Merge branch 'ps/rev-list-object-type-filter'

"git rev-list" learns the "--filter=object:type=<type>" option,
which can be used to exclude objects of the given kind from the
packfile generated by pack-objects.

* ps/rev-list-object-type-filter:
  rev-list: allow filtering of provided items
  pack-bitmap: implement combined filter
  pack-bitmap: implement object type filter
  list-objects: implement object type filter
  list-objects: support filtering by tag and commit
  list-objects: move tag processing into its own function
  revision: mark commit parents as NOT_USER_GIVEN
  uploadpack.txt: document implication of `uploadpackfilter.allow`

Author: gitster

Documentation/config/uploadpack.txt

@@ -59,15 +59,16 @@ uploadpack.allowFilter::
 
 uploadpackfilter.allow::
 	Provides a default value for unspecified object filters (see: the
-	below configuration variable).
+	below configuration variable). If set to `true`, this will also
+	enable all filters which get added in the future.
 	Defaults to `true`.
 
 uploadpackfilter.<filter>.allow::
 	Explicitly allow or ban the object filter corresponding to
 	`<filter>`, where `<filter>` may be one of: `blob:none`,
-	`blob:limit`, `tree`, `sparse:oid`, or `combine`. If using
-	combined filters, both `combine` and all of the nested filter
-	kinds must be allowed. Defaults to `uploadpackfilter.allow`.
+	`blob:limit`, `object:type`, `tree`, `sparse:oid`, or `combine`.
+	If using combined filters, both `combine` and all of the nested
+	filter kinds must be allowed. Defaults to `uploadpackfilter.allow`.
 
 uploadpackfilter.tree.maxDepth::
 	Only allow `--filter=tree:<n>` when `<n>` is no more than the value of

Documentation/rev-list-options.txt

@@ -892,6 +892,9 @@ 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'.
 +
+The form '--filter=object:type=(tag|commit|tree|blob)' omits all objects
+which are not of the requested type.
++
 The form '--filter=sparse:oid=<blob-ish>' uses a sparse-checkout
 specification contained in the blob (or blob-expression) '<blob-ish>'
 to omit blobs that would not be not required for a sparse checkout on
@@ -930,6 +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)

list-objects-filter-options.c

@@ -29,6 +29,8 @@ const char *list_object_filter_config_name(enum list_objects_filter_choice c)
 		return "tree";
 	case LOFC_SPARSE_OID:
 		return "sparse:oid";
+	case LOFC_OBJECT_TYPE:
+		return "object:type";
 	case LOFC_COMBINE:
 		return "combine";
 	case LOFC__COUNT:
@@ -97,6 +99,19 @@ static int gently_parse_list_objects_filter(
 		}
 		return 1;
 
+	} else if (skip_prefix(arg, "object:type=", &v0)) {
+		int type = type_from_string_gently(v0, strlen(v0), 1);
+		if (type < 0) {
+			strbuf_addf(errbuf, _("'%s' for 'object:type=<type>' is"
+					      "not a valid object type"), v0);
+			return 1;
+		}
+
+		filter_options->object_type = type;
+		filter_options->choice = LOFC_OBJECT_TYPE;
+
+		return 0;
+
 	} else if (skip_prefix(arg, "combine:", &v0)) {
 		return parse_combine_filter(filter_options, v0, errbuf);
 

list-objects-filter-options.h

@@ -1,6 +1,7 @@
 #ifndef LIST_OBJECTS_FILTER_OPTIONS_H
 #define LIST_OBJECTS_FILTER_OPTIONS_H
 
+#include "cache.h"
 #include "parse-options.h"
 #include "string-list.h"
 
@@ -13,6 +14,7 @@ enum list_objects_filter_choice {
 	LOFC_BLOB_LIMIT,
 	LOFC_TREE_DEPTH,
 	LOFC_SPARSE_OID,
+	LOFC_OBJECT_TYPE,
 	LOFC_COMBINE,
 	LOFC__COUNT /* must be last */
 };
@@ -54,6 +56,7 @@ struct list_objects_filter_options {
 	char *sparse_oid_name;
 	unsigned long blob_limit_value;
 	unsigned long tree_exclude_depth;
+	enum object_type object_type;
 
 	/* LOFC_COMBINE values */
 

list-objects-filter.c

@@ -82,6 +82,16 @@ static enum list_objects_filter_result filter_blobs_none(
 	default:
 		BUG("unknown filter_situation: %d", filter_situation);
 
+	case LOFS_TAG:
+		assert(obj->type == OBJ_TAG);
+		/* always include all tag objects */
+		return LOFR_MARK_SEEN | LOFR_DO_SHOW;
+
+	case LOFS_COMMIT:
+		assert(obj->type == OBJ_COMMIT);
+		/* always include all commit objects */
+		return LOFR_MARK_SEEN | LOFR_DO_SHOW;
+
 	case LOFS_BEGIN_TREE:
 		assert(obj->type == OBJ_TREE);
 		/* always include all tree objects */
@@ -173,6 +183,16 @@ static enum list_objects_filter_result filter_trees_depth(
 	default:
 		BUG("unknown filter_situation: %d", filter_situation);
 
