_matches_pattern_list(
 	strbuf_addch(&parent_pathname, '/');
 	strbuf_add(&parent_pathname, pathname, pathlen);
 
+	/*
+	 * Directory entries are matched if and only if a file
+	 * contained immediately within them is matched. For the
+	 * case of a directory entry, modify the path to create
+	 * a fake filename within this directory, allowing us to
+	 * use the file-base matching logic in an equivalent way.
+	 */
+	if (parent_pathname.len > 0 &&
+	    parent_pathname.buf[parent_pathname.len - 1] == '/') {
+		slash_pos = parent_pathname.len - 1;
+		strbuf_add(&parent_pathname, "-", 1);
+	} else {
+		const char *slash_ptr = strrchr(parent_pathname.buf, '/');
+		slash_pos = slash_ptr ? slash_ptr - parent_pathname.buf : 0;
+	}
+
 	if (hashmap_contains_path(&pl->recursive_hashmap,
 				  &parent_pathname)) {
 		result = MATCHED_RECURSIVE;
 		goto done;
 	}
 
-	slash_pos = strrchr(parent_pathname.buf, '/');
+	if (!slash_pos) {
-
-	if (slash_pos == parent_pathname.buf) {
 		/* include every file in root */
 		result = MATCHED;
 		goto done;
 	}
 
-	strbuf_setlen(&parent_pathname, slash_pos - parent_pathname.buf);
+	strbuf_setlen(&parent_pathname, slash_pos);
 
 	if (hashmap_contains_path(&pl->parent_hashmap, &parent_pathname)) {
 		result = MATCHED;

read-cache.c

@@ -1585,8 +1585,7 @@ int refresh_index(struct index_state *istate, unsigned int flags,
 	 */
 	preload_index(istate, pathspec, 0);
 	trace2_region_enter("index", "refresh", NULL);
-	/* TODO: audit for interaction with sparse-index. */
+
-	ensure_full_index(istate);
 	for (i = 0; i < istate->cache_nr; i++) {
 		struct cache_entry *ce, *new_entry;
 		int cache_errno = 0;
@@ -1601,6 +1600,13 @@ int refresh_index(struct index_state *istate, unsigned int flags,
 		if (ignore_skip_worktree && ce_skip_worktree(ce))
 			continue;
 
+		/*
+		 * If this entry is a sparse directory, then there isn't
+		 * any stat() information to update. Ignore the entry.
+		 */
+		if (S_ISSPARSEDIR(ce->ce_mode))
+			continue;
+
 		if (pathspec && !ce_path_match(istate, ce, pathspec, seen))
 			filtered = 1;
 

sparse-index.c

@@ -116,6 +116,17 @@ int set_sparse_index_config(struct repository *repo, int enable)
 	return res;
 }
 
+static int index_has_unmerged_entries(struct index_state *istate)
+{
+	int i;
+	for (i = 0; i < istate->cache_nr; i++) {
+		if (ce_stage(istate->cache[i]))
+			return 1;
+	}
+
+	return 0;
+}
+
 int convert_to_sparse(struct index_state *istate)
 {
 	int test_env;
@@ -152,6 +163,13 @@ int convert_to_sparse(struct index_state *istate)
 		return -1;
 	}
 
+	/*
+	 * NEEDSWORK: If we have unmerged entries, then stay full.
+	 * Unmerged entries prevent the cache-tree extension from working.
+	 */
+	if (index_has_unmerged_entries(istate))
+		return 0;
+
 	if (cache_tree_update(istate, 0)) {
 		warning(_("unable to update cache-tree, staying full"));
 		return -1;
@@ -168,6 +186,10 @@ int convert_to_sparse(struct index_state *istate)
 	cache_tree_free(&istate->cache_tree);
 	cache_tree_update(istate, 0);
 
