3 files changed, 141 insertions, 1 deletions
diff --git a/t/helper/test-path-walk.c b/t/helper/test-path-walk.c
index 7f2d409c5b..61e845e5ec 100644
--- a/t/helper/test-path-walk.c
+++ b/t/helper/test-path-walk.c
@@ -1,6 +1,7 @@
 #define USE_THE_REPOSITORY_VARIABLE
 
 #include "test-tool.h"
+#include "dir.h"
 #include "environment.h"
 #include "hex.h"
 #include "object-name.h"
@@ -9,6 +10,7 @@
 #include "revision.h"
 #include "setup.h"
 #include "parse-options.h"
+#include "strbuf.h"
 #include "path-walk.h"
 #include "oid-array.h"
 
@@ -65,7 +67,7 @@ static int emit_block(const char *path, struct oid_array *oids,
 
 int cmd__path_walk(int argc, const char **argv)
 {
-	int res;
+	int res, stdin_pl = 0;
 	struct rev_info revs = REV_INFO_INIT;
 	struct path_walk_info info = PATH_WALK_INFO_INIT;
 	struct path_walk_test_data data = { 0 };
@@ -80,6 +82,8 @@ int cmd__path_walk(int argc, const char **argv)
 			 N_("toggle inclusion of tree objects")),
 		OPT_BOOL(0, "prune", &info.prune_all_uninteresting,
 			 N_("toggle pruning of uninteresting paths")),
+		OPT_BOOL(0, "stdin-pl", &stdin_pl,
+			 N_("read a pattern list over stdin")),
 		OPT_END(),
 	};
 
@@ -99,6 +103,17 @@ int cmd__path_walk(int argc, const char **argv)
 	info.path_fn = emit_block;
 	info.path_fn_data = &data;
 
+	if (stdin_pl) {
+		struct strbuf in = STRBUF_INIT;
+		CALLOC_ARRAY(info.pl, 1);
+
+		info.pl->use_cone_patterns = 1;
+
+		strbuf_fread(&in, 2048, stdin);
+		add_patterns_from_buffer(in.buf, in.len, "", 0, info.pl);
+		strbuf_release(&in);
+	}
+
 	res = walk_objects_by_path(&info);
 
 	printf("commits:%" PRIuMAX "\n"
@@ -107,6 +122,11 @@ int cmd__path_walk(int argc, const char **argv)
 	       "tags:%" PRIuMAX "\n",
 	       data.commit_nr, data.tree_nr, data.blob_nr, data.tag_nr);
 
+	if (info.pl) {
+		clear_pattern_list(info.pl);
+		free(info.pl);
+	}
+
 	release_revisions(&revs);
 	return res;
 }
diff --git a/t/t5620-backfill.sh b/t/t5620-backfill.sh
index 36107a51c5..6b72e9d0e3 100755
--- a/t/t5620-backfill.sh
+++ b/t/t5620-backfill.sh
@@ -77,6 +77,94 @@ test_expect_success 'do partial clone 2, backfill min batch size' '
 	test_line_count = 0 revs2
 '
 
