fetch: support excluding large blobs

Teach fetch to support excluding large blobs through a blob-max-bytes
parameter. This is only allowed for the remote configured in
extensions.partialclone.

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

7 files changed, 82 insertions, 2 deletions

diff --git a/builtin/fetch.c b/builtin/fetch.c
index 1b1f03923d..07beaf5b54 100644
--- a/builtin/fetch.c
+++ b/builtin/fetch.c
@@ -55,6 +55,7 @@ static int recurse_submodules_default = RECURSE_SUBMODULES_ON_DEMAND;
 static int shown_url = 0;
 static int refmap_alloc, refmap_nr;
 static const char **refmap_array;
+static const char *blob_max_bytes;
 
 static int git_fetch_config(const char *k, const char *v, void *cb)
 {
@@ -160,6 +161,8 @@ static struct option builtin_fetch_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()
 };
 
@@ -1044,6 +1047,10 @@ static struct transport *prepare_transport(struct remote *remote, int deepen)
 		set_option(transport, TRANS_OPT_DEEPEN_RELATIVE, "yes");
 	if (update_shallow)
 		set_option(transport, TRANS_OPT_UPDATE_SHALLOW, "yes");
+	if (blob_max_bytes) {
+		set_option(transport, TRANS_OPT_BLOB_MAX_BYTES, blob_max_bytes);
+		set_option(transport, TRANS_OPT_FROM_PROMISOR, "1");
+	}
 	return transport;
 }
 
@@ -1328,6 +1335,8 @@ int cmd_fetch(int argc, const char **argv, const char *prefix)
 
 	packet_trace_identity("fetch");
 
+	fetch_if_missing = 0;
+
 	/* Record the command line for the reflog */
 	strbuf_addstr(&default_rla, "fetch");
 	for (i = 1; i < argc; i++)
@@ -1361,6 +1370,9 @@ int cmd_fetch(int argc, const char **argv, const char *prefix)
 	if (depth || deepen_since || deepen_not.nr)
 		deepen = 1;
 
+	if (blob_max_bytes && !repository_format_partial_clone)
+		die("--blob-max-bytes can only be used when extensions.partialClone is set");
+
 	if (all) {
 		if (argc == 1)
 			die(_("fetch --all does not take a repository argument"));
@@ -1390,10 +1402,16 @@ int cmd_fetch(int argc, const char **argv, const char *prefix)
 		}
 	}
 
-	if (remote)
+	if (remote) {
+		if (blob_max_bytes &&
+		    strcmp(remote->name, repository_format_partial_clone))
+			die(_("--blob-max-bytes can only be used with the remote configured in core.partialClone"));
 		result = fetch_one(remote, argc, argv);
-	else
+	} else {
+		if (blob_max_bytes)
+			die(_("--blob-max-bytes can only be used with the remote configured in core.partialClone"));
 		result = fetch_multiple(&list);
+	}
 
 	if (!result && (recurse_submodules != RECURSE_SUBMODULES_OFF)) {
 		struct argv_array options = ARGV_ARRAY_INIT;
diff --git a/connected.c b/connected.c
index f416b05051..a51c01d636 100644
--- a/connected.c
+++ b/connected.c
@@ -56,6 +56,7 @@ int check_connected(sha1_iterate_fn fn, void *cb_data,
 	argv_array_push(&rev_list.args,"rev-list");
 	argv_array_push(&rev_list.args, "--objects");
 	argv_array_push(&rev_list.args, "--stdin");
+	argv_array_push(&rev_list.args, "--exclude-promisor-objects");
 	argv_array_push(&rev_list.args, "--not");
 	argv_array_push(&rev_list.args, "--all");
 	argv_array_push(&rev_list.args, "--quiet");
diff --git a/remote-curl.c b/remote-curl.c
index 34a81b8d3f..18fd184c13 100644
--- a/remote-curl.c
+++ b/remote-curl.c
@@ -24,6 +24,7 @@ struct options {
 	char *deepen_since;
 	struct string_list deepen_not;
 	struct string_list push_options;
+	char *blob_max_bytes;
 	unsigned progress : 1,
 		check_self_contained_and_connected : 1,
 		cloning : 1,
@@ -165,6 +166,9 @@ static int set_option(const char *name, const char *value)
 	} else if (!strcmp(name, "no-haves")) {
 		options.no_haves = 1;
 		return 0;
+	} else if (!strcmp(name, "blob-max-bytes")) {
+		options.blob_max_bytes = xstrdup(value);
+		return 0;
 	} else {
 		return 1 /* unsupported */;
 	}
@@ -834,6 +838,9 @@ static int fetch_git(struct discovery *heads,
 		argv_array_push(&args, "--from-promisor");
 	if (options.no_haves)
 		argv_array_push(&args, "--no-haves");
+	if (options.blob_max_bytes)
+		argv_array_pushf(&args, "--blob-max-bytes=%s",
+				 options.blob_max_bytes);
 	argv_array_push(&args, url.buf);
 
 	for (i = 0; i < nr_heads; i++) {
diff --git a/t/t5500-fetch-pack.sh b/t/t5500-fetch-pack.sh
index 62e384230d..b2682862f7 100755
--- a/t/t5500-fetch-pack.sh
+++ b/t/t5500-fetch-pack.sh
@@ -782,4 +782,40 @@ test_expect_success '--blob-max-bytes has no effect if support for it is not adv
 	test_i18ngrep "blob-max-bytes not recognized by server" err
 '
 