+	istate->fsmonitor_has_run_once = 0;
+	FREE_AND_NULL(istate->fsmonitor_dirty);
+	FREE_AND_NULL(istate->fsmonitor_last_update);
+
 	istate->sparse_index = 1;
 	trace2_region_leave("index", "convert_to_sparse", istate->repo);
 	return 0;
@@ -195,7 +217,7 @@ static int add_path_to_index(const struct object_id *oid,
 	strbuf_addstr(base, path);
 
 	ce = make_cache_entry(istate, mode, oid, base->buf, 0, 0);
-	ce->ce_flags |= CE_SKIP_WORKTREE;
+	ce->ce_flags |= CE_SKIP_WORKTREE | CE_EXTENDED;
 	set_index_entry(istate, istate->cache_nr++, ce);
 
 	strbuf_setlen(base, len);
@@ -264,6 +286,9 @@ void ensure_full_index(struct index_state *istate)
 	istate->cache = full->cache;
 	istate->cache_nr = full->cache_nr;
 	istate->cache_alloc = full->cache_alloc;
+	istate->fsmonitor_has_run_once = 0;
+	FREE_AND_NULL(istate->fsmonitor_dirty);
+	FREE_AND_NULL(istate->fsmonitor_last_update);
 
 	strbuf_release(&base);
 	free(full);

t/t1092-sparse-checkout-compatibility.sh

@@ -17,7 +17,7 @@ test_expect_success 'setup' '
 		echo "after folder1" >g &&
 		echo "after x" >z &&
 		mkdir folder1 folder2 deep x &&
-		mkdir deep/deeper1 deep/deeper2 &&
+		mkdir deep/deeper1 deep/deeper2 deep/before deep/later &&
 		mkdir deep/deeper1/deepest &&
 		echo "after deeper1" >deep/e &&
 		echo "after deepest" >deep/deeper1/e &&
@@ -25,10 +25,23 @@ test_expect_success 'setup' '
 		cp a folder2 &&
 		cp a x &&
 		cp a deep &&
+		cp a deep/before &&
 		cp a deep/deeper1 &&
 		cp a deep/deeper2 &&
+		cp a deep/later &&
 		cp a deep/deeper1/deepest &&
 		cp -r deep/deeper1/deepest deep/deeper2 &&
+		mkdir deep/deeper1/0 &&
+		mkdir deep/deeper1/0/0 &&
+		touch deep/deeper1/0/1 &&
+		touch deep/deeper1/0/0/0 &&
+		>folder1- &&
+		>folder1.x &&
+		>folder10 &&
+		cp -r deep/deeper1/0 folder1 &&
+		cp -r deep/deeper1/0 folder2 &&
+		echo >>folder1/0/0/0 &&
+		echo >>folder2/0/1 &&
 		git add . &&
 		git commit -m "initial commit" &&
 		git checkout -b base &&
@@ -40,7 +53,7 @@ test_expect_success 'setup' '
 		done &&
 
 		git checkout -b rename-base base &&
-		echo >folder1/larger-content <<-\EOF &&
+		cat >folder1/larger-content <<-\EOF &&
 		matching
 		lines
 		help
@@ -56,11 +69,17 @@ test_expect_success 'setup' '
 		mv folder1/a folder2/b &&
 		mv folder1/larger-content folder2/edited-content &&
 		echo >>folder2/edited-content &&
+		echo >>folder2/0/1 &&
+		echo stuff >>deep/deeper1/a &&
 		git add . &&
 		git commit -m "rename folder1/... to folder2/..." &&
 
 		git checkout -b rename-out-to-in rename-base &&
 		mv folder1/a deep/deeper1/b &&
+		echo more stuff >>deep/deeper1/a &&
+		rm folder2/0/1 &&
+		mkdir folder2/0/1 &&
+		echo >>folder2/0/1/1 &&
 		mv folder1/larger-content deep/deeper1/edited-content &&
 		echo >>deep/deeper1/edited-content &&
 		git add . &&
@@ -68,6 +87,9 @@ test_expect_success 'setup' '
 
 		git checkout -b rename-in-to-out rename-base &&
 		mv deep/deeper1/a folder1/b &&
+		echo >>folder2/0/1 &&
+		rm -rf folder1/0/0 &&
+		echo >>folder1/0/0 &&
 		mv deep/deeper1/larger-content folder1/edited-content &&
 		echo >>folder1/edited-content &&
 		git add . &&
@@ -196,6 +218,14 @@ test_expect_success 'status with options' '
 	test_all_match git status --porcelain=v2 -uno
 '
 
