Pom如下
<?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>spark_application</groupId>
<artifactId>spark_application</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
<spark.version>2.2.0</spark.version>
<hadoop.version>2.6.5</hadoop.version>
<encoding>UTF-8</encoding>
</properties>
<dependencies>
<!-- <dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>2.11.8</version>
</dependency>-->
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
<version>2.8.4</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-core</artifactId>
<version>2.8.4</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.module</groupId>
<artifactId>jackson-module-scala_2.11</artifactId>
<version>2.8.4</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>2.0.0</version>
</dependency>
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka_2.11</artifactId>
<version>1.0.0</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
<version>2.0.0</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>2.0.0</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>2.0.0</version>
</dependency>
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.34</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.2.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.34</version>
</dependency>
<!-- https://mvnrepository.com/artifact/com.google.guava/guava -->
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
<version>25.0-jre</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>
代码如下
import org.apache.spark.sql.SparkSession
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.log4j.{Level, Logger}
import org.apache.spark.streaming.kafka010.KafkaUtils
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
import org.apache.spark.streaming.{Seconds, StreamingContext}
/**
* Created by maokm on 2018/10/16.
*/
object ThirdData {
def getSparkSession = {
SparkSession
.builder()
.appName(s"${this.getClass.getSimpleName}")
.config("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
.master("local[1]")
.getOrCreate()
}
def main(args: Array[String]): Unit = {
Logger.getLogger("org").setLevel(Level.ERROR)
val session: SparkSession = getSparkSession
println("test")
val sc=session.sparkContext
val ssc=new StreamingContext(sc,Seconds(5))
val topics=Array("test")
val kafkaParams=Map[String,Object](
"bootstrap.servers"->constant.BROKERS,
"key.deserializer" -> classOf[StringDeserializer],
"value.deserializer" -> classOf[StringDeserializer],
"group.id" -> "m1",
"auto.offset.reset" -> "latest",
"enable.auto.commit" -> (false: java.lang.Boolean)
)
val messages=KafkaUtils.createDirectStream[String,String](
ssc,
PreferConsistent,//consumer调度分区位置策略
Subscribe[String,String](topics,kafkaParams)//consumer消费策略
)
val lines=messages.map(x=>{
x.value()
})
val wordCounts=lines.flatMap(x=>{
x.split(" ").map(x=>(x,1))
}).reduceByKey(_+_)
wordCounts.print()
ssc.start()
ssc.awaitTermination()
}
}