TST: collect string arithmetic tests (#62507)

Author: jbrockmendel

pandas/tests/arithmetic/test_string.py

@@ -0,0 +1,114 @@
+from pathlib import Path
+
+import numpy as np
+import pytest
+
+from pandas.errors import Pandas4Warning
+
+from pandas import (
+    NA,
+    ArrowDtype,
+    Series,
+    StringDtype,
+)
+import pandas._testing as tm
+
+
+def test_reversed_logical_ops(any_string_dtype):
+    # GH#60234
+    dtype = any_string_dtype
+    warn = None if dtype == object else Pandas4Warning
+    left = Series([True, False, False, True])
+    right = Series(["", "", "b", "c"], dtype=dtype)
+
+    msg = "operations between boolean dtype and"
+    with tm.assert_produces_warning(warn, match=msg):
+        result = left | right
+    expected = left | right.astype(bool)
+    tm.assert_series_equal(result, expected)
+
+    with tm.assert_produces_warning(warn, match=msg):
+        result = left & right
+    expected = left & right.astype(bool)
+    tm.assert_series_equal(result, expected)
+
+    with tm.assert_produces_warning(warn, match=msg):
+        result = left ^ right
+    expected = left ^ right.astype(bool)
+    tm.assert_series_equal(result, expected)
+
+
+def test_pathlib_path_division(any_string_dtype, request):
+    # GH#61940
+    if any_string_dtype == object:
+        mark = pytest.mark.xfail(
+            reason="with NA present we go through _masked_arith_op which "
+            "raises TypeError bc Path is not recognized by lib.is_scalar."
+        )
+        request.applymarker(mark)
+
+    item = Path("/Users/Irv/")
+    ser = Series(["A", "B", NA], dtype=any_string_dtype)
+
+    result = item / ser
+    expected = Series([item / "A", item / "B", ser.dtype.na_value], dtype=object)
+    tm.assert_series_equal(result, expected)
+
+    result = ser / item
+    expected = Series(["A" / item, "B" / item, ser.dtype.na_value], dtype=object)
+    tm.assert_series_equal(result, expected)
+
+
+def test_mixed_object_comparison(any_string_dtype):
+    # GH#60228
+    dtype = any_string_dtype
+    ser = Series(["a", "b"], dtype=dtype)
+
+    mixed = Series([1, "b"], dtype=object)
+
+    result = ser == mixed
+    expected = Series([False, True], dtype=bool)
+    if dtype == object:
+        pass
+    elif dtype.storage == "python" and dtype.na_value is NA:
+        expected = expected.astype("boolean")
+    elif dtype.storage == "pyarrow" and dtype.na_value is NA:
+        expected = expected.astype("bool[pyarrow]")
+
+    tm.assert_series_equal(result, expected)
+
+
+def test_pyarrow_numpy_string_invalid():
+    # GH#56008
+    pa = pytest.importorskip("pyarrow")
+    ser = Series([False, True])
+    ser2 = Series(["a", "b"], dtype=StringDtype(na_value=np.nan))
+    result = ser == ser2
+    expected_eq = Series(False, index=ser.index)
+    tm.assert_series_equal(result, expected_eq)
+
+    result = ser != ser2
+    expected_ne = Series(True, index=ser.index)
+    tm.assert_series_equal(result, expected_ne)
+
+    with pytest.raises(TypeError, match="Invalid comparison"):
+        ser > ser2
+
+    # GH#59505
+    ser3 = ser2.astype("string[pyarrow]")
+    result3_eq = ser3 == ser
+    tm.assert_series_equal(result3_eq, expected_eq.astype("bool[pyarrow]"))
+    result3_ne = ser3 != ser
+    tm.assert_series_equal(result3_ne, expected_ne.astype("bool[pyarrow]"))
+
+    with pytest.raises(TypeError, match="Invalid comparison"):
+        ser > ser3
+
+    ser4 = ser2.astype(ArrowDtype(pa.string()))
+    result4_eq = ser4 == ser
+    tm.assert_series_equal(result4_eq, expected_eq.astype("bool[pyarrow]"))
+    result4_ne = ser4 != ser
+    tm.assert_series_equal(result4_ne, expected_ne.astype("bool[pyarrow]"))
+
+    with pytest.raises(TypeError, match="Invalid comparison"):
+        ser > ser4