+test_expect_success 'status reports sparse-checkout' '
+	init_repos &&
+	git -C sparse-checkout status >full &&
+	git -C sparse-index status >sparse &&
+	test_i18ngrep "You are in a sparse checkout with " full &&
+	test_i18ngrep "You are in a sparse checkout." sparse
+'
+
 test_expect_success 'add, commit, checkout' '
 	init_repos &&
 
@@ -232,6 +262,44 @@ test_expect_success 'add, commit, checkout' '
 	test_all_match git checkout -
 '
 
+test_expect_success 'status/add: outside sparse cone' '
+	init_repos &&
+
+	# adding a "missing" file outside the cone should fail
+	test_sparse_match test_must_fail git add folder1/a &&
+
+	# folder1 is at HEAD, but outside the sparse cone
+	run_on_sparse mkdir folder1 &&
+	cp initial-repo/folder1/a sparse-checkout/folder1/a &&
+	cp initial-repo/folder1/a sparse-index/folder1/a &&
+
+	test_sparse_match git status &&
+
+	write_script edit-contents <<-\EOF &&
+	echo text >>$1
+	EOF
+	run_on_sparse ../edit-contents folder1/a &&
+	run_on_all ../edit-contents folder1/new &&
+
+	test_sparse_match git status --porcelain=v2 &&
+
+	# This "git add folder1/a" fails with a warning
+	# in the sparse repos, differing from the full
+	# repo. This is intentional.
+	test_sparse_match test_must_fail git add folder1/a &&
+	test_sparse_match test_must_fail git add --refresh folder1/a &&
+	test_all_match git status --porcelain=v2 &&
+
+	test_all_match git add . &&
+	test_all_match git status --porcelain=v2 &&
+	test_all_match git commit -m folder1/new &&
+
+	run_on_all ../edit-contents folder1/newer &&
+	test_all_match git add folder1/ &&
+	test_all_match git status --porcelain=v2 &&
+	test_all_match git commit -m folder1/newer
+'
+
 test_expect_success 'checkout and reset --hard' '
 	init_repos &&
 
@@ -262,13 +330,29 @@ test_expect_success 'diff --staged' '
 	test_all_match git diff --staged
 '
 
-test_expect_success 'diff with renames' '
+test_expect_success 'diff with renames and conflicts' '
 	init_repos &&
 
 	for branch in rename-out-to-out rename-out-to-in rename-in-to-out
 	do
 		test_all_match git checkout rename-base &&
 		test_all_match git checkout $branch -- . &&
+		test_all_match git status --porcelain=v2 &&
+		test_all_match git diff --staged --no-renames &&
+		test_all_match git diff --staged --find-renames || return 1
+	done
+'
+
+test_expect_success 'diff with directory/file conflicts' '
+	init_repos &&
+
+	for branch in rename-out-to-out rename-out-to-in rename-in-to-out
+	do
+		git -C full-checkout reset --hard &&
+		test_sparse_match git reset --hard &&
+		test_all_match git checkout $branch &&
+		test_all_match git checkout rename-base -- . &&
+		test_all_match git status --porcelain=v2 &&
 		test_all_match git diff --staged --no-renames &&
 		test_all_match git diff --staged --find-renames || return 1
 	done
@@ -308,8 +392,8 @@ test_expect_failure 'blame with pathspec outside sparse definition' '
 	test_all_match git blame deep/deeper2/deepest/a
 '
 
-# TODO: reset currently does not behave as expected when in a
+# NEEDSWORK: a sparse-checkout behaves differently from a full checkout
-# sparse-checkout.
+# in this scenario, but it shouldn't.
 test_expect_failure 'checkout and reset (mixed)' '
 	init_repos &&
 
