[PATCH GSoC v21 11/13] transport: add client support for object-info

@@ -1169,6 +1169,7 @@ LIB_OBJS += ewah/ewah_io.o
 LIB_OBJS += ewah/ewah_rlw.o
 LIB_OBJS += exec-cmd.o
 LIB_OBJS += fetch-negotiator.o
+LIB_OBJS += fetch-object-info.o
 LIB_OBJS += fetch-pack.o
 LIB_OBJS += fmt-merge-msg.o
 LIB_OBJS += fsck.o

@@ -0,0 +1,138 @@
+#include "git-compat-util.h"
+#include "gettext.h"
+#include "hex.h"
+#include "pkt-line.h"
+#include "connect.h"
+#include "oid-array.h"
+#include "odb.h"
+#include "fetch-object-info.h"
+#include "string-list.h"
+
+/* Sends object-info command and its arguments into the request buffer. */
+static void send_object_info_request(const int fd_out, struct object_info_args *args)
+{
+	struct strbuf req_buf = STRBUF_INIT;
+
+	write_command_and_capabilities(&req_buf, "object-info", args->server_options);
+
+	if (unsorted_string_list_has_string(args->object_info_options, "size"))
+		packet_buf_write(&req_buf, "size");
+	else if (args->object_info_options->nr)
+		BUG("only size should be in object_info_options");
+
+	if (args->oids)
+		for (size_t i = 0; i < args->oids->nr; i++)
+			packet_buf_write(&req_buf, "oid %s", oid_to_hex(&args->oids->oid[i]));
+
+	packet_buf_flush(&req_buf);
+	if (write_in_full(fd_out, req_buf.buf, req_buf.len) < 0)
+		die_errno(_("unable to write request to remote"));
+
+	strbuf_release(&req_buf);
+}
+
+static int parse_object_size(const char *s, size_t *res)
+{
+	uintmax_t uim;
+
+	if (!s[0] || s[strspn(s, "0123456789")])
+		return -1;
+	errno = 0;
+	uim = strtoumax(s, NULL, 10);
+	if (errno || uim > SIZE_MAX)
+		return -1;
+	*res = uim;
+	return 0;
+}
+
+int fetch_object_info(const enum protocol_version version, struct object_info_args *args,
+		      struct packet_reader *reader, struct object_info *object_info_data,
+		      const int stateless_rpc, const int fd_out)
+{
+	int size_index = -1;
+
+	switch (version) {
+	case protocol_v2:
+		if (!server_supports_v2("object-info"))
+			die(_("object-info capability is not enabled on the server"));
+		send_object_info_request(fd_out, args);
+		break;
+	case protocol_v1:
+	case protocol_v0:
+		die(_("object-info requires protocol v2"));
+	case protocol_unknown_version:
+		BUG("unknown protocol version");
+	}
+
+	for (size_t i = 0; i < args->object_info_options->nr; i++) {
+		if (packet_reader_read(reader) != PACKET_READ_NORMAL) {
+			check_stateless_delimiter(stateless_rpc, reader,
+						  "stateless delimiter expected");
+			return -1;
+		}
+
+		if (!string_list_has_string(args->object_info_options, reader->line))
+			return -1;
+
+		if (!strcmp(reader->line, "size")) {
+			/*
+			 * i is the number of supported options which currently
+			 * is only size. No risk of overflow.
+			 */
+			size_index = (int)i;
+			for (size_t j = 0; j < args->oids->nr; j++)
+				object_info_data[j].sizep =
+					xcalloc(1, sizeof(*object_info_data[j].sizep));
+		} else {
+			BUG("only size is supported");
+		}
+	}
+
+	for (size_t i = 0;
+	     packet_reader_read(reader) == PACKET_READ_NORMAL &&
+	     i < args->oids->nr;
+	     i++) {
+		struct string_list object_info_values = STRING_LIST_INIT_DUP;
+
+		string_list_split(&object_info_values, reader->line, " ", -1);
+
+		if (strcmp(object_info_values.items[0].string,
+			   oid_to_hex(&args->oids->oid[i])))
+			die(_("object-info: expected OID: %s, got %s"),
+			    oid_to_hex(&args->oids->oid[i]),
+			    object_info_values.items[0].string);
+
+		/*
+		 * If the response is two elements but the second one is an
+		 * empty string, that means that the OID is unrecognized by the
+		 * server.
+		 */
+		if (object_info_values.nr >= 2 &&
+		    !strcmp(object_info_values.items[1].string, "")) {
+			object_info_data[i].unrecognized = 1;
+			string_list_clear(&object_info_values, 0);
+			continue;
+		}
+
+		/*
+		 * Because we filter the options to be only the supported by
+		 * the server we expect the server to answer with the same
+		 * number of attributes requested.
+		 */
+		if (args->object_info_options->nr + 1 != object_info_values.nr)
+			die("object-info: unexpected number of attributes: %s",
+			    reader->line);
+
+		if (size_index >= 0 &&
+		    parse_object_size(object_info_values.items[size_index + 1].string,
+				      object_info_data[i].sizep))
+			die("object-info: ref %s has invalid size %s",
+			    object_info_values.items[0].string,
+			    object_info_values.items[size_index + 1].string);
+
+		string_list_clear(&object_info_values, 0);
+	}
+	check_stateless_delimiter(stateless_rpc, reader, "stateless delimiter expected");
+
+	return 0;
+}

