一下是一个简单的flink word count任务demo代码
pom配置文件
<?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">
<parent>
<artifactId>simple-demo</artifactId>
<groupId>org.example</groupId>
<version>1.0-SNAPSHOT</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>flink</artifactId>
<properties>
<maven.compiler.source>8</maven.compiler.source>
<maven.compiler.target>8</maven.compiler.target>
<flink.version>1.17.0</flink.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-java</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-clients</artifactId>
<version>${flink.version}</version>
</dependency>
</dependencies>
</project>
任务编写
package com.xx.flink.task;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.AggregateOperator;
import org.apache.flink.api.java.operators.DataSource;
import org.apache.flink.api.java.operators.FlatMapOperator;
import org.apache.flink.api.java.operators.UnsortedGrouping;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;
/**
* TODO DataSet API 实现 wordcount(不推荐)
*/
public class WordCountBatchDemo {
public static void main(String[] args) throws Exception {
// TODO 1. 创建执行环境
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
// TODO 2.读取数据:从文件中读取
DataSource<String> lineDS = env.readTextFile("E:\\code-opensource\\simple-demo\\flink\\input\\word.txt");
// TODO 3.切分、转换 (word,1)
FlatMapOperator<String, Tuple2<String, Integer>> wordAndOne = lineDS.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
@Override
public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
// TODO 3.1 按照 空格 切分单词
String[] words = value.split(" ");
// TODO 3.2 将 单词 转换为 (word,1)
for (String word : words) {
Tuple2<String, Integer> wordTuple2 = Tuple2.of(word, 1);
//TODO 3.3 使用 Collector 向下游发送数据
out.collect(wordTuple2);
}
}
});
// TODO 4.按照 word 分组
UnsortedGrouping<Tuple2<String, Integer>> wordAndOneGroupby = wordAndOne.groupBy(0);
// TODO 5.各分组内聚合
AggregateOperator<Tuple2<String, Integer>> sum = wordAndOneGroupby.sum(1); // 1是位置,表示第二个元素
// TODO 6.输出
sum.print();
}
}
结果输出
over~~