[PATCH v3 4/5] grep: honor sparse checkout patterns

From: Matheus Tavares <matheus.bernardino@usp.br>
Date: May 28, 2020, 01:13 UTC
Message-ID: <5ddac818185d316cd5ad9576105f0e4e695b9456.1590627264.git.matheus.bernardino@usp.br>
In-Reply-To: <cover.1590627264.git.matheus.bernardino@usp.br>

One of the main uses for a sparse checkout is to allow users to focus on the subset of files in a repository in which they are interested. But git-grep currently ignores the sparsity patterns and report all matches found outside this subset, which kind of goes in the opposite direction. Let's fix that, making it honor the sparsity boundaries for every grepping case where this is relevant:

- git grep in worktree
- git grep --cached
- git grep $REVISION

For the worktree case, we will not grep paths that have the SKIP_WORKTREE bit set, even if they are present for some reason (e.g. manually created after `git sparse-checkout init`). But the next patch will add an option to do so. (See 'Note' below.)

For `git grep $REVISION`, we will choose to honor the sparsity patterns only when $REVISION is a commit-ish object. The reason is that, for a tree, we don't know whether it represents the root of a repository or a subtree. So we wouldn't be able to correctly match it against the sparsity patterns. E.g. suppose we have a repository with these two sparsity rules: "/*" and "!/a"; and the following structure:

/
| - a (file)
| - d (dir)
    | - a (file)

If `git grep $REVISION` were to honor the sparsity patterns for every object type, when grepping the /d tree, we would wrongly ignore the /d/a file. This happens because we wouldn't know it resides in /d and therefore it would wrongly match the pattern "!/a". Furthermore, for a search in a blob object, we wouldn't even have a path to check the patterns against. So, let's ignore the sparsity patterns when grepping non-commit-ish objects.

Note: The behavior introduced in this patch is what some users have
reported[1] that they would like by default. But the old behavior is
still desirable for some use cases. Therefore, the next patch will add
an option to allow restoring it when needed.

[1]: https://lore.kernel.org/git/CABPp-BGuFhDwWZBRaD3nA8ui46wor-4=Ha1G1oApsfF8KNpfGQ@mail.gmail.com/

Signed-off-by: Matheus Tavares <matheus.bernardino@usp.br>
---
 builtin/grep.c                   | 125 ++++++++++++++++++++--
 t/t7011-skip-worktree-reading.sh |   9 --
 t/t7817-grep-sparse-checkout.sh  | 174 +++++++++++++++++++++++++++++++
 3 files changed, 291 insertions(+), 17 deletions(-)
 create mode 100755 t/t7817-grep-sparse-checkout.sh

diff --git a/builtin/grep.c b/builtin/grep.c
index a5056f395a..11e33b8aee 100644
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -410,7 +410,7 @@ static int grep_cache(struct grep_opt *opt,
 		      const struct pathspec *pathspec, int cached);
 static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 		     struct tree_desc *tree, struct strbuf *base, int tn_len,
-		     int check_attr);
+		     int is_root_tree);
 
 static int grep_submodule(struct grep_opt *opt,
 			  const struct pathspec *pathspec,
@@ -508,6 +508,10 @@ static int grep_cache(struct grep_opt *opt,
 
 	for (nr = 0; nr < repo->index->cache_nr; nr++) {
 		const struct cache_entry *ce = repo->index->cache[nr];
+
+		if (ce_skip_worktree(ce))
+			continue;
+
 		strbuf_setlen(&name, name_base_len);
 		strbuf_addstr(&name, ce->name);
 
@@ -520,8 +524,7 @@ static int grep_cache(struct grep_opt *opt,
 			 * cache entry are identical, even if worktree file has
 			 * been modified, so use cache version instead
 			 */
-			if (cached || (ce->ce_flags & CE_VALID) ||
-			    ce_skip_worktree(ce)) {
+			if (cached || (ce->ce_flags & CE_VALID)) {
 				if (ce_stage(ce) || ce_intent_to_add(ce))
 					continue;
 				hit |= grep_oid(opt, &ce->oid, name.buf,
@@ -552,9 +555,76 @@ static int grep_cache(struct grep_opt *opt,
 	return hit;
 }
 
