Merge branch 'jt/non-blob-lazy-fetch'

A partial clone that is configured to lazily fetch missing objects
will on-demand issue a "git fetch" request to the originating
repository to fill not-yet-obtained objects.  The request has been
optimized for requesting a tree object (and not the leaf blob
objects contained in it) by telling the originating repository that
no blobs are needed.

* jt/non-blob-lazy-fetch:
  fetch-pack: exclude blobs when lazy-fetching trees
  fetch-pack: avoid object flags if no_dependents

Author: gitster

fetch-pack.c

@@ -253,8 +253,10 @@ static int find_common(struct fetch_negotiator *negotiator,
 	if (args->stateless_rpc && multi_ack == 1)
 		die(_("--stateless-rpc requires multi_ack_detailed"));
 
-	mark_tips(negotiator, args->negotiation_tips);
-	for_each_cached_alternate(negotiator, insert_one_alternate_object);
+	if (!args->no_dependents) {
+		mark_tips(negotiator, args->negotiation_tips);
+		for_each_cached_alternate(negotiator, insert_one_alternate_object);
+	}
 
 	fetching = 0;
 	for ( ; refs ; refs = refs->next) {
@@ -271,8 +273,12 @@ static int find_common(struct fetch_negotiator *negotiator,
 		 * We use lookup_object here because we are only
 		 * interested in the case we *know* the object is
 		 * reachable and we have already scanned it.
+		 *
+		 * Do this only if args->no_dependents is false (if it is true,
+		 * we cannot trust the object flags).
 		 */
-		if (((o = lookup_object(the_repository, remote->hash)) != NULL) &&
+		if (!args->no_dependents &&
+		    ((o = lookup_object(the_repository, remote->hash)) != NULL) &&
 				(o->flags & COMPLETE)) {
 			continue;
 		}
@@ -707,31 +713,29 @@ static void mark_complete_and_common_ref(struct fetch_negotiator *negotiator,
 
 	oidset_clear(&loose_oid_set);
 
-	if (!args->no_dependents) {
-		if (!args->deepen) {
-			for_each_ref(mark_complete_oid, NULL);
-			for_each_cached_alternate(NULL, mark_alternate_complete);
-			commit_list_sort_by_date(&complete);
-			if (cutoff)
-				mark_recent_complete_commits(args, cutoff);
-		}
+	if (!args->deepen) {
+		for_each_ref(mark_complete_oid, NULL);
+		for_each_cached_alternate(NULL, mark_alternate_complete);
+		commit_list_sort_by_date(&complete);
+		if (cutoff)
+			mark_recent_complete_commits(args, cutoff);
+	}
 
-		/*
-		 * Mark all complete remote refs as common refs.
-		 * Don't mark them common yet; the server has to be told so first.
-		 */
-		for (ref = *refs; ref; ref = ref->next) {
-			struct object *o = deref_tag(the_repository,
-						     lookup_object(the_repository,
-						     ref->old_oid.hash),
-						     NULL, 0);
+	/*
+	 * Mark all complete remote refs as common refs.
+	 * Don't mark them common yet; the server has to be told so first.
+	 */
+	for (ref = *refs; ref; ref = ref->next) {
+		struct object *o = deref_tag(the_repository,
+					     lookup_object(the_repository,
+					     ref->old_oid.hash),
+					     NULL, 0);
 
-			if (!o || o->type != OBJ_COMMIT || !(o->flags & COMPLETE))
-				continue;
+		if (!o || o->type != OBJ_COMMIT || !(o->flags & COMPLETE))
+			continue;
 
-			negotiator->known_common(negotiator,
-						 (struct commit *)o);
-		}
+		negotiator->known_common(negotiator,
+					 (struct commit *)o);
 	}
 
 	save_commit_buffer = old_save_commit_buffer;
@@ -987,11 +991,15 @@ static struct ref *do_fetch_pack(struct fetch_pack_args *args,
 	if (!server_supports("deepen-relative") && args->deepen_relative)
 		die(_("Server does not support --deepen"));
 
-	mark_complete_and_common_ref(&negotiator, args, &ref);
-	filter_refs(args, &ref, sought, nr_sought);
-	if (everything_local(args, &ref)) {
-		packet_flush(fd[1]);
-		goto all_done;
+	if (!args->no_dependents) {
+		mark_complete_and_common_ref(&negotiator, args, &ref);
+		filter_refs(args, &ref, sought, nr_sought);
+		if (everything_local(args, &ref)) {
+			packet_flush(fd[1]);
+			goto all_done;
+		}
+	} else {
+		filter_refs(args, &ref, sought, nr_sought);
 	}
 	if (find_common(&negotiator, args, fd, &oid, ref) < 0)
 		if (!args->keep_pack)
@@ -1037,7 +1045,7 @@ static void add_shallow_requests(struct strbuf *req_buf,
 	}
 }
 
-static void add_wants(const struct ref *wants, struct strbuf *req_buf)
+static void add_wants(int no_dependents, const struct ref *wants, struct strbuf *req_buf)
 {
 	int use_ref_in_want = server_supports_feature("fetch", "ref-in-want", 0);
 
@@ -1054,8 +1062,12 @@ static void add_wants(const struct ref *wants, struct strbuf *req_buf)
 		 * We use lookup_object here because we are only
 		 * interested in the case we *know* the object is
 		 * reachable and we have already scanned it.
+		 *
+		 * Do this only if args->no_dependents is false (if it is true,
+		 * we cannot trust the object flags).
 		 */
-		if (((o = lookup_object(the_repository, remote->hash)) != NULL) &&
+		if (!no_dependents &&
+		    ((o = lookup_object(the_repository, remote->hash)) != NULL) &&
 		    (o->flags & COMPLETE)) {
 			continue;
 		}
@@ -1152,7 +1164,7 @@ static int send_fetch_request(struct fetch_negotiator *negotiator, int fd_out,
 	}
 