+	case LOFS_TAG:
+		assert(obj->type == OBJ_TAG);
+		/* always include all tag objects */
+		return LOFR_MARK_SEEN | LOFR_DO_SHOW;
+
+	case LOFS_COMMIT:
+		assert(obj->type == OBJ_COMMIT);
+		/* always include all commit objects */
+		return LOFR_MARK_SEEN | LOFR_DO_SHOW;
+
 	case LOFS_END_TREE:
 		assert(obj->type == OBJ_TREE);
 		filter_data->current_depth--;
@@ -267,6 +287,16 @@ static enum list_objects_filter_result filter_blobs_limit(
 	default:
 		BUG("unknown filter_situation: %d", filter_situation);
 
+	case LOFS_TAG:
+		assert(obj->type == OBJ_TAG);
+		/* always include all tag objects */
+		return LOFR_MARK_SEEN | LOFR_DO_SHOW;
+
+	case LOFS_COMMIT:
+		assert(obj->type == OBJ_COMMIT);
+		/* always include all commit objects */
+		return LOFR_MARK_SEEN | LOFR_DO_SHOW;
+
 	case LOFS_BEGIN_TREE:
 		assert(obj->type == OBJ_TREE);
 		/* always include all tree objects */
@@ -371,6 +401,16 @@ static enum list_objects_filter_result filter_sparse(
 	default:
 		BUG("unknown filter_situation: %d", filter_situation);
 
+	case LOFS_TAG:
+		assert(obj->type == OBJ_TAG);
+		/* always include all tag objects */
+		return LOFR_MARK_SEEN | LOFR_DO_SHOW;
+
+	case LOFS_COMMIT:
+		assert(obj->type == OBJ_COMMIT);
+		/* always include all commit objects */
+		return LOFR_MARK_SEEN | LOFR_DO_SHOW;
+
 	case LOFS_BEGIN_TREE:
 		assert(obj->type == OBJ_TREE);
 		dtype = DT_DIR;
@@ -505,6 +545,81 @@ static void filter_sparse_oid__init(
 	filter->free_fn = filter_sparse_free;
 }
 
+/*
+ * A filter for list-objects to omit large blobs.
+ * And to OPTIONALLY collect a list of the omitted OIDs.
+ */
+struct filter_object_type_data {
+	enum object_type object_type;
+};
+
+static enum list_objects_filter_result filter_object_type(
+	struct repository *r,
+	enum list_objects_filter_situation filter_situation,
+	struct object *obj,
+	const char *pathname,
+	const char *filename,
+	struct oidset *omits,
+	void *filter_data_)
+{
+	struct filter_object_type_data *filter_data = filter_data_;
+
+	switch (filter_situation) {
+	default:
+		BUG("unknown filter_situation: %d", filter_situation);
+
+	case LOFS_TAG:
+		assert(obj->type == OBJ_TAG);
+		if (filter_data->object_type == OBJ_TAG)
+			return LOFR_MARK_SEEN | LOFR_DO_SHOW;
+		return LOFR_MARK_SEEN;
+
+	case LOFS_COMMIT:
+		assert(obj->type == OBJ_COMMIT);
+		if (filter_data->object_type == OBJ_COMMIT)
+			return LOFR_MARK_SEEN | LOFR_DO_SHOW;
+		return LOFR_MARK_SEEN;
+
+	case LOFS_BEGIN_TREE:
+		assert(obj->type == OBJ_TREE);
+
+		/*
+		 * If we only want to show commits or tags, then there is no
+		 * need to walk down trees.
+		 */
+		if (filter_data->object_type == OBJ_COMMIT ||
+		    filter_data->object_type == OBJ_TAG)
+			return LOFR_SKIP_TREE;
+
+		if (filter_data->object_type == OBJ_TREE)
+			return LOFR_MARK_SEEN | LOFR_DO_SHOW;
+
+		return LOFR_MARK_SEEN;
+
+	case LOFS_BLOB:
+		assert(obj->type == OBJ_BLOB);
+
+		if (filter_data->object_type == OBJ_BLOB)
+			return LOFR_MARK_SEEN | LOFR_DO_SHOW;
+		return LOFR_MARK_SEEN;
+
+	case LOFS_END_TREE:
+		return LOFR_ZERO;
+	}
+}
+
+static void filter_object_type__init(
+	struct list_objects_filter_options *filter_options,
+	struct filter *filter)
+{
+	struct filter_object_type_data *d = xcalloc(1, sizeof(*d));
+	d->object_type = filter_options->object_type;
+
+	filter->filter_data = d;
+	filter->filter_object_fn = filter_object_type;
+	filter->free_fn = free;
+}
+
 /* A filter which only shows objects shown by all sub-filters. */
 struct combine_filter_data {
 	struct subfilter *sub;
@@ -651,6 +766,7 @@ static filter_init_fn s_filters[] = {
 	filter_blobs_limit__init,
 	filter_trees_depth__init,
 	filter_sparse_oid__init,
+	filter_object_type__init,
 	filter_combine__init,
 };
 

list-objects-filter.h

@@ -55,6 +55,8 @@ enum list_objects_filter_result {
 };
 
 enum list_objects_filter_situation {
+	LOFS_COMMIT,
+	LOFS_TAG,
 	LOFS_BEGIN_TREE,
 	LOFS_END_TREE,
 	LOFS_BLOB