turbaszek commented on a change in pull request #8858:
URL: https://github.com/apache/airflow/pull/8858#discussion_r427835515
##########
File path: airflow/providers/google/cloud/operators/bigquery.py
##########
@@ -963,24 +998,35 @@ def __init__(self,
self.location = location
def execute(self, context):
- bq_hook = BigQueryHook(gcp_conn_id=self.bigquery_conn_id,
- delegate_to=self.delegate_to,
- location=self.location)
+ bq_hook = BigQueryHook(
+ gcp_conn_id=self.bigquery_conn_id,
+ delegate_to=self.delegate_to,
+ location=self.location
+ )
if not self.schema_fields and self.schema_object and
self.source_format != 'DATASTORE_BACKUP':
gcs_hook = GCSHook(
google_cloud_storage_conn_id=self.google_cloud_storage_conn_id,
delegate_to=self.delegate_to)
- schema_fields = json.loads(gcs_hook.download(
- self.bucket,
- self.schema_object).decode("utf-8"))
+ schema_object = gcs_hook.download(self.bucket, self.schema_object)
+ schema_fields = json.loads(schema_object.decode("utf-8"))
else:
schema_fields = self.schema_fields
- source_uris = ['gs://{}/{}'.format(self.bucket, source_object)
- for source_object in self.source_objects]
+ if schema_fields and self.table_resource:
+ self.table_resource["externalDataConfiguration"]["schema"] =
schema_fields
- try:
+ source_uris = [f"gs://{self.bucket}/{source_object}" for source_object
in self.source_objects]
Review comment:
Done
----------------------------------------------------------------
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]