@@ -319,8 +403,8 @@ test_expect_failure 'checkout and reset (mixed)' '
 	test_all_match git reset update-folder2
 '
 
-# Ensure that sparse-index behaves identically to
+# NEEDSWORK: a sparse-checkout behaves differently from a full checkout
-# sparse-checkout with a full index.
+# in this scenario, but it shouldn't.
 test_expect_success 'checkout and reset (mixed) [sparse]' '
 	init_repos &&
 
@@ -352,6 +436,28 @@ test_expect_success 'merge with outside renames' '
 	done
 '
 
+# Sparse-index fails to convert the index in the
+# final 'git cherry-pick' command.
+test_expect_success 'cherry-pick with conflicts' '
+	init_repos &&
+
+	write_script edit-conflict <<-\EOF &&
+	echo $1 >conflict
+	EOF
+
+	test_all_match git checkout -b to-cherry-pick &&
+	run_on_all ../edit-conflict ABC &&
+	test_all_match git add conflict &&
+	test_all_match git commit -m "conflict to pick" &&
+
+	test_all_match git checkout -B base HEAD~1 &&
+	run_on_all ../edit-conflict DEF &&
+	test_all_match git add conflict &&
+	test_all_match git commit -m "conflict in base" &&
+
+	test_all_match test_must_fail git cherry-pick to-cherry-pick
+'
+
 test_expect_success 'clean' '
 	init_repos &&
 
@@ -405,12 +511,52 @@ test_expect_success 'sparse-index is expanded and converted back' '
 	GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \
 		git -C sparse-index -c core.fsmonitor="" reset --hard &&
 	test_region index convert_to_sparse trace2.txt &&
-	test_region index ensure_full_index trace2.txt &&
-
-	rm trace2.txt &&
-	GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \
-		git -C sparse-index -c core.fsmonitor="" status -uno &&
 	test_region index ensure_full_index trace2.txt
 '
 
+test_expect_success 'sparse-index is not expanded' '
+	init_repos &&
+
+	rm -f trace2.txt &&
+	echo >>sparse-index/untracked.txt &&
+	GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \
+		git -C sparse-index status &&
+	test_region ! index ensure_full_index trace2.txt
+'
+
+# NEEDSWORK: a sparse-checkout behaves differently from a full checkout
+# in this scenario, but it shouldn't.
+test_expect_success 'reset mixed and checkout orphan' '
+	init_repos &&
+
+	test_all_match git checkout rename-out-to-in &&
+
+	# Sparse checkouts do not agree with full checkouts about
+	# how to report a directory/file conflict during a reset.
+	# This command would fail with test_all_match because the
+	# full checkout reports "T folder1/0/1" while a sparse
+	# checkout reports "D folder1/0/1". This matches because
+	# the sparse checkouts skip "adding" the other side of
+	# the conflict.
+	test_sparse_match git reset --mixed HEAD~1 &&
+	test_sparse_match test-tool read-cache --table --expand &&
+	test_sparse_match git status --porcelain=v2 &&
+
+	# At this point, sparse-checkouts behave differently
+	# from the full-checkout.
+	test_sparse_match git checkout --orphan new-branch &&
+	test_sparse_match test-tool read-cache --table --expand &&
+	test_sparse_match git status --porcelain=v2
+'
+
+test_expect_success 'add everything with deep new file' '
+	init_repos &&
+
+	run_on_sparse git sparse-checkout set deep/deeper1/deepest &&
+
+	run_on_all touch deep/deeper1/x &&
+	test_all_match git add . &&
+	test_all_match git status --porcelain=v2
+'
+
 test_done

t/t7519-status-fsmonitor.sh

@@ -73,6 +73,7 @@ test_expect_success 'setup' '
 	expect*
 	actual*
 	marker*
+	trace2*
 	EOF
 '
 
@@ -383,4 +384,52 @@ test_expect_success 'status succeeds after staging/unstaging' '
 	)
 '
 
