Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/6830#discussion_r33554191
--- Diff:
external/flume/src/main/scala/org/apache/spark/streaming/flume/FlumeUtils.scala
---
@@ -236,3 +242,71 @@ object FlumeUtils {
createPollingStream(jssc.ssc, addresses, storageLevel, maxBatchSize,
parallelism)
}
}
+
+/**
+ * This is a helper class that wraps the methods in FlumeUtils into more
Python-friendly class and
+ * function so that it can be easily instantiated and called from Python's
FlumeUtils.
+ */
+private class FlumeUtilsPythonHelper {
+
+ def createStream(
+ jssc: JavaStreamingContext,
+ hostname: String,
+ port: Int,
+ storageLevel: StorageLevel,
+ enableDecompression: Boolean
+ ): JavaPairDStream[Array[Byte], Array[Byte]] = {
+ val dstream = FlumeUtils.createStream(jssc, hostname, port,
storageLevel, enableDecompression)
+ FlumeUtilsPythonHelper.toDStreamForPython(dstream)
+ }
+
+ def createPollingStream(
+ jssc: JavaStreamingContext,
+ hosts: JList[String],
+ ports: JList[Int],
+ storageLevel: StorageLevel,
+ maxBatchSize: Int,
+ parallelism: Int
+ ): JavaPairDStream[Array[Byte], Array[Byte]] = {
+ assert(hosts.length == ports.length)
+ val addresses = hosts.zip(ports).map {
+ case (host, port) => new InetSocketAddress(host, port)
+ }
+ val dstream = FlumeUtils.createPollingStream(
+ jssc.ssc, addresses, storageLevel, maxBatchSize, parallelism)
+ FlumeUtilsPythonHelper.toDStreamForPython(dstream)
+ }
+
+}
+
+private object FlumeUtilsPythonHelper {
+
+ private def stringMapToByteArray(map: JMap[CharSequence, CharSequence]):
Array[Byte] = {
+ val byteStream = new ByteArrayOutputStream()
+ val output = new DataOutputStream(byteStream)
+ try {
+ output.writeInt(map.size)
+ map.foreach { kv =>
+ PythonRDD.writeUTF(kv._1.toString, output)
+ PythonRDD.writeUTF(kv._2.toString, output)
+ }
+ byteStream.toByteArray
+ }
+ finally {
+ output.close()
+ }
+ }
+
+ private def toDStreamForPython(dstream:
JavaReceiverInputDStream[SparkFlumeEvent]):
--- End diff --
The name isnt very intuitive, could be `toByteArrayPairDStream`.
---
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]
