rev-list: allow filtering of provided items

When providing an object filter, it is currently impossible to also
filter provided items. E.g. when executing `git rev-list HEAD` , the
commit this reference points to will be treated as user-provided and is
thus excluded from the filtering mechanism. This makes it harder than
necessary to properly use the new `--filter=object:type` filter given
that even if the user wants to only see blobs, he'll still see commits
of provided references.

Improve this by introducing a new `--filter-provided-objects` option
to the git-rev-parse(1) command. If given, then all user-provided
references will be subject to filtering.

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

Author: pks-t

Documentation/rev-list-options.txt

@@ -933,6 +933,11 @@ equivalent.
 --no-filter::
 	Turn off any previous `--filter=` argument.
 
+--filter-provided-objects::
+	Filter the list of explicitly provided objects, which would otherwise
+	always be printed even if they did not match any of the filters. Only
+	useful with `--filter=`.
+
 --filter-print-omitted::
 	Only useful with `--filter=`; prints a list of the objects omitted
 	by the filter.  Object IDs are prefixed with a ``~'' character.

builtin/pack-objects.c

@@ -3516,7 +3516,7 @@ static int pack_options_allow_reuse(void)
 
 static int get_object_list_from_bitmap(struct rev_info *revs)
 {
-	if (!(bitmap_git = prepare_bitmap_walk(revs, &filter_options)))
+	if (!(bitmap_git = prepare_bitmap_walk(revs, &filter_options, 0)))
 		return -1;
 
 	if (pack_options_allow_reuse() &&

builtin/rev-list.c

@@ -398,7 +398,8 @@ static inline int parse_missing_action_value(const char *value)
 }
 
 static int try_bitmap_count(struct rev_info *revs,
-			    struct list_objects_filter_options *filter)
+			    struct list_objects_filter_options *filter,
+			    int filter_provided_objects)
 {
 	uint32_t commit_count = 0,
 		 tag_count = 0,
@@ -433,7 +434,7 @@ static int try_bitmap_count(struct rev_info *revs,
 	 */
 	max_count = revs->max_count;
 
-	bitmap_git = prepare_bitmap_walk(revs, filter);
+	bitmap_git = prepare_bitmap_walk(revs, filter, filter_provided_objects);
 	if (!bitmap_git)
 		return -1;
 
@@ -450,7 +451,8 @@ static int try_bitmap_count(struct rev_info *revs,
 }
 
 static int try_bitmap_traversal(struct rev_info *revs,
-				struct list_objects_filter_options *filter)
+				struct list_objects_filter_options *filter,
+				int filter_provided_objects)
 {
 	struct bitmap_index *bitmap_git;
 
@@ -461,7 +463,7 @@ static int try_bitmap_traversal(struct rev_info *revs,
 	if (revs->max_count >= 0)
 		return -1;
 
-	bitmap_git = prepare_bitmap_walk(revs, filter);
+	bitmap_git = prepare_bitmap_walk(revs, filter, filter_provided_objects);
 	if (!bitmap_git)
 		return -1;
 
@@ -471,14 +473,15 @@ static int try_bitmap_traversal(struct rev_info *revs,
 }
 
 static int try_bitmap_disk_usage(struct rev_info *revs,
-				 struct list_objects_filter_options *filter)
+				 struct list_objects_filter_options *filter,
+				 int filter_provided_objects)
 {
 	struct bitmap_index *bitmap_git;
 
 	if (!show_disk_usage)
 		return -1;
 
-	bitmap_git = prepare_bitmap_walk(revs, filter);
+	bitmap_git = prepare_bitmap_walk(revs, filter, filter_provided_objects);
 	if (!bitmap_git)
 		return -1;
 
@@ -499,6 +502,7 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 	int bisect_show_vars = 0;
 	int bisect_find_all = 0;
 	int use_bitmap_index = 0;
+	int filter_provided_objects = 0;
 	const char *show_progress = NULL;
 
 	if (argc == 2 && !strcmp(argv[1], "-h"))
@@ -599,6 +603,10 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 			list_objects_filter_set_no_filter(&filter_options);
 			continue;
 		}
+		if (!strcmp(arg, "--filter-provided-objects")) {
+			filter_provided_objects = 1;
+			continue;
+		}
 		if (!strcmp(arg, "--filter-print-omitted")) {
 			arg_print_omitted = 1;
 			continue;
@@ -665,11 +673,11 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 		progress = start_delayed_progress(show_progress, 0);
 
 	if (use_bitmap_index) {
-		if (!try_bitmap_count(&revs, &filter_options))
+		if (!try_bitmap_count(&revs, &filter_options, filter_provided_objects))
 			return 0;
-		if (!try_bitmap_disk_usage(&revs, &filter_options))
+		if (!try_bitmap_disk_usage(&revs, &filter_options, filter_provided_objects))
 			return 0;
-		if (!try_bitmap_traversal(&revs, &filter_options))
+		if (!try_bitmap_traversal(&revs, &filter_options, filter_provided_objects))
 			return 0;
 	}
 
@@ -694,6 +702,16 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 			return show_bisect_vars(&info, reaches, all);
 	}
 
+	if (filter_provided_objects) {
+		struct commit_list *c;
+		for (i = 0; i < revs.pending.nr; i++) {
+			struct object_array_entry *pending = revs.pending.objects + i;
+			pending->item->flags |= NOT_USER_GIVEN;
+		}
+		for (c = revs.commits; c; c = c->next)
+			c->item->object.flags |= NOT_USER_GIVEN;
+	}
+
 	if (arg_print_omitted)
 		oidset_init(&omitted_objects, DEFAULT_OIDSET_SIZE);
 	if (arg_missing_action == MA_PRINT)

pack-bitmap.c

@@ -986,7 +986,8 @@ static int can_filter_bitmap(struct list_objects_filter_options *filter)
 }
 
 struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs,
-					 struct list_objects_filter_options *filter)
+					 struct list_objects_filter_options *filter,
+					 int filter_provided_objects)
 {
 	unsigned int i;
 
