spark DirectKafkaWordCount 源码

spark DirectKafkaWordCount 代码

文件路径：/examples/src/main/scala/org/apache/spark/examples/streaming/DirectKafkaWordCount.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.clients.consumer.ConsumerConfig
import org.apache.kafka.common.serialization.StringDeserializer

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 <brokers> <topics>
 *   <brokers> is a list of one or more Kafka brokers
 *   <groupId> is a consumer group name to consume from topics
 *   <topics> is a list of one or more kafka topics to consume from
 *
 * Example:
 *    $ bin/run-example streaming.DirectKafkaWordCount broker1-host:port,broker2-host:port \
 *    consumer-group topic1,topic2
 */
object DirectKafkaWordCount {
  def main(args: Array[String]): Unit = {
    if (args.length < 3) {
      System.err.println(s"""
        |Usage: DirectKafkaWordCount <brokers> <groupId> <topics>
        |  <brokers> is a list of one or more Kafka brokers
        |  <groupId> is a consumer group name to consume from topics
        |  <topics> is a list of one or more kafka topics to consume from
        |
        """.stripMargin)
      System.exit(1)
    }

    StreamingExamples.setStreamingLogLevels()

    val Array(brokers, groupId, 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, Object](
      ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG -> brokers,
      ConsumerConfig.GROUP_ID_CONFIG -> groupId,
      ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG -> classOf[StringDeserializer],
      ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG -> classOf[StringDeserializer])
    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

相关信息

spark 源码目录

相关文章

spark CustomReceiver 源码

spark DirectKerberizedKafkaWordCount 源码

spark HdfsWordCount 源码

spark NetworkWordCount 源码

spark QueueStream 源码

spark RawNetworkGrep 源码

spark RecoverableNetworkWordCount 源码

spark SqlNetworkWordCount 源码

spark StatefulNetworkWordCount 源码

spark StreamingExamples 源码