+test_expect_success 'backfill --sparse' '
+	git clone --sparse --filter=blob:none		\
+		--single-branch --branch=main 		\
+		"file://$(pwd)/srv.bare" backfill3 &&
+
+	# Initial checkout includes four files at root.
+	git -C backfill3 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 44 missing &&
+
+	# Initial sparse-checkout is just the files at root, so we get the
+	# older versions of the four files at tip.
+	GIT_TRACE2_EVENT="$(pwd)/sparse-trace1" git \
+		-C backfill3 backfill --sparse &&
+	test_trace2_data promisor fetch_count 4 <sparse-trace1 &&
+	test_trace2_data path-walk paths 5 <sparse-trace1 &&
+	git -C backfill3 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 40 missing &&
+
+	# Expand the sparse-checkout to include 'd' recursively. This
+	# engages the algorithm to skip the trees for 'a'. Note that
+	# the "sparse-checkout set" command downloads the objects at tip
+	# to satisfy the current checkout.
+	git -C backfill3 sparse-checkout set d &&
+	GIT_TRACE2_EVENT="$(pwd)/sparse-trace2" git \
+		-C backfill3 backfill --sparse &&
+	test_trace2_data promisor fetch_count 8 <sparse-trace2 &&
+	test_trace2_data path-walk paths 15 <sparse-trace2 &&
+	git -C backfill3 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 24 missing
+'
+
+test_expect_success 'backfill --sparse without cone mode (positive)' '
+	git clone --no-checkout --filter=blob:none		\
+		--single-branch --branch=main 		\
+		"file://$(pwd)/srv.bare" backfill4 &&
+
+	# No blobs yet
+	git -C backfill4 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 48 missing &&
+
+	# Define sparse-checkout by filename regardless of parent directory.
+	# This downloads 6 blobs to satisfy the checkout.
+	git -C backfill4 sparse-checkout set --no-cone "**/file.1.txt" &&
+	git -C backfill4 checkout main &&
+
+	# Track new blob count
+	git -C backfill4 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 42 missing &&
+
+	GIT_TRACE2_EVENT="$(pwd)/no-cone-trace1" git \
+		-C backfill4 backfill --sparse &&
+	test_trace2_data promisor fetch_count 6 <no-cone-trace1 &&
+
+	# This walk needed to visit all directories to search for these paths.
+	test_trace2_data path-walk paths 12 <no-cone-trace1 &&
+	git -C backfill4 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 36 missing
+'
+
+test_expect_success 'backfill --sparse without cone mode (negative)' '
+	git clone --no-checkout --filter=blob:none		\
+		--single-branch --branch=main 		\
+		"file://$(pwd)/srv.bare" backfill5 &&
+
+	# No blobs yet
+	git -C backfill5 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 48 missing &&
+
+	# Define sparse-checkout by filename regardless of parent directory.
+	# This downloads 18 blobs to satisfy the checkout
+	git -C backfill5 sparse-checkout set --no-cone "**/file*" "!**/file.1.txt" &&
+	git -C backfill5 checkout main &&
+
+	# Track new blob count
+	git -C backfill5 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 30 missing &&
+
+	GIT_TRACE2_EVENT="$(pwd)/no-cone-trace2" git \
+		-C backfill5 backfill --sparse &&
+	test_trace2_data promisor fetch_count 18 <no-cone-trace2 &&
+
+	# This walk needed to visit all directories to search for these paths, plus
+	# 12 extra "file.?.txt" paths than the previous test.
+	test_trace2_data path-walk paths 24 <no-cone-trace2 &&
+	git -C backfill5 rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 12 missing
+'
+
 . "$TEST_DIRECTORY"/lib-httpd.sh
 start_httpd
 
diff --git a/t/t6601-path-walk.sh b/t/t6601-path-walk.sh
index 5f04acb8a2..c89b0f1e19 100755
--- a/t/t6601-path-walk.sh
+++ b/t/t6601-path-walk.sh
@@ -176,6 +176,38 @@ test_expect_success 'branches and indexed objects mix well' '
 	test_cmp_sorted expect out
 '
 
+test_expect_success 'base & topic, sparse' '
+	cat >patterns <<-EOF &&
+	/*
+	!/*/
+	/left/
+	EOF
+
+	test-tool path-walk --stdin-pl -- base topic <patterns >out &&
+
+	cat >expect <<-EOF &&
+	0:commit::$(git rev-parse topic)
+	0:commit::$(git rev-parse base)
+	0:commit::$(git rev-parse base~1)
+	0:commit::$(git rev-parse base~2)
+	1:tree::$(git rev-parse topic^{tree})
+	1:tree::$(git rev-parse base^{tree})
+	1:tree::$(git rev-parse base~1^{tree})
+	1:tree::$(git rev-parse base~2^{tree})
+	2:blob:a:$(git rev-parse base~2:a)
+	3:tree:left/:$(git rev-parse base:left)
+	3:tree:left/:$(git rev-parse base~2:left)
+	4:blob:left/b:$(git rev-parse base~2:left/b)
+	4:blob:left/b:$(git rev-parse base:left/b)
+	blobs:3
+	commits:4
+	tags:0
+	trees:6
+	EOF
+
+	test_cmp_sorted expect out
+'
+
 test_expect_success 'topic only' '
 	test-tool path-walk -- topic >out &&