pandas/tests/extension/test_string.py

@@ -288,19 +288,3 @@ def test_searchsorted_with_na_raises(data_for_sorting, as_series):
     )
     with pytest.raises(ValueError, match=msg):
         arr.searchsorted(b)
-
-
-def test_mixed_object_comparison(dtype):
-    # GH#60228
-    ser = pd.Series(["a", "b"], dtype=dtype)
-
-    mixed = pd.Series([1, "b"], dtype=object)
-
-    result = ser == mixed
-    expected = pd.Series([False, True], dtype=bool)
-    if dtype.storage == "python" and dtype.na_value is pd.NA:
-        expected = expected.astype("boolean")
-    elif dtype.storage == "pyarrow" and dtype.na_value is pd.NA:
-        expected = expected.astype("bool[pyarrow]")
-
-    tm.assert_series_equal(result, expected)

pandas/tests/io/formats/test_format.py

@@ -1922,37 +1922,6 @@ def test_3d_array(self):
         assert res[0] == " [[True, True], [False, False]]"
         assert res[1] == " [[False, True], [True, False]]"
 
-    def test_2d_extension_type(self):
-        # GH 33770
-
-        # Define a stub extension type with just enough code to run Series.__repr__()
-        class DtypeStub(pd.api.extensions.ExtensionDtype):
-            @property
-            def type(self):
-                return np.ndarray
-
-            @property
-            def name(self):
-                return "DtypeStub"
-
-        class ExtTypeStub(pd.api.extensions.ExtensionArray):
-            def __len__(self) -> int:
-                return 2
-
-            def __getitem__(self, ix):
-                return [ix == 1, ix == 0]
-
-            @property
-            def dtype(self):
-                return DtypeStub()
-
-        series = Series(ExtTypeStub(), copy=False)
-        res = repr(series)  # This line crashed before #33770 was fixed.
-        expected = "\n".join(
-            ["0    [False True]", "1    [True False]", "dtype: DtypeStub"]
-        )
-        assert res == expected
-
 
 def _three_digit_exp():
     return f"{1.7e8:.4g}" == "1.7e+008"

pandas/tests/series/test_formats.py

@@ -280,6 +280,37 @@ def test_different_null_objects(self):
         expected = "True    1\nNone    2\nNaN     3\nNaT     4\ndtype: int64"
         assert result == expected
 
+    def test_2d_extension_type(self):
+        # GH#33770
+
+        # Define a stub extension type with just enough code to run Series.__repr__()
+        class DtypeStub(pd.api.extensions.ExtensionDtype):
+            @property
+            def type(self):
+                return np.ndarray
+
+            @property
+            def name(self):
+                return "DtypeStub"
+
+        class ExtTypeStub(pd.api.extensions.ExtensionArray):
+            def __len__(self) -> int:
+                return 2
+
+            def __getitem__(self, ix):
+                return [ix == 1, ix == 0]
+
+            @property
+            def dtype(self):
+                return DtypeStub()
+
+        series = Series(ExtTypeStub(), copy=False)
+        res = repr(series)  # This line crashed before GH#33770 was fixed.
+        expected = "\n".join(
+            ["0    [False True]", "1    [True False]", "dtype: DtypeStub"]
+        )
+        assert res == expected
+
 
 class TestCategoricalRepr:
     def test_categorical_repr_unicode(self):

pandas/tests/series/test_logical_ops.py

@@ -5,11 +5,9 @@
 import pytest
 
 from pandas import (
-    ArrowDtype,
     DataFrame,
     Index,
     Series,
-    StringDtype,
     bdate_range,
 )
 import pandas._testing as tm
@@ -510,39 +508,3 @@ def test_int_dtype_different_index_not_bool(self):
 
