1 files changed, 158 insertions, 101 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 67941c8a60..067b9e322a 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -32,7 +32,7 @@
 #include "list.h"
 #include "packfile.h"
 #include "object-file.h"
-#include "object-store.h"
+#include "odb.h"
 #include "replace-object.h"
 #include "dir.h"
 #include "midx.h"
@@ -284,6 +284,12 @@ static struct oidmap configured_exclusions;
 static struct oidset excluded_by_config;
 static int name_hash_version = -1;
 
+enum stdin_packs_mode {
+	STDIN_PACKS_MODE_NONE,
+	STDIN_PACKS_MODE_STANDARD,
+	STDIN_PACKS_MODE_FOLLOW,
+};
+
 /**
  * Check whether the name_hash_version chosen by user input is appropriate,
  * and also validate whether it is compatible with other features.
@@ -349,13 +355,13 @@ static void *get_delta(struct object_entry *entry)
 	void *buf, *base_buf, *delta_buf;
 	enum object_type type;
 
-	buf = repo_read_object_file(the_repository, &entry->idx.oid, &type,
-				    &size);
+	buf = odb_read_object(the_repository->objects, &entry->idx.oid,
+			      &type, &size);
 	if (!buf)
 		die(_("unable to read %s"), oid_to_hex(&entry->idx.oid));
-	base_buf = repo_read_object_file(the_repository,
-					 &DELTA(entry)->idx.oid, &type,
-					 &base_size);
+	base_buf = odb_read_object(the_repository->objects,
+				   &DELTA(entry)->idx.oid, &type,
+				   &base_size);
 	if (!base_buf)
 		die("unable to read %s",
 		    oid_to_hex(&DELTA(entry)->idx.oid));
@@ -518,9 +524,9 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent
 				       &size, NULL)) != NULL)
 			buf = NULL;
 		else {
-			buf = repo_read_object_file(the_repository,
-						    &entry->idx.oid, &type,
-						    &size);
+			buf = odb_read_object(the_repository->objects,
+					      &entry->idx.oid, &type,
+					      &size);
 			if (!buf)
 				die(_("unable to read %s"),
 				    oid_to_hex(&entry->idx.oid));
@@ -1907,7 +1913,7 @@ static struct pbase_tree_cache *pbase_tree_get(const struct object_id *oid)
 	/* Did not find one.  Either we got a bogus request or
 	 * we need to read and perhaps cache.
 	 */
-	data = repo_read_object_file(the_repository, oid, &type, &size);
+	data = odb_read_object(the_repository->objects, oid, &type, &size);
 	if (!data)
 		return NULL;
 	if (type != OBJ_TREE) {
@@ -2067,8 +2073,8 @@ static void add_preferred_base(struct object_id *oid)
 	if (window <= num_preferred_base++)
 		return;
 
-	data = read_object_with_reference(the_repository, oid,
-					  OBJ_TREE, &size, &tree_oid);
+	data = odb_read_object_peeled(the_repository->objects, oid,
+				      OBJ_TREE, &size, &tree_oid);
 	if (!data)
 		return;
 
@@ -2166,10 +2172,10 @@ static void prefetch_to_pack(uint32_t object_index_start) {
 	for (i = object_index_start; i < to_pack.nr_objects; i++) {
 		struct object_entry *entry = to_pack.objects + i;
 
-		if (!oid_object_info_extended(the_repository,
-					      &entry->idx.oid,
-					      NULL,
-					      OBJECT_INFO_FOR_PREFETCH))
+		if (!odb_read_object_info_extended(the_repository->objects,
+						   &entry->idx.oid,
+						   NULL,
+						   OBJECT_INFO_FOR_PREFETCH))
 			continue;
 		oid_array_append(&to_fetch, &entry->idx.oid);
 	}
@@ -2310,19 +2316,19 @@ static void check_object(struct object_entry *entry, uint32_t object_index)
 
