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>cn.edu360.spark</groupId>
<artifactId>streaming-kafka10</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
<scala.version>2.11.7</scala.version>
<spark.version>2.2.3</spark.version>
<hadoop.version>2.7.7</hadoop.version>
<encoding>UTF-8</encoding>
</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>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
<version>2.2.3</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.38</version>
</dependency>
<dependency>
<groupId>redis.clients</groupId>
<artifactId>jedis</artifactId>
<version>2.9.0</version>
</dependency>
</dependencies>
<build>
<pluginManagement>
<plugins>
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.2.2</version>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.5.1</version>
</plugin>
</plugins>
</pluginManagement>
<plugins>
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<executions>
<execution>
<id>scala-compile-first</id>
<phase>process-resources</phase>
<goals>
<goal>add-source</goal>
<goal>compile</goal>
</goals>
</execution>
<execution>
<id>scala-test-compile</id>
<phase>process-test-resources</phase>
<goals>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<executions>
<execution>
<phase>compile</phase>
<goals>
<goal>compile</goal>
</goals>
</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>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
DirectStream.scala
package XXX
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.SparkConf
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010._
import org.apache.spark.streaming.{Seconds, StreamingContext}
/**
* Created by ...
*/
object DirectStream {
def main(args: Array[String]): Unit = {
val group = "g0"
val topic = "my-orders"
//创建SparkConf,如果将任务提交到集群中,那么要去掉.setMaster("local[2]")
val conf = new SparkConf().setAppName("DirectStream").setMaster("local[2]")
//创建一个StreamingContext,其里面包含了一个SparkContext
val streamingContext = new StreamingContext(conf, Seconds(5));
//配置kafka的参数
val kafkaParams = Map[String, Object](
//指定broker所在位置
"bootstrap.servers" -> "L1:9092,L2:9092,L3:9092",
//指定写入数据和读取数据的编码方式
"key.deserializer" -> classOf[StringDeserializer],
"value.deserializer" -> classOf[StringDeserializer],
"group.id" -> group,
"auto.offset.reset" -> "earliest", // lastest
"enable.auto.commit" -> (false: java.lang.Boolean)
)
val topics = Array(topic)
//用直连方式读取kafka中的数据,在Kafka中记录读取偏移量
val stream = KafkaUtils.createDirectStream[String, String](
streamingContext,
//位置策略(如果kafka和spark程序部署在一起,会有最优位置)
PreferConsistent,
//订阅的策略(可以指定用正则的方式读取topic,比如my-ordsers-.*)
Subscribe[String, String](topics, kafkaParams)
)
//迭代DStream中的RDD,将每一个时间点对于的RDD拿出来
stream.foreachRDD { rdd =>
if(!rdd.isEmpty()) {
//获取该RDD对于的偏移量
val offsetRanges = rdd.asInstanceOf[HasOffsetRanges].offsetRanges
//拿出对于的数据,foreach是一个aciton
rdd.foreach{ line =>
println(line.key() + " " + line.value())
}
//更新偏移量
// some time later, after outputs have completed
stream.asInstanceOf[CanCommitOffsets].commitAsync(offsetRanges)
}
}
streamingContext.start()
streamingContext.awaitTermination()
}
}