flink2-有界流计算wordcount

流式处理分为有界流和无界流
1）有界流
有界流就是读取的数据是有界限的，在流不关闭的情况下，能读取到数据的尽头
2）无界流
在人为不干预的情况下，流一直在，不会停，数据没有边界

package day01;


import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

public class Flink02_wordCount_Bounded {
    public static void main(String[] args) throws Exception {
        //流式处理，有界流
        //获取执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        //读取文件
        DataStream<String> DS = env.readTextFile("input");
        //对每行数据进行flatMap
        SingleOutputStreamOperator<String> words = DS.flatMap(new Flink01_wordcount_batch.MyFlatMap());
        //改变每个单词的结构：word->(word,1)
        SingleOutputStreamOperator<Tuple2<String, Integer>> wordToOne = words.map(new MapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public Tuple2<String, Integer> map(String s) throws Exception {
                return new Tuple2<>(s,1);
            }
        });
        //按照key进行分组,但是在流处理中，没有groupBy,有keyBY,需要传入KeySelector对象，输入参数是tuple2，输出只要key进行分组就行
        KeyedStream<Tuple2<String, Integer>, String> wordGroup = wordToOne.keyBy(new KeySelector<Tuple2<String, Integer>, String>() {
            @Override
            public String getKey(Tuple2<String, Integer> stringIntegerTuple2) throws Exception {
                return stringIntegerTuple2.f0;
            }
        });
        //将分组好的数据进行聚合
        SingleOutputStreamOperator<Tuple2<String, Integer>> result = wordGroup.sum(1);
        //打印结果
        result.print();
        //开启流
        env.execute("wordcount");


    }
}