         result = ser1 ^ ser2
         tm.assert_series_equal(result, expected)
-
-    # TODO: this belongs in comparison tests
-    def test_pyarrow_numpy_string_invalid(self):
-        # GH#56008
-        pa = pytest.importorskip("pyarrow")
-        ser = Series([False, True])
-        ser2 = Series(["a", "b"], dtype=StringDtype(na_value=np.nan))
-        result = ser == ser2
-        expected_eq = Series(False, index=ser.index)
-        tm.assert_series_equal(result, expected_eq)
-
-        result = ser != ser2
-        expected_ne = Series(True, index=ser.index)
-        tm.assert_series_equal(result, expected_ne)
-
-        with pytest.raises(TypeError, match="Invalid comparison"):
-            ser > ser2
-
-        # GH#59505
-        ser3 = ser2.astype("string[pyarrow]")
-        result3_eq = ser3 == ser
-        tm.assert_series_equal(result3_eq, expected_eq.astype("bool[pyarrow]"))
-        result3_ne = ser3 != ser
-        tm.assert_series_equal(result3_ne, expected_ne.astype("bool[pyarrow]"))
-
-        with pytest.raises(TypeError, match="Invalid comparison"):
-            ser > ser3
-
-        ser4 = ser2.astype(ArrowDtype(pa.string()))
-        result4_eq = ser4 == ser
-        tm.assert_series_equal(result4_eq, expected_eq.astype("bool[pyarrow]"))
-        result4_ne = ser4 != ser
-        tm.assert_series_equal(result4_ne, expected_ne.astype("bool[pyarrow]"))
-
-        with pytest.raises(TypeError, match="Invalid comparison"):
-            ser > ser4

pandas/tests/strings/test_strings.py

@@ -2,13 +2,11 @@
     datetime,
     timedelta,
 )
-from pathlib import Path
 
 import numpy as np
 import pytest
 
 from pandas.compat import pa_version_under21p0
-from pandas.errors import Pandas4Warning
 
 from pandas import (
     NA,
@@ -315,14 +313,14 @@ def test_isnumeric_unicode_missing(method, expected, any_string_dtype):
     tm.assert_series_equal(result, expected)
 
 
-def test_spilt_join_roundtrip(any_string_dtype):
+def test_split_join_roundtrip(any_string_dtype):
     ser = Series(["a_b_c", "c_d_e", np.nan, "f_g_h"], dtype=any_string_dtype)
     result = ser.str.split("_").str.join("_")
     expected = ser.astype(object)
     tm.assert_series_equal(result, expected)
 
 
-def test_spilt_join_roundtrip_mixed_object():
+def test_split_join_roundtrip_mixed_object():
     ser = Series(
         ["a_b", np.nan, "asdf_cas_asdf", True, datetime.today(), "foo", None, 1, 2.0]
     )
@@ -820,48 +818,3 @@ def test_decode_with_dtype_none():
         result = ser.str.decode("utf-8", dtype=None)
         expected = Series(["a", "b", "c"], dtype="str")
         tm.assert_series_equal(result, expected)
-
-
-def test_reversed_logical_ops(any_string_dtype):
-    # GH#60234
-    dtype = any_string_dtype
-    warn = None if dtype == object else Pandas4Warning
-    left = Series([True, False, False, True])
-    right = Series(["", "", "b", "c"], dtype=dtype)
-
-    msg = "operations between boolean dtype and"
-    with tm.assert_produces_warning(warn, match=msg):
-        result = left | right
-    expected = left | right.astype(bool)
-    tm.assert_series_equal(result, expected)
-
-    with tm.assert_produces_warning(warn, match=msg):
-        result = left & right
-    expected = left & right.astype(bool)
-    tm.assert_series_equal(result, expected)
-
-    with tm.assert_produces_warning(warn, match=msg):
-        result = left ^ right
-    expected = left ^ right.astype(bool)
-    tm.assert_series_equal(result, expected)
-
-
-def test_pathlib_path_division(any_string_dtype, request):
-    # GH#61940
-    if any_string_dtype == object:
-        mark = pytest.mark.xfail(
-            reason="with NA present we go through _masked_arith_op which "
-            "raises TypeError bc Path is not recognized by lib.is_scalar."
-        )
-        request.applymarker(mark)
-
-    item = Path("/Users/Irv/")
-    ser = Series(["A", "B", NA], dtype=any_string_dtype)
-
-    result = item / ser
-    expected = Series([item / "A", item / "B", ser.dtype.na_value], dtype=object)
-    tm.assert_series_equal(result, expected)
-
-    result = ser / item
-    expected = Series(["A" / item, "B" / item, ser.dtype.na_value], dtype=object)
-    tm.assert_series_equal(result, expected)