BUG: ArrowExtensionArray logical ops raising KeyError

doc/source/whatsnew/v2.1.0.rst

@@ -202,6 +202,7 @@ Sparse
 ExtensionArray
 ^^^^^^^^^^^^^^
 - Bug in :meth:`Series.any` and :meth:`Series.all` returning ``NA`` for empty or all null pyarrow-backed data when ``skipna=True`` (:issue:`51624`)
+- Bug in :class:`~arrays.ArrowExtensionArray` logical operations ``&`` and ``|`` raising ``KeyError`` (:issue:`51688`)
 -
 
 Styler

pandas/core/arrays/arrow/array.py

@@ -81,10 +81,10 @@
     }
 
     ARROW_LOGICAL_FUNCS = {
-        "and": pc.and_kleene,
-        "rand": lambda x, y: pc.and_kleene(y, x),
-        "or": pc.or_kleene,
-        "ror": lambda x, y: pc.or_kleene(y, x),
+        "and_": pc.and_kleene,
+        "rand_": lambda x, y: pc.and_kleene(y, x),
+        "or_": pc.or_kleene,
+        "ror_": lambda x, y: pc.or_kleene(y, x),
         "xor": pc.xor,
         "rxor": lambda x, y: pc.xor(y, x),
     }
@@ -491,7 +491,12 @@ def _evaluate_op_method(self, other, op, arrow_funcs):
         elif isinstance(other, (np.ndarray, list)):
             result = pc_func(self._data, pa.array(other, from_pandas=True))
         elif is_scalar(other):
-            result = pc_func(self._data, pa.scalar(other))
+            if isna(other) and op.__name__ in ARROW_LOGICAL_FUNCS:
+                # pyarrow kleene ops require null to be typed
+                pa_scalar = pa.scalar(None, type=self._data.type)
+            else:
+                pa_scalar = pa.scalar(other)
+            result = pc_func(self._data, pa_scalar)
         else:
             raise NotImplementedError(
                 f"{op.__name__} not implemented for {type(other)}"

pandas/tests/extension/test_arrow.py

@@ -1265,6 +1265,150 @@ def test_invalid_other_comp(self, data, comparison_op):
             comparison_op(data, object())
 
 
+class TestLogicalOps:
+    """Various Series and DataFrame logical ops methods."""
+
+    def test_kleene_or(self):
+        a = pd.Series([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean[pyarrow]")
+        b = pd.Series([True, False, None] * 3, dtype="boolean[pyarrow]")
+        result = a | b
+        expected = pd.Series(
+            [True, True, True, True, False, None, True, None, None],
+            dtype="boolean[pyarrow]",
+        )
+        tm.assert_series_equal(result, expected)
+
+        result = b | a
+        tm.assert_series_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        tm.assert_series_equal(
+            a,
+            pd.Series([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean[pyarrow]"),
+        )
+        tm.assert_series_equal(
+            b, pd.Series([True, False, None] * 3, dtype="boolean[pyarrow]")
+        )
+
+    @pytest.mark.parametrize(
+        "other, expected",
+        [
+            (None, [True, None, None]),
+            (pd.NA, [True, None, None]),
+            (True, [True, True, True]),
+            (np.bool_(True), [True, True, True]),
+            (False, [True, False, None]),
+            (np.bool_(False), [True, False, None]),
+        ],
+    )
+    def test_kleene_or_scalar(self, other, expected):
+        a = pd.Series([True, False, None], dtype="boolean[pyarrow]")
+        result = a | other
+        expected = pd.Series(expected, dtype="boolean[pyarrow]")
+        tm.assert_series_equal(result, expected)
+
+        result = other | a
+        tm.assert_series_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        tm.assert_series_equal(
+            a, pd.Series([True, False, None], dtype="boolean[pyarrow]")
+        )
+
+    def test_kleene_and(self):
+        a = pd.Series([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean[pyarrow]")
+        b = pd.Series([True, False, None] * 3, dtype="boolean[pyarrow]")
+        result = a & b
+        expected = pd.Series(
+            [True, False, None, False, False, False, None, False, None],
+            dtype="boolean[pyarrow]",
+        )
+        tm.assert_series_equal(result, expected)
+
+        result = b & a
+        tm.assert_series_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        tm.assert_series_equal(
+            a,
+            pd.Series([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean[pyarrow]"),
+        )
+        tm.assert_series_equal(
+            b, pd.Series([True, False, None] * 3, dtype="boolean[pyarrow]")
+        )
+
+    @pytest.mark.parametrize(
+        "other, expected",
+        [
+            (None, [None, False, None]),
+            (pd.NA, [None, False, None]),
+            (True, [True, False, None]),
+            (False, [False, False, False]),
+            (np.bool_(True), [True, False, None]),
+            (np.bool_(False), [False, False, False]),
+        ],
+    )
+    def test_kleene_and_scalar(self, other, expected):
+        a = pd.Series([True, False, None], dtype="boolean[pyarrow]")
+        result = a & other
+        expected = pd.Series(expected, dtype="boolean[pyarrow]")
+        tm.assert_series_equal(result, expected)
+
+        result = other & a
+        tm.assert_series_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        tm.assert_series_equal(
+            a, pd.Series([True, False, None], dtype="boolean[pyarrow]")
+        )
+
+    def test_kleene_xor(self):
+        a = pd.Series([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean[pyarrow]")
+        b = pd.Series([True, False, None] * 3, dtype="boolean[pyarrow]")
+        result = a ^ b
+        expected = pd.Series(
+            [False, True, None, True, False, None, None, None, None],
+            dtype="boolean[pyarrow]",
+        )
+        tm.assert_series_equal(result, expected)
+
+        result = b ^ a
+        tm.assert_series_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        tm.assert_series_equal(
+            a,
+            pd.Series([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean[pyarrow]"),
+        )
+        tm.assert_series_equal(
+            b, pd.Series([True, False, None] * 3, dtype="boolean[pyarrow]")
+        )
+
+    @pytest.mark.parametrize(
+        "other, expected",
+        [
+            (None, [None, None, None]),
+            (pd.NA, [None, None, None]),
+            (True, [False, True, None]),
+            (np.bool_(True), [False, True, None]),
+            (np.bool_(False), [True, False, None]),
+        ],
+    )
+    def test_kleene_xor_scalar(self, other, expected):
+        a = pd.Series([True, False, None], dtype="boolean[pyarrow]")
+        result = a ^ other
+        expected = pd.Series(expected, dtype="boolean[pyarrow]")
+        tm.assert_series_equal(result, expected)
+
+        result = other ^ a
+        tm.assert_series_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        tm.assert_series_equal(
+            a, pd.Series([True, False, None], dtype="boolean[pyarrow]")
+        )
+
+
 def test_arrowdtype_construct_from_string_type_with_unsupported_parameters():
     with pytest.raises(NotImplementedError, match="Passing pyarrow type"):
         ArrowDtype.construct_from_string("not_a_real_dype[s, tz=UTC][pyarrow]")