Ruff RUF: fixed all remaining ruff specific linter issues

evertlammerts · evertlammerts · commit 61ba166c58ff · 2025-09-18T16:19:08.000+02:00
diff --git a/duckdb/experimental/spark/exception.py b/duckdb/experimental/spark/exception.py
@@ -1,10 +1,13 @@
+from typing import Optional
+
+
 class ContributionsAcceptedError(NotImplementedError):  # noqa: D100
     """This method is not planned to be implemented, if you would like to implement this method
     or show your interest in this method to other members of the community,
     feel free to open up a PR or a Discussion over on https://github.com/duckdb/duckdb.
     """  # noqa: D205
 
-    def __init__(self, message: str = None) -> None:  # noqa: D107
+    def __init__(self, message: Optional[str] = None) -> None:  # noqa: D107
         doc = self.__class__.__doc__
         if message:
             doc = message + "\n" + doc
diff --git a/duckdb/experimental/spark/sql/types.py b/duckdb/experimental/spark/sql/types.py
@@ -9,6 +9,7 @@
 import time
 from builtins import tuple
 from collections.abc import Iterator
+from types import MappingProxyType
 from typing import (
     Any,
     ClassVar,
@@ -17,7 +18,7 @@
     TypeVar,
     Union,
     cast,
-    overload,
+    overload, Mapping,
 )
 
 import duckdb
@@ -512,14 +513,14 @@ class DayTimeIntervalType(AtomicType):
     MINUTE = 2
     SECOND = 3
 
-    _fields = {
+    _fields: Mapping[str, int] = MappingProxyType({
         DAY: "day",
         HOUR: "hour",
         MINUTE: "minute",
         SECOND: "second",
-    }
+    })
 
-    _inverted_fields = dict(zip(_fields.values(), _fields.keys()))
+    _inverted_fields: Mapping[int, str] = MappingProxyType(dict(zip(_fields.values(), _fields.keys())))
 
     def __init__(self, startField: Optional[int] = None, endField: Optional[int] = None) -> None:  # noqa: D107
         super().__init__(DuckDBPyType("INTERVAL"))
diff --git a/duckdb/query_graph/__main__.py b/duckdb/query_graph/__main__.py
@@ -228,7 +228,7 @@ def generate_timing_html(graph_json: object, query_timings: object) -> object:
     all_phases = query_timings.get_phases()
     query_timings.add_node_timing(NodeTiming("TOTAL TIME", total_time))
     query_timings.add_node_timing(NodeTiming("Execution Time", execution_time))
-    all_phases = ["TOTAL TIME", "Execution Time"] + all_phases
+    all_phases = ["TOTAL TIME", "Execution Time", *all_phases]
     for phase in all_phases:
         summarized_phase = query_timings.get_summary_phase_timings(phase)
         summarized_phase.calculate_percentage(total_time)
diff --git a/duckdb_packaging/pypi_cleanup.py b/duckdb_packaging/pypi_cleanup.py
@@ -122,7 +122,7 @@ def session_with_retries() -> Generator[Session, None, None]:
             connect=3,  # try 3 times before giving up on connection errors
             read=3,  # try 3 times before giving up on read errors
             status=3,  # try 3 times before giving up on status errors (see forcelist below)
-            status_forcelist=[429] + list(range(500, 512)),
+            status_forcelist=[429, *list(range(500, 512))],
             other=0,  # whatever else may cause an error should break
             backoff_factor=0.1,  # [0.0s, 0.2s, 0.4s]
             raise_on_redirect=True,  # raise exception when redirect error retries are exhausted
diff --git a/tests/extensions/json/test_read_json.py b/tests/extensions/json/test_read_json.py
@@ -38,7 +38,7 @@ def test_read_json_sample_size(self):
 
     def test_read_json_format(self):
         # Wrong option
-        with pytest.raises(duckdb.BinderException, match="format must be one of .* not 'test'"):
+        with pytest.raises(duckdb.BinderException, match=r"format must be one of .* not 'test'"):
             rel = duckdb.read_json(TestFile("example.json"), format="test")
 
         rel = duckdb.read_json(TestFile("example.json"), format="unstructured")
diff --git a/tests/fast/adbc/test_statement_bind.py b/tests/fast/adbc/test_statement_bind.py
@@ -51,7 +51,7 @@ def test_bind_multiple_rows(self):
             with pytest.raises(
                 adbc_driver_manager.NotSupportedError, match="Binding multiple rows at once is not supported yet"
             ):
-                res, number_of_rows = statement.execute_query()
+                statement.execute_query()
 
     def test_bind_single_row(self):
         expected_result = pa.array([8], type=pa.int64())
@@ -171,7 +171,7 @@ def test_too_many_parameters(self):
                 adbc_driver_manager.ProgrammingError,
                 match="Input data has more column than prepared statement has parameters",
             ):
-                res, _ = statement.execute_query()
+                statement.execute_query()
 
     def test_not_enough_parameters(self):
         data = pa.record_batch(
@@ -197,4 +197,4 @@ def test_not_enough_parameters(self):
                 adbc_driver_manager.ProgrammingError,
                 match="Values were not provided for the following prepared statement parameters: 2",
             ):
-                res, _ = statement.execute_query()
+                statement.execute_query()
diff --git a/tests/fast/api/test_duckdb_connection.py b/tests/fast/api/test_duckdb_connection.py
@@ -1,3 +1,5 @@
+import re
+
 import pytest
 from conftest import ArrowPandas, NumpyPandas
 
@@ -384,7 +386,7 @@ def test_connect_with_path(self, tmp_database):
         assert con.sql("select 42").fetchall() == [(42,)]
 
         with pytest.raises(
-            duckdb.InvalidInputException, match="Please provide either a str or a pathlib.Path, not <class 'int'>"
+            duckdb.InvalidInputException, match=re.escape("Please provide either a str or a pathlib.Path, not <class 'int'>")
         ):
             con = duckdb.connect(5)
 
diff --git a/tests/fast/api/test_read_csv.py b/tests/fast/api/test_read_csv.py
@@ -128,7 +128,7 @@ def test_quotechar(self, duckdb_cursor):
 
     def test_quote(self, duckdb_cursor):
         with pytest.raises(
-            duckdb.Error, match='The methods read_csv and read_csv_auto do not have the "quote" argument.'
+            duckdb.Error, match='The methods read_csv and read_csv_auto do not have the "quote" argument'
         ):
             duckdb_cursor.read_csv(TestFile("unquote_without_delimiter.csv"), quote="", header=False)
 
@@ -445,8 +445,6 @@ def scoped_objects(duckdb_cursor) -> None:
         assert CountedObject.instance_count == 0
 
     def test_read_csv_glob(self, tmp_path, create_temp_csv):
-        file1_path, file2_path = create_temp_csv
-
         # Use the temporary file paths to read CSV files
         con = duckdb.connect()
         rel = con.read_csv(f"{tmp_path}/file*.csv")  # noqa: F841
diff --git a/tests/fast/api/test_with_propagating_exceptions.py b/tests/fast/api/test_with_propagating_exceptions.py
@@ -6,7 +6,7 @@
 class TestWithPropagatingExceptions:
     def test_with(self):
         # Should propagate exception raised in the 'with duckdb.connect() ..'
-        with pytest.raises(duckdb.ParserException, match="syntax error at or near *"), duckdb.connect() as con:
+        with pytest.raises(duckdb.ParserException, match=r"syntax error at or near *"), duckdb.connect() as con:
             con.execute("invalid")
 
         # Does not raise an exception
diff --git a/tests/fast/arrow/test_arrow_ipc.py b/tests/fast/arrow/test_arrow_ipc.py
@@ -29,6 +29,6 @@ def test_single_buffer(self, duckdb_cursor):
             stream = ipc.MessageReader.open_stream(buf_reader)
             # This fails
             with pytest.raises(
-                duckdb.Error, match="The nanoarrow community extension is needed to read the Arrow IPC protocol."
+                duckdb.Error, match="The nanoarrow community extension is needed to read the Arrow IPC protocol"
             ):
                 duckdb_cursor.from_arrow(stream).fetchall()
diff --git a/tests/fast/arrow/test_large_offsets.py b/tests/fast/arrow/test_large_offsets.py
@@ -16,7 +16,7 @@ def test_large_lists(self, duckdb_cursor):
         with pytest.raises(
             duckdb.InvalidInputException,
             match="Arrow Appender: The maximum combined list offset for regular list buffers is 2147483647 but "
-            "the offset of 2147481000 exceeds this.",
+            "the offset of 2147481000 exceeds this",
         ):
             duckdb_cursor.sql("SELECT col FROM tbl").fetch_arrow_table()
 
@@ -33,7 +33,7 @@ def test_large_maps(self, duckdb_cursor):
         with pytest.raises(
             duckdb.InvalidInputException,
             match="Arrow Appender: The maximum combined list offset for regular list buffers is 2147483647 but the "
-            "offset of 2147481000 exceeds this.",
+            "offset of 2147481000 exceeds this",
         ):
             duckdb_cursor.sql("select map(col, col) from tbl").fetch_arrow_table()
 
diff --git a/tests/fast/pandas/test_df_object_resolution.py b/tests/fast/pandas/test_df_object_resolution.py
@@ -326,13 +326,13 @@ def test_map_value_upgrade(self, pandas, duckdb_cursor):
     @pytest.mark.parametrize("pandas", [NumpyPandas(), ArrowPandas()])
     def test_map_duplicate(self, pandas, duckdb_cursor):
         x = pandas.DataFrame([[{"key": ["a", "a", "b"], "value": [4, 0, 4]}]])
-        with pytest.raises(duckdb.InvalidInputException, match="Map keys must be unique."):
+        with pytest.raises(duckdb.InvalidInputException, match="Map keys must be unique"):
             duckdb_cursor.sql("select * from x").show()
 
     @pytest.mark.parametrize("pandas", [NumpyPandas(), ArrowPandas()])
     def test_map_nullkey(self, pandas, duckdb_cursor):
         x = pandas.DataFrame([[{"key": [None, "a", "b"], "value": [4, 0, 4]}]])
-        with pytest.raises(duckdb.InvalidInputException, match="Map keys can not be NULL."):
+        with pytest.raises(duckdb.InvalidInputException, match="Map keys can not be NULL"):
             converted_col = duckdb_cursor.sql("select * from x").df()
 
     @pytest.mark.parametrize("pandas", [NumpyPandas(), ArrowPandas()])
@@ -345,7 +345,7 @@ def test_map_nullkeylist(self, pandas, duckdb_cursor):
     @pytest.mark.parametrize("pandas", [NumpyPandas(), ArrowPandas()])
     def test_map_fallback_nullkey(self, pandas, duckdb_cursor):
         x = pandas.DataFrame([[{"a": 4, None: 0, "c": 4}], [{"a": 4, None: 0, "d": 4}]])
-        with pytest.raises(duckdb.InvalidInputException, match="Map keys can not be NULL."):
+        with pytest.raises(duckdb.InvalidInputException, match="Map keys can not be NULL"):
             converted_col = duckdb_cursor.sql("select * from x").df()
 
     @pytest.mark.parametrize("pandas", [NumpyPandas(), ArrowPandas()])
@@ -356,7 +356,7 @@ def test_map_fallback_nullkey_coverage(self, pandas, duckdb_cursor):
                 [{"key": None, None: 5}],
             ]
         )
-        with pytest.raises(duckdb.InvalidInputException, match="Map keys can not be NULL."):
+        with pytest.raises(duckdb.InvalidInputException, match="Map keys can not be NULL"):
             converted_col = duckdb_cursor.sql("select * from x").df()
 
     @pytest.mark.parametrize("pandas", [NumpyPandas(), ArrowPandas()])
diff --git a/tests/fast/pandas/test_fetch_nested.py b/tests/fast/pandas/test_fetch_nested.py
@@ -192,7 +192,6 @@ def test_fetch_df_list(self, duckdb_cursor, query, expected):
             ]
         }),
     ])
-    # fmt: on
     def test_struct_df(self, duckdb_cursor, query, expected):
         compare_results(duckdb_cursor, query, expected)
 
@@ -301,7 +300,6 @@ def test_struct_df(self, duckdb_cursor, query, expected):
             ]
         }, "Map keys can not be NULL"),
     ])
-    # fmt: on
     def test_map_df(self, duckdb_cursor, query, expected, expected_error):
         if not expected_error:
             compare_results(duckdb_cursor, query, expected)
@@ -449,6 +447,5 @@ def test_map_df(self, duckdb_cursor, query, expected, expected_error):
             ]
         }),
     ])
-    # fmt: on
     def test_nested_mix(self, duckdb_cursor, query, expected):
         compare_results(duckdb_cursor, query, expected)
diff --git a/tests/fast/pandas/test_pandas_arrow.py b/tests/fast/pandas/test_pandas_arrow.py
@@ -39,7 +39,7 @@ def test_mixed_columns(self):
         pyarrow_df = df.convert_dtypes(dtype_backend="pyarrow")  # noqa: F841
         con = duckdb.connect()
         with pytest.raises(
-            duckdb.InvalidInputException, match="The dataframe could not be converted to a pyarrow.lib.Table"
+            duckdb.InvalidInputException, match="The dataframe could not be converted to a pyarrow\.lib\.Table"
         ):
             res = con.sql("select * from pyarrow_df").fetchall()  # noqa: F841
 
@@ -66,7 +66,7 @@ def test_mixed_columns(self):
         assert isinstance(df.dtypes["python"], np.dtype("O").__class__)
 
         with pytest.raises(
-            duckdb.InvalidInputException, match="The dataframe could not be converted to a pyarrow.lib.Table"
+            duckdb.InvalidInputException, match="The dataframe could not be converted to a pyarrow\.lib\.Table"
         ):
             con.sql("select * from df").fetchall()
 
diff --git a/tests/fast/spark/test_spark_dataframe_sort.py b/tests/fast/spark/test_spark_dataframe_sort.py
@@ -10,7 +10,7 @@
 
 
 class TestDataFrameSort:
-    data = [(56, "Carol"), (20, "Alice"), (3, "Dave"), (3, "Anna"), (1, "Ben")]
+    data = ((56, "Carol"), (20, "Alice"), (3, "Dave"), (3, "Anna"), (1, "Ben"))
 
     def test_sort_ascending(self, spark):
         df = spark.createDataFrame(self.data, ["age", "name"])
diff --git a/tests/fast/test_map.py b/tests/fast/test_map.py
@@ -78,7 +78,7 @@ def return_empty_df(df):
             print(testrel.map(evil3).df())
 
         with pytest.raises(
-            duckdb.InvalidInputException, match="Expected the UDF to return an object of type 'pandas.DataFrame'"
+            duckdb.InvalidInputException, match="Expected the UDF to return an object of type 'pandas\.DataFrame'"
         ):
             print(testrel.map(evil4).df())
 
@@ -96,7 +96,7 @@ def return_empty_df(df):
         testrel.map(return_dataframe).df().equals(pandas.DataFrame({"A": [1]}))
 
         with pytest.raises(
-            duckdb.InvalidInputException, match="UDF returned more than 2048 rows, which is not allowed."
+            duckdb.InvalidInputException, match="UDF returned more than 2048 rows, which is not allowed"
         ):
             testrel.map(return_big_dataframe).df()
 
diff --git a/tests/fast/test_relation.py b/tests/fast/test_relation.py
@@ -485,7 +485,7 @@ def test_fetchnumpy(self):
                 assert len(res["a"]) == size
             assert np.all(res["a"] == np.arange(start, start + size))
 
-        with pytest.raises(duckdb.ConversionException, match="Conversion Error.*out of range.*"):
+        with pytest.raises(duckdb.ConversionException, match=r"Conversion Error.*out of range.*"):
             # invalid conversion of negative integer to UINTEGER
             rel.project("CAST(a as UINTEGER)").fetchnumpy()
 
diff --git a/tests/fast/test_value.py b/tests/fast/test_value.py
@@ -135,7 +135,7 @@ def test_float_to_decimal_prevention(self):
     def test_timestamp_sec_not_supported(self, value):
         con = duckdb.connect()
         with pytest.raises(
-            duckdb.NotImplementedException, match="Conversion from 'datetime' to type .* is not implemented yet"
+            duckdb.NotImplementedException, match=r"Conversion from 'datetime' to type .* is not implemented yet"
         ):
             con.execute("select $1", [value]).fetchall()
 
diff --git a/tests/fast/test_versioning.py b/tests/fast/test_versioning.py
@@ -129,7 +129,7 @@ def test_bump_version_release_branch(self):
     @patch.dict("os.environ", {"MAIN_BRANCH_VERSIONING": "1"})
     def test_bump_version_dirty(self):
         """Test bump_version with dirty working directory."""
-        with pytest.raises(ValueError, match="Dev distance is 0, cannot bump version."):
+        with pytest.raises(ValueError, match="Dev distance is 0, cannot bump version"):
             _bump_dev_version("1.2.3", 0)
 
     @patch.dict("os.environ", {"MAIN_BRANCH_VERSIONING": "1"})
diff --git a/tests/slow/test_h2oai_arrow.py b/tests/slow/test_h2oai_arrow.py
@@ -206,7 +206,7 @@ def arrow_dataset_register():
         connect=3,  # try 3 times before giving up on connection errors
         read=3,  # try 3 times before giving up on read errors
         status=3,  # try 3 times before giving up on status errors (see forcelist below)
-        status_forcelist=[429] + list(range(500, 512)),
+        status_forcelist=[429, *list(range(500, 512))],
         other=0,  # whatever else may cause an error should break
         backoff_factor=0.1,  # [0.0s, 0.2s, 0.4s]
         raise_on_redirect=True,  # raise exception when redirect error retries are exhausted