 		/*
 		 * No choice but to fall back to the recursive delta walk
-		 * with oid_object_info() to find about the object type
+		 * with odb_read_object_info() to find about the object type
 		 * at this point...
 		 */
 		give_up:
 		unuse_pack(&w_curs);
 	}
 
-	if (oid_object_info_extended(the_repository, &entry->idx.oid, &oi,
-				     OBJECT_INFO_SKIP_FETCH_OBJECT | OBJECT_INFO_LOOKUP_REPLACE) < 0) {
+	if (odb_read_object_info_extended(the_repository->objects, &entry->idx.oid, &oi,
+					  OBJECT_INFO_SKIP_FETCH_OBJECT | OBJECT_INFO_LOOKUP_REPLACE) < 0) {
 		if (repo_has_promisor_remote(the_repository)) {
 			prefetch_to_pack(object_index);
-			if (oid_object_info_extended(the_repository, &entry->idx.oid, &oi,
-						     OBJECT_INFO_SKIP_FETCH_OBJECT | OBJECT_INFO_LOOKUP_REPLACE) < 0)
+			if (odb_read_object_info_extended(the_repository->objects, &entry->idx.oid, &oi,
+							  OBJECT_INFO_SKIP_FETCH_OBJECT | OBJECT_INFO_LOOKUP_REPLACE) < 0)
 				type = -1;
 		} else {
 			type = -1;
@@ -2396,12 +2402,13 @@ static void drop_reused_delta(struct object_entry *entry)
 	if (packed_object_info(the_repository, IN_PACK(entry), entry->in_pack_offset, &oi) < 0) {
 		/*
 		 * We failed to get the info from this pack for some reason;
-		 * fall back to oid_object_info, which may find another copy.
+		 * fall back to odb_read_object_info, which may find another copy.
 		 * And if that fails, the error will be recorded in oe_type(entry)
 		 * and dealt with in prepare_pack().
 		 */
 		oe_set_type(entry,
-			    oid_object_info(the_repository, &entry->idx.oid, &size));
+			    odb_read_object_info(the_repository->objects,
+						 &entry->idx.oid, &size));
 	} else {
 		oe_set_type(entry, type);
 	}
@@ -2689,7 +2696,8 @@ unsigned long oe_get_size_slow(struct packing_data *pack,
 
 	if (e->type_ != OBJ_OFS_DELTA && e->type_ != OBJ_REF_DELTA) {
 		packing_data_lock(&to_pack);
-		if (oid_object_info(the_repository, &e->idx.oid, &size) < 0)
+		if (odb_read_object_info(the_repository->objects,
+					 &e->idx.oid, &size) < 0)
 			die(_("unable to get size of %s"),
 			    oid_to_hex(&e->idx.oid));
 		packing_data_unlock(&to_pack);
@@ -2772,9 +2780,9 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 	/* Load data if not already done */
 	if (!trg->data) {
 		packing_data_lock(&to_pack);
-		trg->data = repo_read_object_file(the_repository,
-						  &trg_entry->idx.oid, &type,
-						  &sz);
+		trg->data = odb_read_object(the_repository->objects,
+					    &trg_entry->idx.oid, &type,
+					    &sz);
 		packing_data_unlock(&to_pack);
 		if (!trg->data)
 			die(_("object %s cannot be read"),
@@ -2787,9 +2795,9 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 	}
 	if (!src->data) {
 		packing_data_lock(&to_pack);
-		src->data = repo_read_object_file(the_repository,
-						  &src_entry->idx.oid, &type,
-						  &sz);
+		src->data = odb_read_object(the_repository->objects,
+					    &src_entry->idx.oid, &type,
+					    &sz);
 		packing_data_unlock(&to_pack);
 		if (!src->data) {
 			if (src_entry->preferred_base) {
@@ -3725,7 +3733,6 @@ static int add_object_entry_from_pack(const struct object_id *oid,
 		return 0;
 
 	if (p) {
-		struct rev_info *revs = _data;
 		struct object_info oi = OBJECT_INFO_INIT;
 
 		oi.typep = &type;
@@ -3733,6 +3740,7 @@ static int add_object_entry_from_pack(const struct object_id *oid,
 			die(_("could not get type of object %s in pack %s"),
 			    oid_to_hex(oid), p->pack_name);
 		} else if (type == OBJ_COMMIT) {
+			struct rev_info *revs = _data;
 			/*
 			 * commits in included packs are used as starting points for the
 			 * subsequent revision walk
@@ -3748,32 +3756,48 @@ static int add_object_entry_from_pack(const struct object_id *oid,
 	return 0;
 }
 
