1.搭建maven工程 flink-2019
1.2pom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.atguigu.flink</groupId>
<artifactId>flink</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-scala_2.11</artifactId>
<version>1.7.0</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.flink/flink-streaming-scala -->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-scala_2.11</artifactId>
<version>1.7.0</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>compile</goal>
<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> |
1.2 添加scala框架 和 scala文件夹
2 批处理wordcount
package com.imau.edu.flink
import org.apache.flink.api.scala.ExecutionEnvironment
import org.apache.flink.api.scala._
object DataSet_WordCount {
def main(args:Array[String]):Unit={
//1.env 初始化环境
val env = ExecutionEnvironment.getExecutionEnvironment
//2.source 数据源
val Dataset = env.readTextFile("D:\\flinkdemo\\hello.txt")
//3.transform 转换
/**
* 在flink里面把reduceBykey分开了，
* Bykey和计算分开了
*/
val datasum = Dataset.flatMap((_.split(" "))).map((_,1)).groupBy(0).sum(1)
//4.sink 类似于行动算子
datasum.print()
}
}
3 流处理 wordcount
package com.imau.edu.flink
import org.apache.flink.streaming.api.scala.StreamExecutionEnvironment
import org.apache.flink.api.scala._
object DataStream_WordCount {
def main(args:Array[String]):Unit={
// env 初始化环境
val env = StreamExecutionEnvironment.getExecutionEnvironment
// source 数据源 使用netcat模拟实时数据 nc -lk 7777
val dataStream = env.socketTextStream("Faded103",7777)
// transform 转换
val sumdatastream = dataStream.flatMap((_.split(" "))).filter(_.nonEmpty).map((_,1)).keyBy(0).sum(1)
// sink 类似于行动算子
sumdatastream.print()
env.execute()
}
}
