TST (string dtype): follow-up on GH-59329 fixing new xfails (#59352)

jorisvandenbossche · jorisvandenbossche · commit d36a5aabff84 · 2024-10-09T20:09:20.000+02:00
* TST (string dtype): follow-up on GH-59329 fixing new xfails * add missing strict
diff --git a/pandas/_testing/asserters.py b/pandas/_testing/asserters.py
@@ -593,13 +593,19 @@ def raise_assert_detail(
 
     if isinstance(left, np.ndarray):
         left = pprint_thing(left)
-    elif isinstance(left, (CategoricalDtype, NumpyEADtype, StringDtype)):
+    elif isinstance(left, (CategoricalDtype, NumpyEADtype)):
         left = repr(left)
+    elif isinstance(left, StringDtype):
+        # TODO(infer_string) this special case could be avoided if we have
+        # a more informative repr https://github.com/pandas-dev/pandas/issues/59342
+        left = f"StringDtype(storage={left.storage}, na_value={left.na_value})"
 
     if isinstance(right, np.ndarray):
         right = pprint_thing(right)
-    elif isinstance(right, (CategoricalDtype, NumpyEADtype, StringDtype)):
+    elif isinstance(right, (CategoricalDtype, NumpyEADtype)):
         right = repr(right)
+    elif isinstance(right, StringDtype):
+        right = f"StringDtype(storage={right.storage}, na_value={right.na_value})"
 
     msg += f"""
 [left]:  {left}
diff --git a/pandas/tests/arrays/interval/test_interval_pyarrow.py b/pandas/tests/arrays/interval/test_interval_pyarrow.py
@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 import pandas._testing as tm
 from pandas.core.arrays import IntervalArray
@@ -80,6 +82,7 @@ def test_arrow_array_missing():
     assert result.storage.equals(expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.filterwarnings(
     "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
 )
diff --git a/pandas/tests/arrays/masked/test_arrow_compat.py b/pandas/tests/arrays/masked/test_arrow_compat.py
@@ -1,12 +1,18 @@
 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"
-)
+pytestmark = [
+    pytest.mark.filterwarnings(
+        "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+    ),
+    pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False),
+]
+
 
 pa = pytest.importorskip("pyarrow")
 
diff --git a/pandas/tests/arrays/masked/test_function.py b/pandas/tests/arrays/masked/test_function.py
@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.core.dtypes.common import is_integer_dtype
 
 import pandas as pd
@@ -60,7 +58,6 @@ def test_tolist(data):
     tm.assert_equal(result, expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_to_numpy():
     # GH#56991
 
diff --git a/pandas/tests/arrays/period/test_arrow_compat.py b/pandas/tests/arrays/period/test_arrow_compat.py
@@ -1,5 +1,7 @@
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.compat.pyarrow import pa_version_under10p1
 
 from pandas.core.dtypes.dtypes import PeriodDtype
@@ -77,6 +79,7 @@ def test_arrow_array_missing():
     assert result.storage.equals(expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_arrow_table_roundtrip():
     from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
 
@@ -96,6 +99,7 @@ def test_arrow_table_roundtrip():
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_arrow_load_from_zero_chunks():
     # GH-41040
 
diff --git a/pandas/tests/arrays/string_/test_string.py b/pandas/tests/arrays/string_/test_string.py
@@ -7,6 +7,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.compat.pyarrow import pa_version_under12p0
 
 from pandas.core.dtypes.common import is_dtype_equal
@@ -513,6 +515,7 @@ 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_storage2, request, using_infer_string):
     # roundtrip possible from arrow 1.0.0
@@ -541,6 +544,7 @@ def test_arrow_roundtrip(dtype, string_storage2, request, using_infer_string):
     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_storage2, request, using_infer_string
diff --git a/pandas/tests/arrays/test_array.py b/pandas/tests/arrays/test_array.py
@@ -6,6 +6,8 @@
 import pytest
 import pytz
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 import pandas._testing as tm
 from pandas.api.extensions import register_extension_dtype
@@ -275,6 +277,7 @@ def test_array_copy():
 cet = pytz.timezone("CET")
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
     "data, expected",
     [
diff --git a/pandas/tests/dtypes/test_common.py b/pandas/tests/dtypes/test_common.py
@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas.util._test_decorators as td
 
