Github user tdas commented on a diff in the pull request: https://github.com/apache/spark/pull/2991#discussion_r20271214 --- Diff: external/kafka/src/test/scala/org/apache/spark/streaming/kafka/ReliableKafkaStreamSuite.scala --- @@ -0,0 +1,160 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.streaming.kafka + +import java.io.File + +import scala.collection.mutable +import scala.concurrent.duration._ +import scala.language.postfixOps +import scala.util.Random + +import kafka.serializer.StringDecoder +import kafka.utils.{ZKGroupTopicDirs, ZkUtils} +import org.scalatest.concurrent.Eventually + +import org.apache.spark.storage.StorageLevel +import org.apache.spark.streaming.StreamingContext +import org.apache.spark.util.Utils + +class ReliableKafkaStreamSuite extends KafkaStreamSuiteBase with Eventually { + val topic = "topic" + val data = Map("a" -> 10, "b" -> 10, "c" -> 10) + var groupId: String = _ + var kafkaParams: Map[String, String] = _ + + before { + beforeFunction() // call this first to start ZK and Kafka + groupId = s"test-consumer-${Random.nextInt(10000)}" + kafkaParams = Map( + "zookeeper.connect" -> zkAddress, + "group.id" -> groupId, + "auto.offset.reset" -> "smallest" + ) + } + + after { + afterFunction() + } + + test("Reliable Kafka input stream") { + sparkConf.set("spark.streaming.receiver.writeAheadLog.enable", "true") + ssc = new StreamingContext(sparkConf, batchDuration) + val checkpointDir = s"${System.getProperty("java.io.tmpdir", "/tmp")}/" + + s"test-checkpoint${Random.nextInt(10000)}" + Utils.registerShutdownDeleteDir(new File(checkpointDir)) + ssc.checkpoint(checkpointDir) + createTopic(topic) + produceAndSendMessage(topic, data) + + val stream = KafkaUtils.createStream[String, String, StringDecoder, StringDecoder]( + ssc, + kafkaParams, + Map(topic -> 1), + StorageLevel.MEMORY_ONLY) + val result = new mutable.HashMap[String, Long]() + stream.map { case (k, v) => v }.foreachRDD { r => + val ret = r.collect() + ret.foreach { v => + val count = result.getOrElseUpdate(v, 0) + 1 + result.put(v, count) + } + } + ssc.start() + eventually(timeout(10000 milliseconds), interval(100 milliseconds)) { + // A basic process verification for ReliableKafkaReceiver. + // Verify whether received message number is equal to the sent message number. + assert(data.size === result.size) + // Verify whether each message is the same as the data to be verified. + data.keys.foreach { k => assert(data(k) === result(k).toInt) } + } + ssc.stop() + } +/* --- End diff -- This test is still commented out.
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org