-static void show_commit_pack_hint(struct commit *commit UNUSED,
-				  void *data UNUSED)
+static void show_object_pack_hint(struct object *object, const char *name,
+				  void *data)
 {
-	/* nothing to do; commits don't have a namehash */
+	enum stdin_packs_mode mode = *(enum stdin_packs_mode *)data;
+	if (mode == STDIN_PACKS_MODE_FOLLOW) {
+		if (object->type == OBJ_BLOB &&
+		    !has_object(the_repository, &object->oid, 0))
+			return;
+		add_object_entry(&object->oid, object->type, name, 0);
+	} else {
+		struct object_entry *oe = packlist_find(&to_pack, &object->oid);
+		if (!oe)
+			return;
+
+		/*
+		 * Our 'to_pack' list was constructed by iterating all
+		 * objects packed in included packs, and so doesn't have
+		 * a non-zero hash field that you would typically pick
+		 * up during a reachability traversal.
+		 *
+		 * Make a best-effort attempt to fill in the ->hash and
+		 * ->no_try_delta fields here in order to perhaps
+		 * improve the delta selection process.
+		 */
+		oe->hash = pack_name_hash_fn(name);
+		oe->no_try_delta = name && no_try_delta(name);
+
+		stdin_packs_hints_nr++;
+	}
 }
 
-static void show_object_pack_hint(struct object *object, const char *name,
-				  void *data UNUSED)
+static void show_commit_pack_hint(struct commit *commit, void *data)
 {
-	struct object_entry *oe = packlist_find(&to_pack, &object->oid);
-	if (!oe)
+	enum stdin_packs_mode mode = *(enum stdin_packs_mode *)data;
+
+	if (mode == STDIN_PACKS_MODE_FOLLOW) {
+		show_object_pack_hint((struct object *)commit, "", data);
 		return;
+	}
 
-	/*
-	 * Our 'to_pack' list was constructed by iterating all objects packed in
-	 * included packs, and so doesn't have a non-zero hash field that you
-	 * would typically pick up during a reachability traversal.
-	 *
-	 * Make a best-effort attempt to fill in the ->hash and ->no_try_delta
-	 * here using a now in order to perhaps improve the delta selection
-	 * process.
-	 */
-	oe->hash = pack_name_hash_fn(name);
-	oe->no_try_delta = name && no_try_delta(name);
+	/* nothing to do; commits don't have a namehash */
 
-	stdin_packs_hints_nr++;
 }
 
 static int pack_mtime_cmp(const void *_a, const void *_b)
@@ -3793,7 +3817,7 @@ static int pack_mtime_cmp(const void *_a, const void *_b)
 		return 0;
 }
 
-static void read_packs_list_from_stdin(void)
+static void read_packs_list_from_stdin(struct rev_info *revs)
 {
 	struct strbuf buf = STRBUF_INIT;
 	struct string_list include_packs = STRING_LIST_INIT_DUP;
@@ -3801,24 +3825,6 @@ static void read_packs_list_from_stdin(void)
 	struct string_list_item *item = NULL;
 
