ruff 0.0.284 (pandas-dev#54548)

* ruff 0.0.284

* fix strict type check

* missing space

Author: twoertwein

.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
     hooks:
       - id: black
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.0.282
+    rev: v0.0.284
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]

pandas/core/arrays/base.py

@@ -479,7 +479,7 @@ def __contains__(self, item: object) -> bool | np.bool_:
             return (item == self).any()  # type: ignore[union-attr]
 
     # error: Signature of "__eq__" incompatible with supertype "object"
-    def __eq__(self, other: Any) -> ArrayLike:  # type: ignore[override]
+    def __eq__(self, other: object) -> ArrayLike:  # type: ignore[override]
         """
         Return for `self == other` (element-wise equality).
         """
@@ -492,11 +492,12 @@ def __eq__(self, other: Any) -> ArrayLike:  # type: ignore[override]
         raise AbstractMethodError(self)
 
     # error: Signature of "__ne__" incompatible with supertype "object"
-    def __ne__(self, other: Any) -> ArrayLike:  # type: ignore[override]
+    def __ne__(self, other: object) -> ArrayLike:  # type: ignore[override]
         """
         Return for `self != other` (element-wise in-equality).
         """
-        return ~(self == other)
+        # error: Unsupported operand type for ~ ("ExtensionArray")
+        return ~(self == other)  # type: ignore[operator]
 
     def to_numpy(
         self,

pandas/core/arrays/string_.py

@@ -574,7 +574,7 @@ def _str_map(
         arr = np.asarray(self)
 
         if is_integer_dtype(dtype) or is_bool_dtype(dtype):
-            constructor: type[IntegerArray] | type[BooleanArray]
+            constructor: type[IntegerArray | BooleanArray]
             if is_integer_dtype(dtype):
                 constructor = IntegerArray
             else:

pandas/core/arrays/string_arrow.py

@@ -262,7 +262,7 @@ def _str_map(
         arr = np.asarray(self)
 
         if is_integer_dtype(dtype) or is_bool_dtype(dtype):
-            constructor: type[IntegerArray] | type[BooleanArray]
+            constructor: type[IntegerArray | BooleanArray]
             if is_integer_dtype(dtype):
                 constructor = IntegerArray
             else:

pandas/core/dtypes/base.py

@@ -110,7 +110,7 @@ class property**.
     def __str__(self) -> str:
         return self.name
 
-    def __eq__(self, other: Any) -> bool:
+    def __eq__(self, other: object) -> bool:
         """
         Check whether 'other' is equal to self.
 
@@ -144,7 +144,7 @@ def __hash__(self) -> int:
         # we need to avoid that and thus use hash function with old behavior
         return object_hash(tuple(getattr(self, attr) for attr in self._metadata))
 
-    def __ne__(self, other: Any) -> bool:
+    def __ne__(self, other: object) -> bool:
         return not self.__eq__(other)
 
     @property
@@ -422,7 +422,7 @@ def __repr__(self) -> str:
     def __str__(self) -> str:
         return self.name
 
-    def __eq__(self, other: Any) -> bool:
+    def __eq__(self, other: object) -> bool:
         if isinstance(other, str) and other == self.name:
             return True
         return super().__eq__(other)

pandas/core/dtypes/dtypes.py

@@ -388,7 +388,7 @@ def __hash__(self) -> int:
         # We *do* want to include the real self.ordered here
         return int(self._hash_categories)
 
-    def __eq__(self, other: Any) -> bool:
+    def __eq__(self, other: object) -> bool:
         """
         Rules for CDT equality:
         1) Any CDT is equal to the string 'category'
@@ -860,7 +860,7 @@ def __hash__(self) -> int:
         # TODO: update this.
         return hash(str(self))
 
-    def __eq__(self, other: Any) -> bool:
+    def __eq__(self, other: object) -> bool:
         if isinstance(other, str):
             if other.startswith("M8["):
                 other = f"datetime64[{other[3:]}"
@@ -1052,13 +1052,13 @@ def name(self) -> str_type:
     def na_value(self) -> NaTType:
         return NaT
 
-    def __eq__(self, other: Any) -> bool:
+    def __eq__(self, other: object) -> bool:
         if isinstance(other, str):
             return other in [self.name, self.name.title()]
 
         return super().__eq__(other)
 
-    def __ne__(self, other: Any) -> bool:
+    def __ne__(self, other: object) -> bool:
         return not self.__eq__(other)
 
     @classmethod
@@ -1301,7 +1301,7 @@ def __hash__(self) -> int:
         # make myself hashable
         return hash(str(self))
 
-    def __eq__(self, other: Any) -> bool:
+    def __eq__(self, other: object) -> bool:
         if isinstance(other, str):
             return other.lower() in (self.name.lower(), str(self).lower())
         elif not isinstance(other, IntervalDtype):
@@ -1647,7 +1647,7 @@ def __hash__(self) -> int:
         # __eq__, so we explicitly do it here.
         return super().__hash__()
 
