Bump pre-commit versions (apache#1344)

Author: Fokko

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ exclude: ^vendor/
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v5.0.0
     hooks:
       - id: trailing-whitespace
       - id: end-of-file-fixer
@@ -29,7 +29,7 @@ repos:
       - id: check-ast
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version (Used for linting)
-    rev: v0.1.8
+    rev: v0.7.4
     hooks:
       - id: ruff
         args: [ --fix, --exit-non-zero-on-fix, --preview ]
@@ -47,7 +47,7 @@ repos:
       - id: pycln
         args: [--config=pyproject.toml]
   - repo: https://github.com/igorshubovych/markdownlint-cli
-    rev: v0.41.0
+    rev: v0.42.0
     hooks:
       - id: markdownlint
         args: ["--fix"]

pyiceberg/catalog/dynamodb.py

@@ -330,7 +330,7 @@ def rename_table(self, from_identifier: Union[str, Identifier], to_identifier: U
                 log_message += f"Rolled back table creation for {to_database_name}.{to_table_name}."
             except (NoSuchTableError, GenericDynamoDbError):
                 log_message += (
-                    f"Failed to roll back table creation for {to_database_name}.{to_table_name}. " f"Please clean up manually"
+                    f"Failed to roll back table creation for {to_database_name}.{to_table_name}. Please clean up manually"
                 )
 
             raise ValueError(log_message) from e
@@ -635,7 +635,7 @@ def _convert_dynamo_table_item_to_iceberg_table(self, dynamo_table_item: Dict[st
 
         if table_type.lower() != ICEBERG:
             raise NoSuchIcebergTableError(
-                f"Property table_type is {table_type}, expected {ICEBERG}: " f"{database_name}.{table_name}"
+                f"Property table_type is {table_type}, expected {ICEBERG}: {database_name}.{table_name}"
             )
 
         io = load_file_io(properties=self.properties, location=metadata_location)

pyiceberg/catalog/glue.py

@@ -611,7 +611,7 @@ def rename_table(self, from_identifier: Union[str, Identifier], to_identifier: U
                 log_message += f"Rolled back table creation for {to_database_name}.{to_table_name}."
             except NoSuchTableError:
                 log_message += (
-                    f"Failed to roll back table creation for {to_database_name}.{to_table_name}. " f"Please clean up manually"
+                    f"Failed to roll back table creation for {to_database_name}.{to_table_name}. Please clean up manually"
                 )
 
             raise ValueError(log_message) from e

pyiceberg/io/pyarrow.py

@@ -2442,7 +2442,7 @@ def write_parquet(task: WriteTask) -> DataFile:
             for batch in task.record_batches
         ]
         arrow_table = pa.Table.from_batches(batches)
-        file_path = f'{table_metadata.location}/data/{task.generate_data_file_path("parquet")}'
+        file_path = f"{table_metadata.location}/data/{task.generate_data_file_path('parquet')}"
         fo = io.new_output(file_path)
         with fo.create(overwrite=True) as fos:
             with pq.ParquetWriter(fos, schema=arrow_table.schema, **parquet_writer_kwargs) as writer:

pyiceberg/table/update/schema.py

@@ -179,7 +179,7 @@ def add_column(
 
         if required and not self._allow_incompatible_changes:
             # Table format version 1 and 2 cannot add required column because there is no initial value
-            raise ValueError(f'Incompatible change: cannot add required column: {".".join(path)}')
+            raise ValueError(f"Incompatible change: cannot add required column: {'.'.join(path)}")
 
         name = path[-1]
         parent = path[:-1]

pyiceberg/typedef.py

@@ -157,7 +157,7 @@ class IcebergRootModel(RootModel[T], Generic[T]):
 
 @lru_cache
 def _get_struct_fields(struct_type: StructType) -> Tuple[str, ...]:
-    return tuple([field.name for field in struct_type.fields])
+    return tuple(field.name for field in struct_type.fields)
 
 
 class Record(StructProtocol):

pyiceberg/utils/schema_conversion.py

@@ -447,7 +447,7 @@ def _convert_logical_map_type(self, avro_type: Dict[str, Any]) -> MapType:
         """
         fields = avro_type["items"]["fields"]
         if len(fields) != 2:
-            raise ValueError(f'Invalid key-value pair schema: {avro_type["items"]}')
+            raise ValueError(f"Invalid key-value pair schema: {avro_type['items']}")
         key = self._convert_field(list(filter(lambda f: f["name"] == "key", fields))[0])
         value = self._convert_field(list(filter(lambda f: f["name"] == "value", fields))[0])
         return MapType(

tests/avro/test_file.py

@@ -15,6 +15,7 @@
 #  specific language governing permissions and limitations
 #  under the License.
 import inspect
+from _decimal import Decimal
 from copy import copy
 from datetime import date, datetime, time
 from enum import Enum
@@ -23,7 +24,6 @@
 from uuid import UUID
 
 import pytest
-from _decimal import Decimal
 from fastavro import reader, writer
 
 import pyiceberg.avro.file as avro

tests/avro/test_writer.py

@@ -18,10 +18,10 @@
 
 import io
 import struct
+from _decimal import Decimal
 from typing import Dict, List
 
 import pytest
-from _decimal import Decimal
 
 from pyiceberg.avro.encoder import BinaryEncoder
 from pyiceberg.avro.resolver import construct_writer

tests/catalog/test_base.py

@@ -102,7 +102,7 @@ def create_table(
                 self.__namespaces[namespace] = {}
 
             if not location:
-                location = f'{self._warehouse_location}/{"/".join(identifier)}'
+                location = f"{self._warehouse_location}/{'/'.join(identifier)}"
             location = location.rstrip("/")
 
             metadata_location = self._get_metadata_location(location=location)