hardeybisey commented on code in PR #44960:
URL: https://github.com/apache/airflow/pull/44960#discussion_r1890028402
##########
providers/src/airflow/providers/databricks/operators/databricks.py:
##########
@@ -1037,17 +1040,21 @@ def _get_hook(self, caller: str) -> DatabricksHook:
caller=caller,
)
- def _get_databricks_task_id(self, task_id: str) -> str:
- """Get the databricks task ID using dag_id and task_id. Removes
illegal characters."""
- task_id = f"{self.dag_id}__{task_id.replace('.', '__')}"
- if len(task_id) > 100:
- self.log.warning(
- "The generated task_key '%s' exceeds 100 characters and will
be truncated by the Databricks API. "
- "This will cause failure when trying to monitor the task.
task_key is generated by ",
- "concatenating dag_id and task_id.",
- task_id,
+ @cached_property
+ def databricks_task_key(self) -> str:
+ return self._generate_databricks_task_key()
+
+ def _generate_databricks_task_key(self, task_id: str | None = None) -> str:
+ """Create a databricks task key using the hash of dag_id and
task_id."""
+ if self._databricks_task_key is None:
Review Comment:
I think some users may want to control the value of the task_key, so I have
kept that option. I've also added a check to ensure the user provided key does
not exceeds 100 characters, otherwise we fall back to using the auto-generate
key.
--
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]
