fix constructor to not convert to NA

Author: jorisvandenbossche

pandas/_testing/asserters.py

@@ -805,6 +805,16 @@ def assert_extension_array_equal(
         left_na, right_na, obj=f"{obj} NA mask", index_values=index_values
     )
 
+    # Specifically for StringArrayNumpySemantics, validate here we have a valid array
+    if isinstance(left.dtype, StringDtype) and left.dtype.storage == "python_numpy":
+        assert np.all(
+            [np.isnan(val) for val in left._ndarray[left_na]]
+        ), "wrong missing value sentinels"
+    if isinstance(right.dtype, StringDtype) and right.dtype.storage == "python_numpy":
+        assert np.all(
+            [np.isnan(val) for val in right._ndarray[right_na]]
+        ), "wrong missing value sentinels"
+
     left_valid = left[~left_na].to_numpy(dtype=object)
     right_valid = right[~right_na].to_numpy(dtype=object)
     if check_exact:

pandas/core/arrays/string_.py

@@ -697,6 +697,19 @@ def _str_map(
 class StringArrayNumpySemantics(StringArray):
     _storage = "python_numpy"
 
+    def _validate(self) -> None:
+        """Validate that we only store NaN or strings."""
+        if len(self._ndarray) and not lib.is_string_array(self._ndarray, skipna=True):
+            raise ValueError(
+                "StringArrayNumpySemantics requires a sequence of strings or NaN"
+            )
+        if self._ndarray.dtype != "object":
+            raise ValueError(
+                "StringArrayNumpySemantics requires a sequence of strings or NaN. Got "
+                f"'{self._ndarray.dtype}' dtype instead."
+            )
+        # TODO validate or force NA/None to NaN
+
     @classmethod
     def _from_sequence(
         cls, scalars, *, dtype: Dtype | None = None, copy: bool = False

pandas/tests/arrays/string_/test_string.py

@@ -325,8 +325,10 @@ def test_comparison_methods_array(comparison_op, dtype):
 
 
 def test_constructor_raises(cls):
-    if cls is pd.arrays.StringArray or cls is StringArrayNumpySemantics:
+    if cls is pd.arrays.StringArray:
         msg = "StringArray requires a sequence of strings or pandas.NA"
+    elif cls is StringArrayNumpySemantics:
+        msg = "StringArrayNumpySemantics requires a sequence of strings or NaN"
     else:
         msg = "Unsupported type '<class 'numpy.ndarray'>' for ArrowExtensionArray"
 
@@ -377,6 +379,8 @@ def test_from_sequence_no_mutate(copy, cls, dtype):
         import pyarrow as pa
 
         expected = cls(pa.array(na_arr, type=pa.string(), from_pandas=True))
+    elif cls is StringArrayNumpySemantics:
+        expected = cls(nan_arr)
     else:
         expected = cls(na_arr)