fetch, upload-pack: --deepen=N extends shallow boundary by N commits

In git-fetch, --depth argument is always relative with the latest
remote refs. This makes it a bit difficult to cover this use case,
where the user wants to make the shallow history, say 3 levels
deeper. It would work if remote refs have not moved yet, but nobody
can guarantee that, especially when that use case is performed a
couple months after the last clone or "git fetch --depth". Also,
modifying shallow boundary using --depth does not work well with
clones created by --since or --not.

This patch fixes that. A new argument --deepen=<N> will add <N> more (*)
parent commits to the current history regardless of where remote refs
are.

Have/Want negotiation is still respected. So if remote refs move, the
server will send two chunks: one between "have" and "want" and another
to extend shallow history. In theory, the client could send no "want"s
in order to get the second chunk only. But the protocol does not allow
that. Either you send no want lines, which means ls-remote; or you
have to send at least one want line that carries deep-relative to the
server..

The main work was done by Dongcan Jiang. I fixed it up here and there.
And of course all the bugs belong to me.

(*) We could even support --deepen=<N> where <N> is negative. In that
case we can cut some history from the shallow clone. This operation
(and --depth=<shorter depth>) does not require interaction with remote
side (and more complicated to implement as a result).

Helped-by: Duy Nguyen <[email protected]>
Helped-by: Eric Sunshine <[email protected]>
Helped-by: Junio C Hamano <[email protected]>
Signed-off-by: Dongcan Jiang <[email protected]>
Signed-off-by: Nguyễn Thái Ngọc Duy <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: pclouds

Documentation/fetch-options.txt

@@ -14,6 +14,11 @@
 	linkgit:git-clone[1]), deepen or shorten the history to the specified
 	number of commits. Tags for the deepened commits are not fetched.
 
+--deepen=<depth>::
+	Similar to --depth, except it specifies the number of commits
+	from the current shallow boundary instead of from the tip of
+	each remote branch history.
+
 --shallow-since=<date>::
 	Deepen or shorten the history of a shallow repository to
 	include all reachable commits after <date>.

Documentation/git-fetch-pack.txt

@@ -96,6 +96,11 @@ be in a separate packet, and the list must end with a flush packet.
 	exclude commits reachable from a specified remote branch or tag.
 	This option can be specified multiple times.
 
+--deepen-relative::
+	Argument --depth specifies the number of commits from the
+	current shallow boundary instead of from the tip of each
+	remote branch history.
+
 --no-progress::
 	Do not show the progress.
 

Documentation/gitremote-helpers.txt

@@ -422,6 +422,10 @@ set by Git if the remote helper has the 'option' capability.
 	Deepens the history of a shallow repository excluding ref.
 	Multiple options add up.
 
+'option deepen-relative {'true'|'false'}::
+	Deepens the history of a shallow repository relative to
+	current boundary. Only valid when used with "option depth".
+
 'option followtags' {'true'|'false'}::
 	If enabled the helper should automatically fetch annotated
 	tag objects if the object the tag points at was transferred

Documentation/technical/protocol-capabilities.txt

@@ -197,6 +197,13 @@ specific revision, instead of depth. Internally it's equivalent of
 doing "rev-list --not <rev>" on the server side. "deepen-not"
 cannot be used with "deepen", but can be used with "deepen-since".
 
+deepen-relative
+---------------
+
+If this capability is requested by the client, the semantics of
+"deepen" command is changed. The "depth" argument is the depth from
+the current shallow boundary, instead of the depth from remote refs.
+
 no-progress
 -----------
 

builtin/fetch-pack.c

@@ -113,6 +113,10 @@ int cmd_fetch_pack(int argc, const char **argv, const char *prefix)
 			string_list_append(&deepen_not, arg);
 			continue;
 		}
+		if (!strcmp(arg, "--deepen-relative")) {
+			args.deepen_relative = 1;
+			continue;
+		}
 		if (!strcmp("--no-progress", arg)) {
 			args.no_progress = 1;
 			continue;

builtin/fetch.c

@@ -34,7 +34,7 @@ static int fetch_prune_config = -1; /* unspecified */
 static int prune = -1; /* unspecified */
 #define PRUNE_BY_DEFAULT 0 /* do we prune by default? */
 
