package com.ippon.dojo.driver import org.apache.spark.SparkConf import org.apache.spark.SparkContext import org.apache.spark.streaming.StreamingContext import org.apache.spark.streaming.Seconds import kafka.serializer.StringDecoder import org.apache.spark.streaming._ import org.apache.spark.SparkConf import org.apache.spark.streaming.kafka010.KafkaUtils import org.apache.kafka.common.serialization.StringDeserializer import org.apache.spark.streaming.kafka010._ import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe object KafkaStreamingDriver { def main(args: Array[String]): Unit = { //configure the Streaming Context val sparkConf = new SparkConf().setAppName("KafkaStreamingDojoApp") val sparkContext = new SparkContext(sparkConf) val streamingContext = new StreamingContext(sparkContext, Seconds(1)) val kafkaTopic = "dojo" // Create direct kafka stream with brokers and topics val kafkaParams = Map[String, Object]( "bootstrap.servers" -> "ec2-54-174-179-236.compute-1.amazonaws.com:9092", "key.deserializer" -> classOf[StringDeserializer], "value.deserializer" -> classOf[StringDeserializer], "group.id" -> "dojo", "auto.offset.reset" -> "latest", "enable.auto.commit" -> (false: java.lang.Boolean)) val topics = Array("dojo") val complaints = KafkaUtils.createDirectStream[String, String]( streamingContext, PreferConsistent, Subscribe[String, String](topics, kafkaParams)) //perform action on the stream complaints.foreachRDD((rdd, time) => { val count = rdd.count() System.out.println(count + " complaints were collected at " + time) }) //start the stream streamingContext.start() streamingContext.awaitTermination() } }