STY: Removed unconcatenated strings (#30464)

Author: ShaharNaveh

pandas/core/arrays/datetimelike.py

@@ -916,9 +916,7 @@ def _is_unique(self):
 
     def _add_datetimelike_scalar(self, other):
         # Overriden by TimedeltaArray
-        raise TypeError(
-            f"cannot add {type(self).__name__} and " f"{type(other).__name__}"
-        )
+        raise TypeError(f"cannot add {type(self).__name__} and {type(other).__name__}")
 
     _add_datetime_arraylike = _add_datetimelike_scalar
 

pandas/core/dtypes/cast.py

@@ -820,9 +820,7 @@ def astype_nansafe(arr, dtype, copy: bool = True, skipna: bool = False):
         if dtype.kind == "M":
             return arr.astype(dtype)
 
-        raise TypeError(
-            f"cannot astype a datetimelike from [{arr.dtype}] " f"to [{dtype}]"
-        )
+        raise TypeError(f"cannot astype a datetimelike from [{arr.dtype}] to [{dtype}]")
 
     elif is_timedelta64_dtype(arr):
         if is_object_dtype(dtype):
@@ -842,9 +840,7 @@ def astype_nansafe(arr, dtype, copy: bool = True, skipna: bool = False):
         elif dtype == _TD_DTYPE:
             return arr.astype(_TD_DTYPE, copy=copy)
 
-        raise TypeError(
-            f"cannot astype a timedelta from [{arr.dtype}] " f"to [{dtype}]"
-        )
+        raise TypeError(f"cannot astype a timedelta from [{arr.dtype}] to [{dtype}]")
 
     elif np.issubdtype(arr.dtype, np.floating) and np.issubdtype(dtype, np.integer):
 

pandas/io/json/_json.py

@@ -53,7 +53,7 @@ def to_json(
 
     if not index and orient not in ["split", "table"]:
         raise ValueError(
-            "'index=False' is only valid when 'orient' is " "'split' or 'table'"
+            "'index=False' is only valid when 'orient' is 'split' or 'table'"
         )
 
     path_or_buf = stringify_path(path_or_buf)

pandas/io/json/_table_schema.py

@@ -81,9 +81,7 @@ def set_default_names(data):
         if len(nms) == 1 and data.index.name == "index":
             warnings.warn("Index name of 'index' is not round-trippable")
         elif len(nms) > 1 and any(x.startswith("level_") for x in nms):
-            warnings.warn(
-                "Index names beginning with 'level_' are not " "round-trippable"
-            )
+            warnings.warn("Index names beginning with 'level_' are not round-trippable")
         return data
 
     data = data.copy()
@@ -317,12 +315,12 @@ def parse_table_schema(json, precise_float):
 
     # Cannot directly use as_type with timezone data on object; raise for now
     if any(str(x).startswith("datetime64[ns, ") for x in dtypes.values()):
-        raise NotImplementedError('table="orient" can not yet read timezone ' "data")
+        raise NotImplementedError('table="orient" can not yet read timezone data')
 
     # No ISO constructor for Timedelta as of yet, so need to raise
     if "timedelta64" in dtypes.values():
         raise NotImplementedError(
-            'table="orient" can not yet read ' "ISO-formatted Timedelta data"
+            'table="orient" can not yet read ISO-formatted Timedelta data'
         )
 
     df = df.astype(dtypes)

pandas/tests/arithmetic/test_period.py

@@ -168,9 +168,7 @@ def test_parr_cmp_pi_mismatched_freq_raises(self, freq, box_with_array):
 
         # TODO: Could parametrize over boxes for idx?
         idx = PeriodIndex(["2011", "2012", "2013", "2014"], freq="A")
-        rev_msg = (
-            r"Input has different freq=(M|2M|3M) from " r"PeriodArray\(freq=A-DEC\)"
-        )
+        rev_msg = r"Input has different freq=(M|2M|3M) from PeriodArray\(freq=A-DEC\)"
         idx_msg = rev_msg if box_with_array is tm.to_array else msg
         with pytest.raises(IncompatibleFrequency, match=idx_msg):
             base <= idx
@@ -184,7 +182,7 @@ def test_parr_cmp_pi_mismatched_freq_raises(self, freq, box_with_array):
             Period("2011", freq="4M") >= base
 
         idx = PeriodIndex(["2011", "2012", "2013", "2014"], freq="4M")
-        rev_msg = r"Input has different freq=(M|2M|3M) from " r"PeriodArray\(freq=4M\)"
+        rev_msg = r"Input has different freq=(M|2M|3M) from PeriodArray\(freq=4M\)"
         idx_msg = rev_msg if box_with_array is tm.to_array else msg
         with pytest.raises(IncompatibleFrequency, match=idx_msg):
             base <= idx