 from pandas.core.dtypes.astype import astype_array
@@ -128,6 +130,7 @@ def test_dtype_equal(name1, dtype1, name2, dtype2):
         assert not com.is_dtype_equal(dtype1, dtype2)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("name,dtype", list(dtypes.items()), ids=lambda x: str(x))
 def test_pyarrow_string_import_error(name, dtype):
     # GH-44276
diff --git a/pandas/tests/frame/methods/test_astype.py b/pandas/tests/frame/methods/test_astype.py
@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas.util._test_decorators as td
 
 import pandas as pd
@@ -757,6 +759,7 @@ def test_astype_tz_object_conversion(self, tz):
         result = result.astype({"tz": "datetime64[ns, Europe/London]"})
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_astype_dt64_to_string(
         self, frame_or_series, tz_naive_fixture, using_infer_string
     ):
diff --git a/pandas/tests/frame/test_arithmetic.py b/pandas/tests/frame/test_arithmetic.py
@@ -2124,6 +2124,7 @@ def test_enum_column_equality():
     tm.assert_series_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_mixed_col_index_dtype():
     # GH 47382
     df1 = DataFrame(columns=list("abc"), data=1.0, index=[0])
diff --git a/pandas/tests/groupby/test_apply.py b/pandas/tests/groupby/test_apply.py
@@ -6,6 +6,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -940,6 +942,7 @@ def test_func_returns_object():
     tm.assert_series_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize(
     "group_column_dtlike",
     [datetime.today(), datetime.today().date(), datetime.today().time()],
diff --git a/pandas/tests/indexes/base_class/test_formats.py b/pandas/tests/indexes/base_class/test_formats.py
@@ -9,6 +9,7 @@
 
 
 class TestIndexRendering:
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_repr_is_valid_construction_code(self):
         # for the case of Index, where the repr is traditional rather than
         # stylized
diff --git a/pandas/tests/indexes/multi/test_setops.py b/pandas/tests/indexes/multi/test_setops.py
@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 from pandas import (
     CategoricalIndex,
@@ -758,6 +760,7 @@ def test_intersection_keep_ea_dtypes(val, any_numeric_ea_dtype):
     tm.assert_index_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_union_with_na_when_constructing_dataframe():
     # GH43222
     series1 = Series(
diff --git a/pandas/tests/indexes/test_old_base.py b/pandas/tests/indexes/test_old_base.py
@@ -232,6 +232,7 @@ def test_logical_compat(self, simple_index):
             with pytest.raises(TypeError, match=msg):
                 idx.any()
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     def test_repr_roundtrip(self, simple_index):
         if isinstance(simple_index, IntervalIndex):
             pytest.skip(f"Not a valid repr for {type(simple_index).__name__}")
diff --git a/pandas/tests/io/excel/test_readers.py b/pandas/tests/io/excel/test_readers.py
@@ -660,7 +660,9 @@ def test_dtype_backend_and_dtype(self, read_ext):
             )
         tm.assert_frame_equal(result, df)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="infer_string takes precedence")
+    @pytest.mark.xfail(
+        using_string_dtype(), reason="infer_string takes precedence", strict=False
+    )
     def test_dtype_backend_string(self, read_ext, string_storage):
         # GH#36712
         if read_ext in (".xlsb", ".xls"):
diff --git a/pandas/tests/io/json/test_json_table_schema.py b/pandas/tests/io/json/test_json_table_schema.py
@@ -6,6 +6,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.core.dtypes.dtypes import (
     CategoricalDtype,
     DatetimeTZDtype,
@@ -24,6 +26,10 @@
     set_default_names,
 )
 
+pytestmark = pytest.mark.xfail(
+    using_string_dtype(), reason="TODO(infer_string)", strict=False
+)
+
 
