kacpermuda commented on code in PR #47508:
URL: https://github.com/apache/airflow/pull/47508#discussion_r1987084020
##########
providers/apache/spark/src/airflow/providers/apache/spark/operators/spark_submit.py:
##########
@@ -169,9 +180,15 @@ def __init__(
self._hook: SparkSubmitHook | None = None
self._conn_id = conn_id
self._use_krb5ccache = use_krb5ccache
+ self._openlineage_inject_parent_job_info =
openlineage_inject_parent_job_info
+ self._openlineage_inject_transport_info =
openlineage_inject_transport_info
def execute(self, context: Context) -> None:
"""Call the SparkSubmitHook to run the provided spark job."""
+ if self._openlineage_inject_parent_job_info:
+ self.conf =
inject_parent_job_information_into_spark_properties(self.conf, context)
+ if self._openlineage_inject_transport_info:
+ self.conf =
inject_transport_information_into_spark_properties(self.conf, context)
Review Comment:
Maybe worth adding some logging so that users are aware that their Spark job
conf is being modified?
--
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]