pandas/tests/arrays/test_timedeltas.py

@@ -41,13 +41,12 @@ def test_other_type_raises(self):
     def test_incorrect_dtype_raises(self):
         # TODO: why TypeError for 'category' but ValueError for i8?
         with pytest.raises(
-            ValueError, match=r"category cannot be converted " r"to timedelta64\[ns\]"
+            ValueError, match=r"category cannot be converted to timedelta64\[ns\]"
         ):
             TimedeltaArray(np.array([1, 2, 3], dtype="i8"), dtype="category")
 
         with pytest.raises(
-            ValueError,
-            match=r"dtype int64 cannot be converted " r"to timedelta64\[ns\]",
+            ValueError, match=r"dtype int64 cannot be converted to timedelta64\[ns\]",
         ):
             TimedeltaArray(np.array([1, 2, 3], dtype="i8"), dtype=np.dtype("int64"))
 

pandas/tests/base/test_ops.py

@@ -698,9 +698,7 @@ def test_duplicated_drop_duplicates_index(self):
 
                 with pytest.raises(
                     TypeError,
-                    match=(
-                        r"drop_duplicates\(\) got an " r"unexpected keyword argument"
-                    ),
+                    match=r"drop_duplicates\(\) got an unexpected keyword argument",
                 ):
                     idx.drop_duplicates(inplace=True)
 

pandas/tests/frame/test_constructors.py

@@ -479,11 +479,11 @@ def test_constructor_error_msgs(self):
             DataFrame(np.zeros((3, 3, 3)), columns=["A", "B", "C"], index=[1])
 
         # wrong size axis labels
-        msg = "Shape of passed values " r"is \(2, 3\), indices " r"imply \(1, 3\)"
+        msg = r"Shape of passed values is \(2, 3\), indices imply \(1, 3\)"
         with pytest.raises(ValueError, match=msg):
             DataFrame(np.random.rand(2, 3), columns=["A", "B", "C"], index=[1])
 
-        msg = "Shape of passed values " r"is \(2, 3\), indices " r"imply \(2, 2\)"
+        msg = r"Shape of passed values is \(2, 3\), indices imply \(2, 2\)"
         with pytest.raises(ValueError, match=msg):
             DataFrame(np.random.rand(2, 3), columns=["A", "B"], index=[1, 2])
 

pandas/tests/frame/test_missing.py

@@ -662,7 +662,7 @@ def test_fillna_invalid_method(self, float_frame):
 
     def test_fillna_invalid_value(self, float_frame):
         # list
-        msg = '"value" parameter must be a scalar or dict, but you passed' ' a "{}"'
+        msg = '"value" parameter must be a scalar or dict, but you passed a "{}"'
         with pytest.raises(TypeError, match=msg.format("list")):
             float_frame.fillna([1, 2])
         # tuple

pandas/tests/indexes/datetimes/test_tools.py

@@ -1298,7 +1298,7 @@ def test_dataframe(self, cache):
         tm.assert_series_equal(result, expected)
 
         # extra columns
-        msg = "extra keys have been passed to the datetime assemblage: " r"\[foo\]"
+        msg = r"extra keys have been passed to the datetime assemblage: \[foo\]"
         with pytest.raises(ValueError, match=msg):
             df2 = df.copy()
             df2["foo"] = 1

pandas/tests/indexing/test_loc.py

@@ -242,9 +242,7 @@ def test_loc_to_fail(self):
         with pytest.raises(KeyError, match=msg):
             s.loc[[-1, -2]]
 
-        msg = (
-            r"\"None of \[Index\(\['4'\], dtype='object'\)\] are" r" in the \[index\]\""
-        )
+        msg = r"\"None of \[Index\(\['4'\], dtype='object'\)\] are in the \[index\]\""
         with pytest.raises(KeyError, match=msg):
             s.loc[["4"]]
 

