[GSoC PATCH v5 4/6] builtin/repack: enumerate promisor blobs for --drop-filtered

@@ -15,6 +15,8 @@
 #include "repack.h"
 #include "shallow.h"
 #include "list-objects-filter-options.h"
+#include "oidset.h"
+#include "hex.h"
 
 #define ALL_INTO_ONE 1
 #define LOOSEN_UNREACHABLE 2

@@ -160,6 +162,7 @@ int cmd_repack(int argc,
 	struct string_list_item *item;
 	struct string_list names = STRING_LIST_INIT_DUP;
 	struct existing_packs existing = EXISTING_PACKS_INIT;
+	struct oidset drop_oids = OIDSET_INIT;
 	struct pack_geometry geometry = { 0 };
 	struct tempfile *refs_snapshot = NULL;
 	int i, ret;

@@ -318,6 +321,20 @@ int cmd_repack(int argc,
 			die(_("--drop-filtered requires a promisor remote"));
 
 		write_bitmaps = 0;
+
+		ret = enumerate_promisor_blobs(repo, &po_args.filter_options, &drop_oids);
+
+		if (ret)
+			goto cleanup;
+
+		if (dry_run) {
+			struct oidset_iter iter;
+			const struct object_id *oid;
+
+			oidset_iter_init(&drop_oids, &iter);
+			while ((oid = oidset_iter_next(&iter)))
+				printf("%s\n", oid_to_hex(oid));
+		}
 	}
 
 	if (delete_redundant && repo->repository_format_precious_objects)

@@ -613,7 +630,7 @@ int cmd_repack(int argc,
 		}
 	}
 
-	if (po_args.filter_options.choice) {
+	if (po_args.filter_options.choice && !drop_filtered) {
 		struct write_pack_opts opts = {
 			.po_args = &po_args,
 			.destination = filter_to,

@@ -706,6 +723,7 @@ int cmd_repack(int argc,
 cleanup:
 	string_list_clear(&keep_pack_list, 0);
 	string_list_clear(&names, 1);
+	oidset_clear(&drop_oids);
 	existing_packs_release(&existing);
 	pack_geometry_release(&geometry);
 	pack_objects_args_release(&po_args);

@@ -3,6 +3,12 @@
 #include "repository.h"
 #include "run-command.h"
 #include "string-list.h"
+#include "hex.h"
+#include "packfile.h"
+#include "list-objects-filter-options.h"
+#include "list-objects-filter.h"
+#include "odb.h"
+#include "promisor-remote.h"
 
 int write_filtered_pack(const struct write_pack_opts *opts,
 			struct existing_packs *existing,

@@ -49,3 +55,79 @@ int write_filtered_pack(const struct write_pack_opts *opts,
 	return finish_pack_objects_cmd(existing->repo->hash_algo, opts, &cmd,
 				       names);
 }
+
+struct collect_cb_data {
+	struct repository *repo;
+	struct oidset *set;
+};
+
+static int collect_promisor_blob(const struct object_id *oid,
+				 struct object_info *oi UNUSED,
+				 void *cb_data)
+{
+	struct collect_cb_data *data = cb_data;
+	struct object_info info = OBJECT_INFO_INIT;
+	enum object_type type;
+
+	info.typep = &type;
+
+	/*
+	 * Use OBJECT_INFO_SKIP_FETCH_OBJECT to avoid triggering a
+	 * lazy fetch while collecting promisor blobs.
+	 */
+	if (odb_read_object_info_extended(data->repo->objects, oid, &info,
+			OBJECT_INFO_SKIP_FETCH_OBJECT) < 0)
+		return 0;
+
+	if (type == OBJ_BLOB)
+		oidset_insert(data->set, oid);
+
+	return 0;
+}
+
+int enumerate_promisor_blobs(struct repository *repo,
+			     const struct list_objects_filter_options *filter,
+			     struct oidset *to_drop)
+{
+	struct oidset all_promisor_blobs = OIDSET_INIT;
+	struct collect_cb_data cb = {
+		.repo = repo,
+		.set = &all_promisor_blobs
+	};
+	int ret = 0;
+
+	/*
+	 * The caller (cmd_repack) is responsible for validating that a
+	 * blob:limit filter and a promisor remote are present before
+	 * calling this function.
+	 *
+	 * Walk only promisor objects. Every object visited here is a
+	 * promisor object, so it is recoverable from the promisor remote
+	 * as long as the remote still has it, the same assumption the rest
+	 * of partial clone relies on.
+	 *
+	 * We do not use write_filtered_pack() here because git repack
+	 * routes promisor objects through repack_promisor_objects()
+	 * before the filter machinery runs, so the filtered pack never
+	 * contains promisor blobs. Direct enumeration via
+	 * ODB_FOR_EACH_OBJECT_PROMISOR_ONLY is the correct approach.
+	 */
+	ret = odb_for_each_object(repo->objects, NULL,
+			collect_promisor_blob, &cb,
+			ODB_FOR_EACH_OBJECT_PROMISOR_ONLY);
+	if (ret)
+		goto cleanup;
+
+	/*
+	 * Apply the filter to find which blobs exceed the threshold.
+	 * The caller has to_drop and is responsible for clearing it.
+	 */
+	ret = list_objects_filter__filter_oidset(repo,
+		filter,
+		&all_promisor_blobs,
+		to_drop);
+
+cleanup:
+	oidset_clear(&all_promisor_blobs);
+	return ret;
+}

