Backport PR #52075 on branch 2.0.x (BUG: Arrow setitem segfaults when…

… len > 145 000) (#52259)

* BUG: Arrow setitem segfaults when len > 145 000 (#52075)

* BUG: Arrow setitem segfaults when len > 145 000

* Add gh ref

* Address review

* Restrict to bool type

(cherry picked from commit 10000db)

* _data

---------

Co-authored-by: Patrick Hoefler <61934744+phofl@users.noreply.github.com>

pandas/core/arrays/arrow/array.py

@@ -1618,6 +1618,10 @@ def _replace_with_mask(
                 indices = pa.array(indices, type=pa.int64())
                 replacements = replacements.take(indices)
             return cls._if_else(mask, replacements, values)
+        if isinstance(values, pa.ChunkedArray) and pa.types.is_boolean(values.type):
+            # GH#52059 replace_with_mask segfaults for chunked array
+            # https://github.com/apache/arrow/issues/34634
+            values = values.combine_chunks()
         try:
             return pc.replace_with_mask(values, mask, replacements)
         except pa.ArrowNotImplementedError:

pandas/tests/extension/test_arrow.py

@@ -2333,3 +2333,12 @@ def test_series_from_string_array(dtype):
     ser = pd.Series(arr, dtype=dtype)
     expected = pd.Series(ArrowExtensionArray(arr), dtype=dtype)
     tm.assert_series_equal(ser, expected)
+
+
+def test_setitem_boolean_replace_with_mask_segfault():
+    # GH#52059
+    N = 145_000
+    arr = ArrowExtensionArray(pa.chunked_array([np.ones((N,), dtype=np.bool_)]))
+    expected = arr.copy()
+    arr[np.zeros((N,), dtype=np.bool_)] = False
+    assert arr._data == expected._data