 	/* add wants */
-	add_wants(wants, &req_buf);
+	add_wants(args->no_dependents, wants, &req_buf);
 
 	if (args->no_dependents) {
 		packet_buf_write(&req_buf, "done");
@@ -1343,16 +1355,21 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
 				args->deepen = 1;
 
 			/* Filter 'ref' by 'sought' and those that aren't local */
-			mark_complete_and_common_ref(&negotiator, args, &ref);
-			filter_refs(args, &ref, sought, nr_sought);
-			if (everything_local(args, &ref))
-				state = FETCH_DONE;
-			else
+			if (!args->no_dependents) {
+				mark_complete_and_common_ref(&negotiator, args, &ref);
+				filter_refs(args, &ref, sought, nr_sought);
+				if (everything_local(args, &ref))
+					state = FETCH_DONE;
+				else
+					state = FETCH_SEND_REQUEST;
+
+				mark_tips(&negotiator, args->negotiation_tips);
+				for_each_cached_alternate(&negotiator,
+							  insert_one_alternate_object);
+			} else {
+				filter_refs(args, &ref, sought, nr_sought);
 				state = FETCH_SEND_REQUEST;
-
-			mark_tips(&negotiator, args->negotiation_tips);
-			for_each_cached_alternate(&negotiator,
-						  insert_one_alternate_object);
+			}
 			break;
 		case FETCH_SEND_REQUEST:
 			if (send_fetch_request(&negotiator, fd[1], args, ref,
@@ -1595,6 +1612,20 @@ struct ref *fetch_pack(struct fetch_pack_args *args,
 	if (nr_sought)
 		nr_sought = remove_duplicates_in_refs(sought, nr_sought);
 
+	if (args->no_dependents && !args->filter_options.choice) {
+		/*
+		 * The protocol does not support requesting that only the
+		 * wanted objects be sent, so approximate this by setting a
+		 * "blob:none" filter if no filter is already set. This works
+		 * for all object types: note that wanted blobs will still be
+		 * sent because they are directly specified as a "want".
+		 *
+		 * NEEDSWORK: Add an option in the protocol to request that
+		 * only the wanted objects be sent, and implement it.
+		 */
+		parse_list_objects_filter(&args->filter_options, "blob:none");
+	}
+
 	if (!ref) {
 		packet_flush(fd[1]);
 		die(_("no matching remote head"));

fetch-pack.h

@@ -43,6 +43,13 @@ struct fetch_pack_args {
 	unsigned from_promisor:1;
 
 	/*
+	 * Attempt to fetch only the wanted objects, and not any objects
+	 * referred to by them. Due to protocol limitations, extraneous
+	 * objects may still be included. (When fetching non-blob
+	 * objects, only blobs are excluded; when fetching a blob, the
+	 * blob itself will still be sent. The client does not need to
+	 * know whether a wanted object is a blob or not.)
+	 *
 	 * If 1, fetch_pack() will also not modify any object flags.
 	 * This allows fetch_pack() to safely be called by any function,
 	 * regardless of which object flags it uses (if any).

t/t0410-partial-clone.sh

@@ -182,6 +182,47 @@ test_expect_success 'fetching of missing objects works with ref-in-want enabled'
 	grep "git< fetch=.*ref-in-want" trace
 '
 
+test_expect_success 'fetching of missing blobs works' '
+	rm -rf server repo &&
+	test_create_repo server &&
+	test_commit -C server foo &&
+	git -C server repack -a -d --write-bitmap-index &&
+
+	git clone "file://$(pwd)/server" repo &&
+	git hash-object repo/foo.t >blobhash &&
+	rm -rf repo/.git/objects/* &&
+
+	git -C server config uploadpack.allowanysha1inwant 1 &&
+	git -C server config uploadpack.allowfilter 1 &&
+	git -C repo config core.repositoryformatversion 1 &&
+	git -C repo config extensions.partialclone "origin" &&
+
+	git -C repo cat-file -p $(cat blobhash)
+'
+
+test_expect_success 'fetching of missing trees does not fetch blobs' '
+	rm -rf server repo &&
+	test_create_repo server &&
+	test_commit -C server foo &&
+	git -C server repack -a -d --write-bitmap-index &&
+
+	git clone "file://$(pwd)/server" repo &&
+	git -C repo rev-parse foo^{tree} >treehash &&
+	git hash-object repo/foo.t >blobhash &&
+	rm -rf repo/.git/objects/* &&
+
+	git -C server config uploadpack.allowanysha1inwant 1 &&
+	git -C server config uploadpack.allowfilter 1 &&
+	git -C repo config core.repositoryformatversion 1 &&
+	git -C repo config extensions.partialclone "origin" &&
+	git -C repo cat-file -p $(cat treehash) &&
+
+	# Ensure that the tree, but not the blob, is fetched
+	git -C repo rev-list --objects --missing=print $(cat treehash) >objects &&
+	grep "^$(cat treehash)" objects &&
+	grep "^[?]$(cat blobhash)" objects
+'
+
 test_expect_success 'rev-list stops traversal at missing and promised commit' '
 	rm -rf repo &&
 	test_create_repo repo &&