STYLE: replace unwanted-patterns-strings-to-concatenate with ruff (#51613)

natmokval · web-flow · commit 29140d44f9e9 · 2023-02-27T10:27:59.000-05:00
* STYLE: replace unwanted-patterns-strings-to-concatenate with ruff

* STYLE: replace unwanted-patterns-strings-to-concatenate with ruff II
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -342,11 +342,6 @@ repos:
             (?x)
             ^(asv_bench|pandas/tests|doc)/
             |scripts/validate_min_versions_in_sync\.py$
-    -   id: unwanted-patterns-strings-to-concatenate
-        name: Check for use of not concatenated strings
-        language: python
-        entry: python scripts/validate_unwanted_patterns.py --validation-type="strings_to_concatenate"
-        types_or: [python, cython]
     -   id: unwanted-patterns-strings-with-misplaced-whitespace
         name: Check for strings with misplaced spaces
         language: python
diff --git a/asv_bench/benchmarks/io/csv.py b/asv_bench/benchmarks/io/csv.py
@@ -318,7 +318,7 @@ def setup(self, sep, decimal, float_precision):
             "".join([random.choice(string.digits) for _ in range(28)])
             for _ in range(15)
         ]
-        rows = sep.join([f"0{decimal}" + "{}"] * 3) + "\n"
+        rows = sep.join([f"0{decimal}{{}}"] * 3) + "\n"
         data = rows * 5
         data = data.format(*floats) * 200  # 1000 x 3 strings csv
         self.StringIO_input = StringIO(data)
diff --git a/pandas/io/formats/style.py b/pandas/io/formats/style.py
@@ -3658,7 +3658,7 @@ def css(rgba, text_only) -> str:
                 text_color = "#f1f1f1" if dark else "#000000"
                 return (
                     f"background-color: {_matplotlib.colors.rgb2hex(rgba)};"
-                    + f"color: {text_color};"
+                    f"color: {text_color};"
                 )
             else:
                 return f"color: {_matplotlib.colors.rgb2hex(rgba)};"
diff --git a/pandas/io/sas/sas_constants.py b/pandas/io/sas/sas_constants.py
@@ -4,9 +4,9 @@
 
 magic: Final = (
     b"\x00\x00\x00\x00\x00\x00\x00\x00"
-    + b"\x00\x00\x00\x00\xc2\xea\x81\x60"
-    + b"\xb3\x14\x11\xcf\xbd\x92\x08\x00"
-    + b"\x09\xc7\x31\x8c\x18\x1f\x10\x11"
+    b"\x00\x00\x00\x00\xc2\xea\x81\x60"
+    b"\xb3\x14\x11\xcf\xbd\x92\x08\x00"
+    b"\x09\xc7\x31\x8c\x18\x1f\x10\x11"
 )
 
 align_1_checker_value: Final = b"3"
diff --git a/pandas/tests/groupby/test_raises.py b/pandas/tests/groupby/test_raises.py
@@ -342,25 +342,25 @@ def test_groupby_raises_category(
         "cummax": (
             (NotImplementedError, TypeError),
             "(category type does not support cummax operations|"
-            + "category dtype not supported|"
-            + "cummax is not supported for category dtype)",
+            "category dtype not supported|"
+            "cummax is not supported for category dtype)",
         ),
         "cummin": (
             (NotImplementedError, TypeError),
             "(category type does not support cummin operations|"
-            + "category dtype not supported|"
+            "category dtype not supported|"
             "cummin is not supported for category dtype)",
         ),
         "cumprod": (
             (NotImplementedError, TypeError),
             "(category type does not support cumprod operations|"
-            + "category dtype not supported|"
+            "category dtype not supported|"
             "cumprod is not supported for category dtype)",
         ),
         "cumsum": (
             (NotImplementedError, TypeError),
             "(category type does not support cumsum operations|"
-            + "category dtype not supported|"
+            "category dtype not supported|"
             "cumsum is not supported for category dtype)",
         ),
         "diff": (
@@ -371,7 +371,7 @@ def test_groupby_raises_category(
         "fillna": (
             TypeError,
             r"Cannot setitem on a Categorical with a new category \(0\), "
-            + "set the categories first",
+            "set the categories first",
         )
         if not using_copy_on_write
         else (None, ""),  # no-op with CoW
@@ -539,33 +539,33 @@ def test_groupby_raises_category_on_category(
         "cummax": (
             (NotImplementedError, TypeError),
             "(cummax is not supported for category dtype|"
-            + "category dtype not supported|"
-            + "category type does not support cummax operations)",
+            "category dtype not supported|"
+            "category type does not support cummax operations)",
         ),
         "cummin": (
             (NotImplementedError, TypeError),
             "(cummin is not supported for category dtype|"
-            + "category dtype not supported|"
+            "category dtype not supported|"
             "category type does not support cummin operations)",
         ),
         "cumprod": (
             (NotImplementedError, TypeError),
             "(cumprod is not supported for category dtype|"
-            + "category dtype not supported|"
+            "category dtype not supported|"
             "category type does not support cumprod operations)",
         ),
         "cumsum": (
             (NotImplementedError, TypeError),
             "(cumsum is not supported for category dtype|"
-            + "category dtype not supported|"
-            + "category type does not support cumsum operations)",
+            "category dtype not supported|"
+            "category type does not support cumsum operations)",
         ),
         "diff": (TypeError, "unsupported operand type"),
         "ffill": (None, ""),
         "fillna": (
             TypeError,
             r"Cannot setitem on a Categorical with a new category \(0\), "
-            + "set the categories first",
+            "set the categories first",
         )
         if not using_copy_on_write
         else (None, ""),  # no-op with CoW
diff --git a/pandas/tests/io/excel/test_readers.py b/pandas/tests/io/excel/test_readers.py
@@ -341,7 +341,8 @@ def test_index_col_with_unnamed(self, read_ext, index_col):
     def test_usecols_pass_non_existent_column(self, read_ext):
         msg = (
             "Usecols do not match columns, "
-            "columns expected but not found: " + r"\['E'\]"
+            "columns expected but not found: "
+            r"\['E'\]"
         )
 
