dstandish commented on code in PR #24908:
URL: https://github.com/apache/airflow/pull/24908#discussion_r917286582
##########
airflow/models/dataset.py:
##########
@@ -199,3 +199,86 @@ def __repr__(self):
for attr in [x.name for x in self.__mapper__.primary_key]:
args.append(f"{attr}={getattr(self, attr)!r}")
return f"{self.__class__.__name__}({', '.join(args)})"
+
+
+class DatasetEvent(Base):
+ """
+ A table to store datasets events.
+
+ :param dataset_id: reference to Dataset record
+ :param extra: JSON field for arbitrary extra info
+ :param source_task_id: the task_id of the TI which updated the dataset
+ :param source_dag_id: the dag_id of the TI which updated the dataset
+ :param source_run_id: the run_id of the TI which updated the dataset
+ :param source_map_index: the map_index of the TI which updated the dataset
+
+ We use relationships instead of foreign keys so that dataset events are
not deleted even
+ if the foreign key object is.
+ """
+
+ id = Column(Integer, primary_key=True, autoincrement=True)
+ dataset_id = Column(Integer, nullable=False)
+ extra = Column(ExtendedJSON, nullable=True)
+ source_task_id = Column(StringID(), nullable=True)
+ source_dag_id = Column(StringID(), nullable=True)
+ source_run_id = Column(StringID(), nullable=True)
+ source_map_index = Column(Integer, nullable=True,
server_default=text("-1"))
Review Comment:
Yeah need to think through best way to model this so that everything can be
tied together. We can discuss next week.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
