Adjust format tests for new string option (pandas-dev#56535)

Author: phofl

pandas/tests/io/formats/style/test_to_latex.py

@@ -6,6 +6,7 @@
 from pandas import (
     DataFrame,
     MultiIndex,
+    Series,
     option_context,
 )
 
@@ -22,7 +23,9 @@
 
 @pytest.fixture
 def df():
-    return DataFrame({"A": [0, 1], "B": [-0.61, -1.22], "C": ["ab", "cd"]})
+    return DataFrame(
+        {"A": [0, 1], "B": [-0.61, -1.22], "C": Series(["ab", "cd"], dtype=object)}
+    )
 
 
 @pytest.fixture

pandas/tests/io/formats/style/test_to_string.py

@@ -2,15 +2,20 @@
 
 import pytest
 
-from pandas import DataFrame
+from pandas import (
+    DataFrame,
+    Series,
+)
 
 pytest.importorskip("jinja2")
 from pandas.io.formats.style import Styler
 
 
 @pytest.fixture
 def df():
-    return DataFrame({"A": [0, 1], "B": [-0.61, -1.22], "C": ["ab", "cd"]})
+    return DataFrame(
+        {"A": [0, 1], "B": [-0.61, -1.22], "C": Series(["ab", "cd"], dtype=object)}
+    )
 
 
 @pytest.fixture

pandas/tests/io/formats/test_format.py

@@ -11,6 +11,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_pyarrow_string_dtype
+
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -892,7 +894,7 @@ def test_truncate_with_different_dtypes(self, dtype):
 
     def test_truncate_with_different_dtypes2(self):
         # 12045
-        df = DataFrame({"text": ["some words"] + [None] * 9})
+        df = DataFrame({"text": ["some words"] + [None] * 9}, dtype=object)
 
         with option_context("display.max_rows", 8, "display.max_columns", 3):
             result = str(df)
@@ -1295,9 +1297,9 @@ def test_float_trim_zeros(self):
             ([3.50, None, "3.50"], "0     3.5\n1    None\n2    3.50\ndtype: object"),
         ],
     )
-    def test_repr_str_float_truncation(self, data, expected):
+    def test_repr_str_float_truncation(self, data, expected, using_infer_string):
         # GH#38708
-        series = Series(data)
+        series = Series(data, dtype=object if "3.50" in data else None)
         result = repr(series)
         assert result == expected
 
@@ -1394,6 +1396,9 @@ def test_unicode_name_in_footer(self):
         sf = fmt.SeriesFormatter(s, name="\u05e2\u05d1\u05e8\u05d9\u05ea")
         sf._get_footer()  # should not raise exception
 
+    @pytest.mark.xfail(
+        using_pyarrow_string_dtype(), reason="Fixup when arrow is default"
+    )
     def test_east_asian_unicode_series(self):
         # not aligned properly because of east asian width
 
@@ -1762,15 +1767,15 @@ def test_consistent_format(self):
         assert res == exp
 
     def chck_ncols(self, s):
-        with option_context("display.max_rows", 10):
-            res = repr(s)
-        lines = res.split("\n")
         lines = [
             line for line in repr(s).split("\n") if not re.match(r"[^\.]*\.+", line)
         ][:-1]
         ncolsizes = len({len(line.strip()) for line in lines})
         assert ncolsizes == 1
 
+    @pytest.mark.xfail(
+        using_pyarrow_string_dtype(), reason="change when arrow is default"
+    )
     def test_format_explicit(self):
         test_sers = gen_series_formatting()
         with option_context("display.max_rows", 4, "display.show_dimensions", False):

pandas/tests/io/formats/test_to_csv.py

@@ -666,7 +666,7 @@ def test_na_rep_truncated(self):
     def test_to_csv_errors(self, errors):
         # GH 22610
         data = ["\ud800foo"]
-        ser = pd.Series(data, index=Index(data))
+        ser = pd.Series(data, index=Index(data, dtype=object), dtype=object)
         with tm.ensure_clean("test.csv") as path:
             ser.to_csv(path, errors=errors)
         # No use in reading back the data as it is not the same anymore
@@ -682,8 +682,8 @@ def test_to_csv_binary_handle(self, mode):
         """
         df = DataFrame(
             1.1 * np.arange(120).reshape((30, 4)),
-            columns=Index(list("ABCD"), dtype=object),
-            index=Index([f"i-{i}" for i in range(30)], dtype=object),
+            columns=Index(list("ABCD")),
+            index=Index([f"i-{i}" for i in range(30)]),
         )
         with tm.ensure_clean() as path:
             with open(path, mode="w+b") as handle:
@@ -720,8 +720,8 @@ def test_to_csv_iterative_compression_name(compression):
     # GH 38714
     df = DataFrame(
         1.1 * np.arange(120).reshape((30, 4)),
-        columns=Index(list("ABCD"), dtype=object),
-        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+        columns=Index(list("ABCD")),
+        index=Index([f"i-{i}" for i in range(30)]),
     )
     with tm.ensure_clean() as path:
         df.to_csv(path, compression=compression, chunksize=1)
@@ -734,8 +734,8 @@ def test_to_csv_iterative_compression_buffer(compression):
     # GH 38714
     df = DataFrame(
         1.1 * np.arange(120).reshape((30, 4)),
-        columns=Index(list("ABCD"), dtype=object),
-        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+        columns=Index(list("ABCD")),
+        index=Index([f"i-{i}" for i in range(30)]),
     )
     with io.BytesIO() as buffer:
         df.to_csv(buffer, compression=compression, chunksize=1)

pandas/tests/io/formats/test_to_html.py

@@ -240,7 +240,7 @@ def test_to_html_multiindex_odd_even_truncate(max_rows, expected, datapath):
         (
             DataFrame(
                 [[0, 1], [2, 3], [4, 5], [6, 7]],
-                columns=["foo", None],
+                columns=Index(["foo", None], dtype=object),
                 index=np.arange(4),
             ),
             {"__index__": lambda x: "abcd"[x]},
@@ -771,7 +771,7 @@ def test_to_html_render_links(render_links, expected, datapath):
         [0, "https://pandas.pydata.org/?q1=a&q2=b", "pydata.org"],
         [0, "www.pydata.org", "pydata.org"],
     ]
-    df = DataFrame(data, columns=["foo", "bar", None])
+    df = DataFrame(data, columns=Index(["foo", "bar", None], dtype=object))
 
     result = df.to_html(render_links=render_links)
     expected = expected_html(datapath, expected)

pandas/tests/io/formats/test_to_string.py

@@ -10,6 +10,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_pyarrow_string_dtype
+
 from pandas import (
     CategoricalIndex,
     DataFrame,
@@ -849,6 +851,7 @@ def test_to_string(self):
         frame.to_string()
 
     # TODO: split or simplify this test?
+    @pytest.mark.xfail(using_pyarrow_string_dtype(), reason="fix when arrow is default")
     def test_to_string_index_with_nan(self):
         # GH#2850
         df = DataFrame(