sparkstreamming 消费kafka(1)

pom

<!--<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
    <version>${spark.version}</version>
</dependency>-->
<dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
    <version>${spark.version}</version>
</dependency>

1 recevier方式
 

package com.tal.streaming

import org.apache.spark.streaming.dstream.{DStream, ReceiverInputDStream}
import org.apache.spark.streaming.kafka.KafkaUtilsimport org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.{SparkConf, SparkContext}
import scala.collection.immutable
object SparkKafka {
  def main(args: Array[String]): Unit = {
    //1.创建StreamingContextval
    val config: SparkConf = new SparkConf().setAppName("SparkStream").setMaster("local[*]") .set("spark.streaming.receiver.writeAheadLog.enable", "true")//开启WAL预写日志，保证数据源端可靠性
    val sc = new SparkContext(config)
    sc.setLogLevel("WARN")
    val ssc = new StreamingContext(sc,Seconds(5))
    ssc.checkpoint("./kafka")
    //==============================================
    //2.准备配置参数
    val zkQuorum = "node01:2181,node02:2181,node03:2181"
    val groupId = "spark"
    val topics = Map("spark_kafka" -> 2)
    //2表示每一个topic对应分区都采用2个线程去消费,
    //ssc的rdd分区和kafka的topic分区不一样，增加消费线程数，并不增加spark的并行处理数据数量
    //3.通过receiver接收器获取kafka中topic数据，可以并行运行更多的接收器读取kafak topic中的数据，这里为3个
    val receiverDStream: immutable.IndexedSeq[ReceiverInputDStream[(String, String)]] = (1 to 3).map(
      x => {
        val stream: ReceiverInputDStream[(String, String)] = KafkaUtils.createStream(ssc, zkQuorum, groupId, topics)
        stream
      }
    )//4.使用union方法，将所有receiver接受器产生的Dstream进行合并
    val allDStream: DStream[(String, String)] = ssc.union(receiverDStream)
    //5.获取topic的数据(String, String) 第1个String表示topic的名称，第2个String表示topic的数据
    val data: DStream[String] = allDStream.map(_._2)
    //==============================================
    //6.WordCount
    val words: DStream[String] = data.flatMap(_.split(" "))
    val wordAndOne: DStream[(String, Int)] = words.map((_, 1))
    val result: DStream[(String, Int)] = wordAndOne.reduceByKey(_ + _)
    result.print()
    ssc.start()
    ssc.awaitTermination()
  }
}

2 direct方式

package com.tal.streaming

import kafka.serializer.StringDecoder
import org.apache.spark.streaming.dstream.{DStream, InputDStream}
import org.apache.spark.streaming.kafka.KafkaUtils
import org.apache.spark.streaming.kafka010.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.{SparkConf, SparkContext}
object SparkKafka {
  def main(args: Array[String]): Unit = {
    //1.创建StreamingContext
    val config: SparkConf = new SparkConf().setAppName("SparkStream").setMaster("local[*]")
    val sc = new SparkContext(config)
    sc.setLogLevel("WARN")
    val ssc = new StreamingContext(sc,Seconds(5))
    ssc.checkpoint("./kafka")
    //==============================================
    // 2.准备配置参数
    val kafkaParams = Map("metadata.broker.list" -> "node01:9092,node02:9092,node03:9092", "group.id" -> "spark")
    val topics = Set("spark_kafka")
    val allDStream: InputDStream[(String, String)] = KafkaUtils.createDirectStream[String, String, StringDecoder, StringDecoder](ssc, kafkaParams, topics)
    //3.获取topic的数据
    val data: DStream[String] = allDStream.map(_._2)
    //==============================================
    // WordCount
    val words: DStream[String] = data.flatMap(_.split(" "))
    val wordAndOne: DStream[(String, Int)] = words.map((_, 1))
    val result: DStream[(String, Int)] = wordAndOne.reduceByKey(_ + _) 
    result.print() 
    ssc.start() 
    ssc.awaitTermination() 
    }
  }

direct方式升级api方式代码

import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.streaming.dstream.{DStream, InputDStream}
import org.apache.spark.streaming.kafka010.{ConsumerStrategies, KafkaUtils, LocationStrategies}
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.{SparkConf, SparkContext}

object SparkKafkaDemo {
  def main(args: Array[String]): Unit = {
    //1.创建StreamingContext
    //spark.master should be set as local[n], n > 1
    val conf = new SparkConf().setAppName("wc").setMaster("local[*]")
    val sc = new SparkContext(conf)
    sc.setLogLevel("WARN")
    val ssc = new StreamingContext(sc,Seconds(5))//5表示5秒中对数据进行切分形成一个RDD
    //准备连接Kafka的参数
    val kafkaParams = Map[String, Object](
      "bootstrap.servers" -> "node01:9092,node02:9092,node03:9092",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> "SparkKafkaDemo",
      //earliest:当各分区下有已提交的offset时，从提交的offset开始消费；无提交的offset时，从头开始消费
      //latest:当各分区下有已提交的offset时，从提交的offset开始消费；无提交的offset时，消费新产生的该分区下的数据
      //none:topic各分区都存在已提交的offset时，从offset后开始消费；只要有一个分区不存在已提交的offset，则抛出异常
      //这里配置latest自动重置偏移量为最新的偏移量,即如果有偏移量从偏移量位置开始消费,没有偏移量从新来的数据开始消费
      "auto.offset.reset" -> "latest",
      //false表示关闭自动提交.由spark帮你提交到Checkpoint或程序员手动维护
      "enable.auto.commit" -> (false: java.lang.Boolean)
    )
    val topics = Array("spark_kafka")
    //2.使用KafkaUtil连接Kafak获取数据
    val recordDStream: InputDStream[ConsumerRecord[String, String]] = KafkaUtils.createDirectStream[String, String](ssc,
      LocationStrategies.PreferConsistent,//位置策略,源码强烈推荐使用该策略,会让Spark的Executor和Kafka的Broker均匀对应
      ConsumerStrategies.Subscribe[String, String](topics, kafkaParams))//消费策略,源码强烈推荐使用该策略
    //3.获取VALUE数据
    val lineDStream: DStream[String] = recordDStream.map(_.value())//_指的是ConsumerRecord
    val wrodDStream: DStream[String] = lineDStream.flatMap(_.split(" ")) //_指的是发过来的value,即一行数据
    val wordAndOneDStream: DStream[(String, Int)] = wrodDStream.map((_,1))
    val result: DStream[(String, Int)] = wordAndOneDStream.reduceByKey(_+_)
    result.print()
    ssc.start()//开启
    ssc.awaitTermination()//等待优雅停止
  }
}