-static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
-		     struct tree_desc *tree, struct strbuf *base, int tn_len,
-		     int check_attr)
+static struct pattern_list *get_sparsity_patterns(struct repository *repo)
+{
+	struct pattern_list *patterns;
+	char *sparse_file;
+	int sparse_config, cone_config;
+
+	if (repo_config_get_bool(repo, "core.sparsecheckout", &sparse_config) ||
+	    !sparse_config) {
+		return NULL;
+	}
+
+	sparse_file = repo_git_path(repo, "info/sparse-checkout");
+	patterns = xcalloc(1, sizeof(*patterns));
+
+	if (repo_config_get_bool(repo, "core.sparsecheckoutcone", &cone_config))
+		cone_config = 0;
+	patterns->use_cone_patterns = cone_config;
+
+	if (add_patterns_from_file_to_list(sparse_file, "", 0, patterns, NULL)) {
+		if (file_exists(sparse_file)) {
+			warning(_("failed to load sparse-checkout file: '%s'"),
+				sparse_file);
+		}
+		free(sparse_file);
+		free(patterns);
+		return NULL;
+	}
+
+	free(sparse_file);
+	return patterns;
+}
+
+static int in_sparse_checkout(struct strbuf *path, int prefix_len,
+			      unsigned int entry_mode,
+			      struct index_state *istate,
+			      struct pattern_list *sparsity,
+			      enum pattern_match_result parent_match,
+			      enum pattern_match_result *match)
+{
+	int dtype = DT_UNKNOWN;
+	int is_dir = S_ISDIR(entry_mode);
+
+	if (parent_match == MATCHED_RECURSIVE) {
+		*match = parent_match;
+		return 1;
+	}
+
+	if (is_dir && !is_dir_sep(path->buf[path->len - 1]))
+		strbuf_addch(path, '/');
+
+	*match = path_matches_pattern_list(path->buf, path->len,
+					   path->buf + prefix_len, &dtype,
+					   sparsity, istate);
+	if (*match == UNDECIDED)
+		*match = parent_match;
+
+	if (is_dir)
+		strbuf_trim_trailing_dir_sep(path);
+
+	if (*match == NOT_MATCHED &&
+		(!is_dir || (is_dir && sparsity->use_cone_patterns)))
+	     return 0;
+
+	return 1;
+}
+
+static int do_grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
+			struct tree_desc *tree, struct strbuf *base, int tn_len,
+			int check_attr, struct pattern_list *sparsity,
+			enum pattern_match_result default_sparsity_match)
 {
 	struct repository *repo = opt->repo;
 	int hit = 0;
@@ -570,6 +640,7 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 
 	while (tree_entry(tree, &entry)) {
 		int te_len = tree_entry_len(&entry);
+		enum pattern_match_result sparsity_match = 0;
 
 		if (match != all_entries_interesting) {
 			strbuf_addstr(&name, base->buf + tn_len);
@@ -586,6 +657,19 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 
 		strbuf_add(base, entry.path, te_len);
 
+		if (sparsity) {
+			struct strbuf path = STRBUF_INIT;
+			strbuf_addstr(&path, base->buf + tn_len);
+
+			if (!in_sparse_checkout(&path, old_baselen - tn_len,
+						entry.mode, repo->index,
+						sparsity, default_sparsity_match,
+						&sparsity_match)) {
+				strbuf_setlen(base, old_baselen);
+				continue;
+			}
+		}
+
 		if (S_ISREG(entry.mode)) {
 			hit |= grep_oid(opt, &entry.oid, base->buf, tn_len,
 					 check_attr ? base->buf + tn_len : NULL);
@@ -602,8 +686,8 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 
 			strbuf_addch(base, '/');
 			init_tree_desc(&sub, data, size);
-			hit |= grep_tree(opt, pathspec, &sub, base, tn_len,
-					 check_attr);
+			hit |= do_grep_tree(opt, pathspec, &sub, base, tn_len,
+					    check_attr, sparsity, sparsity_match);
 			free(data);
 		} else if (recurse_submodules && S_ISGITLINK(entry.mode)) {
 			hit |= grep_submodule(opt, pathspec, &entry.oid,
@@ -621,6 +705,31 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
 	return hit;
 }
 
