udim commented on a change in pull request #13493:
URL: https://github.com/apache/beam/pull/13493#discussion_r538729953
##########
File path: sdks/python/apache_beam/transforms/util.py
##########
@@ -815,18 +817,25 @@ def __init__(self, batch_size,
max_buffering_duration_secs=None):
_shard_id_prefix = uuid.uuid4().bytes
def expand(self, pcoll):
+ key_type, value_type = pcoll.element_type.tuple_types
sharded_pcoll = pcoll | Map(
lambda key_value: (
ShardedKey(
key_value[0],
# Use [uuid, thread id] as the shard id.
GroupIntoBatches.WithShardedKey._shard_id_prefix + bytes(
threading.get_ident().to_bytes(8, 'big'))),
- key_value[1]))
+ key_value[1])).with_output_types(
+ TupleConstraint([ShardedKeyType[key_type], value_type]))
Review comment:
Sorry, my mistake I didn't read this carefully enough.
----------------------------------------------------------------
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]
