sha1_file: when writing objects, skip the read_object_hook

If we are going to write an object there is no use in calling
the read object hook to get an object from a potentially remote
source.  We would rather just write out the object and avoid the
potential round trip for an object that doesn't exist.

This change adds a flag to the check_and_freshen() and
freshen_loose_object() functions' signatures so that the hook
is bypassed when the functions are called before writing loose
objects. The check for a local object is still performed so we
don't overwrite something that has already been written to one
of the objects directories.

Based on a patch by Kevin Willford.

Signed-off-by: Johannes Schindelin <[email protected]>

Author: dscho

object-file.c

@@ -92,15 +92,16 @@ int check_and_freshen_file(const char *fn, int freshen)
 
 static int check_and_freshen_source(struct odb_source *source,
 				    const struct object_id *oid,
-				    int freshen)
+				    int freshen, int skip_virtualized_objects)
 {
 	static struct strbuf path = STRBUF_INIT;
 	int ret, tried_hook = 0;
 
 	odb_loose_path(source, &path, oid);
 retry:
 	ret = check_and_freshen_file(path.buf, freshen);
-	if (!ret && gvfs_virtualize_objects(source->odb->repo) && !tried_hook) {
+	if (!ret && gvfs_virtualize_objects(source->odb->repo) &&
+	    !skip_virtualized_objects && !tried_hook) {
 		tried_hook = 1;
 		if (!read_object_process(source->odb->repo, oid))
 			goto retry;
@@ -111,7 +112,7 @@ static int check_and_freshen_source(struct odb_source *source,
 int has_loose_object(struct odb_source *source,
 		     const struct object_id *oid)
 {
-	return check_and_freshen_source(source, oid, 0);
+	return check_and_freshen_source(source, oid, 0, 0);
 }
 
 int format_object_header(char *str, size_t size, enum object_type type,
@@ -909,11 +910,12 @@ static int write_loose_object(struct odb_source *source,
 }
 
 static int freshen_loose_object(struct object_database *odb,
-				const struct object_id *oid)
+				const struct object_id *oid,
+				int skip_virtualized_objects)
 {
 	odb_prepare_alternates(odb);
 	for (struct odb_source *source = odb->sources; source; source = source->next)
-		if (check_and_freshen_source(source, oid, 1))
+		if (check_and_freshen_source(source, oid, 1, skip_virtualized_objects))
 			return 1;
 	return 0;
 }
@@ -1014,7 +1016,7 @@ int stream_loose_object(struct odb_source *source,
 	close_loose_object(source, fd, tmp_file.buf);
 
 	if (freshen_packed_object(source->odb, oid) ||
-	    freshen_loose_object(source->odb, oid)) {
+	    freshen_loose_object(source->odb, oid, 1)) {
 		unlink_or_warn(tmp_file.buf);
 		goto cleanup;
 	}
@@ -1078,7 +1080,7 @@ int write_object_file(struct odb_source *source,
 	 */
 	write_object_file_prepare(algo, buf, len, type, oid, hdr, &hdrlen);
 	if (freshen_packed_object(source->odb, oid) ||
-	    freshen_loose_object(source->odb, oid))
+	    freshen_loose_object(source->odb, oid, 1))
 		return 0;
 	if (write_loose_object(source, oid, hdr, hdrlen, buf, len, 0, flags))
 		return -1;

t/t0410/read-object

@@ -108,6 +108,10 @@ while (1) {
 		system ('git --git-dir="' . $DIR . '" cat-file blob ' . $sha1 . ' | git -c core.virtualizeobjects=false hash-object -w --stdin >/dev/null 2>&1');
 		packet_txt_write(($?) ? "status=error" : "status=success");
 		packet_flush();
+
+		open my $log, '>>.git/read-object-hook.log';
+		print $log "Read object $sha1, exit code $?\n";
+		close $log;
 	} else {
 		die "bad command '$command'";
 	}

t/t0499-read-object.sh

@@ -26,5 +26,12 @@ test_expect_success 'invalid blobs generate errors' '
 	 test_must_fail git cat-file blob "invalid")
 '
 
+test_expect_success 'read-object-hook is bypassed when writing objects' '
+	(cd guest-repo &&
+	 echo hello >hello.txt &&
+	 git add hello.txt &&
+	 hash="$(git rev-parse --verify :hello.txt)" &&
+	 ! grep "$hash" .git/read-object-hook.log)
+'
 
 test_done