Skip to content
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

TST: Fix shares_memory for arrow string dtype #55823

Merged
merged 4 commits into from
Nov 6, 2023
Merged

TST: Fix shares_memory for arrow string dtype #55823

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
57cb8f4
TST: Fix shares_memory for arrow string dtype
phofl Nov 4, 2023
7697059
TST: Fix shares_memory for arrow string dtype
phofl Nov 4, 2023
285f7bb
TST: Fix shares_memory for arrow string dtype
phofl Nov 4, 2023
dfc83f9
Fix mypy
phofl Nov 5, 2023
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
13 changes: 11 additions & 2 deletions pandas/_testing/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@
is_float_dtype,
is_sequence,
is_signed_integer_dtype,
is_string_dtype,
is_unsigned_integer_dtype,
pandas_dtype,
)
Expand Down Expand Up @@ -1044,10 +1045,18 @@ def shares_memory(left, right) -> bool:
if isinstance(left, pd.core.arrays.IntervalArray):
return shares_memory(left._left, right) or shares_memory(left._right, right)

if isinstance(left, ExtensionArray) and left.dtype == "string[pyarrow]":
if (
isinstance(left, ExtensionArray)
and is_string_dtype(left.dtype)
and left.dtype.storage in ("pyarrow", "pyarrow_numpy") # type: ignore[attr-defined] # noqa: E501
):
# https://github.com/pandas-dev/pandas/pull/43930#discussion_r736862669
left = cast("ArrowExtensionArray", left)
if isinstance(right, ExtensionArray) and right.dtype == "string[pyarrow]":
if (
isinstance(right, ExtensionArray)
and is_string_dtype(right.dtype)
and right.dtype.storage in ("pyarrow", "pyarrow_numpy") # type: ignore[attr-defined] # noqa: E501
):
right = cast("ArrowExtensionArray", right)
left_pa_data = left._pa_array
right_pa_data = right._pa_array
Expand Down
17 changes: 17 additions & 0 deletions pandas/tests/util/test_shares_memory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,5 @@
import pandas.util._test_decorators as td

import pandas as pd
import pandas._testing as tm

Expand All @@ -11,3 +13,18 @@ def test_shares_memory_interval():
assert tm.shares_memory(obj, obj[:2])

assert not tm.shares_memory(obj, obj._data.copy())


@td.skip_if_no("pyarrow")
def test_shares_memory_string():
# GH#55823
import pyarrow as pa

obj = pd.array(["a", "b"], dtype="string[pyarrow]")
assert tm.shares_memory(obj, obj)

obj = pd.array(["a", "b"], dtype="string[pyarrow_numpy]")
assert tm.shares_memory(obj, obj)

obj = pd.array(["a", "b"], dtype=pd.ArrowDtype(pa.string()))
assert tm.shares_memory(obj, obj)
Loading