fix: types

Author: kukushking

awswrangler/distributed/ray/_executor.py

@@ -39,7 +39,7 @@ def __init__(self, max_concurrency: int) -> None:
         super().__init__()
 
         _logger.debug("Initializing Ray Actor with maximum concurrency %d", max_concurrency)
-        self._actor: ray.actor.ActorHandle = AsyncActor.options(max_concurrency=max_concurrency).remote()  # type: ignore[attr-defined]
+        self._actor: "ray.actor.ActorHandle[AsyncActor]" = AsyncActor.options(max_concurrency=max_concurrency).remote()  # type: ignore[attr-defined]
 
     def map(self, func: Callable[..., MapOutputType], _: "BaseClient" | None, *args: Any) -> list[MapOutputType]:
         """Map func and return ray futures."""

awswrangler/distributed/ray/datasources/arrow_parquet_datasource.py

@@ -344,7 +344,6 @@ def get_read_tasks(self, parallelism: int) -> list[ReadTask]:
 
             meta = self._meta_provider(
                 paths,  # type: ignore[arg-type]
-                self._inferred_schema,
                 num_fragments=len(fragments),
                 prefetched_metadata=metadata,
             )
@@ -566,7 +565,7 @@ def compute_batch_size_rows(sample_info: _SampleInfo) -> int:
         if sample_info.actual_bytes_per_row is None:
             return PARQUET_READER_ROW_BATCH_SIZE
         else:
-            max_parquet_reader_row_batch_size_bytes = DataContext.get_current().target_max_block_size // 10
+            max_parquet_reader_row_batch_size_bytes = DataContext.get_current().target_max_block_size // 10  # type: ignore[operator]
             return max(
                 1,
                 min(

awswrangler/distributed/ray/datasources/file_datasink.py

@@ -78,7 +78,7 @@ def _write_block(write_path: str, block: pd.DataFrame) -> str:
         write_path = self.path
 
         if write_path.endswith("/"):
-            filename = self.filename_provider.get_filename_for_block(block, ctx.task_idx, 0)
+            filename = self.filename_provider.get_filename_for_block(block, "", ctx.task_idx, 0)
             write_path = posixpath.join(self.path, filename)
 
         return _write_block(write_path, block)

awswrangler/distributed/ray/datasources/filename_provider.py

@@ -26,13 +26,14 @@ def __init__(
     def get_filename_for_block(
         self,
         block: Block,
+        write_uuid: str,
         task_index: int,
         block_index: int,
     ) -> str:
         file_id = f"{task_index:06}_{block_index:06}"
         return self._generate_filename(file_id)
 
-    def get_filename_for_row(self, row: dict[str, Any], task_index: int, block_index: int, row_index: int) -> str:
+    def get_filename_for_row(self, row: dict[str, Any], write_uuid: str, task_index: int, block_index: int, row_index: int) -> str:
         file_id = f"{task_index:06}_{block_index:06}_{row_index:06}"
         return self._generate_filename(file_id)