         with pytest.raises(ValueError, match=msg):
diff --git a/pandas/tests/io/formats/test_css.py b/pandas/tests/io/formats/test_css.py
@@ -193,7 +193,7 @@ def test_css_border_shorthands(prop, expected):
             "margin: 1px; margin-top: 2px",
             "",
             "margin-left: 1px; margin-right: 1px; "
-            + "margin-bottom: 1px; margin-top: 2px",
+            "margin-bottom: 1px; margin-top: 2px",
         ),
         ("margin-top: 2px", "margin: 1px", "margin: 1px; margin-top: 2px"),
         ("margin: 1px", "margin-top: 2px", "margin: 1px"),
diff --git a/pandas/tests/io/formats/test_format.py b/pandas/tests/io/formats/test_format.py
@@ -2160,18 +2160,18 @@ def test_freq_name_separation(self):
     def test_to_string_mixed(self):
         s = Series(["foo", np.nan, -1.23, 4.56])
         result = s.to_string()
-        expected = "0     foo\n" + "1     NaN\n" + "2   -1.23\n" + "3    4.56"
+        expected = "".join(["0     foo\n", "1     NaN\n", "2   -1.23\n", "3    4.56"])
         assert result == expected
 
         # but don't count NAs as floats
         s = Series(["foo", np.nan, "bar", "baz"])
         result = s.to_string()
-        expected = "0    foo\n" + "1    NaN\n" + "2    bar\n" + "3    baz"
+        expected = "".join(["0    foo\n", "1    NaN\n", "2    bar\n", "3    baz"])
         assert result == expected
 
         s = Series(["foo", 5, "bar", "baz"])
         result = s.to_string()
-        expected = "0    foo\n" + "1      5\n" + "2    bar\n" + "3    baz"
+        expected = "".join(["0    foo\n", "1      5\n", "2    bar\n", "3    baz"])
         assert result == expected
 
     def test_to_string_float_na_spacing(self):
@@ -2181,18 +2181,18 @@ def test_to_string_float_na_spacing(self):
         result = s.to_string()
         expected = (
             "0       NaN\n"
-            + "1    1.5678\n"
-            + "2       NaN\n"
-            + "3   -3.0000\n"
-            + "4       NaN"
+            "1    1.5678\n"
+            "2       NaN\n"
+            "3   -3.0000\n"
+            "4       NaN"
         )
         assert result == expected
 
     def test_to_string_without_index(self):
         # GH 11729 Test index=False option
         s = Series([1, 2, 3, 4])
         result = s.to_string(index=False)
-        expected = "1\n" + "2\n" + "3\n" + "4"
+        expected = "\n".join(["1", "2", "3", "4"])
         assert result == expected
 
     def test_unicode_name_in_footer(self):
@@ -2823,7 +2823,9 @@ def dtype(self):
 
         series = Series(ExtTypeStub())
         res = repr(series)  # This line crashed before #33770 was fixed.
-        expected = "0    [False  True]\n" + "1    [ True False]\n" + "dtype: DtypeStub"
+        expected = "\n".join(
+            ["0    [False  True]", "1    [ True False]", "dtype: DtypeStub"]
+        )
         assert res == expected
 
 
diff --git a/pandas/tests/io/json/test_normalize.py b/pandas/tests/io/json/test_normalize.py
@@ -397,7 +397,7 @@ def test_record_prefix(self, state_data):
     def test_non_ascii_key(self):
         testjson = (
             b'[{"\xc3\x9cnic\xc3\xb8de":0,"sub":{"A":1, "B":2}},'
-            + b'{"\xc3\x9cnic\xc3\xb8de":1,"sub":{"A":3, "B":4}}]'
+            b'{"\xc3\x9cnic\xc3\xb8de":1,"sub":{"A":3, "B":4}}]'
         ).decode("utf8")
 
         testdata = {
diff --git a/pandas/tests/io/parser/conftest.py b/pandas/tests/io/parser/conftest.py
@@ -189,7 +189,7 @@ def all_parsers_all_precisions(request):
 _encoding_prefixes = ["utf", "UTF"]
 
