CI/TST: Fix xfail in test_columns_dtypes_not_invalid for pyarrow nightly (#61042)

Author: mroeschke

pandas/compat/pyarrow.py

@@ -19,6 +19,7 @@
     pa_version_under17p0 = _palv < Version("17.0.0")
     pa_version_under18p0 = _palv < Version("18.0.0")
     pa_version_under19p0 = _palv < Version("19.0.0")
+    pa_version_under20p0 = _palv < Version("20.0.0")
     HAS_PYARROW = True
 except ImportError:
     pa_version_under10p1 = True
@@ -32,4 +33,5 @@
     pa_version_under17p0 = True
     pa_version_under18p0 = True
     pa_version_under19p0 = True
+    pa_version_under20p0 = True
     HAS_PYARROW = False

pandas/tests/io/test_parquet.py

@@ -18,6 +18,7 @@
     pa_version_under15p0,
     pa_version_under17p0,
     pa_version_under19p0,
+    pa_version_under20p0,
 )
 
 import pandas as pd
@@ -1075,27 +1076,34 @@ def test_read_dtype_backend_pyarrow_config_index(self, pa):
             expected=expected,
         )
 
-    @pytest.mark.xfail(
-        pa_version_under17p0, reason="pa.pandas_compat passes 'datetime64' to .astype"
+    @pytest.mark.parametrize(
+        "columns",
+        [
+            [0, 1],
+            pytest.param(
+                [b"foo", b"bar"],
+                marks=pytest.mark.xfail(
+                    pa_version_under20p0,
+                    raises=NotImplementedError,
+                    reason="https://github.com/apache/arrow/pull/44171",
+                ),
+            ),
+            pytest.param(
+                [
+                    datetime.datetime(2011, 1, 1, 0, 0),
+                    datetime.datetime(2011, 1, 1, 1, 1),
+                ],
+                marks=pytest.mark.xfail(
+                    pa_version_under17p0,
+                    reason="pa.pandas_compat passes 'datetime64' to .astype",
+                ),
+            ),
+        ],
     )
-    def test_columns_dtypes_not_invalid(self, pa):
+    def test_columns_dtypes_not_invalid(self, pa, columns):
         df = pd.DataFrame({"string": list("abc"), "int": list(range(1, 4))})
 
-        # numeric
-        df.columns = [0, 1]
-        check_round_trip(df, pa)
-
-        # bytes
-        df.columns = [b"foo", b"bar"]
-        with pytest.raises(NotImplementedError, match="|S3"):
-            # Bytes fails on read_parquet
-            check_round_trip(df, pa)
-
-        # python object
-        df.columns = [
-            datetime.datetime(2011, 1, 1, 0, 0),
-            datetime.datetime(2011, 1, 1, 1, 1),
-        ]
+        df.columns = columns
         check_round_trip(df, pa)
 
     def test_empty_columns(self, pa):