Skip to content

GH-50658: [C++][Dev] Add RunEndEncoded support to gdb_arrow.py #50768

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
fenfeng9 wants to merge 1 commit into
base: main
Choose a base branch
from
+77 −1
Open

GH-50658: [C++][Dev] Add RunEndEncoded support to gdb_arrow.py #50768

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 25 additions & 1 deletion cpp/gdb_arrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,7 +95,8 @@ def identity(v):


def has_null_bitmap(type_id):
return type_id not in (Type.NA, Type.SPARSE_UNION, Type.DENSE_UNION)
return type_id not in (Type.NA, Type.SPARSE_UNION, Type.DENSE_UNION,
Type.RUN_END_ENCODED)


@lru_cache()
Expand Down Expand Up @@ -1069,6 +1070,7 @@ def num_rows(self):
'SparseUnionType': 'sparse_union',
'DenseUnionType': 'dense_union',
'DictionaryType': 'dictionary',
'RunEndEncodedType': 'run_end_encoded',
}


Expand Down Expand Up @@ -1170,6 +1172,20 @@ def to_string(self):
return f"{self._format_type()}({child})"


class RunEndEncodedTypePrinter(TypePrinter):
"""
Pretty-printer for run-end encoded types.
"""

def to_string(self):
fields = self.fields
if len(fields) != 2:
return f"{self._format_type()}<uninitialized or corrupt>"
run_end_type = fields[0].type
value_type = fields[1].type
return f"{self._format_type()}({run_end_type}, {value_type})"


class FixedSizeListTypePrinter(ListTypePrinter):
"""
Pretty-printer for fixed-size list type.
Expand Down Expand Up @@ -1999,6 +2015,12 @@ class FixedSizeListTypeClass(DataTypeClass):
scalar_printer = BaseListScalarPrinter


class RunEndEncodedTypeClass(DataTypeClass):
is_parametric = True
type_printer = RunEndEncodedTypePrinter
scalar_printer = BaseListScalarPrinter

@pitrou pitrou Sep 22, 2026 •
edited
Loading

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This (using BaseListScalarPrinter) might work by chance, but I don't think this is conceptually right. Run-end-encoded is not a list type, and a run-end-encoded scalar represents a single child value, not an entire run of values.

(as the tests show, by the way)


@pitrou pitrou Sep 22, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ideally we would also define a array_data_printer to actually print out the array's contents but the current PR is obviously better than supporting REE at all.


class MapTypeClass(DataTypeClass):
is_parametric = True
type_printer = MapTypePrinter
Expand Down Expand Up @@ -2085,6 +2107,8 @@ class ExtensionTypeClass(DataTypeClass):
Type.LARGE_LIST: DataTypeTraits(BaseListTypeClass, 'LargeListType'),
Type.FIXED_SIZE_LIST: DataTypeTraits(FixedSizeListTypeClass,
'FixedSizeListType'),
Type.RUN_END_ENCODED: DataTypeTraits(RunEndEncodedTypeClass,
'RunEndEncodedType'),
Comment on lines +2110 to +2111

@pitrou pitrou Sep 22, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nit: since REE is not a list type, it would be better to move this below with Dictionary and Extension.

Type.MAP: DataTypeTraits(MapTypeClass, 'MapType'),

Type.STRUCT: DataTypeTraits(StructTypeClass, 'StructType'),
Expand Down
19 changes: 19 additions & 0 deletions python/pyarrow/src/arrow/python/gdb.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -222,6 +222,9 @@ void TestSession() {
FixedSizeListType fixed_size_list_type(float64(), 3);
auto heap_fixed_size_list_type = fixed_size_list(float64(), 3);

RunEndEncodedType run_end_encoded_type(int32(), utf8());
auto heap_run_end_encoded_type = run_end_encoded(int32(), utf8());

DictionaryType dict_type_unordered(int16(), utf8());
DictionaryType dict_type_ordered(int16(), utf8(), /*ordered=*/true);
auto heap_dict_type = dictionary(int16(), utf8());
Expand Down Expand Up @@ -389,6 +392,14 @@ void TestSession() {
FixedSizeListScalar fixed_size_list_scalar_null{
list_value_array, fixed_size_list(int32(), 3), /*is_valid=*/false};

auto run_end_encoded_scalar_type = run_end_encoded(int32(), utf8());
RunEndEncodedScalar run_end_encoded_scalar{MakeScalar("foo"),
run_end_encoded_scalar_type};
RunEndEncodedScalar run_end_encoded_scalar_null{run_end_encoded_scalar_type};
std::shared_ptr<Scalar> heap_run_end_encoded_scalar =
std::make_shared<RunEndEncodedScalar>(MakeScalar("foo"),
run_end_encoded_scalar_type);

auto struct_scalar_type = struct_({field("ints", int32()), field("strs", utf8())});
StructScalar struct_scalar{
ScalarVector{MakeScalar(int32_t(42)), MakeScalar("some text")}, struct_scalar_type};
Expand Down Expand Up @@ -448,6 +459,14 @@ void TestSession() {
auto heap_list_array = SliceArrayFromJSON(list(int64()), "[[1, 2], null, []]");
ListArray list_array{heap_list_array->data()};