pandas/tests/io/formats/test_to_csv.py

@@ -376,16 +376,14 @@ def test_to_csv_string_with_lf(self):
                 assert f.read() == expected_noarg
         with tm.ensure_clean("lf_test.csv") as path:
             # case 2: LF as line terminator
-            expected_lf = b"int,str_lf\n" b"1,abc\n" b'2,"d\nef"\n' b'3,"g\nh\n\ni"\n'
+            expected_lf = b'int,str_lf\n1,abc\n2,"d\nef"\n3,"g\nh\n\ni"\n'
             df.to_csv(path, line_terminator="\n", index=False)
             with open(path, "rb") as f:
                 assert f.read() == expected_lf
         with tm.ensure_clean("lf_test.csv") as path:
             # case 3: CRLF as line terminator
             # 'line_terminator' should not change inner element
-            expected_crlf = (
-                b"int,str_lf\r\n" b"1,abc\r\n" b'2,"d\nef"\r\n' b'3,"g\nh\n\ni"\r\n'
-            )
+            expected_crlf = b'int,str_lf\r\n1,abc\r\n2,"d\nef"\r\n3,"g\nh\n\ni"\r\n'
             df.to_csv(path, line_terminator="\r\n", index=False)
             with open(path, "rb") as f:
                 assert f.read() == expected_crlf
@@ -412,9 +410,7 @@ def test_to_csv_string_with_crlf(self):
                 assert f.read() == expected_noarg
         with tm.ensure_clean("crlf_test.csv") as path:
             # case 2: LF as line terminator
-            expected_lf = (
-                b"int,str_crlf\n" b"1,abc\n" b'2,"d\r\nef"\n' b'3,"g\r\nh\r\n\r\ni"\n'
-            )
+            expected_lf = b'int,str_crlf\n1,abc\n2,"d\r\nef"\n3,"g\r\nh\r\n\r\ni"\n'
             df.to_csv(path, line_terminator="\n", index=False)
             with open(path, "rb") as f:
                 assert f.read() == expected_lf

pandas/tests/io/json/test_pandas.py

@@ -1244,7 +1244,7 @@ def test_to_jsonl(self):
         # GH15096: escaped characters in columns and data
         df = DataFrame([["foo\\", "bar"], ['foo"', "bar"]], columns=["a\\", "b"])
         result = df.to_json(orient="records", lines=True)
-        expected = '{"a\\\\":"foo\\\\","b":"bar"}\n' '{"a\\\\":"foo\\"","b":"bar"}'
+        expected = '{"a\\\\":"foo\\\\","b":"bar"}\n{"a\\\\":"foo\\"","b":"bar"}'
         assert result == expected
         tm.assert_frame_equal(pd.read_json(result, lines=True), df)
 

pandas/tests/io/json/test_readlines.py

@@ -56,7 +56,7 @@ def test_to_jsonl():
     # GH15096: escaped characters in columns and data
     df = DataFrame([["foo\\", "bar"], ['foo"', "bar"]], columns=["a\\", "b"])
     result = df.to_json(orient="records", lines=True)
-    expected = '{"a\\\\":"foo\\\\","b":"bar"}\n' '{"a\\\\":"foo\\"","b":"bar"}'
+    expected = '{"a\\\\":"foo\\\\","b":"bar"}\n{"a\\\\":"foo\\"","b":"bar"}'
     assert result == expected
     tm.assert_frame_equal(read_json(result, lines=True), df)
 

pandas/tests/io/json/test_ujson.py

@@ -111,9 +111,9 @@ def test_encode_decimal(self):
     @pytest.mark.parametrize("ensure_ascii", [True, False])
     def test_encode_string_conversion(self, ensure_ascii):
         string_input = "A string \\ / \b \f \n \r \t </script> &"
-        not_html_encoded = '"A string \\\\ \\/ \\b \\f \\n ' '\\r \\t <\\/script> &"'
+        not_html_encoded = '"A string \\\\ \\/ \\b \\f \\n \\r \\t <\\/script> &"'
         html_encoded = (
-            '"A string \\\\ \\/ \\b \\f \\n \\r \\t ' '\\u003c\\/script\\u003e \\u0026"'
+            '"A string \\\\ \\/ \\b \\f \\n \\r \\t \\u003c\\/script\\u003e \\u0026"'
         )
 
         def helper(expected_output, **encode_kwargs):
@@ -816,7 +816,7 @@ def test_array_numpy_labelled(self):
 
         # see gh-10837: write out the dump explicitly
         # so there is no dependency on iteration order
-        input_dumps = '[{"a": 42, "b":31}, {"a": 24, "c": 99}, ' '{"a": 2.4, "b": 78}]'
+        input_dumps = '[{"a": 42, "b":31}, {"a": 24, "c": 99}, {"a": 2.4, "b": 78}]'
         output = ujson.loads(input_dumps, numpy=True, labelled=True)
         expected_vals = np.array([42, 31, 24, 99, 2.4, 78], dtype=int).reshape((3, 2))
         assert (expected_vals == output[0]).all()

pandas/tests/io/parser/test_common.py

@@ -1144,9 +1144,8 @@ def test_escapechar(all_parsers):
         StringIO(data), escapechar="\\", quotechar='"', encoding="utf-8"
     )
 
