DirectKafka010WordCount.scala

/*
 * 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.
 */

// scalastyle:off println
package org.apache.spark.examples.streaming

import org.apache.kafka.common.serialization.StringDeserializer

import org.apache.spark.SparkConf
import org.apache.spark.streaming._
import org.apache.spark.streaming.kafka010._
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent

/**
 * Consumes messages from one or more topics in Kafka and does wordcount.
 * Usage: DirectKafka010WordCount <brokers> <topics>
 *   <brokers> is a list of one or more Kafka brokers
 *   <topics> is a list of one or more kafka topics to consume from
 *
 * Example:
 *   $ bin/spark-submit \
 *     --driver-java-options -Djava.security.auth.login.config=/etc/hadoop/conf/kafka_client_for_ranger_yarn_jaas.conf \
 *     --conf "spark.executor.extraJavaOptions=-Djava.security.auth.login.config=/etc/hadoop/conf/kafka_client_for_ranger_yarn_jaas.conf" \
 *     --jars spark-streaming-kafka-0-10-assembly_2.11-2.1.0.jar \
 *     --class org.apache.spark.examples.streaming.DirectKafka010WordCount \
 *     examples/jars/spark-examples_2.11-2.1.0.jar broker1-host:port,broker2-host:port topic1,topic2
 */
object DirectKafka010WordCount {
  def main(args: Array[String]) {
    if (args.length < 2) {
      System.err.println(s"""
        |Usage: DirectKafka010WordCount <brokers> <topics>
        |  <brokers> is a list of one or more Kafka brokers
        |  <topics> is a list of one or more kafka topics to consume from
        |
        """.stripMargin)
      System.exit(1)
    }

    StreamingExamples.setStreamingLogLevels()

    val Array(brokers, topics) = args

    // Create context with 2 second batch interval
    val sparkConf = new SparkConf().setAppName("DirectKafka010WordCount")
    val ssc = new StreamingContext(sparkConf, Seconds(2))

    // Create direct kafka stream with brokers and topics
    // @see https://spark.apache.org/docs/2.1.0/streaming-kafka-0-10-integration.html
    val kafkaParams = Map[String, Object](
      "bootstrap.servers" -> brokers,
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> "tbds_spark_streaming_group",
      "security.protocol" -> "SASL_PLAINTEXT",
      "sasl.mechanism" -> "PLAIN"
    )
    val messages = KafkaUtils.createDirectStream[String, String](
      ssc,
      PreferConsistent,
      Subscribe[String, String](topics.split(","), kafkaParams)
    )

    // Get the lines, split them into words, count the words and print
    val lines = messages.map(record => record.value)
    val words = lines.flatMap(_.split(" "))
    val wordCounts = words.map(x => (x, 1L)).reduceByKey(_ + _)
    wordCounts.print()

    // Start the computation
    ssc.start()
    ssc.awaitTermination()
  }
}
// scalastyle:on println