make lint

Author: kevinjqliu

pyiceberg/cli/output.py

@@ -242,8 +242,10 @@ def version(self, version: str) -> None:
         self._out({"version": version})
 
     def describe_refs(self, refs: List[Tuple[str, SnapshotRefType, Dict[str, str]]]) -> None:
-        self._out([
-            {"name": name, "type": type, detail_key: detail_val}
-            for name, type, detail in refs
-            for detail_key, detail_val in detail.items()
-        ])
+        self._out(
+            [
+                {"name": name, "type": type, detail_key: detail_val}
+                for name, type, detail in refs
+                for detail_key, detail_val in detail.items()
+            ]
+        )

pyiceberg/io/pyarrow.py

@@ -2449,27 +2449,31 @@ def _dataframe_to_data_files(
         yield from write_file(
             io=io,
             table_metadata=table_metadata,
-            tasks=iter([
-                WriteTask(write_uuid=write_uuid, task_id=next(counter), record_batches=batches, schema=task_schema)
-                for batches in bin_pack_arrow_table(df, target_file_size)
-            ]),
+            tasks=iter(
+                [
+                    WriteTask(write_uuid=write_uuid, task_id=next(counter), record_batches=batches, schema=task_schema)
+                    for batches in bin_pack_arrow_table(df, target_file_size)
+                ]
+            ),
         )
     else:
         partitions = _determine_partitions(spec=table_metadata.spec(), schema=table_metadata.schema(), arrow_table=df)
         yield from write_file(
             io=io,
             table_metadata=table_metadata,
-            tasks=iter([
-                WriteTask(
-                    write_uuid=write_uuid,
-                    task_id=next(counter),
-                    record_batches=batches,
-                    partition_key=partition.partition_key,
-                    schema=task_schema,
-                )
-                for partition in partitions
-                for batches in bin_pack_arrow_table(partition.arrow_table_partition, target_file_size)
-            ]),
+            tasks=iter(
+                [
+                    WriteTask(
+                        write_uuid=write_uuid,
+                        task_id=next(counter),
+                        record_batches=batches,
+                        partition_key=partition.partition_key,
+                        schema=task_schema,
+                    )
+                    for partition in partitions
+                    for batches in bin_pack_arrow_table(partition.arrow_table_partition, target_file_size)
+                ]
+            ),
         )
 
 
@@ -2534,10 +2538,12 @@ def _determine_partitions(spec: PartitionSpec, schema: Schema, arrow_table: pa.T
     partition_columns: List[Tuple[PartitionField, NestedField]] = [
         (partition_field, schema.find_field(partition_field.source_id)) for partition_field in spec.fields
     ]
-    partition_values_table = pa.table({
-        str(partition.field_id): partition.transform.pyarrow_transform(field.field_type)(arrow_table[field.name])
-        for partition, field in partition_columns
-    })
+    partition_values_table = pa.table(
+        {
+            str(partition.field_id): partition.transform.pyarrow_transform(field.field_type)(arrow_table[field.name])
+            for partition, field in partition_columns
+        }
+    )
 
     # Sort by partitions
     sort_indices = pa.compute.sort_indices(

pyiceberg/manifest.py

@@ -292,28 +292,32 @@ def __repr__(self) -> str:
 
 
 def data_file_with_partition(partition_type: StructType, format_version: TableVersion) -> StructType:
-    data_file_partition_type = StructType(*[
-        NestedField(
-            field_id=field.field_id,
-            name=field.name,
-            field_type=field.field_type,
-            required=field.required,
-        )
-        for field in partition_type.fields
-    ])
+    data_file_partition_type = StructType(
+        *[
+            NestedField(
+                field_id=field.field_id,
+                name=field.name,
+                field_type=field.field_type,
+                required=field.required,
+            )
+            for field in partition_type.fields
+        ]
+    )
 
