[RFC PATCH 3/3] list-objects-filter: teach tree:# how to handle >0

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Implement positive values for <depth> in the tree:<depth> filter. The
exact semantics are described in Documentation/rev-list-options.txt.

The long-term goal at the end of this is to allow a partial clone to
eagerly fetch an entire directory of files by fetching a tree and
specifying <depth>=1. This, for instance, would make a build operation
fast and convenient. It is fast because the partial clone does not need
to fetch each file individually, and convenient because the user does
not need to supply a sparse-checkout specification.

Signed-off-by: Matthew DeVore <matvore@xxxxxxxxxx>
---
 Documentation/rev-list-options.txt  |  8 ++-
 list-objects-filter-options.c       |  6 +--
 list-objects-filter-options.h       |  1 +
 list-objects-filter.c               | 49 +++++++++++++----
 t/t6112-rev-list-filters-objects.sh | 84 +++++++++++++++++++++++++++++
 5 files changed, 132 insertions(+), 16 deletions(-)

diff --git a/Documentation/rev-list-options.txt b/Documentation/rev-list-options.txt
index c2c1c40e6..c78985c41 100644
--- a/Documentation/rev-list-options.txt
+++ b/Documentation/rev-list-options.txt
@@ -734,8 +734,12 @@ specification contained in <path>.
 +
 The form '--filter=tree:<depth>' omits all blobs and trees whose depth
 from the root tree is >= <depth> (minimum depth if an object is located
-at multiple depths in the commits traversed). Currently, only <depth>=0
-is supported, which omits all blobs and trees.
+at multiple depths in the commits traversed). <depth>=0 will not include
+any trees or blobs unless included explicitly in <object>. <depth>=1
+will include only the tree and blobs which are referenced directly by a
+commit reachable from <object> or an object given in <object>. <depth>=2
+is like <depth>=1 while also including trees and blobs one more level
+removed from <object> or a reachable commit.
 
 --no-filter::
 	Turn off any previous `--filter=` argument.
diff --git a/list-objects-filter-options.c b/list-objects-filter-options.c
index e8da2e858..9dc61d6e6 100644
--- a/list-objects-filter-options.c
+++ b/list-objects-filter-options.c
@@ -50,12 +50,12 @@ static int gently_parse_list_objects_filter(
 		}
 
 	} else if (skip_prefix(arg, "tree:", &v0)) {
-		unsigned long depth;
-		if (!git_parse_ulong(v0, &depth) || depth != 0) {
+		if (!git_parse_ulong(v0,
+				     &filter_options->tree_depth_limit_value)) {
 			if (errbuf) {
 				strbuf_addstr(
 					errbuf,
-					_("only 'tree:0' is supported"));
+					_("expected 'tree:<int>'"));
 			}
 			return 1;
 		}
diff --git a/list-objects-filter-options.h b/list-objects-filter-options.h
index af64e5c66..c1ae70cd8 100644
--- a/list-objects-filter-options.h
+++ b/list-objects-filter-options.h
@@ -44,6 +44,7 @@ struct list_objects_filter_options {
 	struct object_id *sparse_oid_value;
 	char *sparse_path_value;
 	unsigned long blob_limit_value;
+	unsigned long tree_depth_limit_value;
 };
 
 /* Normalized command line arguments */
diff --git a/list-objects-filter.c b/list-objects-filter.c
index 37fba456d..e69fb9b82 100644
--- a/list-objects-filter.c
+++ b/list-objects-filter.c
@@ -83,53 +83,80 @@ static void *filter_blobs_none__init(
  * A filter for list-objects to omit ALL trees and blobs from the traversal.
  * Can OPTIONALLY collect a list of the omitted OIDs.
  */
-struct filter_trees_none_data {
+struct filter_trees_depth_data {
 	struct oidset *omits;
+	unsigned long max_depth;
+	unsigned long current_depth;
 };
 
-static enum list_objects_filter_result filter_trees_none(
+static enum list_objects_filter_result filter_trees_depth(
 	enum list_objects_filter_situation filter_situation,
 	struct object *obj,
 	const char *pathname,
 	const char *filename,
 	void *filter_data_)
 {
-	struct filter_trees_none_data *filter_data = filter_data_;
+	struct filter_trees_depth_data *filter_data = filter_data_;
+
+	int too_deep = filter_data->current_depth >= filter_data->max_depth;
+
+	/*
+	 * Note that we do not use _MARK_SEEN in order to allow re-traversal in
+	 * case we encounter a tree or blob again at a shallower depth.
+	 */
 
 	switch (filter_situation) {
 	default:
 		BUG("unknown filter_situation: %d", filter_situation);
 
-	case LOFS_BEGIN_TREE:
 	case LOFS_BLOB:
+		if (!too_deep) goto include_it;
+
+		if (filter_data->omits)
+			oidset_insert(filter_data->omits, &obj->oid);
+
+		return LOFR_ZERO;
+
+	case LOFS_BEGIN_TREE:
+		filter_data->current_depth++;
+
+		if (!too_deep) goto include_it;
+
 		if (filter_data->omits) {
 			oidset_insert(filter_data->omits, &obj->oid);
-			/* _MARK_SEEN but not _DO_SHOW (hard omit) */
-			return LOFR_MARK_SEEN;
+			return LOFR_ZERO;
 		}
 		else
 			/*
 			 * Not collecting omits so no need to to traverse tree.
 			 */
-			return LOFR_SKIP_TREE | LOFR_MARK_SEEN;
+			return LOFR_SKIP_TREE;
 
 	case LOFS_END_TREE:
 		assert(obj->type == OBJ_TREE);
+		filter_data->current_depth--;
 		return LOFR_ZERO;
 
