Merge branch 'ps/object-read-stream' into jc/object-read-stream-fix

* ps/object-read-stream: (32 commits)
  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`
  object-file: refactor writing objects via a stream
  ...

1 files changed, 182 insertions, 1 deletions

diff --git a/packfile.c b/packfile.c
index 1ae2b2fe1e..7a16aaa90d 100644
--- a/packfile.c
+++ b/packfile.c
@@ -20,6 +20,7 @@
 #include "tree.h"
 #include "object-file.h"
 #include "odb.h"
+#include "odb/streaming.h"
 #include "midx.h"
 #include "commit-graph.h"
 #include "pack-revindex.h"
@@ -2048,7 +2049,9 @@ static int fill_pack_entry(const struct object_id *oid,
 	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;
 
@@ -2071,6 +2074,57 @@ int find_pack_entry(struct repository *r, const struct object_id *oid, struct pa
 	return 0;
 }
 
+int packfile_store_freshen_object(struct packfile_store *store,
+				  const struct object_id *oid)
+{
+	struct pack_entry e;
+	if (!find_pack_entry(store->odb->repo, oid, &e))
+		return 0;
+	if (e.p->is_cruft)
+		return 0;
+	if (e.p->freshened)
+		return 1;
+	if (utime(e.p->pack_name, NULL))
+		return 0;
+	e.p->freshened = 1;
+	return 1;
+}
+
+int packfile_store_read_object_info(struct packfile_store *store,
+				    const struct object_id *oid,
+				    struct object_info *oi,
+				    unsigned flags UNUSED)
+{
+	static struct object_info blank_oi = OBJECT_INFO_INIT;
+	struct pack_entry e;
+	int rtype;
+
+	if (!find_pack_entry(store->odb->repo, oid, &e))
+		return 1;
+
+	/*
+	 * We know that the caller doesn't actually need the
+	 * information below, so return early.
+	 */
+	if (oi == &blank_oi)
+		return 0;
+
+	rtype = packed_object_info(store->odb->repo, e.p, e.offset, oi);
+	if (rtype < 0) {
+		mark_bad_packed_object(e.p, oid);
+		return -1;
+	}
+
+	if (oi->whence == OI_PACKED) {
+		oi->u.packed.offset = e.offset;
+		oi->u.packed.pack = e.p;
+		oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
+					 rtype == OBJ_OFS_DELTA);
+	}
+
+	return 0;
+}
+
 static void maybe_invalidate_kept_pack_cache(struct repository *r,
 					     unsigned flags)
 {
@@ -2353,3 +2407,130 @@ void packfile_store_close(struct packfile_store *store)
 		close_pack(p);
 	}
 }
+
+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;
+}