object-file: adapt `stream_object_signature()` to take a stream

The function `stream_object_signature()` is responsible for verifying
whether the given object ID matches the actual hash of the object's
contents. In contrast to `check_object_signature()` it does so in a
streaming fashion so that we don't have to load the full object into
memory.

In a subsequent commit we'll want to adapt one of its callsites to pass
a preconstructed stream. Prepare for this by accepting a stream as input
that the caller needs to assemble.

While at it, improve the error reporting in `parse_object_with_flags()`
to tell apart the two failure modes.

Helped-by: Jeff King <peff@peff.net>
Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

4 files changed, 31 insertions, 14 deletions

diff --git a/object-file.c b/object-file.c
index e7e4c3348f..a59b7abaaf 100644
--- a/object-file.c
+++ b/object-file.c
@@ -129,18 +129,15 @@ int check_object_signature(struct repository *r, const struct object_id *oid,
 	return !oideq(oid, &real_oid) ? -1 : 0;
 }
 
-int stream_object_signature(struct repository *r, const struct object_id *oid)
+int stream_object_signature(struct repository *r,
+			    struct odb_read_stream *st,
+			    const struct object_id *oid)
 {
 	struct object_id real_oid;
-	struct odb_read_stream *st;
 	struct git_hash_ctx c;
 	char hdr[MAX_HEADER_LEN];
 	int hdrlen;
 
-	st = odb_read_stream_open(r->objects, oid, NULL);
-	if (!st)
-		return -1;
-
 	/* Generate the header */
 	hdrlen = format_object_header(hdr, sizeof(hdr), st->type, st->size);
 
@@ -160,7 +157,6 @@ int stream_object_signature(struct repository *r, const struct object_id *oid)
 		git_hash_update(&c, buf, readlen);
 	}
 	git_hash_final_oid(&real_oid, &c);
-	odb_read_stream_close(st);
 	return !oideq(oid, &real_oid) ? -1 : 0;
 }
 
diff --git a/object-file.h b/object-file.h
index 1229d5f675..6936fd0fef 100644
--- a/object-file.h
+++ b/object-file.h
@@ -164,7 +164,9 @@ int check_object_signature(struct repository *r, const struct object_id *oid,
  * Try reading the object named with "oid" using
  * the streaming interface and rehash it to do the same.
  */
-int stream_object_signature(struct repository *r, const struct object_id *oid);
+int stream_object_signature(struct repository *r,
+			    struct odb_read_stream *stream,
+			    const struct object_id *oid);
 
 enum finalize_object_file_flags {
 	FOF_SKIP_COLLISION_CHECK = 1,
diff --git a/object.c b/object.c
index 4669b8d65e..9d2c676b16 100644
--- a/object.c
+++ b/object.c
@@ -6,6 +6,7 @@
 #include "object.h"
 #include "replace-object.h"
 #include "object-file.h"
+#include "odb/streaming.h"
 #include "blob.h"
 #include "statinfo.h"
 #include "tree.h"
@@ -330,9 +331,21 @@ struct object *parse_object_with_flags(struct repository *r,
 
 	if ((!obj || obj->type == OBJ_NONE || obj->type == OBJ_BLOB) &&
 	    odb_read_object_info(r->objects, oid, NULL) == OBJ_BLOB) {
-		if (!skip_hash && stream_object_signature(r, repl) < 0) {
-			error(_("hash mismatch %s"), oid_to_hex(oid));
-			return NULL;
+		if (!skip_hash) {
+			struct odb_read_stream *stream = odb_read_stream_open(r->objects, oid, NULL);
+
+			if (!stream) {
+				error(_("unable to open object stream for %s"), oid_to_hex(oid));
+				return NULL;
+			}
+
+			if (stream_object_signature(r, stream, repl) < 0) {
+				error(_("hash mismatch %s"), oid_to_hex(oid));
+				odb_read_stream_close(stream);
+				return NULL;
+			}
+
+			odb_read_stream_close(stream);
 		}
 		parse_blob_buffer(lookup_blob(r, oid));
 		return lookup_object(r, oid);
diff --git a/pack-check.c b/pack-check.c
index 67cb2cf72f..46782a29d5 100644
--- a/pack-check.c
+++ b/pack-check.c
@@ -9,6 +9,7 @@
 #include "packfile.h"
 #include "object-file.h"
 #include "odb.h"
+#include "odb/streaming.h"
 
 struct idx_entry {
 	off_t                offset;
@@ -104,6 +105,7 @@ static int verify_packfile(struct repository *r,
 	QSORT(entries, nr_objects, compare_entries);
 
 	for (i = 0; i < nr_objects; i++) {
+		struct odb_read_stream *stream = NULL;
 		void *data;
 		struct object_id oid;
 		enum object_type type;
@@ -152,7 +154,9 @@ static int verify_packfile(struct repository *r,
 							type) < 0)
 			err = error("packed %s from %s is corrupt",
 				    oid_to_hex(&oid), p->pack_name);
-		else if (!data && stream_object_signature(r, &oid) < 0)
+		else if (!data &&
+			 (!(stream = odb_read_stream_open(r->objects, &oid, NULL)) ||
+			  stream_object_signature(r, stream, &oid) < 0))
 			err = error("packed %s from %s is corrupt",
 				    oid_to_hex(&oid), p->pack_name);
 		else if (fn) {
@@ -163,12 +167,14 @@ static int verify_packfile(struct repository *r,
 		}
 		if (((base_count + i) & 1023) == 0)
 			display_progress(progress, base_count + i);
-		free(data);
 
+		if (stream)
+			odb_read_stream_close(stream);
+		free(data);
 	}
+
 	display_progress(progress, base_count + i);
 	free(entries);
-
 	return err;
 }