Backport PR pandas-dev#55821: BUG: Index.isin raising for arrow strings and null set

Author: phofl

pandas/core/arrays/string_arrow.py

@@ -215,7 +215,9 @@ def isin(self, values) -> npt.NDArray[np.bool_]:
         if not len(value_set):
             return np.zeros(len(self), dtype=bool)
 
-        result = pc.is_in(self._pa_array, value_set=pa.array(value_set))
+        result = pc.is_in(
+            self._pa_array, value_set=pa.array(value_set, type=self._pa_array.type)
+        )
         # pyarrow 2.0.0 returned nulls, so we explicily specify dtype to convert nulls
         # to False
         return np.array(result, dtype=np.bool_)

pandas/tests/indexes/test_base.py

@@ -10,6 +10,7 @@
 
 from pandas.compat import IS64
 from pandas.errors import InvalidIndexError
+import pandas.util._test_decorators as td
 
 from pandas.core.dtypes.common import (
     is_any_real_numeric_dtype,
@@ -915,6 +916,14 @@ def test_isin_empty(self, empty):
         result = index.isin(empty)
         tm.assert_numpy_array_equal(expected, result)
 
+    @td.skip_if_no("pyarrow")
+    def test_isin_arrow_string_null(self):
+        # GH#55821
+        index = Index(["a", "b"], dtype="string[pyarrow_numpy]")
+        result = index.isin([None])
+        expected = np.array([False, False])
+        tm.assert_numpy_array_equal(result, expected)
+
     @pytest.mark.parametrize(
         "values",
         [