- 在resource 中添加01_wordCount.txt
hello flink
hello flink
pom
<?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.stt.flink</groupId>
<artifactId>flink-demo</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-scala_2.11</artifactId>
<version>1.7.2</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>1.7.2</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>
scala
package com.stt.flink
import org.apache.flink.api.scala.{AggregateDataSet, DataSet, ExecutionEnvironment}
import org.apache.flink.api.scala._ // 隐式转换需要
// 批处理wordCount程序
object Ch_01_wordCount {
def main(args: Array[String]): Unit = {
// 创建运行环境
val env = ExecutionEnvironment.getExecutionEnvironment
// 从文件中读取数据
val inputPath = this.getClass.getClassLoader.getResource("01_wordCount.txt").getPath
val inputDS: DataSet[String] = env.readTextFile(inputPath)
// 分词之后,对单词进行groupby 分组,然后用sum进行聚合
val wordCountDS: AggregateDataSet[(String, Int)] = inputDS
.flatMap(_.split("\\s+")) // 对每一行进行空格分隔
.map((_,1)) // 转换为元组
.groupBy(0) // 对第一个元素进行分组
.sum(1) // 对第二个元素进行聚合统计
// 打印输出
wordCountDS.print()
}
}
SLF4J: Failed to load class "org.slf4j.impl.StaticLoggerBinder".
SLF4J: Defaulting to no-operation (NOP) logger implementation
SLF4J: See http://www.slf4j.org/codes.html#StaticLoggerBinder for further details.
(flink,2)
(hello,2)
网友评论