// Encodes ["foo", "foo", null, null, null].
auto run_end_encoded_run_ends = SliceArrayFromJSON(int32(), "[2, 5]");
auto run_end_encoded_values = SliceArrayFromJSON(utf8(), R"(["foo", null])");
std::shared_ptr<Array> heap_run_end_encoded_array = *RunEndEncodedArray::Make(
/*logical_length=*/5, run_end_encoded_run_ends, run_end_encoded_values);
RunEndEncodedArray run_end_encoded_array{heap_run_end_encoded_array->data()};
auto heap_run_end_encoded_array_sliced = heap_run_end_encoded_array->Slice(1, 3);

const char* json_double_array = "[-1.5, null]";
auto heap_double_array = SliceArrayFromJSON(float64(), json_double_array);

Expand Down
33 changes: 33 additions & 0 deletions python/pyarrow/tests/test_gdb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -407,6 +407,9 @@ def test_types_stack(gdb_arrow):
"arrow::large_list(arrow::large_utf8())")
check_stack_repr(gdb_arrow, "fixed_size_list_type",
"arrow::fixed_size_list(arrow::float64(), 3)")
check_stack_repr(
gdb_arrow, "run_end_encoded_type",
"arrow::run_end_encoded(arrow::int32(), arrow::utf8())")
check_stack_repr(
gdb_arrow, "map_type_unsorted",
"arrow::map(arrow::utf8(), arrow::binary(), keys_sorted=false)")
Expand Down Expand Up @@ -468,6 +471,9 @@ def test_types_heap(gdb_arrow):
"arrow::large_list(arrow::large_utf8())")
check_heap_repr(gdb_arrow, "heap_fixed_size_list_type",
"arrow::fixed_size_list(arrow::float64(), 3)")
check_heap_repr(
gdb_arrow, "heap_run_end_encoded_type",
"arrow::run_end_encoded(arrow::int32(), arrow::utf8())")
check_heap_repr(
gdb_arrow, "heap_map_type",
"arrow::map(arrow::utf8(), arrow::binary(), keys_sorted=false)")
Expand Down Expand Up @@ -744,6 +750,14 @@ def test_scalars_stack(gdb_arrow):
gdb_arrow, "fixed_size_list_scalar_null",
('arrow::FixedSizeListScalar of type '
'arrow::fixed_size_list(arrow::int32(), 3), null value'))
check_stack_repr(
gdb_arrow, "run_end_encoded_scalar",
('arrow::RunEndEncodedScalar of value '
'arrow::StringScalar of size 3, value "foo"'))
check_stack_repr(
gdb_arrow, "run_end_encoded_scalar_null",
('arrow::RunEndEncodedScalar of type '
'arrow::run_end_encoded(arrow::int32(), arrow::utf8()), null value'))

check_stack_repr(
gdb_arrow, "struct_scalar",
Expand Down Expand Up @@ -810,6 +824,10 @@ def test_scalars_heap(gdb_arrow):
gdb_arrow, "heap_map_scalar_null",
('arrow::MapScalar of type arrow::map(arrow::utf8(), arrow::int32(), '
'keys_sorted=false), null value'))
check_heap_repr(
gdb_arrow, "heap_run_end_encoded_scalar",
('arrow::RunEndEncodedScalar of value '
'arrow::StringScalar of size 3, value "foo"'))


def test_array_data(gdb_arrow):
Expand All @@ -828,6 +846,11 @@ def test_arrays_stack(gdb_arrow):
gdb_arrow, "list_array",
("arrow::ListArray of type arrow::list(arrow::int64()), "
"length 3, offset 0, null count 1"))
check_stack_repr(
gdb_arrow, "run_end_encoded_array",
("arrow::RunEndEncodedArray of type "
"arrow::run_end_encoded(arrow::int32(), arrow::utf8()), "
"length 5, offset 0, null count 0"))


def test_arrays_heap(gdb_arrow):
Expand Down Expand Up @@ -1081,6 +1104,16 @@ def test_arrays_heap(gdb_arrow):
gdb_arrow, "heap_list_array",
("arrow::ListArray of type arrow::list(arrow::int64()), "
"length 3, offset 0, null count 1"))
check_heap_repr(
gdb_arrow, "heap_run_end_encoded_array",
("arrow::RunEndEncodedArray of type "
"arrow::run_end_encoded(arrow::int32(), arrow::utf8()), "
"length 5, offset 0, null count 0"))
check_heap_repr(
gdb_arrow, "heap_run_end_encoded_array_sliced",
("arrow::RunEndEncodedArray of type "
"arrow::run_end_encoded(arrow::int32(), arrow::utf8()), "
"length 3, offset 1, null count 0"))


def test_schema(gdb_arrow):
Expand Down
Loading