+# Usage:
+# check_sparse_index_behavior [!]
+# If "!" is supplied, then we verify that we do not call ensure_full_index
+# during a call to 'git status'. Otherwise, we verify that we _do_ call it.
+check_sparse_index_behavior () {
+	git status --porcelain=v2 >expect &&
+	git sparse-checkout init --cone --sparse-index &&
+	git sparse-checkout set dir1 dir2 &&
+	GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \
+		git status --porcelain=v2 >actual &&
+	test_region $1 index ensure_full_index trace2.txt &&
+	test_region fsm_hook query trace2.txt &&
+	test_cmp expect actual &&
+	rm trace2.txt &&
+	git sparse-checkout disable
+}
+
+test_expect_success 'status succeeds with sparse index' '
+	git reset --hard &&
+
+	test_config core.fsmonitor "$TEST_DIRECTORY/t7519/fsmonitor-all" &&
+	check_sparse_index_behavior ! &&
+
+	write_script .git/hooks/fsmonitor-test<<-\EOF &&
+		printf "last_update_token\0"
+	EOF
+	git config core.fsmonitor .git/hooks/fsmonitor-test &&
+	check_sparse_index_behavior ! &&
+
+	write_script .git/hooks/fsmonitor-test<<-\EOF &&
+		printf "last_update_token\0"
+		printf "dir1/modified\0"
+	EOF
+	check_sparse_index_behavior ! &&
+
+	cp -r dir1 dir1a &&
+	git add dir1a &&
+	git commit -m "add dir1a" &&
+
+	# This one modifies outside the sparse-checkout definition
+	# and hence we expect to expand the sparse-index.
+	write_script .git/hooks/fsmonitor-test<<-\EOF &&
+		printf "last_update_token\0"
+		printf "dir1a/modified\0"
+	EOF
+	check_sparse_index_behavior
+'
+
 test_done

unpack-trees.c

@@ -600,6 +600,13 @@ static void mark_ce_used(struct cache_entry *ce, struct unpack_trees_options *o)
 {
 	ce->ce_flags |= CE_UNPACKED;
 
+	/*
+	 * If this is a sparse directory, don't advance cache_bottom.
+	 * That will be advanced later using the cache-tree data.
+	 */
+	if (S_ISSPARSEDIR(ce->ce_mode))
+		return;
+
 	if (o->cache_bottom < o->src_index->cache_nr &&
 	    o->src_index->cache[o->cache_bottom] == ce) {
 		int bottom = o->cache_bottom;
@@ -797,7 +804,7 @@ static int traverse_by_cache_tree(int pos, int nr_entries, int nr_names,
 		BUG("We need cache-tree to do this optimization");
 
 	/*
-	 * Do what unpack_callback() and unpack_nondirectories() normally
+	 * Do what unpack_callback() and unpack_single_entry() normally
 	 * do. But we walk all paths in an iterative loop instead.
 	 *
 	 * D/F conflicts and higher stage entries are not a concern
@@ -976,6 +983,7 @@ static int do_compare_entry(const struct cache_entry *ce,
 	int pathlen, ce_len;
 	const char *ce_name;
 	int cmp;
+	unsigned ce_mode;
 
 	/*
 	 * If we have not precomputed the traverse path, it is quicker
@@ -998,7 +1006,8 @@ static int do_compare_entry(const struct cache_entry *ce,
 	ce_len -= pathlen;
 	ce_name = ce->name + pathlen;
 
-	return df_name_compare(ce_name, ce_len, S_IFREG, name, namelen, mode);
+	ce_mode = S_ISSPARSEDIR(ce->ce_mode) ? S_IFDIR : S_IFREG;
+	return df_name_compare(ce_name, ce_len, ce_mode, name, namelen, mode);
 }
 
 static int compare_entry(const struct cache_entry *ce, const struct traverse_info *info, const struct name_entry *n)
@@ -1007,6 +1016,16 @@ static int compare_entry(const struct cache_entry *ce, const struct traverse_inf
 	if (cmp)
 		return cmp;
 