-    assert result["SEARCH_TERM"][2] == (
-        'SLAGBORD, "Bergslagen", ' "IKEA:s 1700-tals serie"
-    )
+    assert result["SEARCH_TERM"][2] == 'SLAGBORD, "Bergslagen", IKEA:s 1700-tals serie'
+
     tm.assert_index_equal(result.columns, Index(["SEARCH_TERM", "ACTUAL_URL"]))
 
 

pandas/tests/io/parser/test_textreader.py

@@ -179,7 +179,7 @@ def test_header_not_enough_lines(self):
         assert_array_dicts_equal(recs, expected)
 
     def test_escapechar(self):
-        data = '\\"hello world"\n' '\\"hello world"\n' '\\"hello world"'
+        data = '\\"hello world"\n\\"hello world"\n\\"hello world"'
 
         reader = TextReader(StringIO(data), delimiter=",", header=None, escapechar="\\")
         result = reader.read()

pandas/tests/io/pytables/test_store.py

@@ -3214,7 +3214,7 @@ def test_frame_select_complex(self, setup_path):
             tm.assert_frame_equal(result, expected)
 
             result = store.select(
-                "df", "(index>df.index[3] & " 'index<=df.index[6]) | string="bar"'
+                "df", '(index>df.index[3] & index<=df.index[6]) | string="bar"'
             )
             expected = df.loc[
                 ((df.index > df.index[3]) & (df.index <= df.index[6]))

pandas/tests/io/test_common.py

@@ -142,9 +142,7 @@ def test_read_non_existant(self, reader, module, error_class, fn_ext):
 
         path = os.path.join(HERE, "data", "does_not_exist." + fn_ext)
         msg1 = r"File (b')?.+does_not_exist\.{}'? does not exist".format(fn_ext)
-        msg2 = (
-            r"\[Errno 2\] No such file or directory: '.+does_not_exist" r"\.{}'"
-        ).format(fn_ext)
+        msg2 = fr"\[Errno 2\] No such file or directory: '.+does_not_exist\.{fn_ext}'"
         msg3 = "Expected object or value"
         msg4 = "path_or_buf needs to be a string file path or file-like"
         msg5 = (
@@ -180,9 +178,7 @@ def test_read_expands_user_home_dir(
         monkeypatch.setattr(icom, "_expand_user", lambda x: os.path.join("foo", x))
 
         msg1 = r"File (b')?.+does_not_exist\.{}'? does not exist".format(fn_ext)
-        msg2 = (
-            r"\[Errno 2\] No such file or directory:" r" '.+does_not_exist\.{}'"
-        ).format(fn_ext)
+        msg2 = fr"\[Errno 2\] No such file or directory: '.+does_not_exist\.{fn_ext}'"
         msg3 = "Unexpected character found when decoding 'false'"
         msg4 = "path_or_buf needs to be a string file path or file-like"
         msg5 = (

pandas/tests/reshape/merge/test_join.py

@@ -226,9 +226,7 @@ def test_join_on_fails_with_different_right_index(self):
             {"a": np.random.choice(["m", "f"], size=10), "b": np.random.randn(10)},
             index=tm.makeCustomIndex(10, 2),
         )
-        msg = (
-            r"len\(left_on\) must equal the number of levels in the index" ' of "right"'
-        )
+        msg = r'len\(left_on\) must equal the number of levels in the index of "right"'
         with pytest.raises(ValueError, match=msg):
             merge(df, df2, left_on="a", right_index=True)
 
@@ -240,9 +238,7 @@ def test_join_on_fails_with_different_left_index(self):
         df2 = DataFrame(
             {"a": np.random.choice(["m", "f"], size=10), "b": np.random.randn(10)}
         )
-        msg = (
-            r"len\(right_on\) must equal the number of levels in the index" ' of "left"'
-        )
+        msg = r'len\(right_on\) must equal the number of levels in the index of "left"'
         with pytest.raises(ValueError, match=msg):
             merge(df, df2, right_on="b", left_index=True)
 
@@ -737,9 +733,7 @@ def test_join_multi_to_multi(self, join_type):
         )
         tm.assert_frame_equal(expected, result)
 
-        msg = (
-            r"len\(left_on\) must equal the number of levels in the index" ' of "right"'
-        )
+        msg = r'len\(left_on\) must equal the number of levels in the index of "right"'
         with pytest.raises(ValueError, match=msg):
             left.join(right, on="xy", how=join_type)
 

pandas/tests/reshape/merge/test_merge.py

@@ -744,7 +744,7 @@ def test_overlapping_columns_error_message(self):
 
