Skip to content

BUG: pickling ArrowExtensionArray with _pa_data rename #52027

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.

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

Merged
merged 2 commits into from
Mar 16, 2023
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
8 changes: 6 additions & 2 deletions pandas/core/arrays/arrow/array.py
Original file line number Diff line number Diff line change
Expand Up @@ -433,11 +433,15 @@ def __abs__(self) -> Self:
# https://issues.apache.org/jira/browse/ARROW-10739 is addressed
def __getstate__(self):
state = self.__dict__.copy()
state["_data"] = self._pa_array.combine_chunks()
state["_pa_array"] = self._pa_array.combine_chunks()
return state

def __setstate__(self, state) -> None:
state["_pa_array"] = pa.chunked_array(state["_data"])
if "_data" in state:
data = state.pop("_data")
else:
data = state["_pa_array"]
state["_pa_array"] = pa.chunked_array(data)
self.__dict__.update(state)

def _cmp_method(self, other, op):
Expand Down
17 changes: 17 additions & 0 deletions pandas/tests/extension/test_arrow.py
Original file line number Diff line number Diff line change
Expand Up @@ -2351,3 +2351,20 @@ def test_concat_empty_arrow_backed_series(dtype):
expected = ser.copy()
result = pd.concat([ser[np.array([], dtype=np.bool_)]])
tm.assert_series_equal(result, expected)


# _data was renamed to _pa_data
class OldArrowExtensionArray(ArrowExtensionArray):
def __getstate__(self):
state = super().__getstate__()
state["_data"] = state.pop("_pa_array")
return state


def test_pickle_old_arrowextensionarray():
data = pa.array([1])
expected = OldArrowExtensionArray(data)
result = pickle.loads(pickle.dumps(expected))
tm.assert_extension_array_equal(result, expected)
assert result._pa_array == pa.chunked_array(data)
assert not hasattr(result, "_data")