flink进阶篇-02-Flink快速上手_flink上手难度-CSDN博客

本文链接：https://blog.csdn.net/q287573145/article/details/124117338

1、搭建 maven 工程 FlinkTutorial

pom 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>com.wyb.flink</groupId>
    <artifactId>FlinkTutorial</artifactId>
    <version>1.0-SNAPSHOT</version>
    
    <properties>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</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>
    
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>
   
</project>

2、批处理 wordcount

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.operators.DataSource;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.util.Collector;

/**
 * 批处理word count
 */
public class WordCount {
    public static void main(String[] args) throws Exception{
        // 1、创建批处理执行环境
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        // 2、从文件中读取数据
        String inputPath = "D:\\Projects\\BigData\\FlinkTutorial\\src\\main\\resources\\hello.txt";
        DataSet<String> inputDataSet = env.readTextFile(inputPath);

        ///3、对数据集进行处理，按空格分词展开，转换成(word, 1)二元组进行统计
        DataSet<Tuple2<String, Integer>> resultSet = inputDataSet.flatMap(new MyFlatMapper())
                .groupBy(0)    // 按照第一个位置的word分组
                .sum(1);    // 将第二个位置上的数据求和

        resultSet.print();
    }

    // 自定义类，实现FlatMapFunction接口
    public static class MyFlatMapper implements FlatMapFunction<String, Tuple2<String, Integer>> {
        @Override
        public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
            // 按空格分词
            String[] words = value.split(" ");
            // 遍历所有word，包成二元组输出
            for (String word : words) {
                out.collect(new Tuple2<>(word, 1));
            }
        }
    }
}

示例文件：hello.txt

hello world
hello flink
hello java
how are you
hello tom

3、流处理 wordcount

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.environment.StreamExecutionEnvironment;

/**
 * 流处理word count
 */
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();

        //2、用parameter tool工具从程序启动参数中提取配置项
        ParameterTool parameterTool = ParameterTool.fromArgs(args);
        String host = parameterTool.get("host");
        int port = parameterTool.getInt("port");

        //3、从socket文本流读取数据
        DataStream<String> inputDataStream = env.socketTextStream(host, port);

        //4、基于数据流进行转换计算
        DataStream<Tuple2<String, Integer>> resultStream = inputDataStream.flatMap(new WordCount.MyFlatMapper()).slotSharingGroup("green")
                .keyBy(0)
                .sum(1).setParallelism(2).slotSharingGroup("red");

        resultStream.print().setParallelism(1);

        // 执行任务
        env.execute();
    }
}