Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/7410#discussion_r35552522
--- Diff:
external/kafka/src/main/scala/org/apache/spark/streaming/kafka/KafkaUtils.scala
---
@@ -684,3 +679,53 @@ private class KafkaUtilsPythonHelper {
kafkaRDD.offsetRanges.toSeq
}
}
+
+private object KafkaUtilsPythonHelper {
+ private var initialized = false
+
+ def initialize(): Unit = {
+ SerDeUtil.initialize()
+ synchronized {
+ if (!initialized) {
+ new PythonMessageAndMetadataPickler().register()
+ initialized = true
+ }
+ }
+ }
+ // will not called in Executor automatically
+ initialize()
+
+ case class PythonMessageAndMetadata(
+ topic: String,
+ partition: JInt,
+ offset: JLong,
+ key: Array[Byte],
+ message: Array[Byte])
+
+ class PythonMessageAndMetadataPickler extends IObjectPickler {
+ private val module = "pyspark.streaming.kafka"
+
+ def register(): Unit = {
+ Pickler.registerCustomPickler(classOf[PythonMessageAndMetadata],
this)
+ Pickler.registerCustomPickler(this.getClass, this)
+ }
+
+ def pickle(obj: Object, out: OutputStream, pickler: Pickler) {
+ if (obj == this) {
+ out.write(Opcodes.GLOBAL)
+ out.write(s"$module\nKafkaMessageAndMetadata\n".getBytes("utf-8"))
--- End diff --
Nit: could you import `com.google.common.base.Charsets.UTF_8` and use
`UTF_8` here?
---
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]
