FlinkSQL实现WordCount

最新推荐文章于 2024-08-06 10:35:08 发布

原创

最新推荐文章于 2024-08-06 10:35:08 发布 · 940 阅读

2 ·

CC 4.0 BY-SA版权

本文详细介绍了如何使用FlinkSQL实现经典的WordCount案例，从数据源接入到SQL编写，再到结果输出，深入浅出地展示了Flink在流处理场景中的应用。

import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.TableEnvironment;
import org.apache.flink.table.api.java.BatchTableEnvironment;

import java.util.ArrayList;
import java.util.List;

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

        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        BatchTableEnvironment tEnv = TableEnvironment.getTableEnvironment(env);

        List list = new ArrayList();
        String wordsStr = "Hello Flink Hello TOM";
        String[] words = wordsStr.split("\\W+");
        for(String word : words){
            WC wc = new WC(word, 1);
            list.add(wc);
        }
        DataSet<WC> input = env.fromCollection(list);
        tEnv.registerDataSet("WordCount", input, "word, frequency");
        Table table = tEnv.sqlQuery(
                "SELECT word, SUM(frequency) as frequency FROM WordCount GROUP BY word");
        DataSet<WC> result = tEnv.toDataSet(table, WC.class);
        result.print();
    }//main

    public static class WC {
        public String word;//hello
        public long frequency;//1

        // public constructor to make it a Flink POJO
        public WC() {}

        public WC(String word, long frequency) {
            this.word = word;
            this.frequency = frequency;
        }

        @Override
        public String toString() {
            return "WC " + word + " " + frequency;
        }
    }
}

<?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>FlinkSql</groupId>
    <artifactId>FlinkSql</artifactId>
    <version>1.0-SNAPSHOT</version>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>1.7</source>
                    <target>1.7</target>
                    <encoding>UTF-8</encoding>
                </configuration>
            </plugin>
            <!--scala插件-->
            <plugin>
                <groupId>org.scala-tools</groupId>
                <artifactId>maven-scala-plugin</artifactId>
                <version>2.15.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal&