Ruff linting - remaining unsafe fixes

Author: evertlammerts

duckdb/experimental/spark/_globals.py

@@ -31,8 +31,6 @@ def foo(arg=pyducdkb.spark._NoValue):
 Note that this approach is taken after from NumPy.
 """
 
-from typing import Type
-
 __ALL__ = ["_NoValue"]
 
 
@@ -59,7 +57,7 @@ class _NoValueType:
     def __new__(cls) -> "_NoValueType":
         # ensure that only one instance exists
         if not cls.__instance:
-            cls.__instance = super(_NoValueType, cls).__new__(cls)
+            cls.__instance = super().__new__(cls)
         return cls.__instance
 
     # Make the _NoValue instance falsey
@@ -69,7 +67,7 @@ def __nonzero__(self) -> bool:
     __bool__ = __nonzero__
 
     # needed for python 2 to preserve identity through a pickle
-    def __reduce__(self) -> tuple[Type, tuple]:
+    def __reduce__(self) -> tuple[type, tuple]:
         return (self.__class__, ())
 
     def __repr__(self) -> str:

duckdb/experimental/spark/_typing.py

@@ -20,7 +20,7 @@
 from typing import Callable, TypeVar, Union
 
 from numpy import float32, float64, int32, int64, ndarray
-from typing_extensions import Literal, Protocol
+from typing_extensions import Literal, Protocol, Self
 
 F = TypeVar("F", bound=Callable)
 T_co = TypeVar("T_co", covariant=True)
@@ -31,7 +31,7 @@
 
 
 class SupportsIAdd(Protocol):
-    def __iadd__(self, other: "SupportsIAdd") -> "SupportsIAdd": ...
+    def __iadd__(self, other: "SupportsIAdd") -> Self: ...
 
 
 class SupportsOrdering(Protocol):

duckdb/experimental/spark/sql/dataframe.py

@@ -16,7 +16,6 @@
 
 from ..errors import PySparkIndexError, PySparkTypeError, PySparkValueError
 from ..exception import ContributionsAcceptedError
-from ._typing import ColumnOrName
 from .column import Column
 from .readwriter import DataFrameWriter
 from .type_utils import duckdb_to_spark_schema
@@ -26,6 +25,7 @@
     import pyarrow as pa
     from pandas.core.frame import DataFrame as PandasDataFrame
 
+    from ._typing import ColumnOrName
     from .group import GroupedData
     from .session import SparkSession
 
@@ -896,7 +896,8 @@ def __getattr__(self, name: str) -> Column:
         [Row(age=2), Row(age=5)]
         """
         if name not in self.relation.columns:
-            raise AttributeError(f"'{self.__class__.__name__}' object has no attribute '{name}'")
+            msg = f"'{self.__class__.__name__}' object has no attribute '{name}'"
+            raise AttributeError(msg)
         return Column(duckdb.ColumnExpression(self.relation.alias, name))
 
     @overload

duckdb/experimental/spark/sql/group.py

@@ -15,16 +15,19 @@
 # limitations under the License.
 #
 
-from typing import Callable, Union, overload
+from typing import TYPE_CHECKING, Callable, Union, overload
 
 from ..exception import ContributionsAcceptedError
-from ._typing import ColumnOrName
 from .column import Column
 from .dataframe import DataFrame
 from .functions import _to_column_expr
-from .session import SparkSession
 from .types import NumericType
 
+# Only import symbols needed for type checking if something is type checking
+if TYPE_CHECKING:
+    from ._typing import ColumnOrName
+    from .session import SparkSession
+
 __all__ = ["GroupedData", "Grouping"]
 
 

duckdb/experimental/spark/sql/types.py

@@ -123,7 +123,7 @@ class DataTypeSingleton(type):
 
     def __call__(cls: type[T]) -> T:  # type: ignore[override]
         if cls not in cls._instances:  # type: ignore[attr-defined]
-            cls._instances[cls] = super(DataTypeSingleton, cls).__call__()  # type: ignore[misc, attr-defined]
+            cls._instances[cls] = super().__call__()  # type: ignore[misc, attr-defined]
         return cls._instances[cls]  # type: ignore[attr-defined]
 
 
@@ -535,7 +535,8 @@ def __init__(self, startField: Optional[int] = None, endField: Optional[int] = N
 
         fields = DayTimeIntervalType._fields
         if startField not in fields or endField not in fields:
-            raise RuntimeError(f"interval {startField} to {endField} is invalid")
+            msg = f"interval {startField} to {endField} is invalid"
+            raise RuntimeError(msg)
         self.startField = cast("int", startField)
         self.endField = cast("int", endField)
 
