Spark Streaming整合Kafka实现词频统计

pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.SparkStream</groupId>
    <artifactId>SparkStreamspace</artifactId>
    <version>1.0-SNAPSHOT</version>

    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <arg>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.4.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                            <transformers>
                                <transformer implementation=
                                                     "org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass></mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>6</source>
                    <target>6</target>
                </configuration>
            </plugin>
        </plugins>
    </build>


    <properties>
        <scala.version>2.11.8</scala.version>
        <hadoop.version>2.7.4</hadoop.version>
        <spark.version>2.3.2</spark.version>
    </properties>
    <dependencies>
        <!--Scala-->
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <!--Spark-->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <!--Hadoop-->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>2.3.2</version>
        </dependency>

        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.46</version>
        </dependency>
        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka-clients</artifactId>
            <version>2.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka-streams</artifactId>
            <version>2.0.0</version>
        </dependency>




        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>2.11.8</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.0.2</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>2.0.2</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
            <version>2.3.2</version>
        </dependency>

    </dependencies>

</project>

SparkStreaming_Kafka_createDstream.scala

import org.apache.spark.streaming.dstream.{DStream, ReceiverInputDStream}
import org.apache.spark.streaming.kafka.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.{SparkConf, SparkContext}
import scala.collection.immutable

/**
  * 从kafka中拉取数据
  * 读取数据时, consumer记录的offset发送回kafka中, 保存在zk中
  * 需要开始WAL日志保存模式防止数据丢失, 需要设置检查点
  */
object SparkStreaming_Kafka_createDstream {
  def main(args: Array[String]): Unit = {
    //1. 初始化参数,conf, sc, ssc
    val sparkConf: SparkConf = new SparkConf()
      .setAppName("SparkStreaming_Kafka_createDstream")
      .setMaster("local[4]")
      .set("spark.streaming.receiver.writeAheadLog.enable", "true")
    val sc: SparkContext = new SparkContext(sparkConf)
    //设置日志级别
    sc.setLogLevel("WARN")
    //创建StreamingContext
    val ssc: StreamingContext = new StreamingContext(sc, Seconds(5))
    //设置检查点, 开启WLA日志保存机制就要设置检查点
    ssc.checkpoint("./Kafka_Receiver")

    //2. 从kafka中拉取数据, KafKaUtil
    val zkQuorum = "hadoop01:2181,hadoop02:2181,hadoop03:2181"
    val groupId = "spark_receiver"
    //这里的1, 代表每一个分区被N个消费者消费
    val topics = Map("kafka_spark" -> 1)

    val receiverDstream: immutable.IndexedSeq[ReceiverInputDStream[(String, String)]] = (1 to 3)
      .map(x => {
        val stream: ReceiverInputDStream[(String, String)] = KafkaUtils
          .createStream(ssc, zkQuorum, groupId, topics)
        stream
      })

    //3. 从主体中获取具体的数据, 也就是value值, key是offect
    val unionDstream: DStream[(String, String)] = ssc.union(receiverDstream)

    //4. 单词计数
    val topicData: DStream[String] = unionDstream.map(_._2)

    val wordAndOne: DStream[(String, Int)] = topicData.flatMap(_.split(" ")).map((_, 1))

    val result: DStream[(String, Int)] = wordAndOne.reduceByKey(_ + _)

    //5. 打印
    result.print()

    //6. 开启流模式
    ssc.start()
    ssc.awaitTermination()

  }
}

开启zookeeper和kafka集群。

创建主题

kafka-topics.sh --create \
--topic kafka_spark \
--partitions 3 \
--replication-factor 1 \
--zookeeper hadoop01:2181,hadoop02:2181,hadoop03:2181

启动生产者

kafka-console-producer.sh \
--broker-list hadoop01:9092 \
--topic kafka_spark

SparkStreaming_Kafka_createDirectStream.scala

import kafka.serializer.StringDecoder
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.dstream.{DStream, InputDStream}
import org.apache.spark.streaming.kafka.KafkaUtils

//todo:利用sparkStreaming对接kafka实现单词计数----采用Direct(低级API)
object SparkStreaming_Kafka_createDirectStream {
  def main(args: Array[String]): Unit = {
    //1、创建sparkConf
    val sparkConf: SparkConf = new SparkConf()
      .setAppName("SparkStreaming_Kafka_createDirectStream")
      .setMaster("local[2]")
    //2、创建sparkContext
    val sc = new SparkContext(sparkConf)
    sc.setLogLevel("WARN")
    //3、创建StreamingContext
    val ssc = new StreamingContext(sc,Seconds(5))
    ssc.checkpoint("./Kafka_Direct")
    //4、配置kafka相关参数
    val kafkaParams=Map("metadata.broker.list"->"hadoop01:9092,hadoop02:9092,hadoop03:9092","group.id"->"spark_direct")
    //5、定义topic
    val topics=Set("kafka_direct0")
    //6、通过 KafkaUtils.createDirectStream接受kafka数据，这里采用是kafka低级api偏移量不受zk管理
    val dstream: InputDStream[(String, String)] = KafkaUtils.createDirectStream[String,String,StringDecoder,StringDecoder](ssc,kafkaParams,topics)
    //7、获取kafka中topic中的数据
    val topicData: DStream[String] = dstream.map(_._2)
    //8、切分每一行,每个单词计为1
    val wordAndOne: DStream[(String, Int)] = topicData.flatMap(_.split(" ")).map((_,1))
    //9、相同单词出现的次数累加
    val result: DStream[(String, Int)] = wordAndOne.reduceByKey(_+_)
    //10、打印输出
    result.print()
    //开启计算
    ssc.start()
    ssc.awaitTermination()
  }
}

创建主题

kafka-topics.sh --create \
--topic kafka_direct0 \
--partitions 3 \
--replication-factor 1 \
--zookeeper hadoop01:2181,hadoop02:2181,hadoop03:2181

启动生产者

kafka-console-producer.sh \
--broker-list hadoop01:9092 \
--topic kafka_direct0