path-walk: mark trees and blobs as UNINTERESTING

When the input rev_info has UNINTERESTING starting points, we want to be
sure that the UNINTERESTING flag is passed appropriately through the
objects. To match how this is done in places such as 'git pack-objects', we
use the mark_edges_uninteresting() method.

This method has an option for using the "sparse" walk, which is similar in
spirit to the path-walk API's walk. To be sure to keep it independent, add a
new 'prune_all_uninteresting' option to the path_walk_info struct.

To check how the UNINTERSTING flag is spread through our objects, extend the
'test-tool path-walk' command to output whether or not an object has that
flag. This changes our tests significantly, including the removal of some
objects that were previously visited due to the incomplete implementation.

Signed-off-by: Derrick Stolee <stolee@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

path-walk.c

@@ -8,6 +8,7 @@
 #include "dir.h"
 #include "hashmap.h"
 #include "hex.h"
+#include "list-objects.h"
 #include "object.h"
 #include "oid-array.h"
 #include "revision.h"
@@ -23,6 +24,7 @@ static const char *root_path = "";
 struct type_and_oid_list {
 	enum object_type type;
 	struct oid_array oids;
+	int maybe_interesting;
 };
 
 #define TYPE_AND_OID_LIST_INIT { \
@@ -142,6 +144,10 @@ static int add_tree_entries(struct path_walk_context *ctx,
 			strmap_put(&ctx->paths_to_lists, path.buf, list);
 		}
 		push_to_stack(ctx, path.buf);
+
+		if (!(o->flags & UNINTERESTING))
+			list->maybe_interesting = 1;
+
 		oid_array_append(&list->oids, &entry.oid);
 	}
 
@@ -169,6 +175,43 @@ static int walk_path(struct path_walk_context *ctx,
 	if (!list->oids.nr)
 		return 0;
 
+	if (ctx->info->prune_all_uninteresting) {
+		/*
+		 * This is true if all objects were UNINTERESTING
+		 * when added to the list.
+		 */
+		if (!list->maybe_interesting)
+			return 0;
+
+		/*
+		 * But it's still possible that the objects were set
+		 * as UNINTERESTING after being added. Do a quick check.
+		 */
+		list->maybe_interesting = 0;
+		for (size_t i = 0;
+		     !list->maybe_interesting && i < list->oids.nr;
+		     i++) {
+			if (list->type == OBJ_TREE) {
+				struct tree *t = lookup_tree(ctx->repo,
+							     &list->oids.oid[i]);
+				if (t && !(t->object.flags & UNINTERESTING))
+					list->maybe_interesting = 1;
+			} else if (list->type == OBJ_BLOB) {
+				struct blob *b = lookup_blob(ctx->repo,
+							     &list->oids.oid[i]);
+				if (b && !(b->object.flags & UNINTERESTING))
+					list->maybe_interesting = 1;
+			} else {
+				/* Tags are always interesting if visited. */
+				list->maybe_interesting = 1;
+			}
+		}
+
+		/* We have confirmed that all objects are UNINTERESTING. */
+		if (!list->maybe_interesting)
+			return 0;
+	}
+
 	/* Evaluate function pointer on this data, if requested. */
 	if ((list->type == OBJ_TREE && ctx->info->trees) ||
 	    (list->type == OBJ_BLOB && ctx->info->blobs) ||
@@ -203,6 +246,26 @@ static void clear_paths_to_lists(struct strmap *map)
 	strmap_init(map);
 }
 
+static struct repository *edge_repo;
+static struct type_and_oid_list *edge_tree_list;
+
+static void show_edge(struct commit *commit)
+{
+	struct tree *t = repo_get_commit_tree(edge_repo, commit);
+
+	if (!t)
+		return;
+
+	if (commit->object.flags & UNINTERESTING)
+		t->object.flags |= UNINTERESTING;
+
+	if (t->object.flags & SEEN)
+		return;
+	t->object.flags |= SEEN;
+
+	oid_array_append(&edge_tree_list->oids, &t->object.oid);
+}
+
 static int setup_pending_objects(struct path_walk_info *info,
 				 struct path_walk_context *ctx)
 {
@@ -314,6 +377,7 @@ static int setup_pending_objects(struct path_walk_info *info,
 		if (tagged_blobs->oids.nr) {
 			const char *tagged_blob_path = "/tagged-blobs";
 			tagged_blobs->type = OBJ_BLOB;
+			tagged_blobs->maybe_interesting = 1;
 			push_to_stack(ctx, tagged_blob_path);
 			strmap_put(&ctx->paths_to_lists, tagged_blob_path, tagged_blobs);
 		} else {
@@ -325,6 +389,7 @@ static int setup_pending_objects(struct path_walk_info *info,
 		if (tags->oids.nr) {
 			const char *tag_path = "/tags";
 			tags->type = OBJ_TAG;
+			tags->maybe_interesting = 1;
 			push_to_stack(ctx, tag_path);
 			strmap_put(&ctx->paths_to_lists, tag_path, tags);
 		} else {
@@ -369,6 +434,7 @@ int walk_objects_by_path(struct path_walk_info *info)
 	/* Insert a single list for the root tree into the paths. */
 	CALLOC_ARRAY(root_tree_list, 1);
 	root_tree_list->type = OBJ_TREE;
+	root_tree_list->maybe_interesting = 1;
 	strmap_put(&ctx.paths_to_lists, root_path, root_tree_list);
 	push_to_stack(&ctx, root_path);
 
@@ -382,6 +448,14 @@ int walk_objects_by_path(struct path_walk_info *info)
 	if (prepare_revision_walk(info->revs))
 		die(_("failed to setup revision walk"));
 
+	/* Walk trees to mark them as UNINTERESTING. */
+	edge_repo = info->revs->repo;
+	edge_tree_list = root_tree_list;
+	mark_edges_uninteresting(info->revs, show_edge,
+				 info->prune_all_uninteresting);
+	edge_repo = NULL;
+	edge_tree_list = NULL;
+
 	info->revs->blob_objects = info->revs->tree_objects = 0;
 
 	trace2_region_enter("path-walk", "pending-walk", info->revs->repo);