+fetch_blob_max_bytes () {
+	SERVER="$1"
+	URL="$2"
+
+	rm -rf "$SERVER" client &&
+	test_create_repo "$SERVER" &&
+	test_commit -C "$SERVER" one &&
+	test_config -C "$SERVER" uploadpack.advertiseblobmaxbytes 1 &&
+
+	git clone "$URL" client &&
+	test_config -C client extensions.partialclone origin &&
+
+	test_commit -C "$SERVER" two &&
+
+	git -C client fetch --blob-max-bytes=0 origin HEAD:somewhere &&
+
+	# Ensure that commit is fetched, but blob is not
+	test_config -C client extensions.partialclone "arbitrary string" &&
+	git -C client cat-file -e $(git -C "$SERVER" rev-parse two) &&
+	test_must_fail git -C client cat-file -e $(git hash-object "$SERVER/two.t")
+}
+
+test_expect_success 'fetch with --blob-max-bytes' '
+	fetch_blob_max_bytes server server
+'
+
+. "$TEST_DIRECTORY"/lib-httpd.sh
+start_httpd
+
+test_expect_success 'fetch with --blob-max-bytes and HTTP' '
+	fetch_blob_max_bytes "$HTTPD_DOCUMENT_ROOT_PATH/server" "$HTTPD_URL/smart/server"
+'
+
+stop_httpd
+
+
 test_done
diff --git a/transport-helper.c b/transport-helper.c
index 42b960ff86..9c1874b704 100644
--- a/transport-helper.c
+++ b/transport-helper.c
@@ -672,6 +672,10 @@ static int fetch(struct transport *transport,
 	if (data->transport_options.update_shallow)
 		set_helper_option(transport, "update-shallow", "true");
 
+	if (data->transport_options.blob_max_bytes)
+		set_helper_option(transport, "blob-max-bytes",
+				  data->transport_options.blob_max_bytes);
+
 	if (data->fetch)
 		return fetch_with_fetch(transport, nr_heads, to_fetch);
 
diff --git a/transport.c b/transport.c
index fb46e33bf1..6408af19ec 100644
--- a/transport.c
+++ b/transport.c
@@ -167,6 +167,9 @@ static int set_git_option(struct git_transport_options *opts,
 	} else if (!strcmp(name, TRANS_OPT_NO_HAVES)) {
 		opts->no_haves = !!value;
 		return 0;
+	} else if (!strcmp(name, TRANS_OPT_BLOB_MAX_BYTES)) {
+		opts->blob_max_bytes = value;
+		return 0;
 	}
 	return 1;
 }
@@ -237,6 +240,13 @@ static int fetch_refs_via_pack(struct transport *transport,
 	args.update_shallow = data->options.update_shallow;
 	args.from_promisor = data->options.from_promisor;
 	args.no_haves = data->options.no_haves;
+	if (data->options.blob_max_bytes) {
+		unsigned long *ptr = xmalloc(sizeof(*ptr));
+		if (!git_parse_ulong(data->options.blob_max_bytes, ptr))
+			die("Invalid blob-max-bytes value: %s",
+			    data->options.blob_max_bytes);
+		args.blob_max_bytes = ptr;
+	}
 
 	if (!data->got_remote_heads) {
 		connect_setup(transport, 0);
diff --git a/transport.h b/transport.h
index 67428f6df6..79d4442b1c 100644
--- a/transport.h
+++ b/transport.h
@@ -23,6 +23,7 @@ struct git_transport_options {
 	const char *uploadpack;
 	const char *receivepack;
 	struct push_cas_option *cas;
+	const char *blob_max_bytes;
 };
 
 enum transport_family {
@@ -218,6 +219,9 @@ void transport_check_allowed(const char *type);
 /* Do not send "have" lines */
 #define TRANS_OPT_NO_HAVES "no-haves"
 
+/* Exclude blobs above a certain size */
+#define TRANS_OPT_BLOB_MAX_BYTES "blob-max-bytes"
+
 /**
  * Returns 0 if the option was used, non-zero otherwise. Prints a
  * message to stderr if the option is not used.