 	}
+
+include_it:
+	if (filter_data->omits)
+		oidset_remove(filter_data->omits, &obj->oid);
+	return LOFR_MARK_SEEN | LOFR_DO_SHOW;
 }
 
-static void* filter_trees_none__init(
+static void* filter_trees_depth__init(
 	struct oidset *omitted,
 	struct list_objects_filter_options *filter_options,
 	filter_object_fn *filter_fn,
 	filter_free_fn *filter_free_fn)
 {
-	struct filter_trees_none_data *d = xcalloc(1, sizeof(*d));
+	struct filter_trees_depth_data *d = xcalloc(1, sizeof(*d));
 	d->omits = omitted;
+	d->max_depth = filter_options->tree_depth_limit_value;
+	d->current_depth = 0;
 
-	*filter_fn = filter_trees_none;
+	*filter_fn = filter_trees_depth;
 	*filter_free_fn = free;
 	return d;
 }
@@ -426,7 +453,7 @@ static filter_init_fn s_filters[] = {
 	NULL,
 	filter_blobs_none__init,
 	filter_blobs_limit__init,
-	filter_trees_none__init,
+	filter_trees_depth__init,
 	filter_sparse_oid__init,
 	filter_sparse_path__init,
 };
diff --git a/t/t6112-rev-list-filters-objects.sh b/t/t6112-rev-list-filters-objects.sh
index efb1bee2e..43ee0df80 100755
--- a/t/t6112-rev-list-filters-objects.sh
+++ b/t/t6112-rev-list-filters-objects.sh
@@ -254,6 +254,90 @@ test_expect_success 'filter a GIANT tree through tree:0' '
 	test_line_count = 2 actual
 '
 
+# Test tree:# filters.
+
+expect_has () {
+	commit=$1 &&
+	name=$2 &&
+
+	hash=$(git -C r3 rev-parse $commit:$name) &&
+	grep "^$hash $name$" actual
+}
+
+test_expect_success 'verify tree:1 includes root trees' '
+	git -C r3 rev-list --objects --filter=tree:1 HEAD >actual &&
+
+	# We should get two root directories and two commits.
+	expect_has HEAD "" &&
+	expect_has HEAD~1 ""  &&
+	test_line_count = 4 actual
+'
+
+test_expect_success 'verify tree:2 includes root trees and immediate children' '
+	git -C r3 rev-list --objects --filter=tree:2 HEAD >actual &&
+
+	expect_has HEAD "" &&
+	expect_has HEAD~1 "" &&
+	expect_has HEAD dir1 &&
+	expect_has HEAD pattern &&
+	expect_has HEAD sparse1 &&
+	expect_has HEAD sparse2 &&
+
+	# There are also 2 commit objects
+	test_line_count = 8 actual
+'
+
+test_expect_success 'verify tree:3 includes everything expected' '
+	git -C r3 rev-list --objects --filter=tree:3 HEAD >actual &&
+
+	expect_has HEAD "" &&
+	expect_has HEAD~1 "" &&
+	expect_has HEAD dir1 &&
+	expect_has HEAD dir1/sparse1 &&
+	expect_has HEAD dir1/sparse2 &&
+	expect_has HEAD pattern &&
+	expect_has HEAD sparse1 &&
+	expect_has HEAD sparse2 &&
+
+	# There are also 2 commit objects
+	test_line_count = 10 actual
+'
+
+# Test provisional omit collection logic with a repo that has objects appearing
+# at multiple depths - first deeper than the filter's threshold, then shallow.
+
+test_expect_success 'setup r4' '
+	git init r4 &&
+
+	echo foo > r4/foo &&
+	mkdir r4/subdir &&
+	echo bar > r4/subdir/bar &&
+
+	mkdir r4/filt &&
+	cp -r r4/foo r4/subdir r4/filt &&
+
+	git -C r4 add foo subdir filt &&
+	git -C r4 commit -m "commit msg"
+'
+
+expect_has_with_different_name () {
+	commit=$1 &&
+	name=$2 &&
+
+	hash=$(git -C r4 rev-parse $commit:$name) &&
+	! grep "^$hash $name$" actual &&
+	grep "^$hash " actual &&
+	! grep "~$hash" actual
+}
+
+test_expect_success 'test tree:# filter provisional omit for blob and tree' '
+	git -C r4 rev-list --objects --filter-print-omitted --filter=tree:2 \
+		HEAD >actual &&
+
+	expect_has_with_different_name HEAD filt/foo &&
+	expect_has_with_different_name HEAD filt/subdir
+'
+
 # Delete some loose objects and use rev-list, but WITHOUT any filtering.
 # This models previously omitted objects that we did not receive.
 
-- 
2.19.1.331.ge82ca0e54c-goog




[Index of Archives]     [Linux Kernel Development]     [Gcc Help]     [IETF Annouce]     [DCCP]     [Netdev]     [Networking]     [Security]     [V4L]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux SCSI]     [Fedora Users]

  Powered by Linux