 	struct packed_git *p;
-	struct rev_info revs;
-
-	repo_init_revisions(the_repository, &revs, NULL);
-	/*
-	 * Use a revision walk to fill in the namehash of objects in the include
-	 * packs. To save time, we'll avoid traversing through objects that are
-	 * in excluded packs.
-	 *
-	 * That may cause us to avoid populating all of the namehash fields of
-	 * all included objects, but our goal is best-effort, since this is only
-	 * an optimization during delta selection.
-	 */
-	revs.no_kept_objects = 1;
-	revs.keep_pack_cache_flags |= IN_CORE_KEEP_PACKS;
-	revs.blob_objects = 1;
-	revs.tree_objects = 1;
-	revs.tag_objects = 1;
-	revs.ignore_missing_links = 1;
 
 	while (strbuf_getline(&buf, stdin) != EOF) {
 		if (!buf.len)
@@ -3888,25 +3894,55 @@ static void read_packs_list_from_stdin(void)
 		struct packed_git *p = item->util;
 		for_each_object_in_pack(p,
 					add_object_entry_from_pack,
-					&revs,
+					revs,
 					FOR_EACH_OBJECT_PACK_ORDER);
 	}
 
+	strbuf_release(&buf);
+	string_list_clear(&include_packs, 0);
+	string_list_clear(&exclude_packs, 0);
+}
+
+static void add_unreachable_loose_objects(struct rev_info *revs);
+
+static void read_stdin_packs(enum stdin_packs_mode mode, int rev_list_unpacked)
+{
+	struct rev_info revs;
+
+	repo_init_revisions(the_repository, &revs, NULL);
+	/*
+	 * Use a revision walk to fill in the namehash of objects in the include
+	 * packs. To save time, we'll avoid traversing through objects that are
+	 * in excluded packs.
+	 *
+	 * That may cause us to avoid populating all of the namehash fields of
+	 * all included objects, but our goal is best-effort, since this is only
+	 * an optimization during delta selection.
+	 */
+	revs.no_kept_objects = 1;
+	revs.keep_pack_cache_flags |= IN_CORE_KEEP_PACKS;
+	revs.blob_objects = 1;
+	revs.tree_objects = 1;
+	revs.tag_objects = 1;
+	revs.ignore_missing_links = 1;
+
+	/* avoids adding objects in excluded packs */
+	ignore_packed_keep_in_core = 1;
+	read_packs_list_from_stdin(&revs);
+	if (rev_list_unpacked)
+		add_unreachable_loose_objects(&revs);
+
 	if (prepare_revision_walk(&revs))
 		die(_("revision walk setup failed"));
 	traverse_commit_list(&revs,
 			     show_commit_pack_hint,
 			     show_object_pack_hint,
-			     NULL);
+			     &mode);
 
 	trace2_data_intmax("pack-objects", the_repository, "stdin_packs_found",
 			   stdin_packs_found_nr);
 	trace2_data_intmax("pack-objects", the_repository, "stdin_packs_hints",
 			   stdin_packs_hints_nr);
-
-	strbuf_release(&buf);
-	string_list_clear(&include_packs, 0);
-	string_list_clear(&exclude_packs, 0);
 }
 
 static void add_cruft_object_entry(const struct object_id *oid, enum object_type type,
@@ -4004,7 +4040,6 @@ static void mark_pack_kept_in_core(struct string_list *packs, unsigned keep)
 	}
 }
 
-static void add_unreachable_loose_objects(void);
 static void add_objects_in_unpacked_packs(void);
 
 static void enumerate_cruft_objects(void)
@@ -4014,7 +4049,7 @@ static void enumerate_cruft_objects(void)
 						_("Enumerating cruft objects"), 0);
 
 	add_objects_in_unpacked_packs();
-	add_unreachable_loose_objects();
+	add_unreachable_loose_objects(NULL);
 
 	stop_progress(&progress_state);
 }
@@ -4197,7 +4232,7 @@ static void show_object__ma_allow_any(struct object *obj, const char *name, void
 	 * Quietly ignore ALL missing objects.  This avoids problems with
 	 * staging them now and getting an odd error later.
 	 */
-	if (!has_object(the_repository, &obj->oid, 0))
+	if (!odb_has_object(the_repository->objects, &obj->oid, 0))
 		return;
 
 	show_object(obj, name, data);
@@ -4211,7 +4246,7 @@ static void show_object__ma_allow_promisor(struct object *obj, const char *name,
 	 * Quietly ignore EXPECTED missing objects.  This avoids problems with
 	 * staging them now and getting an odd error later.
 	 */
-	if (!has_object(the_repository, &obj->oid, 0) &&
+	if (!odb_has_object(the_repository->objects, &obj->oid, 0) &&
 	    is_promisor_object(to_pack.repo, &obj->oid))
 		return;
 