+/*
+ * Note: sparsity patterns and paths' attributes will only be considered if
+ * is_root_tree has true value. (Otherwise, we cannot properly perform pattern
+ * matching on paths.)
+ */
+static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec,
+		     struct tree_desc *tree, struct strbuf *base, int tn_len,
+		     int is_root_tree)
+{
+	struct pattern_list *patterns = NULL;
+	int ret;
+
+	if (is_root_tree)
+		patterns = get_sparsity_patterns(opt->repo);
+
+	ret = do_grep_tree(opt, pathspec, tree, base, tn_len, is_root_tree,
+			   patterns, 0);
+
+	if (patterns) {
+		clear_pattern_list(patterns);
+		free(patterns);
+	}
+	return ret;
+}
+
 static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec,
 		       struct object *obj, const char *name, const char *path)
 {
diff --git a/t/t7011-skip-worktree-reading.sh b/t/t7011-skip-worktree-reading.sh
index 37525cae3a..26852586ac 100755
--- a/t/t7011-skip-worktree-reading.sh
+++ b/t/t7011-skip-worktree-reading.sh
@@ -109,15 +109,6 @@ test_expect_success 'ls-files --modified' '
 	test -z "$(git ls-files -m)"
 '
 
-test_expect_success 'grep with skip-worktree file' '
-	git update-index --no-skip-worktree 1 &&
-	echo test > 1 &&
-	git update-index 1 &&
-	git update-index --skip-worktree 1 &&
-	rm 1 &&
-	test "$(git grep --no-ext-grep test)" = "1:test"
-'
-
 echo ":000000 100644 $ZERO_OID $EMPTY_BLOB A	1" > expected
 test_expect_success 'diff-index does not examine skip-worktree absent entries' '
 	setup_absent &&
diff --git a/t/t7817-grep-sparse-checkout.sh b/t/t7817-grep-sparse-checkout.sh
new file mode 100755
index 0000000000..ce080cf572
--- /dev/null
+++ b/t/t7817-grep-sparse-checkout.sh
@@ -0,0 +1,174 @@
+#!/bin/sh
+
+test_description='grep in sparse checkout
+
+This test creates a repo with the following structure:
+
+.
+|-- a
+|-- b
+|-- dir
+|   `-- c
+|-- sub
+|   |-- A
+|   |   `-- a
+|   `-- B
+|       `-- b
+`-- sub2
+    `-- a
+
+Where . has non-cone mode sparsity patterns, sub is a submodule with cone mode
+sparsity patterns and sub2 is a submodule that is excluded by the superproject
+sparsity patterns. The resulting sparse checkout should leave the following
+structure on the working tree:
+
+.
+|-- a
+|-- sub
+|   `-- B
+|       `-- b
+`-- sub2
+    `-- a
+
+But note that sub2 should have the SKIP_WORKTREE bit set.
+'
+
+. ./test-lib.sh
+
+test_expect_success 'setup' '
+	echo "text" >a &&
+	echo "text" >b &&
+	mkdir dir &&
+	echo "text" >dir/c &&
+
+	git init sub &&
+	(
+		cd sub &&
+		mkdir A B &&
+		echo "text" >A/a &&
+		echo "text" >B/b &&
+		git add A B &&
+		git commit -m sub &&
+		git sparse-checkout init --cone &&
+		git sparse-checkout set B
+	) &&
+
+	git init sub2 &&
+	(
+		cd sub2 &&
+		echo "text" >a &&
+		git add a &&
+		git commit -m sub2
+	) &&
+
+	git submodule add ./sub &&
+	git submodule add ./sub2 &&
+	git add a b dir &&
+	git commit -m super &&
+	git sparse-checkout init --no-cone &&
+	git sparse-checkout set "/*" "!b" "!/*/" "sub" &&
+
+	git tag -am tag-to-commit tag-to-commit HEAD &&
