nathadfield commented on a change in pull request #9590:
URL: https://github.com/apache/airflow/pull/9590#discussion_r462247317
##########
File path: airflow/providers/google/cloud/operators/bigquery.py
##########
@@ -1692,32 +1693,48 @@ def prepare_template(self) -> None:
with open(self.configuration, 'r') as file:
self.configuration = json.loads(file.read())
+ def _submit_job(self, hook: BigQueryHook, job_id: str):
+ # Submit a new job
+ job = hook.insert_job(
+ configuration=self.configuration,
+ project_id=self.project_id,
+ location=self.location,
+ job_id=job_id,
+ )
+ # Start the job and wait for it to complete and get the result.
+ job.result()
+ return job
+
def execute(self, context: Any):
hook = BigQueryHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
)
- job_id = self.job_id or f"airflow_{self.task_id}_{int(time())}"
+ exec_date = re.sub("\:|\-|\+", "_",
context['execution_date'].isoformat())
+ job_id = self.job_id or
f"airflow_{self.dag_id}_{self.task_id}_{exec_date}_"
+
try:
- job = hook.insert_job(
- configuration=self.configuration,
- project_id=self.project_id,
- location=self.location,
- job_id=job_id,
- )
- # Start the job and wait for it to complete and get the result.
- job.result()
+ # Submit a new job
+ job = self._submit_job(hook, job_id)
except Conflict:
+ # If the job already exists retrieve it
Review comment:
Then there should be additional parameters. IMHO, I don't think it is
controversial to suggest that, when the status of a BQ task is cleared, the
default behaviour should be that the query if fully rerun. Other cases sound
like less common scenarios (in my experience at least).
##########
File path: airflow/providers/google/cloud/operators/bigquery.py
##########
@@ -1692,32 +1693,48 @@ def prepare_template(self) -> None:
with open(self.configuration, 'r') as file:
self.configuration = json.loads(file.read())
+ def _submit_job(self, hook: BigQueryHook, job_id: str):
+ # Submit a new job
+ job = hook.insert_job(
+ configuration=self.configuration,
+ project_id=self.project_id,
+ location=self.location,
+ job_id=job_id,
+ )
+ # Start the job and wait for it to complete and get the result.
+ job.result()
+ return job
+
def execute(self, context: Any):
hook = BigQueryHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
)
- job_id = self.job_id or f"airflow_{self.task_id}_{int(time())}"
+ exec_date = re.sub("\:|\-|\+", "_",
context['execution_date'].isoformat())
+ job_id = self.job_id or
f"airflow_{self.dag_id}_{self.task_id}_{exec_date}_"
+
try:
- job = hook.insert_job(
- configuration=self.configuration,
- project_id=self.project_id,
- location=self.location,
- job_id=job_id,
- )
- # Start the job and wait for it to complete and get the result.
- job.result()
+ # Submit a new job
+ job = self._submit_job(hook, job_id)
except Conflict:
+ # If the job already exists retrieve it
Review comment:
Indeed. I'd say that should be the default going forward too.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