@@ -4292,9 +4327,10 @@ static void add_objects_in_unpacked_packs(void)
 }
 
 static int add_loose_object(const struct object_id *oid, const char *path,
-			    void *data UNUSED)
+			    void *data)
 {
-	enum object_type type = oid_object_info(the_repository, oid, NULL);
+	struct rev_info *revs = data;
+	enum object_type type = odb_read_object_info(the_repository->objects, oid, NULL);
 
 	if (type < 0) {
 		warning(_("loose object at %s could not be examined"), path);
@@ -4314,6 +4350,10 @@ static int add_loose_object(const struct object_id *oid, const char *path,
 	} else {
 		add_object_entry(oid, type, "", 0);
 	}
+
+	if (revs && type == OBJ_COMMIT)
+		add_pending_oid(revs, NULL, oid, 0);
+
 	return 0;
 }
 
@@ -4322,11 +4362,10 @@ static int add_loose_object(const struct object_id *oid, const char *path,
  * add_object_entry will weed out duplicates, so we just add every
  * loose object we find.
  */
-static void add_unreachable_loose_objects(void)
+static void add_unreachable_loose_objects(struct rev_info *revs)
 {
 	for_each_loose_file_in_objdir(repo_get_object_directory(the_repository),
-				      add_loose_object,
-				      NULL, NULL, NULL);
+				      add_loose_object, NULL, NULL, revs);
 }
 
 static int has_sha1_pack_kept_or_nonlocal(const struct object_id *oid)
@@ -4673,7 +4712,7 @@ static void get_object_list(struct rev_info *revs, int ac, const char **av)
 	if (keep_unreachable)
 		add_objects_in_unpacked_packs();
 	if (pack_loose_unreachable)
-		add_unreachable_loose_objects();
+		add_unreachable_loose_objects(NULL);
 	if (unpack_unreachable)
 		loosen_unused_packed_objects();
 
@@ -4771,7 +4810,7 @@ static int option_parse_cruft_expiration(const struct option *opt UNUSED,
 static int is_not_in_promisor_pack_obj(struct object *obj, void *data UNUSED)
 {
 	struct object_info info = OBJECT_INFO_INIT;
-	if (oid_object_info_extended(the_repository, &obj->oid, &info, 0))
+	if (odb_read_object_info_extended(the_repository->objects, &obj->oid, &info, 0))
 		BUG("should_include_obj should only be called on existing objects");
 	return info.whence != OI_PACKED || !info.u.packed.pack->pack_promisor;
 }
@@ -4780,6 +4819,23 @@ static int is_not_in_promisor_pack(struct commit *commit, void *data) {
 	return is_not_in_promisor_pack_obj((struct object *) commit, data);
 }
 
