Word Count案例

有界流处理

package com.atguigu.wc;

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

public class BoundedStreamWordCount {
    public static void main(String[] args) throws Exception {
        //1.创建流式执行环境
        StreamExecutionEnvironment env=StreamExecutionEnvironment.getExecutionEnvironment();

        //2.读取文件
        DataStreamSource<String> lineDataStreamSource = env.readTextFile("input/words.txt");

        //3.转换计算
        SingleOutputStreamOperator<Tuple2<String,Long>> wordAndOneTuple=lineDataStreamSource.flatMap((String line, Collector< Tuple2<String,Long>> out) -> {
            String[] words=line.split(" ");
            for(String word:words) {
                out.collect(Tuple2.of(word, 1L));
            }
        })
                .returns(Types.TUPLE(Types.STRING,Types.LONG));

        //4.分组
        KeyedStream<Tuple2<String,Long>,String> wordAndOneKeyedStream=wordAndOneTuple.keyBy(data->data.f0);

        //5.求和
        SingleOutputStreamOperator<Tuple2<String,Long>> sum=wordAndOneKeyedStream.sum(1);

        //6.打印
        sum.print();

        //7.启动执行
        env.execute();
    }
}

无界流处理
在虚拟机开启一台服务器hadoop102，并且输入 nc -lk 7777
7777是指设定一个端口号

package com.atguigu.wc;

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

public class StreamWordCount {
    public static void main(String[] args) throws Exception {
        //1.创建流式执行环境
        StreamExecutionEnvironment env=StreamExecutionEnvironment.getExecutionEnvironment();
        //2.读取文本流
        DataStreamSource<String> lineDataStream=env.socketTextStream("hadoop102",7777);
        //3.转换计算
        SingleOutputStreamOperator<Tuple2<String,Long>> wordAndOneTuple=lineDataStream.flatMap((String line, Collector< Tuple2<String,Long>> out) -> {
            String[] words=line.split(" ");
            for(String word:words) {
                out.collect(Tuple2.of(word, 1L));
            }
        })
                .returns(Types.TUPLE(Types.STRING,Types.LONG));

        //4.分组
        KeyedStream<Tuple2<String,Long>,String> wordAndOneKeyedStream=wordAndOneTuple.keyBy(data->data.f0);

        //5.求和
        SingleOutputStreamOperator<Tuple2<String,Long>> sum=wordAndOneKeyedStream.sum(1);

        //6.打印
        sum.print();

        //7.启动执行
        env.execute();
    }
}

上面的做法是直接在程序中指出了主机名hostname和端口号port，在实际生产中是从参数或配置文件中读取。修改代码如图

执行前还要修改一下配置信息