         # #2649, #10639
         df2.columns = ["key1", "foo", "foo"]
-        msg = r"Data columns not unique: Index\(\['foo', 'foo'\]," r" dtype='object'\)"
+        msg = r"Data columns not unique: Index\(\['foo', 'foo'\], dtype='object'\)"
         with pytest.raises(MergeError, match=msg):
             merge(df, df2)
 

pandas/tests/series/test_constructors.py

@@ -773,7 +773,7 @@ def test_constructor_dtype_datetime64(self):
         dts.astype("int64")
 
         # invalid casting
-        msg = r"cannot astype a datetimelike from \[datetime64\[ns\]\] to" r" \[int32\]"
+        msg = r"cannot astype a datetimelike from \[datetime64\[ns\]\] to \[int32\]"
         with pytest.raises(TypeError, match=msg):
             dts.astype("int32")
 
@@ -1198,7 +1198,7 @@ def test_constructor_dtype_timedelta64(self):
         td.astype("int64")
 
         # invalid casting
-        msg = r"cannot astype a timedelta from \[timedelta64\[ns\]\] to" r" \[int32\]"
+        msg = r"cannot astype a timedelta from \[timedelta64\[ns\]\] to \[int32\]"
         with pytest.raises(TypeError, match=msg):
             td.astype("int32")
 

pandas/tests/series/test_dtypes.py

@@ -273,7 +273,7 @@ def test_astype_categorical_to_other(self):
         expected = s
         tm.assert_series_equal(s.astype("category"), expected)
         tm.assert_series_equal(s.astype(CategoricalDtype()), expected)
-        msg = r"could not convert string to float|" r"invalid literal for float\(\)"
+        msg = r"could not convert string to float|invalid literal for float\(\)"
         with pytest.raises(ValueError, match=msg):
             s.astype("float64")
 

pandas/tests/series/test_missing.py

@@ -502,11 +502,11 @@ def test_fillna_int(self):
 
     def test_fillna_raise(self):
         s = Series(np.random.randint(-100, 100, 50))
-        msg = '"value" parameter must be a scalar or dict, but you passed a' ' "list"'
+        msg = '"value" parameter must be a scalar or dict, but you passed a "list"'
         with pytest.raises(TypeError, match=msg):
             s.fillna([1, 2])
 
-        msg = '"value" parameter must be a scalar or dict, but you passed a' ' "tuple"'
+        msg = '"value" parameter must be a scalar or dict, but you passed a "tuple"'
         with pytest.raises(TypeError, match=msg):
             s.fillna((1, 2))
 
@@ -593,11 +593,11 @@ def test_fillna_categorical_raise(self):
         with pytest.raises(ValueError, match="fill value must be in categories"):
             s.fillna({1: "d", 3: "a"})
 
-        msg = '"value" parameter must be a scalar or ' 'dict, but you passed a "list"'
+        msg = '"value" parameter must be a scalar or dict, but you passed a "list"'
         with pytest.raises(TypeError, match=msg):
             s.fillna(["a", "b"])
 
-        msg = '"value" parameter must be a scalar or ' 'dict, but you passed a "tuple"'
+        msg = '"value" parameter must be a scalar or dict, but you passed a "tuple"'
         with pytest.raises(TypeError, match=msg):
             s.fillna(("a", "b"))
 

pandas/tests/tslibs/test_parse_iso8601.py

@@ -59,9 +59,7 @@ def test_parsers_iso8601_invalid(date_str):
 
 def test_parsers_iso8601_invalid_offset_invalid():
     date_str = "2001-01-01 12-34-56"
-    msg = "Timezone hours offset out of range " 'in datetime string "{s}"'.format(
-        s=date_str
-    )
+    msg = f'Timezone hours offset out of range in datetime string "{date_str}"'
 
     with pytest.raises(ValueError, match=msg):
         tslib._test_parse_iso8601(date_str)

pandas/tests/util/test_validate_args_and_kwargs.py

@@ -76,9 +76,7 @@ def test_duplicate_argument():
     kwargs = {"foo": None, "bar": None}
     args = (None,)  # duplicate value for "foo"
 
-    msg = r"{fname}\(\) got multiple values for keyword " r"argument '{arg}'".format(
-        fname=_fname, arg="foo"
-    )
+    msg = fr"{_fname}\(\) got multiple values for keyword argument 'foo'"
 
     with pytest.raises(TypeError, match=msg):
         validate_args_and_kwargs(_fname, args, kwargs, min_fname_arg_count, compat_args)