Merge branch 'sy/sparse-grep'

"git grep" learned to expand the sparse-index more lazily and on
demand in a sparse checkout.

* sy/sparse-grep:
  builtin/grep.c: integrate with sparse index

Author: gitster

builtin/grep.c

@@ -458,6 +458,33 @@ static int grep_submodule(struct grep_opt *opt,
 	 * subrepo's odbs to the in-memory alternates list.
 	 */
 	obj_read_lock();
+
+	/*
+	 * NEEDSWORK: when reading a submodule, the sparsity settings in the
+	 * superproject are incorrectly forgotten or misused. For example:
+	 *
+	 * 1. "command_requires_full_index"
+	 * 	When this setting is turned on for `grep`, only the superproject
+	 *	knows it. All the submodules are read with their own configs
+	 *	and get prepare_repo_settings()'d. Therefore, these submodules
+	 *	"forget" the sparse-index feature switch. As a result, the index
+	 *	of these submodules are expanded unexpectedly.
+	 *
+	 * 2. "core_apply_sparse_checkout"
+	 *	When running `grep` in the superproject, this setting is
+	 *	populated using the superproject's configs. However, once
+	 *	initialized, this config is globally accessible and is read by
+	 *	prepare_repo_settings() for the submodules. For instance, if a
+	 *	submodule is using a sparse-checkout, however, the superproject
+	 *	is not, the result is that the config from the superproject will
+	 *	dictate the behavior for the submodule, making it "forget" its
+	 *	sparse-checkout state.
+	 *
+	 * 3. "core_sparse_checkout_cone"
+	 *	ditto.
+	 *
+	 * Note that this list is not exhaustive.
+	 */
 	repo_read_gitmodules(subrepo, 0);
 
 	/*
@@ -520,8 +547,6 @@ static int grep_cache(struct grep_opt *opt,
 	if (repo_read_index(repo) < 0)
 		die(_("index file corrupt"));
 
-	/* TODO: audit for interaction with sparse-index. */
-	ensure_full_index(repo->index);
 	for (nr = 0; nr < repo->index->cache_nr; nr++) {
 		const struct cache_entry *ce = repo->index->cache[nr];
 
@@ -530,8 +555,20 @@ static int grep_cache(struct grep_opt *opt,
 
 		strbuf_setlen(&name, name_base_len);
 		strbuf_addstr(&name, ce->name);
+		if (S_ISSPARSEDIR(ce->ce_mode)) {
+			enum object_type type;
+			struct tree_desc tree;
+			void *data;
+			unsigned long size;
 
-		if (S_ISREG(ce->ce_mode) &&
+			data = read_object_file(&ce->oid, &type, &size);
+			init_tree_desc(&tree, data, size);
+
+			hit |= grep_tree(opt, pathspec, &tree, &name, 0, 0);
+			strbuf_setlen(&name, name_base_len);
+			strbuf_addstr(&name, ce->name);
+			free(data);
+		} else if (S_ISREG(ce->ce_mode) &&
 		    match_pathspec(repo->index, pathspec, name.buf, name.len, 0, NULL,
 				   S_ISDIR(ce->ce_mode) ||
 				   S_ISGITLINK(ce->ce_mode))) {
@@ -984,6 +1021,11 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 			     PARSE_OPT_KEEP_DASHDASH |
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if (the_repository->gitdir) {
+		prepare_repo_settings(the_repository);
+		the_repository->settings.command_requires_full_index = 0;
+	}
+
 	if (use_index && !startup_info->have_repository) {
 		int fallback = 0;
 		git_config_get_bool("grep.fallbacktonoindex", &fallback);

t/perf/p2000-sparse-operations.sh

@@ -124,5 +124,6 @@ test_perf_on_all git read-tree -mu HEAD
 test_perf_on_all git checkout-index -f --all
 test_perf_on_all git update-index --add --remove $SPARSE_CONE/a
 test_perf_on_all "git rm -f $SPARSE_CONE/a && git checkout HEAD -- $SPARSE_CONE/a"
+test_perf_on_all git grep --cached --sparse bogus -- "f2/f1/f1/*"
 
 test_done

t/t1092-sparse-checkout-compatibility.sh

@@ -162,6 +162,19 @@ init_repos () {
 	git -C sparse-index sparse-checkout set deep
 }
 
+init_repos_as_submodules () {
+	git reset --hard &&
+	init_repos &&
+	git submodule add ./full-checkout &&
+	git submodule add ./sparse-checkout &&
+	git submodule add ./sparse-index &&
+
+	git submodule status >actual &&
+	grep full-checkout actual &&
+	grep sparse-checkout actual &&
+	grep sparse-index actual
+}
+
 run_on_sparse () {
 	(
 		cd sparse-checkout &&
@@ -1981,4 +1994,63 @@ test_expect_success 'sparse index is not expanded: rm' '
 	ensure_not_expanded rm -r deep
 '
 
+test_expect_success 'grep with and --cached' '
+	init_repos &&
+
+	test_all_match git grep --cached a &&
+	test_all_match git grep --cached a -- "folder1/*"
+'
+
+test_expect_success 'grep is not expanded' '
+	init_repos &&
+
+	ensure_not_expanded grep a &&
+	ensure_not_expanded grep a -- deep/* &&
+
+	# All files within the folder1/* pathspec are sparse,
+	# so this command does not find any matches
+	ensure_not_expanded ! grep a -- folder1/* &&
+
+	# test out-of-cone pathspec with or without wildcard
+	ensure_not_expanded grep --cached a -- "folder1/a" &&
+	ensure_not_expanded grep --cached a -- "folder1/*" &&
+
+	# test in-cone pathspec with or without wildcard
+	ensure_not_expanded grep --cached a -- "deep/a" &&
+	ensure_not_expanded grep --cached a -- "deep/*"
+'
+
+# NEEDSWORK: when running `grep` in the superproject with --recurse-submodules,
+# Git expands the index of the submodules unexpectedly. Even though `grep`
+# builtin is marked as "command_requires_full_index = 0", this config is only
+# useful for the superproject. Namely, the submodules have their own configs,
+# which are _not_ populated by the one-time sparse-index feature switch.
+test_expect_failure 'grep within submodules is not expanded' '
+	init_repos_as_submodules &&
+
+	# do not use ensure_not_expanded() here, becasue `grep` should be
+	# run in the superproject, not in "./sparse-index"
+	GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \
+	git grep --cached --recurse-submodules a -- "*/folder1/*" &&
+	test_region ! index ensure_full_index trace2.txt
+'
+
+# NEEDSWORK: this test is not actually testing the code. The design purpose
+# of this test is to verify the grep result when the submodules are using a
+# sparse-index. Namely, we want "folder1/" as a tree (a sparse directory); but
+# because of the index expansion, we are now grepping the "folder1/a" blob.
+# Because of the problem stated above 'grep within submodules is not expanded',
+# we don't have the ideal test environment yet.
+test_expect_success 'grep sparse directory within submodules' '
+	init_repos_as_submodules &&
+
+	cat >expect <<-\EOF &&
+	full-checkout/folder1/a:a
+	sparse-checkout/folder1/a:a
+	sparse-index/folder1/a:a
+	EOF
+	git grep --cached --recurse-submodules a -- "*/folder1/*" >actual &&
+	test_cmp actual expect
+'
+
 test_done