o-nikolas commented on code in PR #34225:
URL: https://github.com/apache/airflow/pull/34225#discussion_r1449340179
##########
airflow/providers/amazon/aws/links/emr.py:
##########
@@ -66,3 +82,98 @@ def get_log_uri(
return None
log_uri = S3Hook.parse_s3_url(cluster_info["LogUri"])
return "/".join(log_uri)
+
+
+class EmrServerlessLogsLink(BaseAwsLink):
+ """Helper class for constructing Amazon EMR Serverless Logs Link."""
+
+ name = "Spark Driver stdout"
+ key = "emr_serverless_logs"
+
+ def get_link(
+ self,
+ operator: BaseOperator,
+ *,
+ ti_key: TaskInstanceKey,
+ ) -> str:
+ """
+ Link to Amazon Web Services Console.
+
+ :param operator: airflow operator
+ :param ti_key: TaskInstance ID to return link for
+ :return: link to external system
+ """
+ conf = XCom.get_value(key=self.key, ti_key=ti_key)
+ if not conf:
+ return ""
+ hook = EmrServerlessHook(aws_conn_id=conf.get("conn_id"))
+ resp = hook.conn.get_dashboard_for_job_run(
+ applicationId=conf.get("application_id"),
jobRunId=conf.get("job_run_id")
+ )
+ o = urlparse(resp["url"])
+ return o._replace(path="/logs/SPARK_DRIVER/stdout.gz").geturl()
Review Comment:
That sounds like a reasonable approach. Do you mind having a go at that? I
don't think I'd like to merge this with 10+ second latency for the link loading
in failure cases.
--
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]
