[PATCH 8/9] repack: implement `--filter-to` for storing filtered out objects

[Christian Couder <christian.couder@gmail.com>]

A previous commit has implemented `git repack --filter=<filter-spec>` to
allow users to filter out some objects from the main pack and move them
into a new different pack.

It would be nice if this new different pack could be created in a
different directory than the regular pack. This would make it possible
to move large blobs into a pack on a different kind of storage, for
example cheaper storage. Even in a different directory this pack can be
accessible if, for example, the Git alternates mechanism is used to
point to it.

If users want to remove a pack that contains filtered out objects after
checking that they are all already on a promisor remote, creating the
pack in a different directory makes it easier to do so.

Signed-off-by: Christian Couder <chriscool@tuxfamily.org>
---
 Documentation/git-repack.txt |  6 ++++++
 builtin/repack.c             | 17 ++++++++++++-----
 t/t7700-repack.sh            | 27 +++++++++++++++++++++++++++
 3 files changed, 45 insertions(+), 5 deletions(-)

diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt
index aa29c7e648..070dd22610 100644
--- a/Documentation/git-repack.txt
+++ b/Documentation/git-repack.txt
@@ -148,6 +148,12 @@ depth is 4095.
 	resulting packfile and put them into a separate packfile. See
 	linkgit:git-rev-list[1] for valid `<filter-spec>` forms.
 
+--filter-to=<dir>::
+	Write the pack containing filtered out objects to the
+	directory `<dir>`. This can be used for putting the pack on a
+	separate object directory that is accessed through the Git
+	alternates mechanism. Only useful with `--filter`.
+
 -b::
 --write-bitmap-index::
 	Write a reachability bitmap index as part of the repack. This
diff --git a/builtin/repack.c b/builtin/repack.c
index b13d7196de..8c71e8fd51 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -838,7 +838,8 @@ static void prepare_pack_filtered_cmd(struct child_process *cmd,
 }
 
 static void finish_pack_filtered_cmd(struct child_process *cmd,
-				     struct string_list *names)
+				     struct string_list *names,
+				     const char *destination)
 {
 	if (cmd->in == -1) {
 		/* No packed objects; cmd was never started */
@@ -848,7 +849,7 @@ static void finish_pack_filtered_cmd(struct child_process *cmd,
 
 	close(cmd->in);
 
-	if (finish_pack_objects_cmd(cmd, names, NULL, NULL))
+	if (finish_pack_objects_cmd(cmd, names, destination, NULL))
 		die(_("could not finish pack-objects to pack filtered objects"));
 }
 
@@ -877,6 +878,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	const char *cruft_expiration = NULL;
 	const char *expire_to = NULL;
 	struct child_process pack_filtered_cmd = CHILD_PROCESS_INIT;
+	const char *filter_to = NULL;
 
 	struct option builtin_repack_options[] = {
 		OPT_BIT('a', NULL, &pack_everything,
@@ -930,6 +932,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 			   N_("write a multi-pack index of the resulting packs")),
 		OPT_STRING(0, "expire-to", &expire_to, N_("dir"),
 			   N_("pack prefix to store a pack containing pruned objects")),
+		OPT_STRING(0, "filter-to", &filter_to, N_("dir"),
+			   N_("pack prefix to store a pack containing filtered out objects")),
 		OPT_END()
 	};
 
@@ -1073,8 +1077,11 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		strvec_push(&cmd.args, "--incremental");
 	}
 
-	if (po_args.filter)
-		prepare_pack_filtered_cmd(&pack_filtered_cmd, &po_args, packtmp);
+	if (po_args.filter) {
+		if (!filter_to)
+			filter_to = packtmp;
+		prepare_pack_filtered_cmd(&pack_filtered_cmd, &po_args, filter_to);
+	}
 
 	if (geometry)
 		cmd.in = -1;
@@ -1169,7 +1176,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	}
 
 	if (po_args.filter)
-		finish_pack_filtered_cmd(&pack_filtered_cmd, &names);
+		finish_pack_filtered_cmd(&pack_filtered_cmd, &names, filter_to);
 
 	string_list_sort(&names);
 
diff --git a/t/t7700-repack.sh b/t/t7700-repack.sh
index 9e7654090f..898f8a01b4 100755
--- a/t/t7700-repack.sh
+++ b/t/t7700-repack.sh
@@ -286,6 +286,33 @@ test_expect_success 'repacking with a filter works' '
 	test "$blob_pack2" = "$blob_pack"
 '
 
+test_expect_success '--filter-to stores filtered out objects' '
+	git -C bare.git repack -a -d &&
+	test_stdout_line_count = 1 ls bare.git/objects/pack/*.pack &&
+
+	git init --bare filtered.git &&
+	git -C bare.git -c repack.writebitmaps=false repack -a -d \
+		--filter=blob:none \
+		--filter-to=../filtered.git/objects/pack/pack &&
+	test_stdout_line_count = 1 ls bare.git/objects/pack/pack-*.pack &&
+	test_stdout_line_count = 1 ls filtered.git/objects/pack/pack-*.pack &&
+
+	commit_pack=$(test-tool -C bare.git find-pack HEAD) &&
+	test -n "$commit_pack" &&
+	blob_pack=$(test-tool -C bare.git find-pack HEAD:file1) &&
+	test -z "$blob_pack" &&
+	blob_hash=$(git -C bare.git rev-parse HEAD:file1) &&
+	test -n "$blob_hash" &&
+	blob_pack=$(test-tool -C filtered.git find-pack $blob_hash) &&
+	test -n "$blob_pack" &&
+
+	echo $(pwd)/filtered.git/objects >bare.git/objects/info/alternates &&
+	blob_pack=$(test-tool -C bare.git find-pack HEAD:file1) &&
+	test -n "$blob_pack" &&
+	blob_content=$(git -C bare.git show $blob_hash) &&
+	test "$blob_content" = "content1"
+'
+
 objdir=.git/objects
 midx=$objdir/pack/multi-pack-index
 
-- 
2.41.0.37.gae45d9845e