From: Junio C Hamano Date: Tue, 16 Dec 2025 02:08:34 +0000 (+0900) Subject: Merge branch 'ps/object-read-stream' X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=dbe54273a707406409fa386db5b105557b31a831;p=thirdparty%2Fgit.git Merge branch 'ps/object-read-stream' The "git_istream" abstraction has been revamped to make it easier to interface with pluggable object database design. * ps/object-read-stream: streaming: drop redundant type and size pointers streaming: move into object database subsystem streaming: refactor interface to be object-database-centric streaming: move logic to read packed objects streams into backend streaming: move logic to read loose objects streams into backend streaming: make the `odb_read_stream` definition public streaming: get rid of `the_repository` streaming: rely on object sources to create object stream packfile: introduce function to read object info from a store streaming: move zlib stream into backends streaming: create structure for filtered object streams streaming: create structure for packed object streams streaming: create structure for loose object streams streaming: create structure for in-core object streams streaming: allocate stream inside the backend-specific logic streaming: explicitly pass packfile info when streaming a packed object streaming: propagate final object type via the stream streaming: drop the `open()` callback function streaming: rename `git_istream` into `odb_read_stream` --- dbe54273a707406409fa386db5b105557b31a831 diff --cc packfile.c index 3d8b994a61,7a16aaa90d..c88bd92619 --- a/packfile.c +++ b/packfile.c @@@ -2105,9 -2049,11 +2090,11 @@@ static int fill_pack_entry(const struc return 1; } - int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e) + static int find_pack_entry(struct repository *r, + const struct object_id *oid, + struct pack_entry *e) { - struct list_head *pos; + struct packfile_list_entry *l; packfile_store_prepare(r->objects->packfiles); @@@ -2394,9 -2401,136 +2432,136 @@@ void packfile_store_free(struct packfil void packfile_store_close(struct packfile_store *store) { - for (struct packed_git *p = store->packs; p; p = p->next) { - if (p->do_not_close) + for (struct packfile_list_entry *e = store->packs.head; e; e = e->next) { + if (e->pack->do_not_close) BUG("want to close pack marked 'do-not-close'"); - close_pack(p); + close_pack(e->pack); } } + + struct odb_packed_read_stream { + struct odb_read_stream base; + struct packed_git *pack; + git_zstream z; + enum { + ODB_PACKED_READ_STREAM_UNINITIALIZED, + ODB_PACKED_READ_STREAM_INUSE, + ODB_PACKED_READ_STREAM_DONE, + ODB_PACKED_READ_STREAM_ERROR, + } z_state; + off_t pos; + }; + + static ssize_t read_istream_pack_non_delta(struct odb_read_stream *_st, char *buf, + size_t sz) + { + struct odb_packed_read_stream *st = (struct odb_packed_read_stream *)_st; + size_t total_read = 0; + + switch (st->z_state) { + case ODB_PACKED_READ_STREAM_UNINITIALIZED: + memset(&st->z, 0, sizeof(st->z)); + git_inflate_init(&st->z); + st->z_state = ODB_PACKED_READ_STREAM_INUSE; + break; + case ODB_PACKED_READ_STREAM_DONE: + return 0; + case ODB_PACKED_READ_STREAM_ERROR: + return -1; + case ODB_PACKED_READ_STREAM_INUSE: + break; + } + + while (total_read < sz) { + int status; + struct pack_window *window = NULL; + unsigned char *mapped; + + mapped = use_pack(st->pack, &window, + st->pos, &st->z.avail_in); + + st->z.next_out = (unsigned char *)buf + total_read; + st->z.avail_out = sz - total_read; + st->z.next_in = mapped; + status = git_inflate(&st->z, Z_FINISH); + + st->pos += st->z.next_in - mapped; + total_read = st->z.next_out - (unsigned char *)buf; + unuse_pack(&window); + + if (status == Z_STREAM_END) { + git_inflate_end(&st->z); + st->z_state = ODB_PACKED_READ_STREAM_DONE; + break; + } + + /* + * Unlike the loose object case, we do not have to worry here + * about running out of input bytes and spinning infinitely. If + * we get Z_BUF_ERROR due to too few input bytes, then we'll + * replenish them in the next use_pack() call when we loop. If + * we truly hit the end of the pack (i.e., because it's corrupt + * or truncated), then use_pack() catches that and will die(). + */ + if (status != Z_OK && status != Z_BUF_ERROR) { + git_inflate_end(&st->z); + st->z_state = ODB_PACKED_READ_STREAM_ERROR; + return -1; + } + } + return total_read; + } + + static int close_istream_pack_non_delta(struct odb_read_stream *_st) + { + struct odb_packed_read_stream *st = (struct odb_packed_read_stream *)_st; + if (st->z_state == ODB_PACKED_READ_STREAM_INUSE) + git_inflate_end(&st->z); + return 0; + } + + int packfile_store_read_object_stream(struct odb_read_stream **out, + struct packfile_store *store, + const struct object_id *oid) + { + struct odb_packed_read_stream *stream; + struct pack_window *window = NULL; + struct object_info oi = OBJECT_INFO_INIT; + enum object_type in_pack_type; + unsigned long size; + + oi.sizep = &size; + + if (packfile_store_read_object_info(store, oid, &oi, 0) || + oi.u.packed.is_delta || + repo_settings_get_big_file_threshold(store->odb->repo) >= size) + return -1; + + in_pack_type = unpack_object_header(oi.u.packed.pack, + &window, + &oi.u.packed.offset, + &size); + unuse_pack(&window); + switch (in_pack_type) { + default: + return -1; /* we do not do deltas for now */ + case OBJ_COMMIT: + case OBJ_TREE: + case OBJ_BLOB: + case OBJ_TAG: + break; + } + + CALLOC_ARRAY(stream, 1); + stream->base.close = close_istream_pack_non_delta; + stream->base.read = read_istream_pack_non_delta; + stream->base.type = in_pack_type; + stream->base.size = size; + stream->z_state = ODB_PACKED_READ_STREAM_UNINITIALIZED; + stream->pack = oi.u.packed.pack; + stream->pos = oi.u.packed.offset; + + *out = &stream->base; + + return 0; + } diff --cc packfile.h index 20e1cf17b2,3fcc5ae6e0..59d162a3f4 --- a/packfile.h +++ b/packfile.h @@@ -9,8 -8,12 +9,9 @@@ /* in odb.h */ struct object_info; + struct odb_read_stream; struct packed_git { - struct hashmap_entry packmap_ent; - struct packed_git *next; - struct list_head mru; struct pack_window *windows; off_t pack_size; const void *index_data; @@@ -174,9 -143,23 +175,24 @@@ void packfile_store_add_pack(struct pac * repository. */ #define repo_for_each_pack(repo, p) \ - for (p = packfile_store_get_packs(repo->objects->packfiles); p; p = p->next) + for (struct packfile_list_entry *e = packfile_store_get_packs(repo->objects->packfiles); \ + ((p) = (e ? e->pack : NULL)); e = e->next) + int packfile_store_read_object_stream(struct odb_read_stream **out, + struct packfile_store *store, + const struct object_id *oid); + + /* + * Try to read the object identified by its ID from the object store and + * populate the object info with its data. Returns 1 in case the object was + * not found, 0 if it was and read successfully, and a negative error code in + * case the object was corrupted. + */ + int packfile_store_read_object_info(struct packfile_store *store, + const struct object_id *oid, + struct object_info *oi, + unsigned flags); + /* * Get all packs managed by the given store, including packfiles that are * referenced by multi-pack indices.