Ruff C416: use list() instead of comprehension where possible

Author: evertlammerts

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] + [status for status in 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

tests/fast/arrow/test_arrow_list.py

@@ -46,7 +46,7 @@ def __init__(self, list, list_view) -> None:
 
 
 def generate_list(child_size) -> ListGenerationResult:
-    input = [i for i in range(child_size)]
+    input = list(range(child_size))
     offsets = []
     sizes = []
     lists = []

tests/fast/arrow/test_arrow_offsets.py

@@ -140,7 +140,7 @@ def test_struct_of_bools(self, duckdb_cursor, col1_null, col2_null):
     )
     @null_test_parameters()
     def test_struct_of_dates(self, duckdb_cursor, constructor, expected, col1_null, col2_null):
-        tuples = [i for i in range(MAGIC_ARRAY_SIZE)]
+        tuples = list(range(MAGIC_ARRAY_SIZE))
 
         col1 = tuples
         if col1_null:
@@ -230,7 +230,7 @@ def test_struct_of_time(self, duckdb_cursor, constructor, unit, expected, col1_n
             # TODO: We limit the size because we don't support time values > 24 hours  # noqa: TD002, TD003
             size = 86400  # The amount of seconds in a day
 
-        col1 = [i for i in range(size)]
+        col1 = list(range(size))
         if col1_null:
             col1[-1] = None
         # "a" in the struct matches the value for col1
@@ -300,7 +300,7 @@ def test_struct_of_interval(self, duckdb_cursor, constructor, expected, converte
     def test_struct_of_duration(self, duckdb_cursor, constructor, unit, expected, col1_null, col2_null):
         size = MAGIC_ARRAY_SIZE
 
-        col1 = [i for i in range(size)]
+        col1 = list(range(size))
         if col1_null:
             col1[-1] = None
         # "a" in the struct matches the value for col1
@@ -336,7 +336,7 @@ def test_struct_of_timestamp_tz(self, duckdb_cursor, constructor, unit, expected
         size = MAGIC_ARRAY_SIZE
 
         duckdb_cursor.execute("set timezone='UTC'")
-        col1 = [i for i in range(size)]
+        col1 = list(range(size))
         if col1_null:
             col1[-1] = None
         # "a" in the struct matches the value for col1
@@ -549,7 +549,7 @@ def test_struct_of_list_of_blobs(self, duckdb_cursor, col1_null, col2_null):
 
     @null_test_parameters()
     def test_struct_of_list_of_list(self, duckdb_cursor, col1_null, col2_null):
-        col1 = [i for i in range(MAGIC_ARRAY_SIZE)]
+        col1 = list(range(MAGIC_ARRAY_SIZE))
         if col1_null:
             col1[-1] = None
         # "a" in the struct matches the value for col1

tests/fast/arrow/test_arrow_recordbatchreader.py

@@ -26,7 +26,7 @@ def test_parallel_reader(self, duckdb_cursor):
             format="parquet",
         )
 
-        batches = [r for r in userdata_parquet_dataset.to_batches()]
+        batches = list(userdata_parquet_dataset.to_batches())
         reader = pyarrow.dataset.Scanner.from_batches(batches, schema=userdata_parquet_dataset.schema).to_reader()
 
         rel = duckdb_conn.from_arrow(reader)
@@ -52,7 +52,7 @@ def test_parallel_reader_replacement_scans(self, duckdb_cursor):
             format="parquet",
         )
 
-        batches = [r for r in userdata_parquet_dataset.to_batches()]
+        batches = list(userdata_parquet_dataset.to_batches())
         reader = pyarrow.dataset.Scanner.from_batches(batches, schema=userdata_parquet_dataset.schema).to_reader()  # noqa: F841
 
         assert (
@@ -83,7 +83,7 @@ def test_parallel_reader_register(self, duckdb_cursor):
             format="parquet",
         )
 
-        batches = [r for r in userdata_parquet_dataset.to_batches()]
+        batches = list(userdata_parquet_dataset.to_batches())
         reader = pyarrow.dataset.Scanner.from_batches(batches, schema=userdata_parquet_dataset.schema).to_reader()
 
         duckdb_conn.register("bla", reader)
@@ -109,7 +109,7 @@ def test_parallel_reader_default_conn(self, duckdb_cursor):
             format="parquet",
         )
 
-        batches = [r for r in userdata_parquet_dataset.to_batches()]
+        batches = list(userdata_parquet_dataset.to_batches())
         reader = pyarrow.dataset.Scanner.from_batches(batches, schema=userdata_parquet_dataset.schema).to_reader()
 
         rel = duckdb.from_arrow(reader)

tests/fast/arrow/test_arrow_run_end_encoding.py

@@ -307,7 +307,7 @@ def test_arrow_ree_struct(self, duckdb_cursor):
         iterables = [x.iterchunks() for x in columns]
         zipped = zip(*iterables)
 
-        structured_chunks = [pa.StructArray.from_arrays([y for y in x], names=names) for x in zipped]
+        structured_chunks = [pa.StructArray.from_arrays(list(x), names=names) for x in zipped]
         structured = pa.chunked_array(structured_chunks)
 
         arrow_tbl = pa.Table.from_arrays([structured], names=["ree"])  # noqa: F841
@@ -453,7 +453,7 @@ def test_arrow_ree_dictionary(self, duckdb_cursor):
         for chunk in columns[0].iterchunks():
             ree = chunk
             chunk_length = len(ree)
-            offsets = [i for i in reversed(range(chunk_length))]
+            offsets = list(reversed(range(chunk_length)))
 
             new_array = pa.DictionaryArray.from_arrays(indices=offsets, dictionary=ree)
             structured_chunks.append(new_array)

tests/fast/pandas/test_df_analyze.py

@@ -68,7 +68,7 @@ def test_reset_analyze_sample_setting(self, duckdb_cursor):
     @pytest.mark.parametrize("pandas", [NumpyPandas(), ArrowPandas()])
     def test_10750(self, duckdb_cursor, pandas):
         max_row_number = 2000
-        data = {"id": [i for i in range(max_row_number + 1)], "content": [None for _ in range(max_row_number + 1)]}
+        data = {"id": list(range(max_row_number + 1)), "content": [None for _ in range(max_row_number + 1)]}
 
         pdf = pandas.DataFrame(data=data)
         duckdb_cursor.register("content", pdf)

tests/fast/pandas/test_pandas_na.py

@@ -41,7 +41,7 @@ def test_pandas_na(self, duckdb_cursor):
         null_index = 3
         df = pd.DataFrame(pd.Series([3, 1, 2, pd.NA, 8, 6]))  # noqa: F841
         res = duckdb_cursor.execute("select * from df").fetchall()
-        items = [x[0] for x in [y for y in res]]
+        items = [x[0] for x in list(res)]
         assert_nullness(items, [null_index])
 
         # Test if pd.NA behaves the same as np.nan once converted
@@ -84,5 +84,5 @@ def test_pandas_na(self, duckdb_cursor):
         na_string_df = pd.DataFrame({"a": [str(pd.NA), str(pd.NA), pd.NA, str(pd.NA), pd.NA, pd.NA, pd.NA, str(pd.NA)]})  # noqa: F841
         null_indices = [2, 4, 5, 6]
         res = duckdb_cursor.execute("select * from na_string_df").fetchall()
-        items = [x[0] for x in [y for y in res]]
+        items = [x[0] for x in list(res)]
         assert_nullness(items, null_indices)

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] + [status for status in 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