@@ -0,0 +1,22 @@
+#ifndef FETCH_OBJECT_INFO_H
+#define FETCH_OBJECT_INFO_H
+
+#include "pkt-line.h"
+#include "protocol.h"
+
+struct object_info_args {
+	struct string_list *object_info_options;
+	const struct string_list *server_options;
+	struct oid_array *oids;
+};
+
+struct object_info;
+/*
+ * Sends git-cat-file object-info command into the request buf and read the
+ * results from packets.
+ */
+int fetch_object_info(enum protocol_version version, struct object_info_args *args,
+		      struct packet_reader *reader, struct object_info *object_info_data,
+		      int stateless_rpc, int fd_out);
+
+#endif /* FETCH_OBJECT_INFO_H */

@@ -374,6 +374,7 @@ libgit_sources = [
   'ewah/ewah_rlw.c',
   'exec-cmd.c',
   'fetch-negotiator.c',
+  'fetch-object-info.c',
   'fetch-pack.c',
   'fmt-merge-msg.c',
   'fsck.c',

@@ -340,6 +340,12 @@ struct object_info {
 	 * or multiple times in the same source.
 	 */
 	struct odb_source_info *source_infop;
+
+	/*
+	 * object-info protocol specific. Set by the protocol when the remote
+	 * does not recognize the requested object.
+	 */
+	unsigned int unrecognized:1;
 };
 
 /*

@@ -784,6 +784,15 @@ static int fetch_refs(struct transport *transport,
 	return -1;
 }
 
+static int fetch_object_info_helper(struct transport *transport)
+{
+	get_helper(transport);
+	if (process_connect(transport, 0))
+		return transport->vtable->fetch_object_info(transport);
+
+	die(_("object-info requires protocol v2"));
+}
+
 struct push_update_ref_state {
 	struct ref *hint;
 	struct ref_push_report *report;

@@ -1330,6 +1339,7 @@ static struct transport_vtable vtable = {
 	.get_refs_list	= get_refs_list,
 	.get_bundle_uri = get_bundle_uri,
 	.fetch_refs	= fetch_refs,
+	.fetch_object_info = fetch_object_info_helper,
 	.push_refs	= push_refs,
 	.connect	= connect_helper,
 	.disconnect	= release_helper

@@ -45,6 +45,14 @@ struct transport_vtable {
 	 **/
 	int (*fetch_refs)(struct transport *transport, int refs_nr, struct ref **refs);
 
