flink的local模式实现单词计数器(批处理方式)

naseng

已于 2022-04-16 22:31:34 修改

阅读量876

点赞数

分类专栏：大数据开发文章标签： flink

于 2022-04-16 22:31:24 首次发布

本文链接：https://blog.csdn.net/cqscf/article/details/124222041

版权

大数据开发专栏收录该内容

16 篇文章 1 订阅

订阅专栏

flink的local模式实现单词计数器(批处理方式)

在idea中创建Java maven项目

导入maven依赖

<?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>bigDataCode</artifactId>
        <groupId>org.example</groupId>
        <version>1.0-SNAPSHOT</version>
    </parent>
    <modelVersion>4.0.0</modelVersion>

    <artifactId>flink-wordcount</artifactId>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>1.12.5</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.12</artifactId>
            <version>1.12.5</version>
            <!--<scope>provided</scope>-->
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_2.12</artifactId>
            <version>1.12.5</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <!-- 编译插件 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>

关键代码

package com.xxx.flink;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.*;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;

/***
 * 批处理单词计数器
 */
public class BatchWordCountJava2 {

    public static void main(String[] args) throws Exception{
        // 创建一个批处理的执行环境
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        // 从文件中读取数据
        DataSource<String> inputDataSet = env.readTextFile("D:/tmp/flink/input.txt");
        // 基于 DataSet做转换，首先按空格分词打散，然后按照word作为key做group by
        //3：对接收到的数据进行空格拆分
        FlatMapOperator<String, String> words = inputDataSet.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public void flatMap(String line, Collector<String> out) throws Exception {
                //切分
                String[] words = line.split(" ");
                for (String word : words) {
                    //输出
                    out.collect(word);
                }
            }
        });
        //4：对拆分后的单词，每个单词记一次数
        MapOperator<String, Tuple2<String, Integer>> wordAndOne = words.map(new MapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public Tuple2<String, Integer> map(String word) throws Exception {
                return Tuple2.of(word, 1);
            }
        });
        //5：对拆分后的单词进行分组
        UnsortedGrouping<Tuple2<String, Integer>> groupedStream = wordAndOne.groupBy(0);
        //6：根据单词的次数进行聚合
        AggregateOperator<Tuple2<String, Integer>> summed = groupedStream.sum(1);
        // 打印输出
        summed.print();
    }

}