clone: support excluding large blobs

Teach clone to support excluding large blobs through a blob-max-bytes
parameter.

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

2 files changed, 70 insertions, 2 deletions

diff --git a/builtin/clone.c b/builtin/clone.c
index dbddd98f80..4c2193dc41 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -60,6 +60,7 @@ static struct string_list option_optional_reference = STRING_LIST_INIT_NODUP;
 static int option_dissociate;
 static int max_jobs = -1;
 static struct string_list option_recurse_submodules = STRING_LIST_INIT_NODUP;
+static char *blob_max_bytes;
 
 static int recurse_submodules_cb(const struct option *opt,
 				 const char *arg, int unset)
@@ -135,6 +136,8 @@ static struct option builtin_clone_options[] = {
 			TRANSPORT_FAMILY_IPV4),
 	OPT_SET_INT('6', "ipv6", &family, N_("use IPv6 addresses only"),
 			TRANSPORT_FAMILY_IPV6),
+	OPT_STRING(0, "blob-max-bytes", &blob_max_bytes, N_("bytes"),
+		   N_("do not fetch blobs above this size")),
 	OPT_END()
 };
 
@@ -886,6 +889,8 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	struct refspec *refspec;
 	const char *fetch_pattern;
 
+	fetch_if_missing = 0;
+
 	packet_trace_identity("clone");
 	argc = parse_options(argc, argv, prefix, builtin_clone_options,
 			     builtin_clone_usage, 0);
@@ -1104,7 +1109,13 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		transport_set_option(transport, TRANS_OPT_UPLOADPACK,
 				     option_upload_pack);
 
-	if (transport->smart_options && !deepen)
+	if (blob_max_bytes) {
+		transport_set_option(transport, TRANS_OPT_BLOB_MAX_BYTES,
+				     blob_max_bytes);
+		transport_set_option(transport, TRANS_OPT_FROM_PROMISOR, "1");
+	}
+
+	if (transport->smart_options && !deepen && !blob_max_bytes)
 		transport->smart_options->check_self_contained_and_connected = 1;
 
 	refs = transport_get_remote_refs(transport);
@@ -1164,13 +1175,20 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	write_refspec_config(src_ref_prefix, our_head_points_at,
 			remote_head_points_at, &branch_top);
 
+	if (blob_max_bytes) {
+		git_config_set("core.repositoryformatversion", "1");
+		git_config_set("extensions.partialclone", "origin");
+		repository_format_partial_clone = "origin";
+	}
+
 	if (is_local)
 		clone_local(path, git_dir);
 	else if (refs && complete_refs_before_fetch)
 		transport_fetch_refs(transport, mapped_refs);
 
 	update_remote_refs(refs, mapped_refs, remote_head_points_at,
-			   branch_top.buf, reflog_msg.buf, transport, !is_local);
+			   branch_top.buf, reflog_msg.buf, transport,
+			   !is_local && !blob_max_bytes);
 
 	update_head(our_head_points_at, remote_head, reflog_msg.buf);
 
@@ -1191,6 +1209,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	}
 
 	junk_mode = JUNK_LEAVE_REPO;
+	fetch_if_missing = 1;
 	err = checkout(submodule_progress);
 
 	strbuf_release(&reflog_msg);
diff --git a/t/t5601-clone.sh b/t/t5601-clone.sh
index 9c56f771b6..951b1ffa80 100755
--- a/t/t5601-clone.sh
+++ b/t/t5601-clone.sh
@@ -571,4 +571,53 @@ test_expect_success 'GIT_TRACE_PACKFILE produces a usable pack' '
 	git -C replay.git index-pack -v --stdin <tmp.pack
 '
 
+partial_clone () {
+	SERVER="$1" &&
+	URL="$2" &&
+
+	rm -rf "$SERVER" client &&
+	test_create_repo "$SERVER" &&
+	test_commit -C "$SERVER" one &&
+	HASH1=$(git hash-object "$SERVER/one.t") &&
+	git -C "$SERVER" revert HEAD &&
+	test_commit -C "$SERVER" two &&
+	HASH2=$(git hash-object "$SERVER/two.t") &&
+	test_config -C "$SERVER" uploadpack.advertiseblobmaxbytes 1 &&
+	test_config -C "$SERVER" uploadpack.allowanysha1inwant 1 &&
+
+	git clone --blob-max-bytes=0 "$URL" client &&
+
+	git -C client fsck &&
+
+	# Ensure that unneeded blobs are not inadvertently fetched.
+	test_config -C client extensions.partialclone "not a remote" &&
+	test_must_fail git -C client cat-file -e "$HASH1" &&
+
+	# But this blob was fetched, because clone performs an initial checkout
+	git -C client cat-file -e "$HASH2"
+}
+
+test_expect_success 'partial clone' '
+	partial_clone server "file://$(pwd)/server"
+'
+
+test_expect_success 'partial clone: warn if server does not support blob-max-bytes' '
+	rm -rf server client &&
+	test_create_repo server &&
+	test_commit -C server one &&
+
+	git clone --blob-max-bytes=0 "file://$(pwd)/server" client 2> err &&
+
+	test_i18ngrep "blob-max-bytes not recognized by server" err
+'
+
+. "$TEST_DIRECTORY"/lib-httpd.sh
+start_httpd
+
+test_expect_success 'partial clone using HTTP' '
+	partial_clone "$HTTPD_DOCUMENT_ROOT_PATH/server" "$HTTPD_URL/smart/server"
+'
+
+stop_httpd
+
 test_done