sparse-checkout: optimize string_list construction and add tests to verify deduplication.

Improve O(n^2) complexity to O(n log n) while building a sorted
'string_list' by constructing it unsorted then sorting it
followed by removing duplicates.

sparse-checkout deduplicates repeated cone-mode patterns,
but this behaviour was previously untested, add tests that
verify that sparse-checkout file contain each cone
pattern only once and sparse-checkout list reports each pattern
only once.

Signed-off-by: Amisha Chhajed <amishhhaaaa@gmail.com>
Acked-by: Derrick Stolee <stolee@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 52 insertions, 3 deletions

diff --git a/builtin/sparse-checkout.c b/builtin/sparse-checkout.c
index 15d51e60a8..7dfb276bf0 100644
--- a/builtin/sparse-checkout.c
+++ b/builtin/sparse-checkout.c
@@ -91,10 +91,11 @@ static int sparse_checkout_list(int argc, const char **argv, const char *prefix,
 
 		hashmap_for_each_entry(&pl.recursive_hashmap, &iter, pe, ent) {
 			/* pe->pattern starts with "/", skip it */
-			string_list_insert(&sl, pe->pattern + 1);
+			string_list_append(&sl, pe->pattern + 1);
 		}
 
 		string_list_sort(&sl);
+		string_list_remove_duplicates(&sl, 0);
 
 		for (i = 0; i < sl.nr; i++) {
 			quote_c_style(sl.items[i].string, NULL, stdout, 0);
@@ -289,7 +290,7 @@ static void write_cone_to_file(FILE *fp, struct pattern_list *pl)
 		if (!hashmap_contains_parent(&pl->recursive_hashmap,
 					     pe->pattern,
 					     &parent_pattern))
-			string_list_insert(&sl, pe->pattern);
+			string_list_append(&sl, pe->pattern);
 	}
 
 	string_list_sort(&sl);
@@ -311,7 +312,7 @@ static void write_cone_to_file(FILE *fp, struct pattern_list *pl)
 		if (!hashmap_contains_parent(&pl->recursive_hashmap,
 					     pe->pattern,
 					     &parent_pattern))
-			string_list_insert(&sl, pe->pattern);
+			string_list_append(&sl, pe->pattern);
 	}
 
 	strbuf_release(&parent_pattern);
diff --git a/t/t1091-sparse-checkout-builtin.sh b/t/t1091-sparse-checkout-builtin.sh
index b2da4feaef..cd0aed9975 100755
--- a/t/t1091-sparse-checkout-builtin.sh
+++ b/t/t1091-sparse-checkout-builtin.sh
@@ -817,6 +817,54 @@ test_expect_success 'cone mode clears ignored subdirectories' '
 	test_cmp expect out
 '
 
+test_expect_success 'sparse-checkout deduplicates repeated cone patterns' '
+	rm -f repo/.git/info/sparse-checkout &&
+	git -C repo sparse-checkout init --cone &&
+	git -C repo sparse-checkout add --stdin <<-\EOF &&
+	foo/bar/baz
+	a/b/c
+	foo/bar/baz
+	a/b
+	EOF
+	cat >expect <<-\EOF &&
+	/*
+	!/*/
+	/a/
+	!/a/*/
+	/foo/
+	!/foo/*/
+	/foo/bar/
+	!/foo/bar/*/
+	/a/b/
+	/foo/bar/baz/
+	EOF
+	test_cmp expect repo/.git/info/sparse-checkout
+'
+
+test_expect_success 'sparse-checkout list deduplicates repeated cone patterns' '
+	rm -f repo/.git/info/sparse-checkout &&
+	git -C repo sparse-checkout init --cone &&
+	cat <<-\EOF >repo/.git/info/sparse-checkout &&
+	/*
+	!/*/
+	/a/
+	!/a/*/
+	/foo/
+	!/foo/*/
+	/foo/bar/
+	!/foo/bar/*/
+	/a/b/
+	/foo/bar/baz/
+	/foo/bar/baz/
+	EOF
+	git -C repo sparse-checkout list >actual &&
+	cat <<-\EOF >expect &&
+	a/b
+	foo/bar/baz
+	EOF
+	test_cmp expect actual
+'
+
 test_expect_success 'malformed cone-mode patterns' '
 	git -C repo sparse-checkout init --cone &&
 	mkdir -p repo/foo/bar &&