Spark kafka streaming example

Spark kafka streaming example

Please find below spark kafka streaming example:

	package com.sps.test
	import org.apache.kafka.clients.consumer.ConsumerRecord
	import org.apache.kafka.common.serialization.StringDeserializer
	import org.apache.spark.rdd.RDD
	import org.apache.spark.sql.SparkSession
	import org.apache.spark.streaming.Seconds
	import org.apache.spark.streaming.StreamingContext
	import org.apache.spark.streaming.dstream.InputDStream
	import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
	import org.apache.spark.streaming.kafka010.KafkaUtils
	import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
	object KafkaStreamTest extends App{
	val spark = SparkSession
	.builder
	.appName("SaprkSqlTest")
	.master("local[*]")
	.config("spark.sql.warehouse.dir", "file:///C:/temp")
	.getOrCreate()
	val ssc = new StreamingContext(spark.sparkContext, Seconds(5))
	val kafkaParams = Map[String, Object](
	"bootstrap.servers" -> "localhost:9092",
	"zookeeper" -> "localhost:2181",
	"key.deserializer" -> classOf[StringDeserializer],
	"value.deserializer" -> classOf[StringDeserializer],
	"group.id" -> "testGroup",
	"auto.offset.reset" -> "latest",
	"enable.auto.commit" -> (false: java.lang.Boolean)
	)
	val topics = Array("topicA,topicB")
	val stream = KafkaUtils.createDirectStream[String, String](
	ssc,
	PreferConsistent,
	Subscribe[String, String](topics, kafkaParams)
	)
	startStreamProcessing(stream)
	def startStreamProcessing(stream:InputDStream[ConsumerRecord[String, String]]):Unit={
	stream.foreachRDD(rdd => {
	processStream(rdd)
	})
	}
	def processStream(rdd:RDD[ConsumerRecord[String, String]]):Unit={
	if (!rdd.isEmpty()) {
	rdd.foreach(record=>{
	println("TOPIC NAME:"+record.topic()+"----KEY-"+record.key()+":"+record.value())
	})
	}
	}
	ssc.start()
	ssc.awaitTermination()
	}

view raw KafkaStreamTest.scala hosted with ❤ by GitHub