 _encoding_fmts = [
-    f"{prefix}{sep}" + "{0}" for sep in _encoding_seps for prefix in _encoding_prefixes
+    f"{prefix}{sep}{{0}}" for sep in _encoding_seps for prefix in _encoding_prefixes
 ]
 
 
diff --git a/pandas/tests/io/parser/test_network.py b/pandas/tests/io/parser/test_network.py
@@ -66,7 +66,7 @@ def test_url_encoding_csv():
     """
     path = (
         "https://raw.githubusercontent.com/pandas-dev/pandas/main/"
-        + "pandas/tests/io/parser/data/unicode_series.csv"
+        "pandas/tests/io/parser/data/unicode_series.csv"
     )
     df = read_csv(path, encoding="latin-1", header=None)
     assert df.loc[15, 1] == "Á köldum klaka (Cold Fever) (1994)"
diff --git a/pandas/tests/io/test_sql.py b/pandas/tests/io/test_sql.py
@@ -2921,7 +2921,7 @@ def test_datetime_time(self, tz_aware):
     def _get_index_columns(self, tbl_name):
         ixs = sql.read_sql_query(
             "SELECT * FROM sqlite_master WHERE type = 'index' "
-            + f"AND tbl_name = '{tbl_name}'",
+            f"AND tbl_name = '{tbl_name}'",
             self.conn,
         )
         ix_cols = []
diff --git a/pandas/tests/series/test_repr.py b/pandas/tests/series/test_repr.py
@@ -290,25 +290,26 @@ def test_categorical_repr(self):
         a = Series(Categorical([1, 2, 3, 4]))
         exp = (
             "0    1\n1    2\n2    3\n3    4\n"
-            + "dtype: category\nCategories (4, int64): [1, 2, 3, 4]"
+            "dtype: category\nCategories (4, int64): [1, 2, 3, 4]"
         )
 
         assert exp == a.__str__()
 
         a = Series(Categorical(["a", "b"] * 25))
         exp = (
             "0     a\n1     b\n"
-            + "     ..\n"
-            + "48    a\n49    b\n"
-            + "Length: 50, dtype: category\nCategories (2, object): ['a', 'b']"
+            "     ..\n"
+            "48    a\n49    b\n"
+            "Length: 50, dtype: category\nCategories (2, object): ['a', 'b']"
         )
         with option_context("display.max_rows", 5):
             assert exp == repr(a)
 
         levs = list("abcdefghijklmnopqrstuvwxyz")
         a = Series(Categorical(["a", "b"], categories=levs, ordered=True))
         exp = (
-            "0    a\n1    b\n" + "dtype: category\n"
+            "0    a\n1    b\n"
+            "dtype: category\n"
             "Categories (26, object): ['a' < 'b' < 'c' < 'd' ... 'w' < 'x' < 'y' < 'z']"
         )
         assert exp == a.__str__()
diff --git a/pyproject.toml b/pyproject.toml
@@ -216,6 +216,8 @@ select = [
   "PIE",
   # tidy imports
   "TID",
+  # implicit string concatenation
+  "ISC",
 ]
 
 ignore = [
diff --git a/scripts/tests/test_validate_unwanted_patterns.py b/scripts/tests/test_validate_unwanted_patterns.py
@@ -153,48 +153,6 @@ def test_pytest_raises_raises(self, data, expected):
         assert result == expected
 
 
-@pytest.mark.parametrize(
-    "data, expected",
-    [
-        (
-            'msg = ("bar " "baz")',
-            [
-                (
-                    1,
-                    (
-                        "String unnecessarily split in two by black. "
-                        "Please merge them manually."
-                    ),
-                )
-            ],
-        ),
-        (
-            'msg = ("foo " "bar " "baz")',
-            [
-                (
-                    1,
-                    (
-                        "String unnecessarily split in two by black. "
-                        "Please merge them manually."
-                    ),
-                ),
-                (
-                    1,
-                    (
-                        "String unnecessarily split in two by black. "
-                        "Please merge them manually."
-                    ),
-                ),
-            ],
-        ),
-    ],
-)
-def test_strings_to_concatenate(data, expected):
-    fd = io.StringIO(data.strip())
-    result = list(validate_unwanted_patterns.strings_to_concatenate(fd))
-    assert result == expected
-
-
 class TestStringsWithWrongPlacedWhitespace:
     @pytest.mark.parametrize(
         "data",
diff --git a/scripts/validate_unwanted_patterns.py b/scripts/validate_unwanted_patterns.py
@@ -232,55 +232,6 @@ def private_import_across_module(file_obj: IO[str]) -> Iterable[Tuple[int, str]]
                 yield (node.lineno, f"Import of internal function {repr(module_name)}")
 
