path-walk: allow visiting tags

In anticipation of using the path-walk API to analyze tags or include
them in a pack-file, add the ability to walk the tags that were included
in the revision walk.

Signed-off-by: Derrick Stolee <stolee@gmail.com>

Author: derrickstolee

Diff for: Documentation/technical/api-path-walk.txt

@@ -48,7 +48,7 @@ If you want the path-walk API to emit `UNINTERESTING` objects based on the
 commit walk's boundary, be sure to set `revs.boundary` so the boundary
 commits are emitted.
 
-`commits`, `blobs`, `trees`::
+`commits`, `blobs`, `trees`, `tags`::
 	By default, these members are enabled and signal that the path-walk
 	API should call the `path_fn` on objects of these types. Specialized
 	applications could disable some options to make it simpler to walk

Diff for: path-walk.c

@@ -13,6 +13,7 @@
 #include "revision.h"
 #include "string-list.h"
 #include "strmap.h"
+#include "tag.h"
 #include "trace2.h"
 #include "tree.h"
 #include "tree-walk.h"
@@ -204,13 +205,86 @@ int walk_objects_by_path(struct path_walk_info *info)
 	CALLOC_ARRAY(commit_list, 1);
 	commit_list->type = OBJ_COMMIT;
 
+	if (info->tags)
+		info->revs->tag_objects = 1;
+
 	/* Insert a single list for the root tree into the paths. */
 	CALLOC_ARRAY(root_tree_list, 1);
 	root_tree_list->type = OBJ_TREE;
 	strmap_put(&ctx.paths_to_lists, root_path, root_tree_list);
+
+	/*
+	 * Set these values before preparing the walk to catch
+	 * lightweight tags pointing to non-commits.
+	 */
+	info->revs->blob_objects = info->blobs;
+	info->revs->tree_objects = info->trees;
+
 	if (prepare_revision_walk(info->revs))
 		die(_("failed to setup revision walk"));
 
+	info->revs->blob_objects = info->revs->tree_objects = 0;
+
+	if (info->tags) {
+		struct oid_array tagged_blob_list = OID_ARRAY_INIT;
+		struct oid_array tags = OID_ARRAY_INIT;
+
+		trace2_region_enter("path-walk", "tag-walk", info->revs->repo);
+
+		/*
+		 * Walk any pending objects at this point, but they should only
+		 * be tags.
+		 */
+		for (size_t i = 0; i < info->revs->pending.nr; i++) {
+			struct object_array_entry *pending = info->revs->pending.objects + i;
+			struct object *obj = pending->item;
+
+			if (obj->type == OBJ_COMMIT)
+				continue;
+
+			while (obj->type == OBJ_TAG) {
+				struct tag *tag = lookup_tag(info->revs->repo,
+							     &obj->oid);
+				if (oid_array_lookup(&tags, &obj->oid) < 0)
+					oid_array_append(&tags, &obj->oid);
+				obj = tag->tagged;
+			}
+
+			switch (obj->type) {
+			case OBJ_TREE:
+				if (info->trees &&
+				    oid_array_lookup(&root_tree_list->oids, &obj->oid) < 0)
+					oid_array_append(&root_tree_list->oids, &obj->oid);
+				break;
+
+			case OBJ_BLOB:
+				if (info->blobs &&
+				    oid_array_lookup(&tagged_blob_list, &obj->oid) < 0)
+					oid_array_append(&tagged_blob_list, &obj->oid);
+				break;
+
+			case OBJ_COMMIT:
+				/* Make sure it is in the object walk */
+				add_pending_object(info->revs, obj, "");
+				break;
+
+			default:
+				BUG("should not see any other type here");
+			}
+		}
+
+		info->path_fn("", &tags, OBJ_TAG, info->path_fn_data);
+
+		if (tagged_blob_list.nr && info->blobs)
+			info->path_fn("/tagged-blobs", &tagged_blob_list, OBJ_BLOB,
+				      info->path_fn_data);
+
+		trace2_data_intmax("path-walk", ctx.repo, "tags", tags.nr);
+		trace2_region_leave("path-walk", "tag-walk", info->revs->repo);
+		oid_array_clear(&tags);
+		oid_array_clear(&tagged_blob_list);
+	}
+
 	while ((c = get_revision(info->revs))) {
 		struct object_id *oid;
 		struct tree *t;

