chamikaramj commented on a change in pull request #14491:
URL: https://github.com/apache/beam/pull/14491#discussion_r622518904
##########
File path: sdks/python/apache_beam/runners/dataflow/internal/apiclient.py
##########
@@ -588,11 +588,25 @@ def _stage_resources(self, pipeline, options):
'Found duplicated artifact: %s (%s)',
type_payload.path,
type_payload.sha256)
+ staged_name = hashs[type_payload.sha256]
dep.role_payload = beam_runner_api_pb2.ArtifactStagingToRolePayload(
- staged_name=hashs[type_payload.sha256]).SerializeToString()
+ staged_name=staged_name).SerializeToString()
else:
- resources.append((type_payload.path, role_payload.staged_name))
- hashs[type_payload.sha256] = role_payload.staged_name
+ staged_name = role_payload.staged_name
+ resources.append((type_payload.path, staged_name))
+ hashs[type_payload.sha256] = staged_name
+
+ if google_cloud_options.staging_location.startswith('gs://'):
Review comment:
Might be better to use:
if FileSystems.get_scheme(google_cloud_options.staging_location) ==
GcsFileSystem.scheme():
...
--
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]