+	tree=$(git rev-parse HEAD^{tree}) &&
+	git tag -am tag-to-tree tag-to-tree $tree &&
+
+	test_path_is_missing b &&
+	test_path_is_missing dir &&
+	test_path_is_missing sub/A &&
+	test_path_is_file a &&
+	test_path_is_file sub/B/b &&
+	test_path_is_file sub2/a
+'
+
+# The test bellow checks a special case: the sparsity patterns exclude '/b'
+# and sparse checkout is enable, but the path exists on the working tree (e.g.
+# manually created after `git sparse-checkout init`). In this case, grep should
+# skip it.
+test_expect_success 'grep in working tree should honor sparse checkout' '
+	cat >expect <<-EOF &&
+	a:text
+	EOF
+	echo "new-text" >b &&
+	test_when_finished "rm b" &&
+	git grep "text" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'grep --cached should honor sparse checkout' '
+	cat >expect <<-EOF &&
+	a:text
+	EOF
+	git grep --cached "text" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'grep <commit-ish> should honor sparse checkout' '
+	commit=$(git rev-parse HEAD) &&
+	cat >expect_commit <<-EOF &&
+	$commit:a:text
+	EOF
+	cat >expect_tag-to-commit <<-EOF &&
+	tag-to-commit:a:text
+	EOF
+	git grep "text" $commit >actual_commit &&
+	test_cmp expect_commit actual_commit &&
+	git grep "text" tag-to-commit >actual_tag-to-commit &&
+	test_cmp expect_tag-to-commit actual_tag-to-commit
+'
+
+test_expect_success 'grep <tree-ish> should ignore sparsity patterns' '
+	commit=$(git rev-parse HEAD) &&
+	tree=$(git rev-parse HEAD^{tree}) &&
+	cat >expect_tree <<-EOF &&
+	$tree:a:text
+	$tree:b:text
+	$tree:dir/c:text
+	EOF
+	cat >expect_tag-to-tree <<-EOF &&
+	tag-to-tree:a:text
+	tag-to-tree:b:text
+	tag-to-tree:dir/c:text
+	EOF
+	git grep "text" $tree >actual_tree &&
+	test_cmp expect_tree actual_tree &&
+	git grep "text" tag-to-tree >actual_tag-to-tree &&
+	test_cmp expect_tag-to-tree actual_tag-to-tree
+'
+
+# Note that sub2/ is present in the worktree but it is excluded by the sparsity
+# patterns, so grep should not recurse into it.
+test_expect_success 'grep --recurse-submodules should honor sparse checkout in submodule' '
+	cat >expect <<-EOF &&
+	a:text
+	sub/B/b:text
+	EOF
+	git grep --recurse-submodules "text" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'grep --recurse-submodules --cached should honor sparse checkout in submodule' '
+	cat >expect <<-EOF &&
+	a:text
+	sub/B/b:text
+	EOF
+	git grep --recurse-submodules --cached "text" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'grep --recurse-submodules <commit-ish> should honor sparse checkout in submodule' '
+	commit=$(git rev-parse HEAD) &&
+	cat >expect_commit <<-EOF &&
+	$commit:a:text
+	$commit:sub/B/b:text
+	EOF
+	cat >expect_tag-to-commit <<-EOF &&
+	tag-to-commit:a:text
+	tag-to-commit:sub/B/b:text
+	EOF
+	git grep --recurse-submodules "text" $commit >actual_commit &&
+	test_cmp expect_commit actual_commit &&
+	git grep --recurse-submodules "text" tag-to-commit >actual_tag-to-commit &&
+	test_cmp expect_tag-to-commit actual_tag-to-commit
+'
+
+test_done

-- 
2.26.2