代码
package com.zxl.flink
import org.apache.flink.streaming.api.scala.StreamExecutionEnvironment
/** * flink的流计算的WordCount */
object FlinkStreamWordCount {
def main(args: Array[String]): Unit = {
//1、初始化Flink流计算的环境
val streamEnv: StreamExecutionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment
//修改并行度
streamEnv.setParallelism(1) //默认所有算子的并行度为1
//2、导入隐式转换
import org.apache.flink.streaming.api.scala._
//3、读取数据,读取sock流中的数据
//val stream: DataStream[String] = streamEnv.socketTextStream("hadoop101",8888) //DataStream ==> spark 中Dstream
//nc -lk 8888
val stream: DataStream[String] = streamEnv.socketTextStream("localhost",8888) //DataStream ==> spark 中Dstream
//4、转换和处理数据
val result: DataStream[(String, Int)] = stream.flatMap(_.split(" "))
.map((_, 1)).setParallelism(2)
.keyBy(0)//分组算子 : 0 或者 1 代表下标。前面的DataStream[二元组] , 0代表单词 ,1代表单词出现的次数
.sum(1).setParallelism(2) //聚会累加算子
//5、打印结果
result.print("结果").setParallelism(1)
//6、启动流计算程序
streamEnv.execute("wordcount")
}
}
调试
发数据

console日志输出
结果> (scala,1)
结果> (hello,1)
结果> (zxl,1)
结果> (hello,2)
结果> (hello,3)
结果> (flink,1)
结果> (hello,4)
结果> (spark,1)
结果> (filne,1)
结果> (flink,2)
附pom文件
<?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.zxl</groupId>
<artifactId>Flink-SXT</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-scala_2.11</artifactId>
<version>1.9.1</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-scala_2.11</artifactId>
<version>1.9.1</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.7.2</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.7.2</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-kafka_2.11</artifactId>
<version>1.9.1</version>
</dependency>
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka-clients</artifactId>
<version>0.11.0.3</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-filesystem_2.11</artifactId>
<version>1.9.1</version>
</dependency>
<dependency>
<groupId>org.apache.bahir</groupId>
<artifactId>flink-connector-redis_2.11</artifactId>
<version>1.0</version>
</dependency>
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.44</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-table-planner_2.11</artifactId>
<version>1.9.1</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-table-api-scala-bridge_2.11</artifactId>
<version>1.9.1</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-cep-scala_2.11</artifactId>
<version>1.9.1</version>
</dependency>
</dependencies>
<build>
<plugins>
<!-- 该插件用于将Scala代码编译成class文件 -->
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.4.6</version>
<executions>
<execution>
<!-- 声明绑定到maven的compile阶段 -->
<goals>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-assembly-plugin</artifactId>
<version>3.0.0</version>
<configuration>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
还没有评论,来说两句吧...