Flink批处理WordCount代码实现

1.在Idea工程根目录下新建一个 input 文件夹，并在下面创建文本文件 words.txt

2.在 words.txt 中输入一些文字，例如：

hello world
hello flink
hello java

 3.在 com.atguigu.chapter02 包下新建 Java 类 BatchWordCount，在静态 main 方法中编
写测试代码。

我们进行单词频次统计的基本思路是：先逐行读入文件数据，然后将每一行文字拆分成单
词；接着按照单词分组，统计每组数据的个数，就是对应单词的频次。

package com.atguigu.wc;

import akka.routing.RoutedActorCell;
import org.apache.flink.api.common.typeinfo.Types;
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;

import java.util.Collection;
import java.util.concurrent.ExecutionException;

public class BatchWordCount {
    public static void main(String[] args) throws Exception{
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        DataSource<String>  lineDataSource = env.readTextFile("input/words.txt");

        FlatMapOperator<String ,Tuple2<String, Long>> wordAndOneTuple = lineDataSource.flatMap((String line, Collector<Tuple2<String, Long>> out) -> {
            String[] words = line.split(" ");
            for (String word:words){
                out.collect(Tuple2.of(word,1L));
            }
        })
                .returns(org.apache.flink.api.common.typeinfo.Types.TUPLE(org.apache.flink.api.common.typeinfo.Types.STRING, Types.LONG));

        UnsortedGrouping<Tuple2<String,Long>> wordAndOneGroup = wordAndOneTuple.groupBy(0);

        AggregateOperator<Tuple2<String, Long>> sum = wordAndOneGroup.sum(1);

        sum.print();
    }
}