upload-pack: advertise capabilities when cloning empty repos

When cloning an empty repository, protocol versions 0 and 1 currently
offer nothing but the header and flush packets for the /info/refs
endpoint. This means that no capabilities are provided, so the client
side doesn't know what capabilities are present.

However, this does pose a problem when working with SHA-256
repositories, since we use the capabilities to know the remote side's
object format (hash algorithm).  As of 8b214c2e9d ("clone: propagate
object-format when cloning from void", 2023-04-05), this has been fixed
for protocol v2, since there we always read the hash algorithm from the
remote.

Fortunately, the push version of the protocol already indicates a clue
for how to solve this.  When the /info/refs endpoint is accessed for a
push and the remote is empty, we include a dummy "capabilities^{}" ref
pointing to the all-zeros object ID.  The protocol documentation already
indicates this should _always_ be sent, even for fetches and clones, so
let's just do that, which means we'll properly announce the hash
algorithm as part of the capabilities.  This just works with the
existing code because we share the same ref code for fetches and clones,
and libgit2, JGit, and dulwich do as well.

There is one minor issue to fix, though.  If we called send_ref with
namespaces, we would return NULL with the capabilities entry, which
would cause a crash.  Instead, let's refactor out a function to print
just the ref itself without stripping the namespace and use it for our
special capabilities entry.

Add several sets of tests for HTTP as well as for local clones.  The
behavior can be slightly different for HTTP versus a local or SSH clone
because of the stateless-rpc functionality, so it's worth testing both.

Signed-off-by: brian m. carlson <bk2204@github.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 17 insertions, 5 deletions

diff --git a/upload-pack.c b/upload-pack.c
index 08633dc121..d3312006a3 100644
--- a/upload-pack.c
+++ b/upload-pack.c
@@ -120,6 +120,7 @@ struct upload_pack_data {
 	unsigned allow_ref_in_want : 1;				/* v2 only */
 	unsigned allow_sideband_all : 1;			/* v2 only */
 	unsigned advertise_sid : 1;
+	unsigned sent_capabilities : 1;
 };
 
 static void upload_pack_data_init(struct upload_pack_data *data)
@@ -1206,18 +1207,17 @@ static void format_session_id(struct strbuf *buf, struct upload_pack_data *d) {
 		strbuf_addf(buf, " session-id=%s", trace2_session_id());
 }
 
-static int send_ref(const char *refname, const struct object_id *oid,
-		    int flag UNUSED, void *cb_data)
+static void write_v0_ref(struct upload_pack_data *data,
+			const char *refname, const char *refname_nons,
+			const struct object_id *oid)
 {
 	static const char *capabilities = "multi_ack thin-pack side-band"
 		" side-band-64k ofs-delta shallow deepen-since deepen-not"
 		" deepen-relative no-progress include-tag multi_ack_detailed";
-	const char *refname_nons = strip_namespace(refname);
 	struct object_id peeled;
-	struct upload_pack_data *data = cb_data;
 
 	if (mark_our_ref(refname_nons, refname, oid, &data->hidden_refs))
-		return 0;
+		return;
 
 	if (capabilities) {
 		struct strbuf symref_info = STRBUF_INIT;
@@ -1240,12 +1240,20 @@ static int send_ref(const char *refname, const struct object_id *oid,
 			     git_user_agent_sanitized());
 		strbuf_release(&symref_info);
 		strbuf_release(&session_id);
+		data->sent_capabilities = 1;
 	} else {
 		packet_fwrite_fmt(stdout, "%s %s\n", oid_to_hex(oid), refname_nons);
 	}
 	capabilities = NULL;
 	if (!peel_iterated_oid(oid, &peeled))
 		packet_fwrite_fmt(stdout, "%s %s^{}\n", oid_to_hex(&peeled), refname_nons);
+	return;
+}
+
+static int send_ref(const char *refname, const struct object_id *oid,
+		    int flag UNUSED, void *cb_data)
+{
+	write_v0_ref(cb_data, refname, strip_namespace(refname), oid);
 	return 0;
 }
 
@@ -1379,6 +1387,10 @@ void upload_pack(const int advertise_refs, const int stateless_rpc,
 			data.no_done = 1;
 		head_ref_namespaced(send_ref, &data);
 		for_each_namespaced_ref(send_ref, &data);
+		if (!data.sent_capabilities) {
+			const char *refname = "capabilities^{}";
+			write_v0_ref(&data, refname, refname, null_oid());
+		}
 		/*
 		 * fflush stdout before calling advertise_shallow_grafts because send_ref
 		 * uses stdio.