flink 1.10.1 idea java读取本地文件进行wordcount

1. 创建maven项目，添加依赖

<dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>1.10.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.12</artifactId>
            <version>1.10.1</version>
        </dependency>
    </dependencies>

2. wordcount代码

package com.demo;

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

public class FileWordCount {

    public static void main(String[] args) throws Exception {
        //创建执行环境
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        //从文件中读取数据
        String inputPath = "data/wordcount.txt";
        DataSet<String> inputDataSet = env.readTextFile(inputPath);
        //对数据集进行处理，按照空格进行分词，转换成（word，1）二元组进行统计
        DataSet<Tuple2<String, Integer>> resultSet = inputDataSet.flatMap(new MyflatMapper())
                .groupBy(0) //按照第一个位置的word分组
                .sum(1); //讲第二个位置上的数据求和

        resultSet.print();
    }

    //自定义类，实现FlatMapFunction接口
    public static class MyflatMapper implements FlatMapFunction<String, Tuple2<String, Integer>> {

        public void flatMap(String s, Collector<Tuple2<String, Integer>> collector) throws Exception {
            //按空格分词
            String[] words = s.split(" ");
            //遍历所有word，包成二元组输出
            for(String word:words){
                collector.collect(new Tuple2<String, Integer>(word, 1));
            }
        }
    }
}

3. 数据文件wordcount.txt

hello world
hello spark
hello flink

在项目目录下创建data目录，并在data目录下创建wordcount.txt文件。

4. 运行程序

输出如下：