Github user holdenk commented on a diff in the pull request:
https://github.com/apache/spark/pull/16121#discussion_r91234665
--- Diff: python/pyspark/serializers.py ---
@@ -278,50 +278,51 @@ def __repr__(self):
return "AutoBatchedSerializer(%s)" % self.serializer
-class CartesianDeserializer(FramedSerializer):
+class CartesianDeserializer(Serializer):
"""
Deserializes the JavaRDD cartesian() of two PythonRDDs.
"""
def __init__(self, key_ser, val_ser):
- FramedSerializer.__init__(self)
self.key_ser = key_ser
self.val_ser = val_ser
- def prepare_keys_values(self, stream):
- key_stream = self.key_ser._load_stream_without_unbatching(stream)
- val_stream = self.val_ser._load_stream_without_unbatching(stream)
- key_is_batched = isinstance(self.key_ser, BatchedSerializer)
- val_is_batched = isinstance(self.val_ser, BatchedSerializer)
- for (keys, vals) in zip(key_stream, val_stream):
- keys = keys if key_is_batched else [keys]
- vals = vals if val_is_batched else [vals]
- yield (keys, vals)
+ def _load_stream_without_unbatching(self, stream):
+ key_batch_stream =
self.key_ser._load_stream_without_unbatching(stream)
+ val_batch_stream =
self.val_ser._load_stream_without_unbatching(stream)
+ for (key_batch, val_batch) in zip(key_batch_stream,
val_batch_stream):
+ yield product(key_batch, val_batch)
--- End diff --
Maybe consider adding a comment here explaining why the interaction of
batching & product
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