@@ -167,6 +167,10 @@ int write_filtered_pack(const struct write_pack_opts *opts,
 			struct existing_packs *existing,
 			struct string_list *names);
 
+int enumerate_promisor_blobs(struct repository *repo,
+			     const struct list_objects_filter_options *filter,
+			     struct oidset *to_drop);
+
 int write_cruft_pack(const struct write_pack_opts *opts,
 		     const char *cruft_expiration,
 		     unsigned long combine_cruft_below_size,

@@ -1,9 +1,37 @@
 #!/bin/sh
 
-test_description='git repack --drop-filtered option validation'
+test_description='git repack --drop-filtered enumerates filtered promisor blobs'
 
 . ./test-lib.sh
 
+# Delete a loose or packed object from "repo".
+delete_object () {
+	local repo="$1" &&
+	local obj="$2" &&
+	local path="$repo/.git/objects/$(test_oid_to_path "$obj")" &&
+	rm "$path"
+}
+
+# Pack the objects into a promisor pack inside "repo". It is a pack
+# accompanied by an empty ".promisor" marker file. Objects
+# in such a pack are treated as recoverable from the promisor remote.
+pack_as_from_promisor () {
+	HASH=$(git -C repo pack-objects .git/objects/pack/pack) &&
+	>repo/.git/objects/pack/pack-$HASH.promisor &&
+	echo $HASH
+}
+
+# Write a blob of $1 bytes into "repo", record it as coming from the
+# promisor remote, and remove the loose copy so the object is only
+# present in the promisor pack.
+promisor_blob () {
+	test-tool genrandom "$1" "$2" >blob_content &&
+	OID=$(git -C repo hash-object -w --stdin <blob_content) &&
+	printf "%s\n" "$OID" | pack_as_from_promisor >/dev/null &&
+	delete_object repo "$OID" &&
+	echo "$OID"
+}
+
 # Check option validation before any promisor walk
 test_expect_success 'setup plain repo for validation' '
 	git init plain &&

@@ -52,4 +80,59 @@ test_expect_success '--drop-filtered fails without a promisor remote' '
 	test_grep "drop-filtered requires a promisor remote" err
 '
 
+# Enumeration tests using promisor pack
+test_expect_success 'setup repo with a promisor remote' '
+	rm -rf repo &&
+	test_create_repo repo &&
+	test_commit -C repo base &&
+
+	# Mark the repo as a partial clone with a promisor remote so the
+	# promisor walk and the safety guard are satisfied.
+	git -C repo config core.repositoryformatversion 1 &&
+	git -C repo config extensions.partialclone origin &&
+	git -C repo config remote.origin.promisor true &&
+	git -C repo config remote.origin.url "." &&
+
+	BIG=$(promisor_blob big 3072) &&
+	SMALL=$(promisor_blob small 512) &&
+	echo "$BIG" >big_oid &&
+	echo "$SMALL" >small_oid
+'
+
+test_expect_success 'promisor blob over the threshold is listed' '
+	BIG=$(cat big_oid) &&
+	SMALL=$(cat small_oid) &&
+
+	git -C repo -c repack.writeBitmaps=false \
+		repack --drop-filtered --filter=blob:limit=1k --dry-run -a >out &&
+
+	test_grep "$BIG" out &&
+	test_grep ! "$SMALL" out
+'
+
+test_expect_success 'locally created blob is never listed' '
+	BIG=$(cat big_oid) &&
+
+	# Large blob that exists only locally must never be a drop candidate.
+	# Dropping it would be unrecoverable.
+	test-tool genrandom local 4096 >local_content &&
+	LOCAL=$(git -C repo hash-object -w --stdin <local_content) &&
+
+	git -C repo -c repack.writeBitmaps=false \
+		repack --drop-filtered --filter=blob:limit=1k --dry-run -a >out &&
+
+	test_grep "$BIG" out &&
+	test_grep ! "$LOCAL" out
+'
+
+test_expect_success '--dry-run does not remove the filtered objects' '
+	BIG=$(cat big_oid) &&
+
+	git -C repo -c repack.writeBitmaps=false \
+		repack --drop-filtered --filter=blob:limit=1k --dry-run -a >out &&
+
+	# Candidate blob must still be present after a dry run.
+	git -C repo cat-file -e "$BIG"
+'
+
 test_done