[v4,1/3] builtin/grep.c: add --sparse option

Commit Message

Shaoxuan Yuan Sept. 3, 2022, 12:36 a.m. UTC

Add a --sparse option to `git-grep`.

When the '--cached' option is used with the 'git grep' command, the
search is limited to the blobs found in the index, not in the worktree.
If the user has enabled sparse-checkout, this might present more results
than they would like, since the files outside of the sparse-checkout are
unlikely to be important to them.

Change the default behavior of 'git grep' to focus on the files within
the sparse-checkout definition. To enable the previous behavior, add a
'--sparse' option to 'git grep' that triggers the old behavior that
inspects paths outside of the sparse-checkout definition when paired
with the '--cached' option.

Suggested-by: Victoria Dye <[e-mail]>
Helped-by: Derrick Stolee <[e-mail]>
Helped-by: Victoria Dye <[e-mail]>
Signed-off-by: Shaoxuan Yuan <[e-mail]>
---
 Documentation/git-grep.txt      |  5 ++++-
 builtin/grep.c                  | 10 +++++++++-
 t/t7817-grep-sparse-checkout.sh | 34 +++++++++++++++++++++++++++------
 3 files changed, 41 insertions(+), 8 deletions(-)

Patch

diff --git a/Documentation/git-grep.txt b/Documentation/git-grep.txt
index 58d944bd57..bdd3d5b8a6 100644
--- a/Documentation/git-grep.txt
+++ b/Documentation/git-grep.txt
@@ -28,7 +28,7 @@  SYNOPSIS
 	   [-f <file>] [-e] <pattern>
 	   [--and|--or|--not|(|)|-e <pattern>...]
 	   [--recurse-submodules] [--parent-basename <basename>]
-	   [ [--[no-]exclude-standard] [--cached | --no-index | --untracked] | <tree>...]
+	   [ [--[no-]exclude-standard] [--cached [--sparse] | --no-index | --untracked] | <tree>...]
 	   [--] [<pathspec>...]
 
 DESCRIPTION
@@ -45,6 +45,9 @@  OPTIONS
 	Instead of searching tracked files in the working tree, search
 	blobs registered in the index file.
 
+--sparse::
+	Use with --cached. Search outside of sparse-checkout definition.
+
 --no-index::
 	Search files in the current directory that is not managed by Git.
 
diff --git a/builtin/grep.c b/builtin/grep.c
index e6bcdf860c..12abd832fa 100644
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -96,6 +96,8 @@  static pthread_cond_t cond_result;
 
 static int skip_first_line;
 
+static int grep_sparse = 0;
+
 static void add_work(struct grep_opt *opt, struct grep_source *gs)
 {
 	if (opt->binary != GREP_BINARY_TEXT)
@@ -525,7 +527,11 @@  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 (!cached && ce_skip_worktree(ce))
+		/*
+		 * Skip entries with SKIP_WORKTREE unless both --sparse and
+		 * --cached are given.
+		 */
+		if (!(grep_sparse && cached) && ce_skip_worktree(ce))
 			continue;
 
 		strbuf_setlen(&name, name_base_len);
@@ -963,6 +969,8 @@  int cmd_grep(int argc, const char **argv, const char *prefix)
 			   PARSE_OPT_NOCOMPLETE),
 		OPT_INTEGER('m', "max-count", &opt.max_count,
 			N_("maximum number of results per file")),
+		OPT_BOOL(0, "sparse", &grep_sparse,
+			 N_("search the contents of files outside the sparse-checkout definition")),
 		OPT_END()
 	};
 	grep_prefix = prefix;
diff --git a/t/t7817-grep-sparse-checkout.sh b/t/t7817-grep-sparse-checkout.sh
index eb59564565..a9879cc980 100755
--- a/t/t7817-grep-sparse-checkout.sh
+++ b/t/t7817-grep-sparse-checkout.sh
@@ -118,13 +118,19 @@  test_expect_success 'grep searches unmerged file despite not matching sparsity p
 	test_cmp expect actual
 '
 
-test_expect_success 'grep --cached searches entries with the SKIP_WORKTREE bit' '
+test_expect_success 'grep --cached and --sparse searches entries with the SKIP_WORKTREE bit' '
+	cat >expect <<-EOF &&
+	a:text
+	EOF
+	git grep --cached "text" >actual &&
+	test_cmp expect actual &&
+
 	cat >expect <<-EOF &&
 	a:text
 	b:text
 	dir/c:text
 	EOF
-	git grep --cached "text" >actual &&
+	git grep --cached --sparse "text" >actual &&
 	test_cmp expect actual
 '
 
@@ -143,7 +149,15 @@  test_expect_success 'grep --recurse-submodules honors sparse checkout in submodu
 	test_cmp expect actual
 '
 
-test_expect_success 'grep --recurse-submodules --cached searches entries with the SKIP_WORKTREE bit' '
+test_expect_success 'grep --recurse-submodules --cached and --sparse searches entries with the SKIP_WORKTREE bit' '
+	cat >expect <<-EOF &&
+	a:text
+	sub/B/b:text
+	sub2/a:text
+	EOF
+	git grep --recurse-submodules --cached "text" >actual &&
+	test_cmp expect actual &&
+
 	cat >expect <<-EOF &&
 	a:text
 	b:text
@@ -152,7 +166,7 @@  test_expect_success 'grep --recurse-submodules --cached searches entries with th
 	sub/B/b:text
 	sub2/a:text
 	EOF
-	git grep --recurse-submodules --cached "text" >actual &&
+	git grep --recurse-submodules --cached --sparse "text" >actual &&
 	test_cmp expect actual
 '
 
@@ -166,7 +180,15 @@  test_expect_success 'working tree grep does not search the index with CE_VALID a
 	test_cmp expect actual
 '
 
-test_expect_success 'grep --cached searches index entries with both CE_VALID and SKIP_WORKTREE' '
+test_expect_success 'grep --cached and --sparse searches index entries with both CE_VALID and SKIP_WORKTREE' '
+	cat >expect <<-EOF &&
+	a:text
+	EOF
+	test_when_finished "git update-index --no-assume-unchanged b" &&
+	git update-index --assume-unchanged b &&
+	git grep --cached text >actual &&
+	test_cmp expect actual &&
+
 	cat >expect <<-EOF &&
 	a:text
 	b:text
@@ -174,7 +196,7 @@  test_expect_success 'grep --cached searches index entries with both CE_VALID and
 	EOF
 	test_when_finished "git update-index --no-assume-unchanged b" &&
 	git update-index --assume-unchanged b &&
-	git grep --cached text >actual &&
+	git grep --cached --sparse text >actual &&
 	test_cmp expect actual
 '