TST (string dtype): fix and clean up arrow roundtrip tests (#59678)

* TST (string dtype): fix and clean up arrow roundtrip tests

* fix using_infer_string

Author: jorisvandenbossche

pandas/tests/arrays/masked/test_arrow_compat.py

@@ -1,17 +1,12 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 import pandas as pd
 import pandas._testing as tm
 
-pytestmark = [
-    pytest.mark.filterwarnings(
-        "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
-    ),
-    pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False),
-]
+pytestmark = pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+)
 
 
 pa = pytest.importorskip("pyarrow")

pandas/tests/arrays/string_/test_string.py

@@ -524,7 +524,6 @@ def test_arrow_array(dtype):
     assert arr.equals(expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.filterwarnings("ignore:Passing a BlockManager:DeprecationWarning")
 def test_arrow_roundtrip(dtype, string_storage, using_infer_string):
     # roundtrip possible from arrow 1.0.0
@@ -543,13 +542,16 @@ def test_arrow_roundtrip(dtype, string_storage, using_infer_string):
         assert result["a"].dtype == "object"
     else:
         assert isinstance(result["a"].dtype, pd.StringDtype)
-        expected = df.astype(f"string[{string_storage}]")
+        expected = df.astype(pd.StringDtype(string_storage, na_value=dtype.na_value))
+        if using_infer_string:
+            expected.columns = expected.columns.astype(
+                pd.StringDtype(string_storage, na_value=np.nan)
+            )
         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 result["a"].dtype.na_value
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.filterwarnings("ignore:Passing a BlockManager:DeprecationWarning")
 def test_arrow_load_from_zero_chunks(dtype, string_storage, using_infer_string):
     # GH-41040
@@ -571,7 +573,11 @@ def test_arrow_load_from_zero_chunks(dtype, string_storage, using_infer_string):
         assert result["a"].dtype == "object"
     else:
         assert isinstance(result["a"].dtype, pd.StringDtype)
-        expected = df.astype(f"string[{string_storage}]")
+        expected = df.astype(pd.StringDtype(string_storage, na_value=dtype.na_value))
+        if using_infer_string:
+            expected.columns = expected.columns.astype(
+                pd.StringDtype(string_storage, na_value=np.nan)
+            )
         tm.assert_frame_equal(result, expected)