-    def __eq__(self, other: Any) -> bool:
+    def __eq__(self, other: object) -> bool:
         # We have to override __eq__ to handle NA values in _metadata.
         # The base class does simple == checks, which fail for NA.
         if isinstance(other, str):
@@ -2062,7 +2062,7 @@ def __hash__(self) -> int:
         # make myself hashable
         return hash(str(self))
 
-    def __eq__(self, other: Any) -> bool:
+    def __eq__(self, other: object) -> bool:
         if not isinstance(other, type(self)):
             return super().__eq__(other)
         return self.pyarrow_dtype == other.pyarrow_dtype

pandas/core/frame.py

@@ -3416,7 +3416,7 @@ def to_xml(
 
         lxml = import_optional_dependency("lxml.etree", errors="ignore")
 
-        TreeBuilder: type[EtreeXMLFormatter] | type[LxmlXMLFormatter]
+        TreeBuilder: type[EtreeXMLFormatter | LxmlXMLFormatter]
 
         if parser == "lxml":
             if lxml is not None:

pandas/core/indexes/base.py

@@ -457,7 +457,7 @@ def _can_hold_strings(self) -> bool:
     @property
     def _engine_type(
         self,
-    ) -> type[libindex.IndexEngine] | type[libindex.ExtensionEngine]:
+    ) -> type[libindex.IndexEngine | libindex.ExtensionEngine]:
         return self._engine_types.get(self.dtype, libindex.ObjectEngine)
 
     # whether we support partial string indexing. Overridden
@@ -480,7 +480,7 @@ def __new__(
         copy: bool = False,
         name=None,
         tupleize_cols: bool = True,
-    ) -> Index:
+    ) -> Self:
         from pandas.core.indexes.range import RangeIndex
 
         name = maybe_extract_name(name, data, cls)
@@ -499,7 +499,9 @@ def __new__(
             result = RangeIndex(start=data, copy=copy, name=name)
             if dtype is not None:
                 return result.astype(dtype, copy=False)
-            return result
+            # error: Incompatible return value type (got "MultiIndex",
+            # expected "Self")
+            return result  # type: ignore[return-value]
 
         elif is_ea_or_datetimelike_dtype(dtype):
             # non-EA dtype indexes have special casting logic, so we punt here
@@ -522,7 +524,7 @@ def __new__(
         elif is_scalar(data):
             raise cls._raise_scalar_data_error(data)
         elif hasattr(data, "__array__"):
-            return Index(np.asarray(data), dtype=dtype, copy=copy, name=name)
+            return cls(np.asarray(data), dtype=dtype, copy=copy, name=name)
         elif not is_list_like(data) and not isinstance(data, memoryview):
             # 2022-11-16 the memoryview check is only necessary on some CI
             #  builds, not clear why
@@ -539,7 +541,11 @@ def __new__(
                     # 10697
                     from pandas.core.indexes.multi import MultiIndex
 
-                    return MultiIndex.from_tuples(data, names=name)
+                    # error: Incompatible return value type (got "MultiIndex",
+                    # expected "Self")
+                    return MultiIndex.from_tuples(  # type: ignore[return-value]
+                        data, names=name
+                    )
             # other iterable of some kind
 
             if not isinstance(data, (list, tuple)):

pandas/core/indexes/category.py

@@ -46,6 +46,7 @@
     from pandas._typing import (
         Dtype,
         DtypeObj,
+        Self,
         npt,
     )
 
@@ -210,7 +211,7 @@ def __new__(
         dtype: Dtype | None = None,
         copy: bool = False,
         name: Hashable | None = None,
-    ) -> CategoricalIndex:
+    ) -> Self:
         name = maybe_extract_name(name, data, cls)
 
         if is_scalar(data):

pandas/core/indexes/interval.py

@@ -93,6 +93,7 @@
         Dtype,
         DtypeObj,
         IntervalClosedType,
+        Self,
         npt,
     )
 _index_doc_kwargs = dict(ibase._index_doc_kwargs)
@@ -225,7 +226,7 @@ def __new__(
         copy: bool = False,
         name: Hashable | None = None,
         verify_integrity: bool = True,
-    ) -> IntervalIndex:
+    ) -> Self:
         name = maybe_extract_name(name, data, cls)
 
         with rewrite_exception("IntervalArray", cls.__name__):

pandas/core/indexes/multi.py

@@ -38,6 +38,7 @@
     IgnoreRaise,
     IndexLabel,
     Scalar,
+    Self,
     Shape,
     npt,
 )
@@ -329,7 +330,7 @@ def __new__(
         copy: bool = False,
         name=None,
         verify_integrity: bool = True,
-    ) -> MultiIndex:
+    ) -> Self:
         # compat with Index
         if name is not None:
             names = name

pandas/core/indexes/range.py

@@ -139,12 +139,12 @@ def __new__(
         dtype: Dtype | None = None,
         copy: bool = False,
         name: Hashable | None = None,
-    ) -> RangeIndex:
+    ) -> Self:
         cls._validate_dtype(dtype)
         name = maybe_extract_name(name, start, cls)
 
