向Kafka中发送数据
---
import java.util.HashMap
import org.apache.kafka.clients.producer.{KafkaProducer, ProducerConfig, ProducerRecord}
object KafkaWordProducer {
def main(args: Array[String]): Unit = {
// 打包部署,需要使用如下代码
/*
if(args.length < 4){
System.err.println("Usage: KafkaWordProducer <metadataBrokerList> <topic> <messagesPerSec> <wordsPerMessage>")
System.exit(1)
}
val Array(brokers, topic, messagesPerSec, wordsPerMessage) = args
*/
//直接测试,使用如下代码
val Array(brokers, topic, messagesPerSec, wordsPerMessage) = Array("localhost:9092","test_topic","3","5")
//zookeeper连接设置
//必须是Object,否则 val producer = new KafkaProducer[String,String](props) 报错
val props = new HashMap[String, Object]()
props.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, brokers)
props.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG,"org.apache.kafka.common.serialization.StringSerializer")
props.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG,"org.apache.kafka.common.serialization.StringSerializer")
val producer = new KafkaProducer[String,String](props)
//发送数据
while(true){
(1 to messagesPerSec.toInt).foreach{
messageNum =>
val str = (1 to wordsPerMessage.toInt).map(x=>scala.util.Random.nextInt(10)).mkString(" ")
println(str)
val message = new ProducerRecord[String,String](topic,null, str)
producer.send(message)
}
Thread.sleep(1000)
}
}
}
涉及到的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.test</groupId>
<artifactId>sparkTest</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<spark.version>2.1.0</spark.version>
<scala.version>2.11</scala.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-mllib_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.spark/spark-streaming-kafka-0-8 -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
<version>2.1.0</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.kafka/kafka-clients -->
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka-clients</artifactId>
<version>2.2.2</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.scala-tools</groupId>
<artifactId>maven-scala-plugin</artifactId>
<version>2.15.2</version>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.6.0</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.19</version>
<configuration>
<skip>true</skip>
</configuration>
</plugin>
</plugins>
</build>
</project>
---

浙公网安备 33010602011771号