Diff for: path-walk.h

@@ -37,12 +37,14 @@ struct path_walk_info {
 	int commits;
 	int trees;
 	int blobs;
+	int tags;
 };
 
 #define PATH_WALK_INFO_INIT {   \
 	.blobs = 1,		\
 	.trees = 1,		\
 	.commits = 1,		\
+	.tags = 1,		\
 }
 
 /**

Diff for: t/helper/test-path-walk.c

@@ -21,6 +21,7 @@ struct path_walk_test_data {
 	uintmax_t commit_nr;
 	uintmax_t tree_nr;
 	uintmax_t blob_nr;
+	uintmax_t tag_nr;
 };
 
 static int emit_block(const char *path, struct oid_array *oids,
@@ -45,6 +46,11 @@ static int emit_block(const char *path, struct oid_array *oids,
 		tdata->blob_nr += oids->nr;
 		break;
 
+	case OBJ_TAG:
+		typestr = "TAG";
+		tdata->tag_nr += oids->nr;
+		break;
+
 	default:
 		BUG("we do not understand this type");
 	}
@@ -66,6 +72,8 @@ int cmd__path_walk(int argc, const char **argv)
 			 N_("toggle inclusion of blob objects")),
 		OPT_BOOL(0, "commits", &info.commits,
 			 N_("toggle inclusion of commit objects")),
+		OPT_BOOL(0, "tags", &info.tags,
+			 N_("toggle inclusion of tag objects")),
 		OPT_BOOL(0, "trees", &info.trees,
 			 N_("toggle inclusion of tree objects")),
 		OPT_END(),
@@ -91,8 +99,9 @@ int cmd__path_walk(int argc, const char **argv)
 
 	printf("commits:%" PRIuMAX "\n"
 	       "trees:%" PRIuMAX "\n"
-	       "blobs:%" PRIuMAX "\n",
-	       data.commit_nr, data.tree_nr, data.blob_nr);
+	       "blobs:%" PRIuMAX "\n"
+	       "tags:%" PRIuMAX "\n",
+	       data.commit_nr, data.tree_nr, data.blob_nr, data.tag_nr);
 
 	release_revisions(&revs);
 	return res;

Diff for: t/t6601-path-walk.sh

@@ -7,24 +7,55 @@ test_description='direct path-walk API tests'
 test_expect_success 'setup test repository' '
 	git checkout -b base &&
 
+	# Make some objects that will only be reachable
+	# via non-commit tags.
+	mkdir child &&
+	echo file >child/file &&
+	git add child &&
+	git commit -m "will abandon" &&
+	git tag -a -m "tree" tree-tag HEAD^{tree} &&
+	echo file2 >file2 &&
+	git add file2 &&
+	git commit --amend -m "will abandon" &&
+	git tag tree-tag2 HEAD^{tree} &&
+
+	echo blob >file &&
+	blob_oid=$(git hash-object -t blob -w --stdin <file) &&
+	git tag -a -m "blob" blob-tag "$blob_oid" &&
+	echo blob2 >file2 &&
+	blob2_oid=$(git hash-object -t blob -w --stdin <file2) &&
+	git tag blob-tag2 "$blob2_oid" &&
+
+	rm -fr child file file2 &&
+
 	mkdir left &&
 	mkdir right &&
 	echo a >a &&
 	echo b >left/b &&
 	echo c >right/c &&
 	git add . &&
-	git commit -m "first" &&
+	git commit --amend -m "first" &&
+	git tag -m "first" first HEAD &&
 
 	echo d >right/d &&
 	git add right &&
 	git commit -m "second" &&
+	git tag -a -m "second (under)" second.1 HEAD &&
+	git tag -a -m "second (top)" second.2 second.1 &&
 