-static int all, append, dry_run, force, keep, multiple, update_head_ok, verbosity;
+static int all, append, dry_run, force, keep, multiple, update_head_ok, verbosity, deepen_relative;
 static int progress = -1, recurse_submodules = RECURSE_SUBMODULES_DEFAULT;
 static int tags = TAGS_DEFAULT, unshallow, update_shallow, deepen;
 static int max_children = 1;
@@ -121,6 +121,8 @@ static struct option builtin_fetch_options[] = {
 		   N_("deepen history of shallow repository based on time")),
 	OPT_STRING_LIST(0, "shallow-exclude", &deepen_not, N_("revision"),
 			N_("deepen history of shallow clone by excluding rev")),
+	OPT_INTEGER(0, "deepen", &deepen_relative,
+		    N_("deepen history of shallow clone")),
 	{ OPTION_SET_INT, 0, "unshallow", &unshallow, NULL,
 		   N_("convert to a complete repository"),
 		   PARSE_OPT_NONEG | PARSE_OPT_NOARG, NULL, 1 },
@@ -881,6 +883,8 @@ static struct transport *prepare_transport(struct remote *remote, int deepen)
 	if (deepen && deepen_not.nr)
 		set_option(transport, TRANS_OPT_DEEPEN_NOT,
 			   (const char *)&deepen_not);
+	if (deepen_relative)
+		set_option(transport, TRANS_OPT_DEEPEN_RELATIVE, "yes");
 	if (update_shallow)
 		set_option(transport, TRANS_OPT_UPDATE_SHALLOW, "yes");
 	return transport;
@@ -906,6 +910,7 @@ static void backfill_tags(struct transport *transport, struct ref *ref_map)
 
 	transport_set_option(transport, TRANS_OPT_FOLLOWTAGS, NULL);
 	transport_set_option(transport, TRANS_OPT_DEPTH, "0");
+	transport_set_option(transport, TRANS_OPT_DEEPEN_RELATIVE, NULL);
 	fetch_refs(transport, ref_map);
 
 	if (gsecondary) {
@@ -1177,6 +1182,13 @@ int cmd_fetch(int argc, const char **argv, const char *prefix)
 	argc = parse_options(argc, argv, prefix,
 			     builtin_fetch_options, builtin_fetch_usage, 0);
 
+	if (deepen_relative) {
+		if (deepen_relative < 0)
+			die(_("Negative depth in --deepen is not supported"));
+		if (depth)
+			die(_("--deepen and --depth are mutually exclusive"));
+		depth = xstrfmt("%d", deepen_relative);
+	}
 	if (unshallow) {
 		if (depth)
 			die(_("--depth and --unshallow cannot be used together"));

fetch-pack.c

@@ -324,6 +324,7 @@ static int find_common(struct fetch_pack_args *args,
 			if (no_done)            strbuf_addstr(&c, " no-done");
 			if (use_sideband == 2)  strbuf_addstr(&c, " side-band-64k");
 			if (use_sideband == 1)  strbuf_addstr(&c, " side-band");
+			if (args->deepen_relative) strbuf_addstr(&c, " deepen-relative");
 			if (args->use_thin_pack) strbuf_addstr(&c, " thin-pack");
 			if (args->no_progress)   strbuf_addstr(&c, " no-progress");
 			if (args->include_tag)   strbuf_addstr(&c, " include-tag");
@@ -883,6 +884,8 @@ static struct ref *do_fetch_pack(struct fetch_pack_args *args,
 		deepen_not_ok = 1;
 	else if (args->deepen_not)
 		die(_("Server does not support --shallow-exclude"));
+	if (!server_supports("deepen-relative") && args->deepen_relative)
+		die(_("Server does not support --deepen"));
 
 	if (everything_local(args, &ref, sought, nr_sought)) {
 		packet_flush(fd[1]);

fetch-pack.h

@@ -12,6 +12,7 @@ struct fetch_pack_args {
 	int depth;
 	const char *deepen_since;
 	const struct string_list *deepen_not;
+	unsigned deepen_relative:1;
 	unsigned quiet:1;
 	unsigned keep_pack:1;
 	unsigned lock_pack:1;

