org.apache.spark.examples.streaming.DirectKafkaWordCount.scala Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of snappy-spark-examples_2.11 Show documentation

SnappyData distributed data store and execution engine

There is a newer version: 2.1.3.2

Show newest version

/*
 * 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.spark.SparkConf
import org.apache.spark.streaming._
import org.apache.spark.streaming.kafka010._

/**
 * Consumes messages from one or more topics in Kafka and does wordcount.
 * Usage: DirectKafkaWordCount  
 *    is a list of one or more Kafka brokers
 *    is a list of one or more kafka topics to consume from
 *
 * Example:
 *    $ bin/run-example streaming.DirectKafkaWordCount broker1-host:port,broker2-host:port \
 *    topic1,topic2
 */
object DirectKafkaWordCount {
  def main(args: Array[String]) {
    if (args.length < 2) {
      System.err.println(s"""
        |Usage: DirectKafkaWordCount  
        |   is a list of one or more Kafka brokers
        |   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("DirectKafkaWordCount")
    val ssc = new StreamingContext(sparkConf, Seconds(2))

    // Create direct kafka stream with brokers and topics
    val topicsSet = topics.split(",").toSet
    val kafkaParams = Map[String, String]("metadata.broker.list" -> brokers)
    val messages = KafkaUtils.createDirectStream[String, String](
      ssc,
      LocationStrategies.PreferConsistent,
      ConsumerStrategies.Subscribe[String, String](topicsSet, kafkaParams))

    // Get the lines, split them into words, count the words and print
    val lines = messages.map(_.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