 @pytest.fixture
 def df_schema():
diff --git a/pandas/tests/io/json/test_pandas.py b/pandas/tests/io/json/test_pandas.py
@@ -1479,6 +1479,7 @@ def test_data_frame_size_after_to_json(self):
 
         assert size_before == size_after
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize(
         "index", [None, [1, 2], [1.0, 2.0], ["a", "b"], ["1", "2"], ["1.", "2."]]
     )
@@ -1491,6 +1492,7 @@ def test_from_json_to_json_table_index_and_columns(self, index, columns):
         result = read_json(StringIO(dfjson), orient="table")
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_from_json_to_json_table_dtypes(self):
         # GH21345
         expected = DataFrame({"a": [1, 2], "b": [3.0, 4.0], "c": ["5", "6"]})
diff --git a/pandas/tests/io/parser/dtypes/test_dtypes_basic.py b/pandas/tests/io/parser/dtypes/test_dtypes_basic.py
@@ -463,7 +463,7 @@ def test_dtype_backend_and_dtype(all_parsers):
     tm.assert_frame_equal(result, expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 def test_dtype_backend_string(all_parsers, string_storage):
     # GH#36712
     pa = pytest.importorskip("pyarrow")
diff --git a/pandas/tests/io/parser/test_upcast.py b/pandas/tests/io/parser/test_upcast.py
@@ -86,7 +86,7 @@ def test_maybe_upcaste_all_nan():
     tm.assert_extension_array_equal(result, expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("val", [na_values[np.object_], "c"])
 def test_maybe_upcast_object(val, string_storage):
     # GH#36712
diff --git a/pandas/tests/io/parser/usecols/test_usecols_basic.py b/pandas/tests/io/parser/usecols/test_usecols_basic.py
@@ -7,6 +7,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.errors import ParserError
 
 from pandas import (
@@ -545,6 +547,7 @@ def test_usecols_additional_columns_integer_columns(all_parsers):
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_usecols_dtype(all_parsers):
     parser = all_parsers
     data = """
diff --git a/pandas/tests/io/test_feather.py b/pandas/tests/io/test_feather.py
@@ -13,9 +13,12 @@
 
 from pandas.io.feather_format import read_feather, to_feather  # isort:skip
 
-pytestmark = pytest.mark.filterwarnings(
-    "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
-)
+pytestmark = [
+    pytest.mark.filterwarnings(
+        "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+    ),
+    pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False),
+]
 
 pa = pytest.importorskip("pyarrow")
 
@@ -170,7 +173,6 @@ def test_http_path(self, feather_file, httpserver):
             res = read_feather(httpserver.url)
         tm.assert_frame_equal(expected, res)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     def test_read_feather_dtype_backend(self, string_storage, dtype_backend):
         # GH#50765
         df = pd.DataFrame(
diff --git a/pandas/tests/io/test_fsspec.py b/pandas/tests/io/test_fsspec.py
@@ -277,6 +277,7 @@ def test_not_present_exception():
         read_csv("memory://test/test.csv")
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_feather_options(fsspectest):
     pytest.importorskip("pyarrow")
     df = DataFrame({"a": [0]})
diff --git a/pandas/tests/reshape/test_get_dummies.py b/pandas/tests/reshape/test_get_dummies.py
@@ -4,6 +4,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas.util._test_decorators as td
 
 from pandas.core.dtypes.common import is_integer_dtype
@@ -214,6 +216,7 @@ def test_dataframe_dummies_all_obj(self, df, sparse):
 
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_dataframe_dummies_string_dtype(self, df, using_infer_string):
         # GH44965
         df = df[["A", "B"]]
diff --git a/pandas/tests/series/methods/test_convert_dtypes.py b/pandas/tests/series/methods/test_convert_dtypes.py
@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas._libs import lib
 
 import pandas as pd
@@ -181,6 +183,7 @@ def test_cases(request):
 
 
 class TestSeriesConvertDtypes:
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize("params", product(*[(True, False)] * 5))
     def test_convert_dtypes(
         self,
diff --git a/pandas/tests/test_downstream.py b/pandas/tests/test_downstream.py
