rdblue commented on code in PR #41: URL: https://github.com/apache/iceberg-python/pull/41#discussion_r1451836112
########## pyiceberg/table/__init__.py: ########## @@ -1910,3 +2006,137 @@ def _generate_snapshot_id() -> int: snapshot_id = snapshot_id if snapshot_id >= 0 else snapshot_id * -1 return snapshot_id + + +@dataclass(frozen=True) +class WriteTask: + write_uuid: uuid.UUID + task_id: int + df: pa.Table + sort_order_id: Optional[int] = None + + # Later to be extended with partition information + + def generate_datafile_filename(self, extension: str) -> str: + # Mimics the behavior in the Java API: + # https://github.com/apache/iceberg/blob/a582968975dd30ff4917fbbe999f1be903efac02/core/src/main/java/org/apache/iceberg/io/OutputFileFactory.java#L92-L101 + return f"00000-{self.task_id}-{self.write_uuid}.{extension}" + + +def _new_manifest_path(location: str, num: int, commit_uuid: uuid.UUID) -> str: + return f'{location}/metadata/{commit_uuid}-m{num}.avro' + + +def _generate_manifest_list_filename(snapshot_id: int, attempt: int, commit_uuid: uuid.UUID) -> str: + # Mimics the behavior in Java: + # https://github.com/apache/iceberg/blob/c862b9177af8e2d83122220764a056f3b96fd00c/core/src/main/java/org/apache/iceberg/SnapshotProducer.java#L491 + return f"snap-{snapshot_id}-{attempt}-{commit_uuid}.avro" + + +def _dataframe_to_data_files(table: Table, df: pa.Table) -> Iterable[DataFile]: Review Comment: I think the intent is for this to eventually support partitioning, so I think it would make sense to check `table.spec()` is unpartitioned. Good to be more defensive and open things up later. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org