remote-curl.c

@@ -30,7 +30,8 @@ struct options {
 		dry_run : 1,
 		thin : 1,
 		/* One of the SEND_PACK_PUSH_CERT_* constants. */
-		push_cert : 2;
+		push_cert : 2,
+		deepen_relative : 1;
 };
 static struct options options;
 static struct string_list cas_options = STRING_LIST_INIT_DUP;
@@ -70,6 +71,15 @@ static int set_option(const char *name, const char *value)
 		string_list_append(&options.deepen_not, value);
 		return 0;
 	}
+	else if (!strcmp(name, "deepen-relative")) {
+		if (!strcmp(value, "true"))
+			options.deepen_relative = 1;
+		else if (!strcmp(value, "false"))
+			options.deepen_relative = 0;
+		else
+			return -1;
+		return 0;
+	}
 	else if (!strcmp(name, "followtags")) {
 		if (!strcmp(value, "true"))
 			options.followtags = 1;
@@ -761,6 +771,8 @@ static int fetch_git(struct discovery *heads,
 	for (i = 0; i < options.deepen_not.nr; i++)
 		argv_array_pushf(&args, "--shallow-exclude=%s",
 				 options.deepen_not.items[i].string);
+	if (options.deepen_relative && options.depth)
+		argv_array_push(&args, "--deepen-relative");
 	argv_array_push(&args, url.buf);
 
 	for (i = 0; i < nr_heads; i++) {

t/t5500-fetch-pack.sh

@@ -682,4 +682,27 @@ test_expect_success 'fetch exclude tag one' '
 	test_cmp expected actual
 '
 
+test_expect_success 'fetching deepen' '
+	test_create_repo shallow-deepen &&
+	(
+	cd shallow-deepen &&
+	test_commit one &&
+	test_commit two &&
+	test_commit three &&
+	git clone --depth 1 "file://$(pwd)/." deepen &&
+	test_commit four &&
+	git -C deepen log --pretty=tformat:%s master >actual &&
+	echo three >expected &&
+	test_cmp expected actual &&
+	git -C deepen fetch --deepen=1 &&
+	git -C deepen log --pretty=tformat:%s origin/master >actual &&
+	cat >expected <<-\EOF &&
+	four
+	three
+	two
+	EOF
+	test_cmp expected actual
+	)
+'
+
 test_done

t/t5539-fetch-http-shallow.sh

@@ -120,5 +120,31 @@ test_expect_success 'fetch exclude tag one' '
 	test_cmp expected actual
 '
 
+test_expect_success 'fetching deepen' '
+	test_create_repo shallow-deepen &&
+	(
+	cd shallow-deepen &&
+	test_commit one &&
+	test_commit two &&
+	test_commit three &&
+	mv .git "$HTTPD_DOCUMENT_ROOT_PATH/shallow-deepen.git" &&
+	git clone --depth 1 $HTTPD_URL/smart/shallow-deepen.git deepen &&
+	mv "$HTTPD_DOCUMENT_ROOT_PATH/shallow-deepen.git" .git &&
+	test_commit four &&
+	git -C deepen log --pretty=tformat:%s master >actual &&
+	echo three >expected &&
+	test_cmp expected actual &&
+	mv .git "$HTTPD_DOCUMENT_ROOT_PATH/shallow-deepen.git" &&
+	git -C deepen fetch --deepen=1 &&
+	git -C deepen log --pretty=tformat:%s origin/master >actual &&
+	cat >expected <<-\EOF &&
+	four
+	three
+	two
+	EOF
+	test_cmp expected actual
+	)
+'
+
 stop_httpd
 test_done

transport-helper.c

@@ -258,6 +258,7 @@ static const char *boolean_options[] = {
 	TRANS_OPT_THIN,
 	TRANS_OPT_KEEP,
 	TRANS_OPT_FOLLOWTAGS,
+	TRANS_OPT_DEEPEN_RELATIVE
 	};
 
