目录
说明
spark-streaming-kafka-0-10版本中，API有一定的变化，操作更加灵活，开发中使用
核心概念图解
pom.xml
<!-- 指定仓库位置，依次为aliyun、cloudera和jboss仓库 -->
<repositories>
<repository>
<id>aliyun</id>
<url>http://maven.aliyun.com/nexus/content/groups/public/</url>
</repository>
<repository>
<id>cloudera</id>
<url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
</repository>
<repository>
<id>jboss</id>
<url>http://repository.jboss.com/nexus/content/groups/public</url>
</repository>
</repositories>
<properties>
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
<encoding>UTF-8</encoding>
<scala.version>2.11.8</scala.version>
<scala.compat.version>2.11</scala.compat.version>
<hadoop.version>2.7.4</hadoop.version>
<spark.version>2.2.0</spark.version>
</properties>
<dependencies>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive-thriftserver_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<!-- <dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
<version>${spark.version}</version>
</dependency>-->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql-kafka-0-10_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<!--<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.6.0-mr1-cdh5.14.0</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.2.0-cdh5.14.0</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>1.2.0-cdh5.14.0</version>
</dependency>-->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.7.4</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.3.1</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>1.3.1</version>
</dependency>
<dependency>
<groupId>com.typesafe</groupId>
<artifactId>config</artifactId>
<version>1.3.3</version>
</dependency>
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.38</version>
</dependency>
</dependencies>
<build>
<sourceDirectory>src/main/scala</sourceDirectory>
<testSourceDirectory>src/test/scala</testSourceDirectory>
<plugins>
<!-- 指定编译java的插件 -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.5.1</version>
</plugin>
<!-- 指定编译scala的插件 -->
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.2.2</version>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
<configuration>
<args>
<arg>-dependencyfile</arg>
<arg>${project.build.directory}/.scala_dependencies</arg>
</args>
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.18.1</version>
<configuration>
<useFile>false</useFile>
<disableXmlReport>true</disableXmlReport>
<includes>
<include>**/*Test.*</include>
<include>**/*Suite.*</include>
</includes>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>2.3</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>
</plugins>
</build>
API
http://spark.apache.org/docs/latest/streaming-kafka-0-10-integration.html
创建topic
node001执行以下命令来创建topic
cd /export/servers/kafka_2.11-1.0.0
bin/kafka-topics.sh --create --zookeeper node001:2181 --replication-factor 2 --partitions 3 --topic test
启动生产者
node001服务器执行以下命令来模拟生产者进行生产数据
cd /export/servers/kafka_2.11-1.0.0
bin/kafka-console-producer.sh --broker-list node001:9092,node002:9092,node003:9092 --topic test
代码演示
/**
* Created by 一个蔡狗 on 2020/4/17.
*/
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 Kafka_Spark {
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" -> "node001:9092,node002:9092,node003:9092",
"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("18BD12")
//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
}
}
效果
