文章目录
前言
Flink1.12.0简单实现wordcount
一、Flink1.12.0简单实现wordcount
Flink1.12.0简单实现wordcount
二、使用步骤
1.引入pom.xml
代码如下(示例):
<?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">
<parent>
<artifactId>flinkdemo</artifactId>
<groupId>com.flink.pangsl</groupId>
<version>1.0-SNAPSHOT</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>frauddetection</artifactId>
<packaging>jar</packaging>
<name>Flink Walkthrough DataStram Scala</name>
<url>https://flink.apache.org</url>
<repositories>
<repository>
<id>apache.snapshots</id>
<name>Apache Development Snapshot Repository</name>
<url>https://repository.apache.org/content/repositories/snapshots/</url>
<releases>
<enabled>false</enabled>
</releases>
<snapshots>
<enabled>true</enabled>
</snapshots>
</repository>
</repositories>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<flink.version>1.12.0</flink.version>
<scala.binary.version>2.11</scala.binary.version>
<scala.version>2.11.12</scala.version>
<log4j.version>2.12.1</log4j.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-walkthrough-common_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<!-- Apache Flink dependencies -->
<!-- These dependencies are provided, because they should not be packaged into the JAR file. -->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-scala_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-clients_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<scope>compile</scope>
</dependency>
<!-- Add connector dependencies here. They must be in the default scope (compile). -->
<!-- Example:
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-kafka_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
-->
<!-- Add logging framework, to produce console output when running in the IDE. -->
<!-- These dependencies are excluded from the application JAR by default. -->
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-slf4j-impl</artifactId>
<version>${log4j.version}</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-api</artifactId>
<version>${log4j.version}</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<version>${log4j.version}</version>
<scope>runtime</scope>
</dependency>
</dependencies>
<build>
<plugins>
<!-- We use the maven-shade plugin to create a fat jar that contains all necessary dependencies. -->
<!-- Change the value of <mainClass>...</mainClass> if your program entry point changes. -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>3.0.0</version>
<executions>
<!-- Run shade goal on package phase -->
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<artifactSet>
<excludes>
<exclude>org.apache.flink:force-shading</exclude>
<exclude>com.google.code.findbugs:jsr305</exclude>
<exclude>org.slf4j:*</exclude>
<exclude>org.apache.logging.log4j:*</exclude>
</excludes>
</artifactSet>
<filters>
<filter>
<!-- Do not copy the signatures in the META-INF folder.
Otherwise, this might cause SecurityExceptions when using the JAR. -->
<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>spendreport.FraudDetectionJob</mainClass>
</transformer>
</transformers>
</configuration>
</execution>
</executions>
</plugin>
<!-- Java Compiler -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.1</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
<!-- Scala Compiler -->
<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>
</execution>
</executions>
<configuration>
<args>
<arg>-nobootcp</arg>
</args>
</configuration>
</plugin>
<!-- Eclipse Scala Integration -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-eclipse-plugin</artifactId>
<version>2.8</version>
<configuration>
<downloadSources>true</downloadSources>
<projectnatures>
<projectnature>org.scala-ide.sdt.core.scalanature</projectnature>
<projectnature>org.eclipse.jdt.core.javanature</projectnature>
</projectnatures>
<buildcommands>
<buildcommand>org.scala-ide.sdt.core.scalabuilder</buildcommand>
</buildcommands>
<classpathContainers>
<classpathContainer>org.scala-ide.sdt.launching.SCALA_CONTAINER</classpathContainer>
<classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
</classpathContainers>
<excludes>
<exclude>org.scala-lang:scala-library</exclude>
<exclude>org.scala-lang:scala-compiler</exclude>
</excludes>
<sourceIncludes>
<sourceInclude>**/*.scala</sourceInclude>
<sourceInclude>**/*.java</sourceInclude>
</sourceIncludes>
</configuration>
</plugin>
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>build-helper-maven-plugin</artifactId>
<version>1.9.1</version>
<executions>
<!-- Add src/main/scala to eclipse build path -->
<execution>
<id>add-source</id>
<phase>generate-sources</phase>
<goals>
<goal>add-source</goal>
</goals>
<configuration>
<sources>
<source>src/main/scala</source>
</sources>
</configuration>
</execution>
<!-- Add src/test/scala to eclipse build path -->
<execution>
<id>add-test-source</id>
<phase>generate-test-sources</phase>
<goals>
<goal>add-test-source</goal>
</goals>
<configuration>
<sources>
<source>src/test/scala</source>
</sources>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
2.主类
代码如下(示例):
package wordcount
import org.apache.flink.api.scala.ExecutionEnvironment
/**
* @author pangsl
* @date 2021/3/31 15:38
*/
object WordCount {
def main(args: Array[String]): Unit = {
//1.准备环境-env,注意导scala包
val env: ExecutionEnvironment = ExecutionEnvironment.getExecutionEnvironment
//2.数据源-Source
import org.apache.flink.api.scala._
val linesDS: DataSet[String] = env.fromElements("Flink Spark Hadoop", "Flink Spark", "Flink")
//3.数据转换-Transformation 每一行按照空格切分并压平
val wordDS: DataSet[String] = linesDS.flatMap(_.split(" "))
//每个单词记为1
val wordAndOneDS: DataSet[(String, Int)] = wordDS.map((_, 1))
//分组
val groupedDS: GroupedDataSet[(String, Int)] = wordAndOneDS.groupBy(0) //0表示按照索引为0的元素即单词进行分组
//注意:聚合不支持key选择器函数,也就是不支持_._1,否则报错:Aggregate does not support grouping with KeySelector functions, yet.
//val groupedDS: GroupedDataSet[(String, Int)] = wordAndOneDS.groupBy(_._1)
//聚合
val result: AggregateDataSet[(String, Int)] = groupedDS.sum(1) //1表示按照索引为1的元素即数量进行聚合
//4.数据输出-Sink
result.print() //print可以触发执行
//5.调用执行操作
//env.execute()//latest call to 'execute()', 'count()', 'collect()', or 'print()'
}
}
3.运行结果
总结
Flink1.12.0简单实现wordcount,并打印输出。