 static int strbuf_set_helper_option(struct helper_data *data,

transport.c

@@ -157,6 +157,9 @@ static int set_git_option(struct git_transport_options *opts,
 	} else if (!strcmp(name, TRANS_OPT_DEEPEN_NOT)) {
 		opts->deepen_not = (const struct string_list *)value;
 		return 0;
+	} else if (!strcmp(name, TRANS_OPT_DEEPEN_RELATIVE)) {
+		opts->deepen_relative = !!value;
+		return 0;
 	}
 	return 1;
 }
@@ -213,6 +216,7 @@ static int fetch_refs_via_pack(struct transport *transport,
 	args.depth = data->options.depth;
 	args.deepen_since = data->options.deepen_since;
 	args.deepen_not = data->options.deepen_not;
+	args.deepen_relative = data->options.deepen_relative;
 	args.check_self_contained_and_connected =
 		data->options.check_self_contained_and_connected;
 	args.cloning = transport->cloning;

transport.h

@@ -14,6 +14,7 @@ struct git_transport_options {
 	unsigned check_self_contained_and_connected : 1;
 	unsigned self_contained_and_connected : 1;
 	unsigned update_shallow : 1;
+	unsigned deepen_relative : 1;
 	int depth;
 	const char *deepen_since;
 	const struct string_list *deepen_not;
@@ -181,6 +182,9 @@ int transport_restrict_protocols(void);
 /* Limit the depth of the fetch based on revs if not null */
 #define TRANS_OPT_DEEPEN_NOT "deepen-not"
 
+/* Limit the deepen of the fetch if not null */
+#define TRANS_OPT_DEEPEN_RELATIVE "deepen-relative"
+
 /* Aggressively fetch annotated tags if possible */
 #define TRANS_OPT_FOLLOWTAGS "followtags"
 

upload-pack.c

@@ -32,6 +32,7 @@ static const char upload_pack_usage[] = "git upload-pack [--strict] [--timeout=<
 
 static unsigned long oldest_have;
 
+static int deepen_relative;
 static int multi_ack;
 static int no_done;
 static int use_thin_pack, use_ofs_delta, use_include_tag;
@@ -674,7 +675,8 @@ static void send_unshallow(const struct object_array *shallows)
 	}
 }
 
-static void deepen(int depth, const struct object_array *shallows)
+static void deepen(int depth, int deepen_relative,
+		   struct object_array *shallows)
 {
 	if (depth == INFINITE_DEPTH && !is_repository_shallow()) {
 		int i;
@@ -683,6 +685,17 @@ static void deepen(int depth, const struct object_array *shallows)
 			struct object *object = shallows->objects[i].item;
 			object->flags |= NOT_SHALLOW;
 		}
+	} else if (deepen_relative) {
+		struct object_array reachable_shallows = OBJECT_ARRAY_INIT;
+		struct commit_list *result;
+
+		get_reachable_list(shallows, &reachable_shallows);
+		result = get_shallow_commits(&reachable_shallows,
+					     depth + 1,
+					     SHALLOW, NOT_SHALLOW);
+		send_shallow(result);
+		free_commit_list(result);
+		object_array_clear(&reachable_shallows);
 	} else {
 		struct commit_list *result;
 
@@ -779,6 +792,8 @@ static void receive_needs(void)
 
 		features = arg + 40;
 
+		if (parse_feature_request(features, "deepen-relative"))
+			deepen_relative = 1;
 		if (parse_feature_request(features, "multi_ack_detailed"))
 			multi_ack = 2;
 		else if (parse_feature_request(features, "multi_ack"))
@@ -828,7 +843,7 @@ static void receive_needs(void)
 	if (depth > 0 && deepen_rev_list)
 		die("git upload-pack: deepen and deepen-since (or deepen-not) cannot be used together");
 	if (depth > 0)
-		deepen(depth, &shallows);
+		deepen(depth, deepen_relative, &shallows);
 	else if (deepen_rev_list) {
 		struct argv_array av = ARGV_ARRAY_INIT;
 		int i;
@@ -899,8 +914,8 @@ static int send_ref(const char *refname, const struct object_id *oid,
 		    int flag, void *cb_data)
 {
 	static const char *capabilities = "multi_ack thin-pack side-band"
-		" side-band-64k ofs-delta shallow deepen-since deepen-not no-progress"
-		" include-tag multi_ack_detailed";
+		" 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;