clone: add --single-branch to fetch only one branchnd/clone-single-branch

When --single-branch is given, only one branch, either HEAD or one
specified by --branch, will be fetched. Also only tags that point to
the downloaded history are fetched.

This helps most in shallow clones, where it can reduce the download to
minimum and that is why it is enabled by default when --depth is given.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 129 insertions, 6 deletions

diff --git a/Documentation/git-clone.txt b/Documentation/git-clone.txt
index 4b8b26b75e..0931a3e392 100644
--- a/Documentation/git-clone.txt
+++ b/Documentation/git-clone.txt
@@ -13,7 +13,8 @@ SYNOPSIS
 	  [-l] [-s] [--no-hardlinks] [-q] [-n] [--bare] [--mirror]
 	  [-o <name>] [-b <name>] [-u <upload-pack>] [--reference <repository>]
 	  [--separate-git-dir <git dir>]
-	  [--depth <depth>] [--recursive|--recurse-submodules] [--] <repository>
+	  [--depth <depth>] [--[no-]single-branch]
+	  [--recursive|--recurse-submodules] [--] <repository>
 	  [<directory>]
 
 DESCRIPTION
@@ -179,6 +180,14 @@ objects from the source repository into a pack in the cloned repository.
 	with a long history, and would want to send in fixes
 	as patches.
 
+--single-branch::
+	Clone only the history leading to the tip of a single branch,
+	either specified by the `--branch` option or the primary
+	branch remote's `HEAD` points at. When creating a shallow
+	clone with the `--depth` option, this is the default, unless
+	`--no-single-branch` is given to fetch the histories near the
+	tips of all branches.
+
 --recursive::
 --recurse-submodules::
 	After the clone is created, initialize all submodules within,
diff --git a/builtin/clone.c b/builtin/clone.c
index 86db954730..9dcc5fe775 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -37,7 +37,7 @@ static const char * const builtin_clone_usage[] = {
 	NULL
 };
 
-static int option_no_checkout, option_bare, option_mirror;
+static int option_no_checkout, option_bare, option_mirror, option_single_branch = -1;
 static int option_local, option_no_hardlinks, option_shared, option_recursive;
 static char *option_template, *option_depth;
 static char *option_origin = NULL;
@@ -48,6 +48,7 @@ static int option_verbosity;
 static int option_progress;
 static struct string_list option_config;
 static struct string_list option_reference;
+static const char *src_ref_prefix = "refs/heads/";
 
 static int opt_parse_reference(const struct option *opt, const char *arg, int unset)
 {
@@ -92,6 +93,8 @@ static struct option builtin_clone_options[] = {
 		   "path to git-upload-pack on the remote"),
 	OPT_STRING(0, "depth", &option_depth, "depth",
 		    "create a shallow clone of that depth"),
+	OPT_BOOL(0, "single-branch", &option_single_branch,
+		    "clone only one branch, HEAD or --branch"),
 	OPT_STRING(0, "separate-git-dir", &real_git_dir, "gitdir",
 		   "separate git dir from working tree"),
 	OPT_STRING_LIST('c', "config", &option_config, "key=value",
@@ -427,8 +430,28 @@ static struct ref *wanted_peer_refs(const struct ref *refs,
 	struct ref *local_refs = head;
 	struct ref **tail = head ? &head->next : &local_refs;
 
-	get_fetch_map(refs, refspec, &tail, 0);
-	if (!option_mirror)
+	if (option_single_branch) {
+		struct ref *remote_head = NULL;
+
+		if (!option_branch)
+			remote_head = guess_remote_head(head, refs, 0);
+		else {
+			struct strbuf sb = STRBUF_INIT;
+			strbuf_addstr(&sb, src_ref_prefix);
+			strbuf_addstr(&sb, option_branch);
+			remote_head = find_ref_by_name(refs, sb.buf);
+			strbuf_release(&sb);
+		}
+
+		if (!remote_head && option_branch)
+			warning(_("Could not find remote branch %s to clone."),
+				option_branch);
+		else
+			get_fetch_map(remote_head, refspec, &tail, 0);
+	} else
+		get_fetch_map(refs, refspec, &tail, 0);
+
+	if (!option_mirror && !option_single_branch)
 		get_fetch_map(refs, tag_refspec, &tail, 0);
 
 	return local_refs;
@@ -448,6 +471,21 @@ static void write_remote_refs(const struct ref *local_refs)
 	clear_extra_refs();
 }
 