@@ -1081,7 +1082,8 @@ struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs,
 	if (haves_bitmap)
 		bitmap_and_not(wants_bitmap, haves_bitmap);
 
-	filter_bitmap(bitmap_git, wants, wants_bitmap, filter);
+	filter_bitmap(bitmap_git, (filter && filter_provided_objects) ? NULL : wants,
+		      wants_bitmap, filter);
 
 	bitmap_git->result = wants_bitmap;
 	bitmap_git->haves = haves_bitmap;

pack-bitmap.h

@@ -50,7 +50,8 @@ void traverse_bitmap_commit_list(struct bitmap_index *,
 				 show_reachable_fn show_reachable);
 void test_bitmap_walk(struct rev_info *revs);
 struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs,
-					 struct list_objects_filter_options *filter);
+					 struct list_objects_filter_options *filter,
+					 int filter_provided_objects);
 int reuse_partial_packfile_from_bitmap(struct bitmap_index *,
 				       struct packed_git **packfile,
 				       uint32_t *entries,

reachable.c

@@ -223,7 +223,7 @@ void mark_reachable_objects(struct rev_info *revs, int mark_reflog,
 	cp.progress = progress;
 	cp.count = 0;
 
-	bitmap_git = prepare_bitmap_walk(revs, NULL);
+	bitmap_git = prepare_bitmap_walk(revs, NULL, 0);
 	if (bitmap_git) {
 		traverse_bitmap_commit_list(bitmap_git, revs, mark_object_seen);
 		free_bitmap_index(bitmap_git);

t/t6112-rev-list-filters-objects.sh

@@ -203,6 +203,34 @@ test_expect_success 'verify object:type=tag prints tag' '
 	test_cmp expected actual
 '
 
+test_expect_success 'verify object:type=blob prints only blob with --filter-provided-objects' '
+	printf "%s blob\n" $(git -C object-type rev-parse HEAD:blob) >expected &&
+	git -C object-type rev-list --objects \
+		--filter=object:type=blob --filter-provided-objects HEAD >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'verify object:type=tree prints only tree with --filter-provided-objects' '
+	printf "%s \n" $(git -C object-type rev-parse HEAD^{tree}) >expected &&
+	git -C object-type rev-list --objects \
+		--filter=object:type=tree HEAD --filter-provided-objects >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'verify object:type=commit prints only commit with --filter-provided-objects' '
+	git -C object-type rev-parse HEAD >expected &&
+	git -C object-type rev-list --objects \
+		--filter=object:type=commit --filter-provided-objects HEAD >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'verify object:type=tag prints only tag with --filter-provided-objects' '
+	printf "%s tag\n" $(git -C object-type rev-parse tag) >expected &&
+	git -C object-type rev-list --objects \
+		--filter=object:type=tag --filter-provided-objects tag >actual &&
+	test_cmp expected actual
+'
+
 # Test sparse:path=<path> filter.
 # !!!!
 # NOTE: sparse:path filter support has been dropped for security reasons,

t/t6113-rev-list-bitmap-filters.sh

@@ -98,11 +98,47 @@ test_expect_success 'object:type filter' '
 	test_bitmap_traversal expect actual
 '
 
+test_expect_success 'object:type filter with --filter-provided-objects' '
+	git rev-list --objects --filter-provided-objects --filter=object:type=tag tag >expect &&
+	git rev-list --use-bitmap-index \
+		     --objects --filter-provided-objects --filter=object:type=tag tag >actual &&
+	test_cmp expect actual &&
+
+	git rev-list --objects --filter-provided-objects --filter=object:type=commit tag >expect &&
+	git rev-list --use-bitmap-index \
+		     --objects --filter-provided-objects --filter=object:type=commit tag >actual &&
+	test_bitmap_traversal expect actual &&
+
+	git rev-list --objects --filter-provided-objects --filter=object:type=tree tag >expect &&
+	git rev-list --use-bitmap-index \
+		     --objects --filter-provided-objects --filter=object:type=tree tag >actual &&
+	test_bitmap_traversal expect actual &&
+
+	git rev-list --objects --filter-provided-objects --filter=object:type=blob tag >expect &&
+	git rev-list --use-bitmap-index \
+		     --objects --filter-provided-objects --filter=object:type=blob tag >actual &&
+	test_bitmap_traversal expect actual
+'
+
 test_expect_success 'combine filter' '
 	git rev-list --objects --filter=blob:limit=1000 --filter=object:type=blob tag >expect &&
 	git rev-list --use-bitmap-index \
 		     --objects --filter=blob:limit=1000 --filter=object:type=blob tag >actual &&
 	test_bitmap_traversal expect actual
 '
 
+test_expect_success 'combine filter with --filter-provided-objects' '
+	git rev-list --objects --filter-provided-objects --filter=blob:limit=1000 --filter=object:type=blob tag >expect &&
+	git rev-list --use-bitmap-index \
+		     --objects --filter-provided-objects --filter=blob:limit=1000 --filter=object:type=blob tag >actual &&
+	test_bitmap_traversal expect actual &&
+
+	git cat-file --batch-check="%(objecttype) %(objectsize)" <actual >objects &&
+	while read objecttype objectsize
+	do
+		test "$objecttype" = blob || return 1
+		test "$objectsize" -le 1000 || return 1
+	done <objects
+'
+
 test_done