Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
7 changes: 7 additions & 0 deletions pandas/core/arrays/string_arrow.py
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
from pandas.compat import (
pa_version_under10p1,
pa_version_under13p0,
pa_version_under16p0,
)
from pandas.util._exceptions import find_stack_level

Expand Down Expand Up @@ -71,6 +72,10 @@ def _chk_pyarrow_available() -> None:
raise ImportError(msg)


def _is_string_view(typ):
return not pa_version_under16p0 and pa.types.is_string_view(typ)


# TODO: Inherit directly from BaseStringArrayMethods. Currently we inherit from
# ObjectStringArrayMixin because we want to have the object-dtype based methods as
# fallback for the ones that pyarrow doesn't yet support
Expand Down Expand Up @@ -128,11 +133,13 @@ def __init__(self, values) -> None:
_chk_pyarrow_available()
if isinstance(values, (pa.Array, pa.ChunkedArray)) and (
pa.types.is_string(values.type)
or _is_string_view(values.type)
or (
pa.types.is_dictionary(values.type)
and (
pa.types.is_string(values.type.value_type)
or pa.types.is_large_string(values.type.value_type)
or _is_string_view(values.type.value_type)
)
)
):
Expand Down
14 changes: 14 additions & 0 deletions pandas/tests/arrays/string_/test_string_arrow.py
Original file line number Diff line number Diff line change
Expand Up @@ -99,6 +99,20 @@ def test_constructor_valid_string_type_value_dictionary(string_type, chunked):
assert pa.types.is_large_string(arr._pa_array.type)


@pytest.mark.parametrize("chunked", [True, False])
def test_constructor_valid_string_view(chunked):
# requires pyarrow>=18 for casting string_view to string
pa = pytest.importorskip("pyarrow", minversion="18")

arr = pa.array(["1", "2", "3"], pa.string_view())
if chunked:
arr = pa.chunked_array(arr)

arr = ArrowStringArray(arr)
# dictionary type get converted to dense large string array
assert pa.types.is_large_string(arr._pa_array.type)


def test_constructor_from_list():
# GH#27673
pytest.importorskip("pyarrow")
Expand Down