fetch: remove fetch_if_missing=0

In fetch_pack() (and all functions it calls), pass
OBJECT_INFO_SKIP_FETCH_OBJECT whenever we query an object that could be
a tree or blob that we do not want to be lazy-fetched even if it is
absent. Thus, the only lazy-fetches occurring for trees and blobs are
when resolving deltas.

Thus, we can remove fetch_if_missing=0 from builtin/fetch.c. Remove
this, and also add a test ensuring that such objects are not
lazy-fetched. (We might be able to remove fetch_if_missing=0 from other
places too, but I have limited myself to builtin/fetch.c in this commit
because I have not written tests for the other commands yet.)

Note that commits and tags may still be lazy-fetched. I limited myself
to objects that could be trees or blobs here because Git does not
support creating such commit- and tag-excluding clones yet, and even if
such a clone were manually created, Git does not have good support for
fetching a single commit (when fetching a commit, it and all its
ancestors would be sent).

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

builtin/fetch.c

@@ -1074,7 +1074,8 @@ static int check_exist_and_connected(struct ref *ref_map)
 	 * we need all direct targets to exist.
 	 */
 	for (r = rm; r; r = r->next) {
-		if (!has_object_file(&r->old_oid))
+		if (!has_object_file_with_flags(&r->old_oid,
+						OBJECT_INFO_SKIP_FETCH_OBJECT))
 			return -1;
 	}
 
@@ -1822,8 +1823,6 @@ int cmd_fetch(int argc, const char **argv, const char *prefix)
 		}
 	}
 
-	fetch_if_missing = 0;
-
 	if (remote) {
 		if (filter_options.choice || has_promisor_remote())
 			fetch_one_setup_partial(remote);

fetch-pack.c

@@ -673,7 +673,8 @@ static void mark_complete_and_common_ref(struct fetch_negotiator *negotiator,
 		struct object *o;
 
 		if (!has_object_file_with_flags(&ref->old_oid,
-						OBJECT_INFO_QUICK))
+						OBJECT_INFO_QUICK |
+							OBJECT_INFO_SKIP_FETCH_OBJECT))
 			continue;
 		o = parse_object(the_repository, &ref->old_oid);
 		if (!o)

t/t5616-partial-clone.sh

@@ -296,6 +296,76 @@ test_expect_success 'partial clone with unresolvable sparse filter fails cleanly
 	test_i18ngrep "unable to parse sparse filter data in" err
 '
 
+setup_triangle () {
+	rm -rf big-blob.txt server client promisor-remote &&
+
+	printf "line %d\n" $(test_seq 1 100) >big-blob.txt &&
+
+	# Create a server with 2 commits: a commit with a big blob and a child
+	# commit with an incremental change. Also, create a partial clone
+	# client that only contains the first commit.
+	git init server &&
+	git -C server config --local uploadpack.allowfilter 1 &&
+	cp big-blob.txt server &&
+	git -C server add big-blob.txt &&
+	git -C server commit -m "initial" &&
+	git clone --bare --filter=tree:0 "file://$(pwd)/server" client &&
+	echo another line >>server/big-blob.txt &&
+	git -C server commit -am "append line to big blob" &&
+
+	# Create a promisor remote that only contains the blob from the first
+	# commit, and set it as the promisor remote of client. Thus, whenever
+	# the client lazy fetches, the lazy fetch will succeed only if it is
+	# for this blob.
+	git init promisor-remote &&
+	test_commit -C promisor-remote one && # so that ref advertisement is not empty
+	git -C promisor-remote config --local uploadpack.allowanysha1inwant 1 &&
+	git -C promisor-remote hash-object -w --stdin <big-blob.txt &&
+	git -C client remote set-url origin "file://$(pwd)/promisor-remote"
+}
+
+# NEEDSWORK: The tests beginning with "fetch lazy-fetches" below only
+# test that "fetch" avoid fetching trees and blobs, but not commits or
+# tags. Revisit this if Git is ever taught to support partial clones
+# with commits and/or tags filtered out.
+
+test_expect_success 'fetch lazy-fetches only to resolve deltas' '
+	setup_triangle &&
+
+	# Exercise to make sure it works. Git will not fetch anything from the
+	# promisor remote other than for the big blob (because it needs to
+	# resolve the delta).
+	GIT_TRACE_PACKET="$(pwd)/trace" git -C client \
+		fetch "file://$(pwd)/server" master &&
+
+	# Verify the assumption that the client needed to fetch the delta base
+	# to resolve the delta.
+	git hash-object big-blob.txt >hash &&
+	grep "want $(cat hash)" trace
+'
+
+test_expect_success 'fetch lazy-fetches only to resolve deltas, protocol v2' '
+	setup_triangle &&
+
+	git -C server config --local protocol.version 2 &&
+	git -C client config --local protocol.version 2 &&
+	git -C promisor-remote config --local protocol.version 2 &&
+
+	# Exercise to make sure it works. Git will not fetch anything from the
+	# promisor remote other than for the big blob (because it needs to
+	# resolve the delta).
+	GIT_TRACE_PACKET="$(pwd)/trace" git -C client \
+		fetch "file://$(pwd)/server" master &&
+
+	# Verify that protocol version 2 was used.
+	grep "fetch< version 2" trace &&
+
+	# Verify the assumption that the client needed to fetch the delta base
+	# to resolve the delta.
+	git hash-object big-blob.txt >hash &&
+	grep "want $(cat hash)" trace
+'
+
 . "$TEST_DIRECTORY"/lib-httpd.sh
 start_httpd