phanikumv commented on code in PR #69177:
URL: https://github.com/apache/airflow/pull/69177#discussion_r3498651236
##########
airflow-core/tests/unit/utils/test_db_cleanup.py:
##########
@@ -443,6 +443,112 @@ def test_cleanup_with_dag_id_filtering(self, dag_ids,
exclude_dag_ids, expected_
f"Expected {expected_remaining_dag_ids} to remain, but got
{remaining_dag_ids}"
)
+ def test_cleanup_with_dag_id_filtering_for_joined_tables(self):
+ """
+ Verify that dag_ids and exclude_dag_ids parameters correctly filter
and cleanup
+ asset_event, task_reschedule, and deadline tables.
+ """
+ from airflow.models.asset import AssetEvent
+ from airflow.models.deadline import Deadline
+ from airflow.models.taskreschedule import TaskReschedule
+
+ class SyncCallback:
+ def __init__(self):
+ self.path = "my_path"
+ self.kwargs = {}
+ self.executor = "default"
+
+ def serialize(self):
+ return {"path": self.path, "kwargs": self.kwargs, "executor":
self.executor}
+
+ base_date = pendulum.DateTime(2022, 1, 1,
tzinfo=pendulum.timezone("UTC"))
+
+ with create_session() as session:
+ bundle_name = "testing"
+ session.add(DagBundleModel(name=bundle_name))
+ session.flush()
+
+ # Create records for dag1 (should be cleaned) and dag2 (should be
kept)
+ for dag_id in ["dag1", "dag2"]:
+ dag = DAG(dag_id=dag_id)
+ dm = DagModel(dag_id=dag_id, bundle_name=bundle_name)
+ session.add(dm)
+
SerializedDagModel.write_dag(LazyDeserializedDAG.from_dag(dag),
bundle_name=bundle_name)
+ dag_version = DagVersion.get_latest_version(dag.dag_id)
+
+ dag_run = DagRun(
+ dag.dag_id,
+ run_id=f"{dag_id}_run",
+ run_type=DagRunType.MANUAL,
+ start_date=base_date,
+ )
+ session.add(dag_run)
+ session.flush()
+
+ ti = create_task_instance(
+ PythonOperator(task_id="dummy-task",
python_callable=print),
+ run_id=dag_run.run_id,
+ dag_version_id=dag_version.id,
+ )
+ ti.dag_id = dag.dag_id
+ ti.start_date = base_date
+ session.add(ti)
+ session.flush()
+
+ # 1. AssetEvent
+ ae = AssetEvent(
+ asset_id=1,
+ source_dag_id=dag_id,
+ timestamp=base_date,
+ )
+ session.add(ae)
+
+ # 2. TaskReschedule
+ tr = TaskReschedule(
+ ti_id=ti.id,
+ start_date=base_date,
+ end_date=base_date.add(minutes=5),
+ reschedule_date=base_date.add(minutes=10),
+ )
+ session.add(tr)
+
+ # 3. Deadline
+ dl = Deadline(
+ deadline_time=base_date,
+ callback=SyncCallback(),
+ dagrun_id=dag_run.id,
+ deadline_alert_id=None,
+ )
+ session.add(dl)
+
+ session.commit()
+
+ # Run cleanup targeting only dag1
+ clean_before_date = base_date.add(days=10)
+ run_cleanup(
+ clean_before_timestamp=clean_before_date,
+ table_names=["asset_event", "task_reschedule", "deadline"],
Review Comment:
The test passes only the three joined tables, so it validates the
JOIN-resolves-dag_id logic but skips the path that actually runs in airflow db
clean: a full run cleans `task_instance`/`dag_run` first, which cascade-deletes
the child rows before the child's own dag-filter ever fires.
Worth a second test case (or extending this one) that includes
`task_instance` and `dag_run` in table_names so the cascade-interaction path is
covered
--
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]
