1. flink 基础

flink word count  程序

1. 数据集模式

pom.xml 文件

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>deng.com</groupId>
    <artifactId>flink_demo</artifactId>
    <version>1.0-SNAPSHOT</version>
    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
    </properties>
    <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>

</project>

wordCount 程序

package com.deng;
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 WordCount {
    public static void main(String[] args) throws Exception {
        // 创建执行环境
        ExecutionEnvironment env =ExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(8);
        // 从文件中读取数据
        String inputPath="C:\\Users\\侠客云\\IdeaProjects\\flink_demo\\src\\main\\resources\\hello.txt";
        DataSet<String> inputDataSet = env.readTextFile(inputPath);
        // 对数据集进行处理，按空格分词展开，转换成（word,1）二元组
        DataSet<Tuple2<String,Integer>> resultSets= inputDataSet.flatMap(new MyFlatMaper())
                .groupBy(0)//按照第一个位置word 进行分组
                .sum(1) //按照 第二个位置上的数据求和
        ;
        resultSets.print();
    }
    // 自定义类，实现 FlatMapFunction 接口
    public static class MyFlatMaper implements FlatMapFunction<String, Tuple2<String,Integer>>{
        @Override
        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
            for (String word : words) {
                collector.collect(new Tuple2<>(word,1));
            }
        }
    }

}

2 流式数据集模式

StreamWordCount 程序

package com.deng;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
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.创建流处理执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(8);
        // 2.
        // 从文件中读取数据
//        String inputPath="C:\\Users\\侠客云\\IdeaProjects\\flink_demo\\src\\main\\resources\\hello.txt";
//        DataStream<String> inPutDataStream = env.readTextFile(inputPath);
        // 用parameter tool 从程序启动参数中获取配置项
        ParameterTool parameterTool = ParameterTool.fromArgs(args);
        String host = parameterTool.get("host");
        int port = parameterTool.getInt("port");

        // 从socket文件流中获取数据
//        DataStream<String> inPutDataStream =env.socketTextStream("hadoop102",7777);
        DataStream<String> inPutDataStream =env.socketTextStream(host,port);
        DataStream<Tuple2<String, Integer>> resultStream = inPutDataStream.flatMap(new MyFlatMaper())
                .keyBy(0)
                .sum(1);
        resultStream.print();
        // 执行任务
        env.execute();

    }

    // 自定义类，实现 FlatMapFunction 接口
    public static class MyFlatMaper implements FlatMapFunction<String, Tuple2<String,Integer>> {
        @Override
        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
            for (String word : words) {
                collector.collect(new Tuple2<>(word,1));
            }
        }
    }
}

 测试环境中执行程序传参代码时，如何运行：