二、编写word count示例代码来初步认识flink及了解批与流处理的区别

最新推荐文章于 2025-03-02 06:30:00 发布

我才是真的封不觉

最新推荐文章于 2025-03-02 06:30:00 发布

阅读量578

点赞数

CC 4.0 BY-SA版权

分类专栏： flink从入门到入坟文章标签： flink java apache

本文链接：https://blog.youkuaiyun.com/JavaCoder_juejue/article/details/123315726

flink从入门到入坟专栏收录该内容

5 篇文章

订阅专栏

引入依赖

        <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>

批处理代码（未知原因暂时数据没有打印后续知道了来补充）

package com.robert.flink.wcTest;

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 FlinkBatchWordCountPrintTest {

    public static void main(String[] args) throws Exception {

        //get runtime environment
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        //path of file for test
        String filePath = "D:\\word.txt";

        //read content into dataset from file
        DataSet<String> stringDataSet = env.readTextFile(filePath);

        DataSet<Tuple2<String, Integer>> sum = stringDataSet.flatMap(new FlatMapFunction<String, Tuple2<String,Integer>>() {

            @Override
            public void flatMap(String value, Collector<Tuple2<String, Integer>> collector) {
                String[] words = value.split("");
                for (String word : words) {
                    collector.collect(new Tuple2<>(word, 1));
                }
            }
        }).groupBy(0).sum(1);



        //print content of dataset
        sum.print();

    }

}

流处理代码（未知原因暂时数据没有打印后续知道了来补充）

package com.robert.flink.wcTest;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.DataSet;
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.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

public class FlinStreamWordCountPrintTest {

    public static void main(String[] args) throws Exception {

        //get runtime environment
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        //path of file for test
        String filePath = "C:\\study\\咕泡\\mybatis\\06.MyBatis原理篇\\01.MyBatis应用分析与最佳实践\\课堂源码\\MyBatis第一天代码\\flink\\src\\main\\resources\\static\\word.txt";

        //read content into dataset from file
        DataStream<String> stringDataSet = env.readTextFile(filePath);


        //count word appeared times
        DataStream<Tuple2<String, Integer>> sum = stringDataSet.flatMap((FlatMapFunction<String, Tuple2<String, Integer>>) (value, collector) -> {

            String[] words = value.split(" ");
            for (String word : words) {
                collector.collect(new Tuple2<>(word, 1));
            }
        }).returns(Types.TUPLE(Types.STRING, Types.INT)).keyBy(0).sum(1);

        //print content of dataset
        sum.print();

        env.execute();

    }

}