+	/*
+	 * At this point, we know that we have a prefix match. If ce
+	 * is a sparse directory, then allow an exact match. This only
+	 * works when the input name is a directory, since ce->name
+	 * ends in a directory separator.
+	 */
+	if (S_ISSPARSEDIR(ce->ce_mode) &&
+	    ce->ce_namelen == traverse_path_len(info, tree_entry_len(n)) + 1)
+		return 0;
+
 	/*
 	 * Even if the beginning compared identically, the ce should
 	 * compare as bigger than a directory leading up to it!
@@ -1033,13 +1052,15 @@ static struct cache_entry *create_ce_entry(const struct traverse_info *info,
 	const struct name_entry *n,
 	int stage,
 	struct index_state *istate,
-	int is_transient)
+	int is_transient,
+	int is_sparse_directory)
 {
 	size_t len = traverse_path_len(info, tree_entry_len(n));
+	size_t alloc_len = is_sparse_directory ? len + 1 : len;
 	struct cache_entry *ce =
 		is_transient ?
-		make_empty_transient_cache_entry(len, NULL) :
+		make_empty_transient_cache_entry(alloc_len, NULL) :
-		make_empty_cache_entry(istate, len);
+		make_empty_cache_entry(istate, alloc_len);
 
 	ce->ce_mode = create_ce_mode(n->mode);
 	ce->ce_flags = create_ce_flags(stage);
@@ -1048,6 +1069,13 @@ static struct cache_entry *create_ce_entry(const struct traverse_info *info,
 	/* len+1 because the cache_entry allocates space for NUL */
 	make_traverse_path(ce->name, len + 1, info, n->path, n->pathlen);
 
+	if (is_sparse_directory) {
+		ce->name[len] = '/';
+		ce->name[len + 1] = '\0';
+		ce->ce_namelen++;
+		ce->ce_flags |= CE_SKIP_WORKTREE;
+	}
+
 	return ce;
 }
 
@@ -1056,20 +1084,27 @@ static struct cache_entry *create_ce_entry(const struct traverse_info *info,
  * without actually calling it. If you change the logic here you may need to
  * check and change there as well.
  */
-static int unpack_nondirectories(int n, unsigned long mask,
+static int unpack_single_entry(int n, unsigned long mask,
-				 unsigned long dirmask,
+			       unsigned long dirmask,
-				 struct cache_entry **src,
+			       struct cache_entry **src,
-				 const struct name_entry *names,
+			       const struct name_entry *names,
-				 const struct traverse_info *info)
+			       const struct traverse_info *info)
 {
 	int i;
 	struct unpack_trees_options *o = info->data;
 	unsigned long conflicts = info->df_conflicts | dirmask;
 
-	/* Do we have *only* directories? Nothing to do */
 	if (mask == dirmask && !src[0])
 		return 0;
 
+	/*
+	 * When we have a sparse directory entry for src[0],
+	 * then this isn't necessarily a directory-file conflict.
+	 */
+	if (mask == dirmask && src[0] &&
+	    S_ISSPARSEDIR(src[0]->ce_mode))
+		conflicts = 0;
+
 	/*
 	 * Ok, we've filled in up to any potential index entry in src[0],
 	 * now do the rest.
@@ -1099,7 +1134,9 @@ static int unpack_nondirectories(int n, unsigned long mask,
 		 * not stored in the index.  otherwise construct the
 		 * cache entry from the index aware logic.
 		 */
-		src[i + o->merge] = create_ce_entry(info, names + i, stage, &o->result, o->merge);
+		src[i + o->merge] = create_ce_entry(info, names + i, stage,
+						    &o->result, o->merge,
+						    bit & dirmask);
 	}
 
 	if (o->merge) {
@@ -1203,16 +1240,71 @@ static int find_cache_pos(struct traverse_info *info,
 	return -1;
 }
 
