fetch: support filters

Teach fetch to support filters. This is only allowed for the remote
configured in extensions.partialcloneremote.

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

builtin/fetch.c

@@ -18,6 +18,7 @@
 #include "argv-array.h"
 #include "utf8.h"
 #include "packfile.h"
+#include "list-objects-filter-options.h"
 
 static const char * const builtin_fetch_usage[] = {
 	N_("git fetch [<options>] [<repository> [<refspec>...]]"),
@@ -55,6 +56,7 @@ 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 struct list_objects_filter_options filter_options;
 
 static int git_fetch_config(const char *k, const char *v, void *cb)
 {
@@ -160,6 +162,7 @@ static struct option builtin_fetch_options[] = {
 			TRANSPORT_FAMILY_IPV4),
 	OPT_SET_INT('6', "ipv6", &family, N_("use IPv6 addresses only"),
 			TRANSPORT_FAMILY_IPV6),
+	OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options),
 	OPT_END()
 };
 
@@ -1044,6 +1047,11 @@ 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 (filter_options.choice) {
+		set_option(transport, TRANS_OPT_LIST_OBJECTS_FILTER,
+			   filter_options.filter_spec);
+		set_option(transport, TRANS_OPT_FROM_PROMISOR, "1");
+	}
 	return transport;
 }
 
@@ -1328,6 +1336,8 @@ 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 +1371,9 @@ int cmd_fetch(int argc, const char **argv, const char *prefix)
 	if (depth || deepen_since || deepen_not.nr)
 		deepen = 1;
 
+	if (filter_options.choice && !repository_format_partial_clone)
+		die("--filter 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 +1403,16 @@ int cmd_fetch(int argc, const char **argv, const char *prefix)
 		}
 	}
 
-	if (remote)
+	if (remote) {
+		if (filter_options.choice &&
+		    strcmp(remote->name, repository_format_partial_clone))
+			die(_("--filter can only be used with the remote configured in core.partialClone"));
 		result = fetch_one(remote, argc, argv);
-	else
+	} else {
+		if (filter_options.choice)
+			die(_("--filter 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;

connected.c

@@ -56,6 +56,8 @@ 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");
+	if (repository_format_partial_clone)
+		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");

remote-curl.c

@@ -24,6 +24,7 @@ struct options {
 	char *deepen_since;
 	struct string_list deepen_not;
 	struct string_list push_options;
+	char *filter;
 	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-dependents")) {
 		options.no_dependents = 1;
 		return 0;
+	} else if (!strcmp(name, "filter")) {
+		options.filter = xstrdup(value);;
+		return 0;
 	} else {
 		return 1 /* unsupported */;
 	}
@@ -834,6 +838,8 @@ static int fetch_git(struct discovery *heads,
 		argv_array_push(&args, "--from-promisor");
 	if (options.no_dependents)
 		argv_array_push(&args, "--no-dependents");
+	if (options.filter)
+		argv_array_pushf(&args, "--filter=%s", options.filter);
 	argv_array_push(&args, url.buf);
 
 	for (i = 0; i < nr_heads; i++) {

t/t5500-fetch-pack.sh

@@ -782,4 +782,40 @@ test_expect_success 'filtering by size has no effect if support for it is not ad
 	test_i18ngrep "filtering not recognized by server" err
 '
 
+fetch_filter_blob_limit_zero () {
+	SERVER="$1"
+	URL="$2"
+
+	rm -rf "$SERVER" client &&
+	test_create_repo "$SERVER" &&
+	test_commit -C "$SERVER" one &&
+	test_config -C "$SERVER" uploadpack.allowfilter 1 &&
+
+	git clone "$URL" client &&
+	test_config -C client extensions.partialclone origin &&
+
+	test_commit -C "$SERVER" two &&
+
+	git -C client fetch --filter=blob:limit=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 --filter=blob:limit=0' '
+	fetch_filter_blob_limit_zero server server
+'
+
+. "$TEST_DIRECTORY"/lib-httpd.sh
+start_httpd
+
+test_expect_success 'fetch with --filter=blob:limit=0 and HTTP' '
+	fetch_filter_blob_limit_zero "$HTTPD_DOCUMENT_ROOT_PATH/server" "$HTTPD_URL/smart/server"
+'
+
+stop_httpd
+
+
 test_done