+	# Set up file/dir collision in history.
+	rm a &&
+	mkdir a &&
+	echo a >a/a &&
 	echo bb >left/b &&
-	git commit -a -m "third" &&
+	git add a left &&
+	git commit -m "third" &&
+	git tag -a -m "third" third &&
 
 	git checkout -b topic HEAD~1 &&
 	echo cc >right/c &&
-	git commit -a -m "topic"
+	git commit -a -m "topic" &&
+	git tag -a -m "fourth" fourth
 '
 
 test_expect_success 'all' '
@@ -40,19 +71,35 @@ test_expect_success 'all' '
 	TREE::$(git rev-parse base^{tree})
 	TREE::$(git rev-parse base~1^{tree})
 	TREE::$(git rev-parse base~2^{tree})
+	TREE::$(git rev-parse refs/tags/tree-tag^{})
+	TREE::$(git rev-parse refs/tags/tree-tag2^{})
+	TREE:a/:$(git rev-parse base:a)
 	TREE:left/:$(git rev-parse base:left)
 	TREE:left/:$(git rev-parse base~2:left)
 	TREE:right/:$(git rev-parse topic:right)
 	TREE:right/:$(git rev-parse base~1:right)
 	TREE:right/:$(git rev-parse base~2:right)
-	trees:9
+	TREE:child/:$(git rev-parse refs/tags/tree-tag^{}:child)
+	trees:13
 	BLOB:a:$(git rev-parse base~2:a)
+	BLOB:file2:$(git rev-parse refs/tags/tree-tag2^{}:file2)
 	BLOB:left/b:$(git rev-parse base~2:left/b)
 	BLOB:left/b:$(git rev-parse base:left/b)
 	BLOB:right/c:$(git rev-parse base~2:right/c)
 	BLOB:right/c:$(git rev-parse topic:right/c)
 	BLOB:right/d:$(git rev-parse base~1:right/d)
-	blobs:6
+	BLOB:/tagged-blobs:$(git rev-parse refs/tags/blob-tag^{})
+	BLOB:/tagged-blobs:$(git rev-parse refs/tags/blob-tag2^{})
+	BLOB:child/file:$(git rev-parse refs/tags/tree-tag^{}:child/file)
+	blobs:10
+	TAG::$(git rev-parse refs/tags/first)
+	TAG::$(git rev-parse refs/tags/second.1)
+	TAG::$(git rev-parse refs/tags/second.2)
+	TAG::$(git rev-parse refs/tags/third)
+	TAG::$(git rev-parse refs/tags/fourth)
+	TAG::$(git rev-parse refs/tags/tree-tag)
+	TAG::$(git rev-parse refs/tags/blob-tag)
+	tags:7
 	EOF
 
 	sort expect >expect.sorted &&
@@ -83,6 +130,7 @@ test_expect_success 'topic only' '
 	BLOB:right/c:$(git rev-parse topic:right/c)
 	BLOB:right/d:$(git rev-parse base~1:right/d)
 	blobs:5
+	tags:0
 	EOF
 
 	sort expect >expect.sorted &&
@@ -106,6 +154,7 @@ test_expect_success 'topic, not base' '
 	BLOB:right/c:$(git rev-parse topic:right/c)
 	BLOB:right/d:$(git rev-parse topic:right/d)
 	blobs:4
+	tags:0
 	EOF
 
 	sort expect >expect.sorted &&
@@ -126,6 +175,7 @@ test_expect_success 'topic, not base, only blobs' '
 	BLOB:right/c:$(git rev-parse topic:right/c)
 	BLOB:right/d:$(git rev-parse topic:right/d)
 	blobs:4
+	tags:0
 	EOF
 
 	sort expect >expect.sorted &&
@@ -145,6 +195,7 @@ test_expect_success 'topic, not base, only commits' '
 	commits:1
 	trees:0
 	blobs:0
+	tags:0
 	EOF
 
 	sort expect >expect.sorted &&
@@ -164,6 +215,7 @@ test_expect_success 'topic, not base, only trees' '
 	TREE:right/:$(git rev-parse topic:right)
 	trees:3
 	blobs:0
+	tags:0
 	EOF
 
 	sort expect >expect.sorted &&
@@ -191,6 +243,7 @@ test_expect_success 'topic, not base, boundary' '
 	BLOB:right/c:$(git rev-parse topic:right/c)
 	BLOB:right/d:$(git rev-parse base~1:right/d)
 	blobs:5
+	tags:0
 	EOF
 
 	sort expect >expect.sorted &&