+/*
+ * Given a sparse directory entry 'ce', compare ce->name to
+ * info->name + '/' + p->path + '/' if info->name is non-empty.
+ * Compare ce->name to p->path + '/' otherwise. Note that
+ * ce->name must end in a trailing '/' because it is a sparse
+ * directory entry.
+ */
+static int sparse_dir_matches_path(const struct cache_entry *ce,
+				   struct traverse_info *info,
+				   const struct name_entry *p)
+{
+	assert(S_ISSPARSEDIR(ce->ce_mode));
+	assert(ce->name[ce->ce_namelen - 1] == '/');
+
+	if (info->namelen)
+		return ce->ce_namelen == info->namelen + p->pathlen + 2 &&
+		       ce->name[info->namelen] == '/' &&
+		       !strncmp(ce->name, info->name, info->namelen) &&
+		       !strncmp(ce->name + info->namelen + 1, p->path, p->pathlen);
+	return ce->ce_namelen == p->pathlen + 1 &&
+	       !strncmp(ce->name, p->path, p->pathlen);
+}
+
 static struct cache_entry *find_cache_entry(struct traverse_info *info,
 					    const struct name_entry *p)
 {
+	struct cache_entry *ce;
 	int pos = find_cache_pos(info, p->path, p->pathlen);
 	struct unpack_trees_options *o = info->data;
 
 	if (0 <= pos)
 		return o->src_index->cache[pos];
-	else
+
+	/*
+	 * Check for a sparse-directory entry named "path/".
+	 * Due to the input p->path not having a trailing
+	 * slash, the negative 'pos' value overshoots the
+	 * expected position, hence "-2" instead of "-1".
+	 */
+	pos = -pos - 2;
+
+	if (pos < 0 || pos >= o->src_index->cache_nr)
 		return NULL;
+
+	/*
+	 * Due to lexicographic sorting and sparse directory
+	 * entries ending with a trailing slash, our path as a
+	 * sparse directory (e.g "subdir/") and	our path as a
+	 * file (e.g. "subdir") might be separated by other
+	 * paths (e.g. "subdir-").
+	 */
+	while (pos >= 0) {
+		ce = o->src_index->cache[pos];
+
+		if (strncmp(ce->name, p->path, p->pathlen))
+			return NULL;
+
+		if (S_ISSPARSEDIR(ce->ce_mode) &&
+		    sparse_dir_matches_path(ce, info, p))
+			return ce;
+
+		pos--;
+	}
+
+	return NULL;
 }
 
 static void debug_path(struct traverse_info *info)
@@ -1247,6 +1339,21 @@ static void debug_unpack_callback(int n,
 		debug_name_entry(i, names + i);
 }
 
+/*
+ * Returns true if and only if the given cache_entry is a
+ * sparse-directory entry that matches the given name_entry
+ * from the tree walk at the given traverse_info.
+ */
+static int is_sparse_directory_entry(struct cache_entry *ce,
+				     struct name_entry *name,
+				     struct traverse_info *info)
+{
+	if (!ce || !name || !S_ISSPARSEDIR(ce->ce_mode))
+		return 0;
+
+	return sparse_dir_matches_path(ce, info, name);
+}
+
 /*
  * Note that traverse_by_cache_tree() duplicates some logic in this function
  * without actually calling it. If you change the logic here you may need to
@@ -1303,7 +1410,7 @@ static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, str
 		}
 	}
 
-	if (unpack_nondirectories(n, mask, dirmask, src, names, info) < 0)
+	if (unpack_single_entry(n, mask, dirmask, src, names, info) < 0)
 		return -1;
 
 	if (o->merge && src[0]) {
@@ -1333,9 +1440,12 @@ static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, str
 			}
 		}
 
-		if (traverse_trees_recursive(n, dirmask, mask & ~dirmask,
+		if (!is_sparse_directory_entry(src[0], names, info) &&
-					     names, info) < 0)
+		    traverse_trees_recursive(n, dirmask, mask & ~dirmask,
+						    names, info) < 0) {
 			return -1;
+		}
+
 		return mask;
 	}
 

wt-status.c

@@ -657,6 +657,36 @@ static void wt_status_collect_changes_index(struct wt_status *s)
 	clear_pathspec(&rev.prune_data);
 }
 