+static int parse_stdin_packs_mode(const struct option *opt, const char *arg,
+				  int unset)
+{
+	enum stdin_packs_mode *mode = opt->value;
+
+	if (unset)
+		*mode = STDIN_PACKS_MODE_NONE;
+	else if (!arg || !*arg)
+		*mode = STDIN_PACKS_MODE_STANDARD;
+	else if (!strcmp(arg, "follow"))
+		*mode = STDIN_PACKS_MODE_FOLLOW;
+	else
+		die(_("invalid value for '%s': '%s'"), opt->long_name, arg);
+
+	return 0;
+}
+
 int cmd_pack_objects(int argc,
 		     const char **argv,
 		     const char *prefix,
@@ -4790,7 +4846,7 @@ int cmd_pack_objects(int argc,
 	struct strvec rp = STRVEC_INIT;
 	int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0;
 	int rev_list_index = 0;
-	int stdin_packs = 0;
+	enum stdin_packs_mode stdin_packs = STDIN_PACKS_MODE_NONE;
 	struct string_list keep_pack_list = STRING_LIST_INIT_NODUP;
 	struct list_objects_filter_options filter_options =
 		LIST_OBJECTS_FILTER_INIT;
@@ -4845,6 +4901,9 @@ int cmd_pack_objects(int argc,
 		OPT_SET_INT_F(0, "indexed-objects", &rev_list_index,
 			      N_("include objects referred to by the index"),
 			      1, PARSE_OPT_NONEG),
+		OPT_CALLBACK_F(0, "stdin-packs", &stdin_packs, N_("mode"),
+			     N_("read packs from stdin"),
+			     PARSE_OPT_OPTARG, parse_stdin_packs_mode),
 		OPT_BOOL(0, "stdin-packs", &stdin_packs,
 			 N_("read packs from stdin")),
 		OPT_BOOL(0, "stdout", &pack_to_stdout,
@@ -5010,9 +5069,10 @@ int cmd_pack_objects(int argc,
 		strvec_push(&rp, "--unpacked");
 	}
 
-	if (exclude_promisor_objects && exclude_promisor_objects_best_effort)
-		die(_("options '%s' and '%s' cannot be used together"),
-		    "--exclude-promisor-objects", "--exclude-promisor-objects-best-effort");
+	die_for_incompatible_opt2(exclude_promisor_objects,
+				  "--exclude-promisor-objects",
+				  exclude_promisor_objects_best_effort,
+				  "--exclude-promisor-objects-best-effort");
 	if (exclude_promisor_objects) {
 		use_internal_rev_list = 1;
 		fetch_if_missing = 0;
@@ -5050,13 +5110,14 @@ int cmd_pack_objects(int argc,
 	if (!pack_to_stdout && thin)
 		die(_("--thin cannot be used to build an indexable pack"));
 
-	if (keep_unreachable && unpack_unreachable)
-		die(_("options '%s' and '%s' cannot be used together"), "--keep-unreachable", "--unpack-unreachable");
+	die_for_incompatible_opt2(keep_unreachable, "--keep-unreachable",
+				  unpack_unreachable, "--unpack-unreachable");
 	if (!rev_list_all || !rev_list_reflog || !rev_list_index)
 		unpack_unreachable_expiration = 0;
 
-	if (stdin_packs && filter_options.choice)
-		die(_("cannot use --filter with --stdin-packs"));
+	die_for_incompatible_opt2(stdin_packs, "--stdin-packs",
+				  filter_options.choice, "--filter");
+
 
 	if (stdin_packs && use_internal_rev_list)
 		die(_("cannot use internal rev list with --stdin-packs"));
@@ -5064,8 +5125,8 @@ int cmd_pack_objects(int argc,
 	if (cruft) {
 		if (use_internal_rev_list)
 			die(_("cannot use internal rev list with --cruft"));
-		if (stdin_packs)
-			die(_("cannot use --stdin-packs with --cruft"));
+		die_for_incompatible_opt2(stdin_packs, "--stdin-packs",
+					  cruft, "--cruft");
 	}
 
 	/*
@@ -5133,11 +5194,7 @@ int cmd_pack_objects(int argc,
 		progress_state = start_progress(the_repository,
 						_("Enumerating objects"), 0);
 	if (stdin_packs) {
-		/* avoids adding objects in excluded packs */
-		ignore_packed_keep_in_core = 1;
-		read_packs_list_from_stdin();
-		if (rev_list_unpacked)
-			add_unreachable_loose_objects();
+		read_stdin_packs(stdin_packs, rev_list_unpacked);
 	} else if (cruft) {
 		read_cruft_objects();
 	} else if (!use_internal_rev_list) {