boyuanzz commented on a change in pull request #13405:
URL: https://github.com/apache/beam/pull/13405#discussion_r538917910
##########
File path: sdks/python/apache_beam/transforms/util.py
##########
@@ -825,7 +827,60 @@ def expand(self, pcoll):
key_value[1]))
return (
sharded_pcoll
- | GroupIntoBatches(self.batch_size,
self.max_buffering_duration_secs))
+ | GroupIntoBatches(
+ self.params.batch_size, self.params.max_buffering_duration_secs))
+
+ def to_runner_api_parameter(
+ self,
+ unused_context # type: PipelineContext
+ ): # type: (...) -> Tuple[str,
beam_runner_api_pb2.GroupIntoBatchesPayload]
+ return (
+ common_urns.composites.GROUP_INTO_BATCHES_WITH_SHARDED_KEY.urn,
+ self.params.get_payload())
+
+ @staticmethod
+ @PTransform.register_urn(
+ common_urns.composites.GROUP_INTO_BATCHES_WITH_SHARDED_KEY.urn,
+ beam_runner_api_pb2.GroupIntoBatchesPayload)
+ def from_runner_api_parameter(unused_ptransform, proto, unused_context):
+ return GroupIntoBatches.WithShardedKey(
+ *GroupIntoBatchesParams.parse_payload(proto))
+
+
+class GroupIntoBatchesParams:
Review comment:
Please add some pydoc to describe this class. Other than this, this PR
is ready to go.
----------------------------------------------------------------
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]