-    return StructType(*[
-        NestedField(
-            field_id=102,
-            name="partition",
-            field_type=data_file_partition_type,
-            required=True,
-            doc="Partition data tuple, schema based on the partition spec",
-        )
-        if field.field_id == 102
-        else field
-        for field in DATA_FILE_TYPE[format_version].fields
-    ])
+    return StructType(
+        *[
+            NestedField(
+                field_id=102,
+                name="partition",
+                field_type=data_file_partition_type,
+                required=True,
+                doc="Partition data tuple, schema based on the partition spec",
+            )
+            if field.field_id == 102
+            else field
+            for field in DATA_FILE_TYPE[format_version].fields
+        ]
+    )
 
 
 class DataFile(Record):
@@ -398,10 +402,12 @@ def __eq__(self, other: Any) -> bool:
 
 
 def manifest_entry_schema_with_data_file(format_version: TableVersion, data_file: StructType) -> Schema:
-    return Schema(*[
-        NestedField(2, "data_file", data_file, required=True) if field.field_id == 2 else field
-        for field in MANIFEST_ENTRY_SCHEMAS[format_version].fields
-    ])
+    return Schema(
+        *[
+            NestedField(2, "data_file", data_file, required=True) if field.field_id == 2 else field
+            for field in MANIFEST_ENTRY_SCHEMAS[format_version].fields
+        ]
+    )
 
 
 class ManifestEntry(Record):

pyiceberg/schema.py

@@ -1707,12 +1707,14 @@ def list(self, list_type: ListType, element_result: Callable[[], bool]) -> bool:
         return self._is_field_compatible(list_type.element_field) and element_result()
 
     def map(self, map_type: MapType, key_result: Callable[[], bool], value_result: Callable[[], bool]) -> bool:
-        return all([
-            self._is_field_compatible(map_type.key_field),
-            self._is_field_compatible(map_type.value_field),
-            key_result(),
-            value_result(),
-        ])
+        return all(
+            [
+                self._is_field_compatible(map_type.key_field),
+                self._is_field_compatible(map_type.value_field),
+                key_result(),
+                value_result(),
+            ]
+        )
 
     def primitive(self, primitive: PrimitiveType) -> bool:
         return True

pyiceberg/table/__init__.py

@@ -629,18 +629,20 @@ def delete(
                 if len(filtered_df) == 0:
                     replaced_files.append((original_file.file, []))
                 elif len(df) != len(filtered_df):
-                    replaced_files.append((
-                        original_file.file,
-                        list(
-                            _dataframe_to_data_files(
-                                io=self._table.io,
-                                df=filtered_df,
-                                table_metadata=self.table_metadata,
-                                write_uuid=commit_uuid,
-                                counter=counter,
-                            )
-                        ),
-                    ))
+                    replaced_files.append(
+                        (
+                            original_file.file,
+                            list(
+                                _dataframe_to_data_files(
+                                    io=self._table.io,
+                                    df=filtered_df,
+                                    table_metadata=self.table_metadata,
+                                    write_uuid=commit_uuid,
+                                    counter=counter,
+                                )
+                            ),
+                        )
+                    )
 
             if len(replaced_files) > 0:
                 with self.update_snapshot(snapshot_properties=snapshot_properties).overwrite() as overwrite_snapshot:
@@ -680,9 +682,9 @@ def add_files(
                 raise ValueError(f"Cannot add files that are already referenced by table, files: {', '.join(referenced_files)}")
 
         if self.table_metadata.name_mapping() is None:
-            self.set_properties(**{
-                TableProperties.DEFAULT_NAME_MAPPING: self.table_metadata.schema().name_mapping.model_dump_json()
-            })
+            self.set_properties(
+                **{TableProperties.DEFAULT_NAME_MAPPING: self.table_metadata.schema().name_mapping.model_dump_json()}
+            )
         with self.update_snapshot(snapshot_properties=snapshot_properties).fast_append() as update_snapshot:
             data_files = _parquet_files_to_data_files(
                 table_metadata=self.table_metadata, file_paths=file_paths, io=self._table.io