clone: --dissociate option to mark that reference is only temporaryjc/clone-borrow

While use of the --reference option to borrow objects from an
existing local repository of the same project is an effective way to
reduce traffic when cloning a project over the network, it makes the
resulting "borrowing" repository dependent on the "borrowed"
repository.  After running

	git clone --reference=P $URL Q

the resulting repository Q will be broken if the borrowed repository
P disappears.

The way to allow the borrowed repository to be removed is to repack
the borrowing repository (i.e. run "git repack -a -d" in Q); while
power users may know it very well, it is not easily discoverable.

Teach a new "--dissociate" option to "git clone" to run this
repacking for the user.

Helped-by: Johannes Sixt <j6t@kdbg.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 46 insertions, 2 deletions

diff --git a/Documentation/git-clone.txt b/Documentation/git-clone.txt
index 0363d0039b..f1f2a3f7ea 100644
--- a/Documentation/git-clone.txt
+++ b/Documentation/git-clone.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 'git clone' [--template=<template_directory>]
 	  [-l] [-s] [--no-hardlinks] [-q] [-n] [--bare] [--mirror]
 	  [-o <name>] [-b <name>] [-u <upload-pack>] [--reference <repository>]
-	  [--separate-git-dir <git dir>]
+	  [--dissociate] [--separate-git-dir <git dir>]
 	  [--depth <depth>] [--[no-]single-branch]
 	  [--recursive | --recurse-submodules] [--] <repository>
 	  [<directory>]
@@ -98,7 +98,14 @@ objects from the source repository into a pack in the cloned repository.
 	require fewer objects to be copied from the repository
 	being cloned, reducing network and local storage costs.
 +
-*NOTE*: see the NOTE for the `--shared` option.
+*NOTE*: see the NOTE for the `--shared` option, and also the
+`--dissociate` option.
+
+--dissociate::
+	Borrow the objects from reference repositories specified
+	with the `--reference` options only to reduce network
+	transfer and stop borrowing from them after a clone is made
+	by making necessary local copies of borrowed objects.
 
 --quiet::
 -q::
diff --git a/builtin/clone.c b/builtin/clone.c
index bbd169ceb4..e1ad4df41f 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -48,6 +48,7 @@ static int option_verbosity;
 static int option_progress = -1;
 static struct string_list option_config;
 static struct string_list option_reference;
+static int option_dissociate;
 
 static int opt_parse_reference(const struct option *opt, const char *arg, int unset)
 {
@@ -93,6 +94,8 @@ static struct option builtin_clone_options[] = {
 		    N_("create a shallow clone of that depth")),
 	OPT_BOOL(0, "single-branch", &option_single_branch,
 		    N_("clone only one branch, HEAD or --branch")),
+	OPT_BOOL(0, "dissociate", &option_dissociate,
+		 N_("use --reference only while cloning")),
 	OPT_STRING(0, "separate-git-dir", &real_git_dir, N_("gitdir"),
 		   N_("separate git dir from working tree")),
 	OPT_STRING_LIST('c', "config", &option_config, N_("key=value"),
@@ -736,6 +739,16 @@ static void write_refspec_config(const char* src_ref_prefix,
 	strbuf_release(&value);
 }
 
+static void dissociate_from_references(void)
+{
+	static const char* argv[] = { "repack", "-a", "-d", NULL };
+
+	if (run_command_v_opt(argv, RUN_GIT_CMD|RUN_COMMAND_NO_STDIN))
+		die(_("cannot repack to clean up"));
+	if (unlink(git_path("objects/info/alternates")) && errno != ENOENT)
+		die_errno(_("cannot unlink temporary alternates file"));
+}
+
 int cmd_clone(int argc, const char **argv, const char *prefix)
 {
 	int is_bundle = 0, is_local;
@@ -883,6 +896,10 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 
 	if (option_reference.nr)
 		setup_reference();
+	else if (option_dissociate) {
+		warning(_("--dissociate given, but there is no --reference"));
+		option_dissociate = 0;
+	}
 
 	fetch_pattern = value.buf;
 	refspec = parse_fetch_refspec(1, &fetch_pattern);
@@ -996,6 +1013,9 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	transport_unlock_pack(transport);
 	transport_disconnect(transport);
 
+	if (option_dissociate)
+		dissociate_from_references();
+
 	junk_mode = JUNK_LEAVE_REPO;
 	err = checkout();
 
diff --git a/t/t5700-clone-reference.sh b/t/t5700-clone-reference.sh
index 6537911a43..3e783fc450 100755
--- a/t/t5700-clone-reference.sh
+++ b/t/t5700-clone-reference.sh
@@ -198,4 +198,21 @@ test_expect_success 'clone using repo pointed at by gitfile as reference' '
 	test_cmp expected "$base_dir/O/.git/objects/info/alternates"
 '
 
+test_expect_success 'clone and dissociate from reference' '
+	git init P &&
+	(
+		cd P &&	test_commit one
+	) &&
+	git clone P Q &&
+	(
+		cd Q && test_commit two
+	) &&
+	git clone --no-local --reference=P Q R &&
+	git clone --no-local --reference=P --dissociate Q S &&
+	# removing the reference P would corrupt R but not S
+	rm -fr P &&
+	test_must_fail git -C R fsck &&
+	git -C S fsck
+'
+
 test_done