+	/*
+	 * Fetch object info (only size currently) from remote without
+	 * downloading the objects.
+	 *
+	 * Uses object-info capability of v2 protocol.
+	 */
+	int (*fetch_object_info)(struct transport *transport);
+
 	/**
 	 * Push the objects and refs. Send the necessary objects, and
 	 * then, for any refs where peer_ref is set and

@@ -9,6 +9,7 @@
 #include "hook.h"
 #include "pkt-line.h"
 #include "fetch-pack.h"
+#include "fetch-object-info.h"
 #include "remote.h"
 #include "connect.h"
 #include "send-pack.h"

@@ -432,6 +433,48 @@ static int get_bundle_uri(struct transport *transport)
 				     transport->bundles, stateless_rpc);
 }
 
+static int fetch_object_info_via_pack(struct transport *transport)
+{
+	int ret = 0;
+	struct git_transport_data *data = transport->data;
+	struct packet_reader reader;
+	struct object_info_args args = { 0 };
+
+	args.server_options = transport->server_options;
+	args.oids = transport->smart_options->object_info_oids;
+	args.object_info_options = transport->smart_options->object_info_options;
+	string_list_sort(args.object_info_options);
+
+	connect_setup(transport, 0);
+	packet_reader_init(&reader, data->fd[0], NULL, 0,
+			   PACKET_READ_CHOMP_NEWLINE |
+			   PACKET_READ_GENTLE_ON_EOF |
+			   PACKET_READ_DIE_ON_ERR_PACKET);
+
+	data->version = discover_version(&reader);
+	transport->hash_algo = reader.hash_algo;
+
+	ret = fetch_object_info(data->version, &args, &reader,
+				data->options.object_info_data,
+				transport->stateless_rpc, data->fd[1]);
+
+	close(data->fd[0]);
+	if (data->fd[1] >= 0)
+		close(data->fd[1]);
+	if (finish_connect(data->conn))
+		ret = -1;
+	data->conn = NULL;
+
+	return ret;
+}
+
+int transport_fetch_object_info(struct transport *transport)
+{
+	if (!transport->vtable->fetch_object_info)
+		die(_("remote does not support object-info"));
+	return transport->vtable->fetch_object_info(transport);
+}
+
 static int fetch_refs_via_pack(struct transport *transport,
 			       int nr_heads, struct ref **to_fetch)
 {

@@ -1004,6 +1047,7 @@ static struct transport_vtable taken_over_vtable = {
 	.get_refs_list	= get_refs_via_connect,
 	.get_bundle_uri = get_bundle_uri,
 	.fetch_refs	= fetch_refs_via_pack,
+	.fetch_object_info = fetch_object_info_via_pack,
 	.push_refs	= git_transport_push,
 	.disconnect	= disconnect_git
 };

@@ -1169,6 +1213,7 @@ static struct transport_vtable builtin_smart_vtable = {
 	.get_refs_list	= get_refs_via_connect,
 	.get_bundle_uri = get_bundle_uri,
 	.fetch_refs	= fetch_refs_via_pack,
+	.fetch_object_info = fetch_object_info_via_pack,
 	.push_refs	= git_transport_push,
 	.connect	= connect_git,
 	.disconnect	= disconnect_git

@@ -55,6 +55,10 @@ struct git_transport_options {
 	 * common commits to this oidset instead of fetching any packfiles.
 	 */
 	struct oidset *acked_commits;
+
+	struct oid_array *object_info_oids;
+	struct object_info *object_info_data;
+	struct string_list *object_info_options;
 };
 
 enum transport_family {

@@ -309,6 +313,11 @@ int transport_get_remote_bundle_uri(struct transport *transport);
 const struct git_hash_algo *transport_get_hash_algo(struct transport *transport);
 int transport_fetch_refs(struct transport *transport, struct ref *refs);
 
+/*
+ * Fetch the object info from remote
+ */
+int transport_fetch_object_info(struct transport *transport);
+
 /*
  * If this flag is set, unlocking will avoid to call non-async-signal-safe
  * functions. This will necessarily leave behind some data structures which