+static int add_file_to_list(const struct object_id *oid,
+			    struct strbuf *base, const char *path,
+			    unsigned int mode, void *context)
+{
+	struct string_list_item *it;
+	struct wt_status_change_data *d;
+	struct wt_status *s = context;
+	struct strbuf full_name = STRBUF_INIT;
+
+	if (S_ISDIR(mode))
+		return READ_TREE_RECURSIVE;
+
+	strbuf_add(&full_name, base->buf, base->len);
+	strbuf_addstr(&full_name, path);
+	it = string_list_insert(&s->change, full_name.buf);
+	d = it->util;
+	if (!d) {
+		CALLOC_ARRAY(d, 1);
+		it->util = d;
+	}
+
+	d->index_status = DIFF_STATUS_ADDED;
+	/* Leave {mode,oid}_head zero for adds. */
+	d->mode_index = mode;
+	oidcpy(&d->oid_index, oid);
+	s->committable = 1;
+	strbuf_release(&full_name);
+	return 0;
+}
+
 static void wt_status_collect_changes_initial(struct wt_status *s)
 {
 	struct index_state *istate = s->repo->index;
@@ -671,6 +701,27 @@ static void wt_status_collect_changes_initial(struct wt_status *s)
 			continue;
 		if (ce_intent_to_add(ce))
 			continue;
+		if (S_ISSPARSEDIR(ce->ce_mode)) {
+			/*
+			 * This is a sparse directory entry, so we want to collect all
+			 * of the added files within the tree. This requires recursively
+			 * expanding the trees to find the elements that are new in this
+			 * tree and marking them with DIFF_STATUS_ADDED.
+			 */
+			struct strbuf base = STRBUF_INIT;
+			struct pathspec ps = { 0 };
+			struct tree *tree = lookup_tree(istate->repo, &ce->oid);
+
+			ps.recursive = 1;
+			ps.has_wildcard = 1;
+			ps.max_depth = -1;
+
+			strbuf_add(&base, ce->name, ce->ce_namelen);
+			read_tree_at(istate->repo, tree, &base, &ps,
+				     add_file_to_list, s);
+			continue;
+		}
+
 		it = string_list_insert(&s->change, ce->name);
 		d = it->util;
 		if (!d) {
@@ -1492,9 +1543,12 @@ static void show_sparse_checkout_in_use(struct wt_status *s,
 	if (s->state.sparse_checkout_percentage == SPARSE_CHECKOUT_DISABLED)
 		return;
 
-	status_printf_ln(s, color,
+	if (s->state.sparse_checkout_percentage == SPARSE_CHECKOUT_SPARSE_INDEX)
-			 _("You are in a sparse checkout with %d%% of tracked files present."),
+		status_printf_ln(s, color, _("You are in a sparse checkout."));
-			 s->state.sparse_checkout_percentage);
+	else
+		status_printf_ln(s, color,
+				_("You are in a sparse checkout with %d%% of tracked files present."),
+				s->state.sparse_checkout_percentage);
 	wt_longstatus_print_trailer(s);
 }
 
@@ -1652,6 +1706,11 @@ static void wt_status_check_sparse_checkout(struct repository *r,
 		return;
 	}
 
+	if (r->index->sparse_index) {
+		state->sparse_checkout_percentage = SPARSE_CHECKOUT_SPARSE_INDEX;
+		return;
+	}
+
 	for (i = 0; i < r->index->cache_nr; i++) {
 		struct cache_entry *ce = r->index->cache[i];
 		if (ce_skip_worktree(ce))

wt-status.h

@@ -78,6 +78,7 @@ enum wt_status_format {
 };
 
 #define SPARSE_CHECKOUT_DISABLED -1
+#define SPARSE_CHECKOUT_SPARSE_INDEX -2
 
 struct wt_status_state {
 	int merge_in_progress;