Flink wordCunt
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>flinkProject</groupId>
<artifactId>flinkProject</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
<encoding>UTF-8</encoding>
<scala.version>2.11.8</scala.version>
<scala.binary.version>2.11</scala.binary.version>
<hadoop.version>2.7.1</hadoop.version>
<flink.version>1.7.2</flink.version>
</properties>
<dependencies>
<!-- scala 版本依赖-->
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
</dependency>
<!-- <!– flink版本依赖–>-->
<!-- <dependency>-->
<!-- <groupId>org.apache.flink</groupId>-->
<!-- <artifactId>flink-java</artifactId>-->
<!-- <version>${flink.version}</version>-->
<!-- </dependency>-->
<!-- <!– flink java streaming 依赖–>-->
<!-- <dependency>-->
<!-- <groupId>org.apache.flink</groupId>-->
<!-- <artifactId>flink-streaming-java_${scala.binary.version}</artifactId>-->
<!-- <version>${flink.version}</version>-->
<!-- </dependency>-->
<!-- flink scala 依赖-->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-scala_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<!-- flink scala streaming 依赖-->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-scala_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<!-- flink table 依赖-->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-table_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<!-- flink 客户端依赖-->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-clients_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<!-- flink kafka 依赖-->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-kafka-0.10_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<!-- flink sink ElasticSearch -->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-elasticsearch5_2.11</artifactId>
<version>1.6.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.38</version>
</dependency>
<!-- fasjson 依赖-->
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.4</version>
</dependency>
</dependencies>
<build>
<sourceDirectory>src/main/scala</sourceDirectory>
<plugins>
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.2.2</version>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
<configuration>
<args>
<arg>-dependencyfile</arg>
<arg>${project.build.directory}/.scala_dependencies</arg>
</args>
</configuration>
</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>
<transformers>
<transformer
implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
<mainClass></mainClass>
</transformer>
</transformers>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
import org.apache.flink.streaming.api.scala._
object Flink_readfile {
def main(args: Array[String]): Unit = {
val env = StreamExecutionEnvironment.getExecutionEnvironment
//设置全局并行度
env.setParallelism(1)
case class sensor(pw: String, phone: String, num: Double)
// 数据格式 ad%3*@ikDJFDD&#j1 ,13423781579,131
// 用户密码,手机号,下单笔数
val streamData = env.readTextFile("E:\\Project\\flinkProject\\dataSource\\log.txt")
val stream: DataStream[sensor] = streamData.map(t => {
val arr = t.split(",")
sensor(arr(0).trim, arr(1), arr(2).toDouble)
})
.keyBy(0)
.sum(2)
// 设置 print()的并行度 setParallelism(n)
// stream .print().setParallelism(1)
stream.print()
// 启动
env.execute("Flink_readfile")
}
}
/*
最终结果
sensor(ad%3*@ikDJFDD&#j1,13423781579,131.0)
sensor(ad%3*@ikDJFDD&#j5,13423781575,157.0)
sensor(ad%3*@ikDJFDD&#j3,13423781575,157.0)
sensor(ad%3*@ikDJFDD&#j4,13423781576,156.0)
sensor(ad%3*@ikDJFDD&#j5,13423781575,314.0)
sensor(ad%3*@ikDJFDD&#j4,13423781576,307.0)
sensor(ad%3*@ikDJFDD&#j2,13423781579,151.0)
sensor(ad%3*@ikDJFDD&#j4,13423781576,459.0)
sensor(ad%3*@ikDJFDD&#j1,13423781579,282.0)
sensor(ad%3*@ikDJFDD&#j4,13423781576,613.0)
*/
2224

被折叠的 条评论
为什么被折叠?



