Re: [PATCH 7/7] builtin/cat-file: filter objects via object database
From: Junio C Hamano <hidden>
Date: 2026-07-09 18:59:32
Patrick Steinhardt [off-list ref] writes:
Refactor git-cat-file(1) to use the new object filter option when batching all objects. This significantly simplifies the logic and ensures that we don't have to reach into internals of the "files" source anymore.
This would become more convincing if you spent a few lines before
presenting the solution to give an observation of what the current
code does, e.g.,
When batching all objects, git-cat-file(1) reaches into the
internals of the object database and manually manages bitmaps to
apply object filters. This creates coupling between the command
and ODB backend internals.
to highlight the perceived problem in it. That would flow naturally
to the description of your solution.
Signed-off-by: Patrick Steinhardt <redacted> --- builtin/cat-file.c | 76 +++++------------------------------------------------- 1 file changed, 7 insertions(+), 69 deletions(-)
Very nice.
quoted hunk ↗ jump to hunk
diff --git a/builtin/cat-file.c b/builtin/cat-file.c index b4b99a73da..1458dd76d6 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c@@ -20,7 +20,6 @@ #include "userdiff.h" #include "oid-array.h" #include "packfile.h" -#include "pack-bitmap.h" #include "object-file.h" #include "object-name.h" #include "odb.h"@@ -844,28 +843,6 @@ static int batch_one_object_oi(const struct object_id *oid, return payload->callback(oid, NULL, 0, payload->payload); } -static int batch_one_object_packed(const struct object_id *oid, - struct packed_git *pack, - uint32_t pos, - void *_payload) -{ - struct for_each_object_payload *payload = _payload; - return payload->callback(oid, pack, nth_packed_object_offset(pack, pos), - payload->payload); -} - -static int batch_one_object_bitmapped(const struct object_id *oid, - enum object_type type UNUSED, - int flags UNUSED, - uint32_t hash UNUSED, - struct packed_git *pack, - off_t offset, - void *_payload) -{ - struct for_each_object_payload *payload = _payload; - return payload->callback(oid, pack, offset, payload->payload); -} - static void batch_each_object(struct batch_options *opt, for_each_object_fn callback, unsigned flags,@@ -875,56 +852,17 @@ static void batch_each_object(struct batch_options *opt, .callback = callback, .payload = _payload, }; + struct odb_source_info source_info; + struct object_info oi = { + .source_infop = &source_info, + }; struct odb_for_each_object_options opts = { .flags = flags, + .filter = &opt->objects_filter, }; - struct bitmap_index *bitmap = NULL; - struct odb_source *source; - - /* - * TODO: we still need to tap into implementation details of the object - * database sources. Ideally, we should extend `odb_for_each_object()` - * to handle object filters itself so that we can move the filtering - * logic into the individual sources. - */ - odb_prepare_alternates(the_repository->objects); - for (source = the_repository->objects->sources; source; source = source->next) { - struct odb_source_files *files = odb_source_files_downcast(source); - int ret = odb_source_for_each_object(&files->loose->base, NULL, batch_one_object_oi, - &payload, &opts); - if (ret) - break; - } - - if (opt->objects_filter.choice != LOFC_DISABLED && - (bitmap = prepare_bitmap_git(the_repository)) && - !for_each_bitmapped_object(bitmap, &opt->objects_filter, - batch_one_object_bitmapped, &payload)) { - struct packed_git *pack; - - repo_for_each_pack(the_repository, pack) { - if (bitmap_index_contains_pack(bitmap, pack) || - open_pack_index(pack)) - continue; - for_each_object_in_pack(pack, batch_one_object_packed, - &payload, flags); - } - } else { - struct odb_source_info source_info; - struct object_info oi = { - .source_infop = &source_info, - }; - - for (source = the_repository->objects->sources; source; source = source->next) { - struct odb_source_files *files = odb_source_files_downcast(source); - int ret = odb_source_for_each_object(&files->packed->base, &oi, - batch_one_object_oi, &payload, &opts); - if (ret) - break; - } - } - free_bitmap_index(bitmap); + odb_for_each_object_ext(the_repository->objects, &oi, + batch_one_object_oi, &payload, &opts); } static int batch_objects(struct batch_options *opt)