builtin/cat-file: support "blob:none" objects filter

Implement support for the "blob:none" filter in git-cat-file(1), which
causes us to omit all blobs.

Note that this new filter requires us to read the object type via
`oid_object_info_extended()` in `batch_object_write()`. But as we try to
optimize away reading objects from the database the `data->info.typep`
pointer may not be set. We thus have to adapt the logic to conditionally
set the pointer in cases where the filter is given.

Signed-off-by: Patrick Steinhardt <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: pks-t

Documentation/git-cat-file.adoc

@@ -88,7 +88,9 @@ OPTIONS
 	been explicitly requested via any of the batch modes that read objects
 	via standard input (`--batch`, `--batch-check`) will be reported as
 	"filtered". Excluded objects in `--batch-all-objects` mode will not be
-	printed at all. No filters are supported yet.
+	printed at all. The '<filter-spec>' may be one of the following:
++
+The form '--filter=blob:none' omits all blobs.
 
 --path=<path>::
 	For use with `--textconv` or `--filters`, to allow specifying an object

builtin/cat-file.c

@@ -482,7 +482,8 @@ static void batch_object_write(const char *obj_name,
 	if (!data->skip_object_info) {
 		int ret;
 
-		if (use_mailmap)
+		if (use_mailmap ||
+		    opt->objects_filter.choice == LOFC_BLOB_NONE)
 			data->info.typep = &data->type;
 
 		if (pack)
@@ -500,6 +501,14 @@ static void batch_object_write(const char *obj_name,
 		switch (opt->objects_filter.choice) {
 		case LOFC_DISABLED:
 			break;
+		case LOFC_BLOB_NONE:
+			if (data->type == OBJ_BLOB) {
+				if (!opt->all_objects)
+					report_object_status(opt, obj_name,
+							     &data->oid, "excluded");
+				return;
+			}
+			break;
 		default:
 			BUG("unsupported objects filter");
 		}
@@ -1039,6 +1048,10 @@ int cmd_cat_file(int argc,
 	switch (batch.objects_filter.choice) {
 	case LOFC_DISABLED:
 		break;
+	case LOFC_BLOB_NONE:
+		if (!batch.enabled)
+			usage(_("objects filter only supported in batch mode"));
+		break;
 	default:
 		usagef(_("objects filter not supported: '%s'"),
 		       list_object_filter_config_name(batch.objects_filter.choice));

t/t1006-cat-file.sh

@@ -1354,7 +1354,22 @@ test_expect_success PERL '--batch-command info is unbuffered by default' '
 '
 
 test_expect_success 'setup for objects filter' '
-	git init repo
+	git init repo &&
+	(
+		# Seed the repository with three 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.
+		#
+		# This ensures that we cover all these types as expected.
+		cd repo &&
+		test_commit first &&
+		git repack -Adb &&
+		test_commit second &&
+		git repack -d &&
+		test_commit third
+	)
 '
 
 test_expect_success 'objects filter with unknown option' '
@@ -1365,7 +1380,7 @@ test_expect_success 'objects filter with unknown option' '
 	test_cmp expect err
 '
 
-for option in blob:none blob:limit=1 object:type=tag sparse:oid=1234 tree:1 sparse:path=x
+for option in blob:limit=1 object:type=tag sparse:oid=1234 tree:1 sparse:path=x
 do
 	test_expect_success "objects filter with unsupported option $option" '
 		case "$option" in
@@ -1393,4 +1408,32 @@ test_expect_success 'objects filter: disabled' '
 	test_cmp expect.sorted actual.sorted
 '
 
+test_objects_filter () {
+	filter="$1"
+
+	test_expect_success "objects filter: $filter" '
+		git -C repo cat-file --batch-check="%(objectname)" --batch-all-objects --filter="$filter" >actual &&
+		sort actual >actual.sorted &&
+		git -C repo rev-list --objects --no-object-names --all --filter="$filter" --filter-provided-objects >expect &&
+		sort expect >expect.sorted &&
+		test_cmp expect.sorted actual.sorted
+	'
+
+	test_expect_success "objects filter prints excluded objects: $filter" '
+		# Find all objects that would be excluded by the current filter.
+		git -C repo rev-list --objects --no-object-names --all >all &&
+		git -C repo rev-list --objects --no-object-names --all --filter="$filter" --filter-provided-objects >filtered &&
+		sort all >all.sorted &&
+		sort filtered >filtered.sorted &&
+		comm -23 all.sorted filtered.sorted >expected.excluded &&
+		test_line_count -gt 0 expected.excluded &&
+
+		git -C repo cat-file --batch-check="%(objectname)" --filter="$filter" <expected.excluded >actual &&
+		awk "/excluded/{ print \$1 }" actual | sort >actual.excluded &&
+		test_cmp expected.excluded actual.excluded
+	'
+}
+
+test_objects_filter "blob:none"
+
 test_done