diff --git a/swh/dataset/exporters/orc.py b/swh/dataset/exporters/orc.py --- a/swh/dataset/exporters/orc.py +++ b/swh/dataset/exporters/orc.py @@ -5,6 +5,7 @@ import uuid +from pkg_resources import get_distribution from pyorc import ( BigInt, Binary, @@ -88,6 +89,13 @@ compression=CompressionKind.ZSTD, ) ) + self.writers[table_name].set_user_metadata( + swh_object_type=table_name.encode(), + swh_uuid=unique_id.encode(), + swh_model_version=get_distribution("swh.model").version.encode(), + swh_dataset_version=get_distribution("swh.dataset").version.encode(), + # maybe put a copy of the config (redacted) also? + ) return self.writers[table_name] def process_origin(self, origin):