builtin/cat-file: support "blob:limit=" objects filter

Implement support for the "blob:limit=" filter in git-cat-file(1), which
causes us to omit all blobs that are bigger than a certain size.

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

Documentation/git-cat-file.adoc

@@ -91,6 +91,11 @@ OPTIONS
 	printed at all. The '<filter-spec>' may be one of the following:
 +
 The form '--filter=blob:none' omits all blobs.
++
+The form '--filter=blob:limit=<n>[kmg]' omits blobs of size at least n
+bytes or units.  n may be zero.  The suffixes k, m, and g can be used to name
+units in KiB, MiB, or GiB.  For example, 'blob:limit=1k' is the same as
+'blob:limit=1024'.
 
 --path=<path>::
 	For use with `--textconv` or `--filters`, to allow specifying an object

builtin/cat-file.c

@@ -483,8 +483,11 @@ static void batch_object_write(const char *obj_name,
 		int ret;
 
 		if (use_mailmap ||
-		    opt->objects_filter.choice == LOFC_BLOB_NONE)
+		    opt->objects_filter.choice == LOFC_BLOB_NONE ||
+		    opt->objects_filter.choice == LOFC_BLOB_LIMIT)
 			data->info.typep = &data->type;
+		if (opt->objects_filter.choice == LOFC_BLOB_LIMIT)
+			data->info.sizep = &data->size;
 
 		if (pack)
 			ret = packed_object_info(the_repository, pack, offset,
@@ -509,6 +512,15 @@ static void batch_object_write(const char *obj_name,
 				return;
 			}
 			break;
+		case LOFC_BLOB_LIMIT:
+			if (data->type == OBJ_BLOB &&
+			    data->size >= opt->objects_filter.blob_limit_value) {
+				if (!opt->all_objects)
+					report_object_status(opt, obj_name,
+							     &data->oid, "excluded");
+				return;
+			}
+			break;
 		default:
 			BUG("unsupported objects filter");
 		}
@@ -1049,6 +1061,7 @@ int cmd_cat_file(int argc,
 	case LOFC_DISABLED:
 		break;
 	case LOFC_BLOB_NONE:
+	case LOFC_BLOB_LIMIT:
 		if (!batch.enabled)
 			usage(_("objects filter only supported in batch mode"));
 		break;

t/t1006-cat-file.sh

@@ -1356,11 +1356,12 @@ test_expect_success PERL '--batch-command info is unbuffered by default' '
 test_expect_success 'setup for objects filter' '
 	git init repo &&
 	(
-		# Seed the repository with three different sets of objects:
+		# Seed the repository with four different sets of objects:
 		#
 		#   - The first set is fully packed and has a bitmap.
 		#   - The second set is packed, but has no bitmap.
 		#   - The third set is loose.
+		#   - The fourth set is loose and contains big objects.
 		#
 		# This ensures that we cover all these types as expected.
 		cd repo &&
@@ -1368,7 +1369,14 @@ test_expect_success 'setup for objects filter' '
 		git repack -Adb &&
 		test_commit second &&
 		git repack -d &&
-		test_commit third
+		test_commit third &&
+
+		for n in 1000 10000
+		do
+			printf "%"$n"s" X >large.$n || return 1
+		done &&
+		git add large.* &&
+		git commit -m fourth
 	)
 '
 
@@ -1380,7 +1388,7 @@ test_expect_success 'objects filter with unknown option' '
 	test_cmp expect err
 '
 
-for option in blob:limit=1 object:type=tag sparse:oid=1234 tree:1 sparse:path=x
+for option in object:type=tag sparse:oid=1234 tree:1 sparse:path=x
 do
 	test_expect_success "objects filter with unsupported option $option" '
 		case "$option" in
@@ -1435,5 +1443,9 @@ test_objects_filter () {
 }
 
 test_objects_filter "blob:none"
+test_objects_filter "blob:limit=1"
+test_objects_filter "blob:limit=500"
+test_objects_filter "blob:limit=1000"
+test_objects_filter "blob:limit=1k"
 
 test_done