fixup roundtrip tests

Author: simonjayhawkins

pandas/conftest.py

@@ -1152,6 +1152,10 @@ def string_storage(request):
     return request.param
 
 
+# Alias so we can test with cartesian product of string_storage
+string_storage2 = string_storage
+
+
 @pytest.fixture(params=tm.BYTES_DTYPES)
 def bytes_dtype(request):
     """

pandas/tests/arrays/string_/test_string.py

@@ -431,23 +431,25 @@ def test_arrow_array(dtype):
 
 
 @td.skip_if_no("pyarrow")
-def test_arrow_roundtrip(dtype):
+def test_arrow_roundtrip(dtype, string_storage2):
     # roundtrip possible from arrow 1.0.0
     import pyarrow as pa
 
     data = pd.array(["a", "b", None], dtype=dtype)
     df = pd.DataFrame({"a": data})
     table = pa.table(df)
     assert table.field("a").type == "string"
-    result = table.to_pandas()
-    assert isinstance(result["a"].dtype, type(dtype))
-    tm.assert_frame_equal(result, df)
+    with pd.option_context("string_storage", string_storage2):
+        result = table.to_pandas()
+    assert isinstance(result["a"].dtype, pd.StringDtype)
+    expected = df.astype(f"string[{string_storage2}]")
+    tm.assert_frame_equal(result, expected)
     # ensure the missing value is represented by NA and not np.nan or None
     assert result.loc[2, "a"] is pd.NA
 
 
 @td.skip_if_no("pyarrow")
-def test_arrow_load_from_zero_chunks(dtype):
+def test_arrow_load_from_zero_chunks(dtype, string_storage2):
     # GH-41040
     import pyarrow as pa
 
@@ -457,9 +459,11 @@ def test_arrow_load_from_zero_chunks(dtype):
     assert table.field("a").type == "string"
     # Instantiate the same table with no chunks at all
     table = pa.table([pa.chunked_array([], type=pa.string())], schema=table.schema)
-    result = table.to_pandas()
-    assert isinstance(result["a"].dtype, type(dtype))
-    tm.assert_frame_equal(result, df)
+    with pd.option_context("string_storage", string_storage2):
+        result = table.to_pandas()
+    assert isinstance(result["a"].dtype, pd.StringDtype)
+    expected = df.astype(f"string[{string_storage2}]")
+    tm.assert_frame_equal(result, expected)
 
 
 def test_value_counts_na(dtype):

pandas/tests/io/test_parquet.py

@@ -810,10 +810,11 @@ def test_additional_extension_arrays(self, pa):
         check_round_trip(df, pa)
 
     @td.skip_if_no("pyarrow", min_version="1.0.0")
-    def test_pyarrow_backed_string_array(self, pa):
+    def test_pyarrow_backed_string_array(self, pa, string_storage):
         # test ArrowStringArray supported through the __arrow_array__ protocol
         df = pd.DataFrame({"a": pd.Series(["a", None, "c"], dtype="string[pyarrow]")})
-        check_round_trip(df, pa, expected=df)
+        with pd.option_context("string_storage", string_storage):
+            check_round_trip(df, pa, expected=df.astype(f"string[{string_storage}]"))
 
     @td.skip_if_no("pyarrow")
     def test_additional_extension_types(self, pa):