Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/7410#discussion_r35558319
--- Diff: python/pyspark/streaming/kafka.py ---
@@ -347,3 +369,43 @@ def _jdstream(self):
dstream =
self._sc._jvm.PythonTransformedDStream(self.prev._jdstream.dstream(), jfunc)
self._jdstream_val = dstream.asJavaDStream()
return self._jdstream_val
+
+
+class KafkaMessageAndMetadata(object):
+ """
+ Kafka message and metadata information. Including topic, partition,
offset and message
+ """
+
+ def __init__(self, topic, partition, offset, key, message):
+ self.topic = topic
+ self.partition = partition
+ self.offset = offset
+ self._rawkey = key
+ self._rawMessage = message
+ self._keyDecoder = utf8_decoder
+ self._valueDecoder = utf8_decoder
+
+ def __str__(self):
+ return "KafkaMessageAndMetadata(topic: %s, partition: %d, offset:
%d, key and message...)" \
+ % (self.topic, self.partition, self.offset)
+
+ def __repr__(self):
+ return self.__str__()
+
+ def __reduce__(self):
+ return (KafkaMessageAndMetadata,
+ (self.topic, self.partition, self.offset, self._rawkey,
self._rawMessage))
+
+ def set_key_decoder(self, decoder):
+ self._keyDecoder = decoder
+
+ def set_value_decoder(self, decoder):
--- End diff --
Same as `set_key_decoder`.
---
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]