         # RangeIndex
-        if isinstance(start, RangeIndex):
+        if isinstance(start, cls):
             return start.copy(name=name)
         elif isinstance(start, range):
             return cls._simple_new(start, name=name)

pandas/core/tools/datetimes.py

@@ -133,7 +133,7 @@ class FulldatetimeDict(YearMonthDayDict, total=False):
 def _guess_datetime_format_for_array(arr, dayfirst: bool | None = False) -> str | None:
     # Try to guess the format based on the first non-NaN element, return None if can't
     if (first_non_null := tslib.first_non_null(arr)) != -1:
-        if type(first_non_nan_element := arr[first_non_null]) is str:
+        if type(first_non_nan_element := arr[first_non_null]) is str:  # noqa: E721
             # GH#32264 np.str_ object
             guessed_format = guess_datetime_format(
                 first_non_nan_element, dayfirst=dayfirst

pandas/core/tools/numeric.py

@@ -291,7 +291,7 @@ def to_numeric(
             IntegerArray,
         )
 
-        klass: type[IntegerArray] | type[BooleanArray] | type[FloatingArray]
+        klass: type[IntegerArray | BooleanArray | FloatingArray]
         if is_integer_dtype(data.dtype):
             klass = IntegerArray
         elif is_bool_dtype(data.dtype):

pandas/io/common.py

@@ -30,6 +30,7 @@
 import tarfile
 from typing import (
     IO,
+    TYPE_CHECKING,
     Any,
     AnyStr,
     DefaultDict,
@@ -51,13 +52,7 @@
 
 from pandas._typing import (
     BaseBuffer,
-    CompressionDict,
-    CompressionOptions,
-    FilePath,
-    ReadBuffer,
     ReadCsvBuffer,
-    StorageOptions,
-    WriteBuffer,
 )
 from pandas.compat import (
     get_bz2_file,
@@ -84,6 +79,19 @@
 BaseBufferT = TypeVar("BaseBufferT", bound=BaseBuffer)
 
 
+if TYPE_CHECKING:
+    from types import TracebackType
+
+    from pandas._typing import (
+        CompressionDict,
+        CompressionOptions,
+        FilePath,
+        ReadBuffer,
+        StorageOptions,
+        WriteBuffer,
+    )
+
+
 @dataclasses.dataclass
 class IOArgs:
     """
@@ -138,7 +146,12 @@ def close(self) -> None:
     def __enter__(self) -> IOHandles[AnyStr]:
         return self
 
-    def __exit__(self, *args: Any) -> None:
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc_value: BaseException | None,
+        traceback: TracebackType | None,
+    ) -> None:
         self.close()
 
 

pandas/io/parsers/readers.py

@@ -79,6 +79,7 @@
         HashableT,
         IndexLabel,
         ReadCsvBuffer,
+        Self,
         StorageOptions,
     )
 _doc_read_csv_and_table = (
@@ -1776,7 +1777,7 @@ def get_chunk(self, size: int | None = None) -> DataFrame:
             size = min(size, self.nrows - self._currow)
         return self.read(nrows=size)
 
-    def __enter__(self) -> TextFileReader:
+    def __enter__(self) -> Self:
         return self
 
     def __exit__(

pandas/io/pytables.py

@@ -1731,7 +1731,7 @@ def _create_storer(
         errors: str = "strict",
     ) -> GenericFixed | Table:
         """return a suitable class to operate"""
-        cls: type[GenericFixed] | type[Table]
+        cls: type[GenericFixed | Table]
 
         if value is not None and not isinstance(value, (Series, DataFrame)):
             raise TypeError("value must be None, Series, or DataFrame")
@@ -2119,7 +2119,7 @@ def __repr__(self) -> str:
             ]
         )
 
-    def __eq__(self, other: Any) -> bool:
+    def __eq__(self, other: object) -> bool:
         """compare 2 col items"""
         return all(
             getattr(self, a, None) == getattr(other, a, None)
@@ -2160,7 +2160,7 @@ def convert(
         if self.freq is not None:
             kwargs["freq"] = _ensure_decoded(self.freq)
 
-        factory: type[Index] | type[DatetimeIndex] = Index
+        factory: type[Index | DatetimeIndex] = Index
         if lib.is_np_dtype(values.dtype, "M") or isinstance(
             values.dtype, DatetimeTZDtype
         ):
@@ -2426,7 +2426,7 @@ def __repr__(self) -> str:
             ]
         )
 
-    def __eq__(self, other: Any) -> bool:
+    def __eq__(self, other: object) -> bool:
         """compare 2 col items"""
         return all(
             getattr(self, a, None) == getattr(other, a, None)