@@ -917,7 +918,8 @@ def toInternal(self, obj: tuple) -> tuple:  # noqa: D102
                     for n, f, c in zip(self.names, self.fields, self._needConversion)
                 )
             else:
-                raise ValueError(f"Unexpected tuple {obj!r} with StructType")
+                msg = f"Unexpected tuple {obj!r} with StructType"
+                raise ValueError(msg)
         else:
             if isinstance(obj, dict):
                 return tuple(obj.get(n) for n in self.names)
@@ -927,7 +929,8 @@ def toInternal(self, obj: tuple) -> tuple:  # noqa: D102
                 d = obj.__dict__
                 return tuple(d.get(n) for n in self.names)
             else:
-                raise ValueError(f"Unexpected tuple {obj!r} with StructType")
+                msg = f"Unexpected tuple {obj!r} with StructType"
+                raise ValueError(msg)
 
     def fromInternal(self, obj: tuple) -> "Row":  # noqa: D102
         if obj is None:
@@ -1177,23 +1180,24 @@ def __contains__(self, item: Any) -> bool:  # noqa: D105, ANN401
         if hasattr(self, "__fields__"):
             return item in self.__fields__
         else:
-            return super(Row, self).__contains__(item)
+            return super().__contains__(item)
 
     # let object acts like class
     def __call__(self, *args: Any) -> "Row":  # noqa: ANN401
         """Create new Row object."""
         if len(args) > len(self):
-            raise ValueError(f"Can not create Row with fields {self}, expected {len(self):d} values but got {args}")
+            msg = f"Can not create Row with fields {self}, expected {len(self):d} values but got {args}"
+            raise ValueError(msg)
         return _create_row(self, args)
 
     def __getitem__(self, item: Any) -> Any:  # noqa: D105, ANN401
         if isinstance(item, (int, slice)):
-            return super(Row, self).__getitem__(item)
+            return super().__getitem__(item)
         try:
             # it will be slow when it has many fields,
             # but this will not be used in normal cases
             idx = self.__fields__.index(item)
-            return super(Row, self).__getitem__(idx)
+            return super().__getitem__(idx)
         except IndexError:
             raise KeyError(item)  # noqa: B904
         except ValueError:

duckdb/query_graph/__main__.py

@@ -1,7 +1,6 @@
 import argparse  # noqa: D100
 import json
 import re
-import sys
 import webbrowser
 from functools import reduce
 from pathlib import Path
@@ -322,9 +321,6 @@ def translate_json_to_html(input_file: str, output_file: str) -> None:  # noqa:
 
 
 def main() -> None:  # noqa: D103
-    if sys.version_info[0] < 3:
-        print("Please use python3")
-        exit(1)
     parser = argparse.ArgumentParser(
         prog="Query Graph Generator",
         description="""Given a json profile output, generate a html file showing the query graph and

duckdb_packaging/pypi_cleanup.py

@@ -230,7 +230,8 @@ def run(self) -> int:
         elif self._mode == CleanMode.LIST_ONLY:
             logging.info("Running in DRY RUN mode, nothing will be deleted")
         else:
-            raise RuntimeError("Unexpected mode")
+            msg = "Unexpected mode"
+            raise RuntimeError(msg)
 
         logging.info(f"Max development releases to keep per unreleased version: {self._max_dev_releases}")
 

duckdb_packaging/setuptools_scm_version.py

@@ -68,7 +68,8 @@ def _tag_to_version(tag: str) -> str:
 def _bump_dev_version(base_version: str, distance: int) -> str:
     """Bump the given version."""
     if distance == 0:
-        raise ValueError("Dev distance is 0, cannot bump version.")
+        msg = "Dev distance is 0, cannot bump version."
+        raise ValueError(msg)
     major, minor, patch, post, rc = parse_version(base_version)
 
     if post != 0:

tests/extensions/test_httpfs.py

@@ -48,7 +48,7 @@ def test_httpfs(self, require, pandas):
             if str(e).startswith("HTTP HEAD error") or str(e).startswith("Unable to connect"):
                 return
             else:
-                raise e
+                raise
 
         result_df = connection.fetchdf()
         exp_result = pandas.DataFrame(

tests/fast/adbc/test_adbc.py

@@ -1,18 +1,11 @@
 import datetime
-import sys
 from pathlib import Path
 
 import numpy as np
 import pytest
 
 import duckdb
 
-if sys.version_info < (3, 9):
-    pytest.skip(
-        "Python Version must be higher or equal to 3.9 to run this test",
-        allow_module_level=True,
-    )
-
 adbc_driver_manager = pytest.importorskip("adbc_driver_manager.dbapi")
 adbc_driver_manager_lib = pytest.importorskip("adbc_driver_manager._lib")