 
-def strings_to_concatenate(file_obj: IO[str]) -> Iterable[Tuple[int, str]]:
-    """
-    This test case is necessary after 'Black' (https://github.com/psf/black),
-    is formatting strings over multiple lines.
-
-    For example, when this:
-
-    >>> foo = (
-    ...     "bar "
-    ...     "baz"
-    ... )
-
-    Is becoming this:
-
-    >>> foo = ("bar " "baz")
-
-    'Black' is not considering this as an
-    issue (see https://github.com/psf/black/issues/1051),
-    so we are checking it here instead.
-
-    Parameters
-    ----------
-    file_obj : IO
-        File-like object containing the Python code to validate.
-
-    Yields
-    ------
-    line_number : int
-        Line number of unconcatenated string.
-    msg : str
-        Explanation of the error.
-
-    Notes
-    -----
-    GH #30454
-    """
-    tokens: List = list(tokenize.generate_tokens(file_obj.readline))
-
-    for current_token, next_token in zip(tokens, tokens[1:]):
-        if current_token.type == next_token.type == token.STRING:
-            yield (
-                current_token.start[0],
-                (
-                    "String unnecessarily split in two by black. "
-                    "Please merge them manually."
-                ),
-            )
-
-
 def strings_with_wrong_placed_whitespace(
     file_obj: IO[str],
 ) -> Iterable[Tuple[int, str]]:
@@ -457,7 +408,6 @@ def main(
         "bare_pytest_raises",
         "private_function_across_module",
         "private_import_across_module",
-        "strings_to_concatenate",
         "strings_with_wrong_placed_whitespace",
     ]
 

Original file line number	Diff line number	Diff line change
`@@ -318,7 +318,7 @@ def setup(self, sep, decimal, float_precision):`
`318`	`318`	`"".join([random.choice(string.digits) for _ in range(28)])`
`319`	`319`	`for _ in range(15)`
`320`	`320`	`]`
`321`		`- rows = sep.join([f"0{decimal}" + "{}"] * 3) + "\n"`
	`321`	`+ rows = sep.join([f"0{decimal}{{}}"] * 3) + "\n"`
`322`	`322`	`data = rows * 5`
`323`	`323`	`data = data.format(floats) 200 # 1000 x 3 strings csv`
`324`	`324`	`self.StringIO_input = StringIO(data)`
Original file line number	Diff line number	Diff line change
`@@ -3658,7 +3658,7 @@ def css(rgba, text_only) -> str:`
`3658`	`3658`	`text_color = "#f1f1f1" if dark else "#000000"`
`3659`	`3659`	`return (`
`3660`	`3660`	`f"background-color: {_matplotlib.colors.rgb2hex(rgba)};"`
`3661`		`- + f"color: {text_color};"`
	`3661`	`+ f"color: {text_color};"`
`3662`	`3662`	`)`
`3663`	`3663`	`else:`
`3664`	`3664`	`return f"color: {_matplotlib.colors.rgb2hex(rgba)};"`
Original file line number	Diff line number	Diff line change
`@@ -341,7 +341,8 @@ def test_index_col_with_unnamed(self, read_ext, index_col):`
`341`	`341`	`def test_usecols_pass_non_existent_column(self, read_ext):`
`342`	`342`	`msg = (`
`343`	`343`	`"Usecols do not match columns, "`
`344`		`- "columns expected but not found: " + r"\['E'\]"`
	`344`	`+ "columns expected but not found: "`
	`345`	`+ r"\['E'\]"`
`345`	`346`	`)`
`346`	`347`
`347`	`348`	`with pytest.raises(ValueError, match=msg):`
Original file line number	Diff line number	Diff line change
`@@ -189,7 +189,7 @@ def all_parsers_all_precisions(request):`
`189`	`189`	`_encoding_prefixes = ["utf", "UTF"]`
`190`	`190`
`191`	`191`	`_encoding_fmts = [`
`192`		`- f"{prefix}{sep}" + "{0}" for sep in _encoding_seps for prefix in _encoding_prefixes`
	`192`	`+ f"{prefix}{sep}{{0}}" for sep in _encoding_seps for prefix in _encoding_prefixes`
`193`	`193`	`]`
`194`	`194`
`195`	`195`