+static void write_followtags(const struct ref *refs, const char *msg)
+{
+	const struct ref *ref;
+	for (ref = refs; ref; ref = ref->next) {
+		if (prefixcmp(ref->name, "refs/tags/"))
+			continue;
+		if (!suffixcmp(ref->name, "^{}"))
+			continue;
+		if (!has_sha1_file(ref->old_sha1))
+			continue;
+		update_ref(msg, ref->name, ref->old_sha1,
+			   NULL, 0, DIE_ON_ERR);
+	}
+}
+
 static int write_one_config(const char *key, const char *value, void *data)
 {
 	return git_config_set_multivar(key, value ? value : "true", "^$", 0);
@@ -478,7 +516,6 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	struct strbuf key = STRBUF_INIT, value = STRBUF_INIT;
 	struct strbuf branch_top = STRBUF_INIT, reflog_msg = STRBUF_INIT;
 	struct transport *transport = NULL;
-	char *src_ref_prefix = "refs/heads/";
 	int err = 0;
 
 	struct refspec *refspec;
@@ -498,6 +535,9 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		usage_msg_opt(_("You must specify a repository to clone."),
 			builtin_clone_usage, builtin_clone_options);
 
+	if (option_single_branch == -1)
+		option_single_branch = option_depth ? 1 : 0;
+
 	if (option_mirror)
 		option_bare = 1;
 
@@ -645,6 +685,8 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		if (option_depth)
 			transport_set_option(transport, TRANS_OPT_DEPTH,
 					     option_depth);
+		if (option_single_branch)
+			transport_set_option(transport, TRANS_OPT_FOLLOWTAGS, "1");
 
 		transport_set_verbosity(transport, option_verbosity, option_progress);
 
@@ -663,6 +705,8 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		clear_extra_refs();
 
 		write_remote_refs(mapped_refs);
+		if (option_single_branch)
+			write_followtags(refs, reflog_msg.buf);
 
 		remote_head = find_ref_by_name(refs, "HEAD");
 		remote_head_points_at =
diff --git a/t/t5500-fetch-pack.sh b/t/t5500-fetch-pack.sh
index 9bf69e9a0f..7e85c71ad1 100755
--- a/t/t5500-fetch-pack.sh
+++ b/t/t5500-fetch-pack.sh
@@ -114,8 +114,19 @@ pull_to_client 2nd "refs/heads/B" $((64*3))
 
 pull_to_client 3rd "refs/heads/A" $((1*3))
 
+test_expect_success 'single branch clone' '
+	git clone --single-branch "file://$(pwd)/." singlebranch
+'
+
+test_expect_success 'single branch object count' '
+	GIT_DIR=singlebranch/.git git count-objects -v |
+		grep "^in-pack:" > count.singlebranch &&
+	echo "in-pack: 198" >expected &&
+	test_cmp expected count.singlebranch
+'
+
 test_expect_success 'clone shallow' '
-	git clone --depth 2 "file://$(pwd)/." shallow
+	git clone --no-single-branch --depth 2 "file://$(pwd)/." shallow
 '
 
 test_expect_success 'clone shallow object count' '
@@ -248,4 +259,63 @@ test_expect_success 'clone shallow object count' '
 	grep "^count: 52" count.shallow
 '
 
+test_expect_success 'clone shallow without --no-single-branch' '
+	git clone --depth 1 "file://$(pwd)/." shallow2
+'
+
+test_expect_success 'clone shallow object count' '
+	(
+		cd shallow2 &&
+		git count-objects -v
+	) > count.shallow2 &&
+	grep "^in-pack: 6" count.shallow2
+'
+
+test_expect_success 'clone shallow with --branch' '
+	git clone --depth 1 --branch A "file://$(pwd)/." shallow3
+'
+
+test_expect_success 'clone shallow object count' '
+	echo "in-pack: 12" > count3.expected &&
+	GIT_DIR=shallow3/.git git count-objects -v |
+		grep "^in-pack" > count3.actual &&
+	test_cmp count3.expected count3.actual
+'
+
+test_expect_success 'clone shallow with nonexistent --branch' '
+	git clone --depth 1 --branch Z "file://$(pwd)/." shallow4 &&
+	GIT_DIR=shallow4/.git git rev-parse HEAD >actual &&
+	git rev-parse HEAD >expected &&
+	test_cmp expected actual
+'
+
+test_expect_success 'clone shallow with detached HEAD' '
+	git checkout HEAD^ &&
+	git clone --depth 1 "file://$(pwd)/." shallow5 &&
+	git checkout - &&
+	GIT_DIR=shallow5/.git git rev-parse HEAD >actual &&
+	git rev-parse HEAD^ >expected &&
+	test_cmp expected actual
+'
+
+test_expect_success 'shallow clone pulling tags' '
+	git tag -a -m A TAGA1 A &&
+	git tag -a -m B TAGB1 B &&
+	git tag TAGA2 A &&
+	git tag TAGB2 B &&
+	git clone --depth 1 "file://$(pwd)/." shallow6 &&
+
+	cat >taglist.expected <<\EOF &&
+TAGB1
+TAGB2
+EOF
+	GIT_DIR=shallow6/.git git tag -l >taglist.actual &&
+	test_cmp taglist.expected taglist.actual &&
+
+	echo "in-pack: 7" > count6.expected &&
+	GIT_DIR=shallow6/.git git count-objects -v |
+		grep "^in-pack" > count6.actual &&
+	test_cmp count6.expected count6.actual
+'
+
 test_done