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

@@ -1105,15 +1105,17 @@ static int check_and_freshen_nonlocal(const struct object_id *oid, int freshen)
 	return 0;
 }
 
-static int check_and_freshen(const struct object_id *oid, int freshen)
+static int check_and_freshen(const struct object_id *oid, int freshen,
+			     int skip_virtualized_objects)
 {
 	int ret;
 	int tried_hook = 0;
 
 retry:
 	ret = check_and_freshen_local(oid, freshen) ||
 	       check_and_freshen_nonlocal(oid, freshen);
-	if (!ret && core_virtualize_objects && !tried_hook) {
+	if (!ret && core_virtualize_objects && !skip_virtualized_objects &&
+	    !tried_hook) {
 		tried_hook = 1;
 		if (!read_object_process(oid))
 			goto retry;
@@ -1129,7 +1131,7 @@ int has_loose_object_nonlocal(const struct object_id *oid)
 
 int has_loose_object(const struct object_id *oid)
 {
-	return check_and_freshen(oid, 0);
+	return check_and_freshen(oid, 0, 0);
 }
 
 static void mmap_limit_check(size_t length)
@@ -2201,9 +2203,10 @@ static int write_loose_object(const struct object_id *oid, char *hdr,
 	return finalize_object_file(tmp_file.buf, filename.buf);
 }
 
-static int freshen_loose_object(const struct object_id *oid)
+static int freshen_loose_object(const struct object_id *oid,
+				int skip_virtualized_objects)
 {
-	return check_and_freshen(oid, 1);
+	return check_and_freshen(oid, 1, skip_virtualized_objects);
 }
 
 static int freshen_packed_object(const struct object_id *oid)
@@ -2297,7 +2300,7 @@ int stream_loose_object(struct input_stream *in_stream, size_t len,
 		die(_("deflateEnd on stream object failed (%d)"), ret);
 	close_loose_object(fd, tmp_file.buf);
 
-	if (freshen_packed_object(oid) || freshen_loose_object(oid)) {
+	if (freshen_packed_object(oid) || freshen_loose_object(oid, 1)) {
 		unlink_or_warn(tmp_file.buf);
 		goto cleanup;
 	}
@@ -2337,7 +2340,7 @@ int write_object_file_flags(const void *buf, size_t len,
 	 */
 	write_object_file_prepare(the_hash_algo, buf, len, type, oid, hdr,
 				  &hdrlen);
-	if (freshen_packed_object(oid) || freshen_loose_object(oid))
+	if (freshen_packed_object(oid) || freshen_loose_object(oid, 1))
 		return 0;
 	return write_loose_object(oid, hdr, hdrlen, buf, len, 0, flags);
 }
@@ -2358,7 +2361,7 @@ int write_object_file_literally(const void *buf, size_t len,
 
 	if (!(flags & HASH_WRITE_OBJECT))
 		goto cleanup;
-	if (freshen_packed_object(oid) || freshen_loose_object(oid))
+	if (freshen_packed_object(oid) || freshen_loose_object(oid, 1))
 		goto cleanup;
 	status = write_loose_object(oid, header, hdrlen, buf, len, 0, 0);
 

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/t0411-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