Flink 入门级别代码 单词统计 Java版本和scala 版本(一)

单词批处理:

scala版本:

package liangde.tech

import org.apache.flink.api.scala.ExecutionEnvironment
import org.apache.flink.streaming.api.scala._


/**
  * Scala版本
  */

object BatchWordCountScala {

  def main(args: Array[String]): Unit = {

    val env = ExecutionEnvironment.getExecutionEnvironment

    val inputpath = "C:\\Users\\liangde.li\\IdeaProjects\\FlinkExample\\src\\test\\file"
    val outpath = "C:\\Users\\liangde.li\\IdeaProjects\\FlinkExample\\src\\test"

    val text  =env.readTextFile(inputpath)

    val count = text.flatMap(_.toLowerCase.split("\\W+"))
      .filter(_.nonEmpty)
      .map(w=>(w,1))
      .groupBy(0)
      .sum(1)

    count.writeAsCsv(outpath,"\n"," ", org.apache.flink.core.fs.FileSystem.WriteMode.OVERWRITE).setParallelism(1)
    env.execute("batch word count!")


  }
}

Java 版本:

package liangde.tech;

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.util.Collector;


/**
 *
 */
public class BatchWordCountJava {
    public static void main(String[] args) throws Exception {

        //获取运行环境
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        String inputpath = "C:\\Users\\liangde.li\\IdeaProjects\\FlinkExample\\src\\test\\file";
        String outpath = "C:\\Users\\liangde.li\\IdeaProjects\\FlinkExample\\src\\test";
        //读取本地文件
        DataSource<String> text =  env.readTextFile(inputpath);

        DataSet<Tuple2<String,Integer>> counts =  text.flatMap(new Tokenizer()).groupBy(0).sum(1);
        counts.writeAsCsv(outpath,"\n"," ",org.apache.flink.core.fs.FileSystem.WriteMode.OVERWRITE).setParallelism(1);
        env.execute("bath word count");

    }

    public static class Tokenizer implements FlatMapFunction<String, Tuple2<String,Integer>>{
        public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
            String[] tokens = value.toLowerCase().split("\\W+");
            for(String token:tokens){
                if(token.length()>0){
                    out.collect(new Tuple2<String, Integer>(token,1));
                }
            }
        }
    }
}

注意创建环境用的是

ExecutionEnvironment 

返回类型用的是:

DataSet

 

流处理:

使用套接字socket来实现

scala 版本:

package liangde.tech



import org.apache.flink.api.java.utils.ParameterTool
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.api.windowing.time.Time


/**
  * 滑动窗口计算
  *
  * 每隔一秒最近2秒内的数据，打印到控制台
  *
  */


object SocketWindowWordCount {
  def main(args: Array[String]): Unit = {

      //获取socket端口号
      val port:Int = try{
        ParameterTool.fromArgs(args).getInt("port")
      }catch {
        case e: Exception=>{
          System.err.println("No port set. Use default port 9000!")
        }
          9000
      }

       //获取运行环境
      val env: StreamExecutionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment

      //链接socket获取输入数据
      val text =  env.socketTextStream("192.168.1.xx",port,'\n')

      import org.apache.flink.api.scala._
      //解析数据(数据扁平化)，分组，窗口计算，并且聚合求sum
      val wordWithCount = text.flatMap(line => line.split("\\s")).map(w =>WordWithCount(w,1))
         .keyBy("word")//分组
         .timeWindow(Time.seconds(2),Time.seconds(1))//指定窗口大小，间隔时间
         //.sum("count");//sum 或者reduce 都行
         .reduce((a,b)=>WordWithCount(a.word,a.count+b.count));


        wordWithCount.print().setParallelism(1); //打印到控制台

       env.execute("Socket Window Count!")
  }

  case class WordWithCount(word:String,count:Long
  )

}

 

Java 版本：

package liangde.tech;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.ReduceFunction;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.DataStreamSink;
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.streaming.api.windowing.time.Time;
import org.apache.flink.util.Collector;

/**
 * 滑动窗口计算
 * 通过socket模拟产生单词数据
 * flink对数据进行统计计算
 *
 * 需要实现每隔一秒对最近两秒内的数据进行汇总计算
 */

public class SocketWindowWordCountJava {

    public static void main(String[] args) throws Exception {
        // 获取需要的端口号
        int port;
        try {
            ParameterTool parameterTool = ParameterTool.fromArgs(args);
            port = parameterTool.getInt("port");
        }catch (Exception e){
            System.out.print("No port set .Use default port 9000");
            port = 9000;
        }


        //获取Flink的运行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        String hostname = "192.168.1.35";
        String delimiter = "\n";
        //链接socket获取输入的数据
        DataStreamSource<String> text =  env.socketTextStream(hostname,port,delimiter);

        // a b c
        // a 1
        // b 1
        // c 1
        DataStream<WordWithCount> windowCounts = text.flatMap(new FlatMapFunction<String, WordWithCount>() {
            public void flatMap(String value, Collector<WordWithCount> out) throws Exception {
                String[] splits = value.split("\\s");
                for(String word:splits){
                    out.collect(new WordWithCount(word,1));
                }
            }
        }).keyBy("word")
                .timeWindow(Time.seconds(2),Time.seconds(1)) //指定时间窗口大小为
                .sum("count"); // 在这里使用sum或者reduce都可以
//                .reduce(new ReduceFunction<WordWithCount>() {
//                    public WordWithCount reduce(WordWithCount a, WordWithCount b) throws Exception {
//                        return  new WordWithCount(a.word,a.count+b.count);
//                    }
//                })
        //把数据打印到控制台并且设置并行度
        windowCounts.print().setParallelism(1);

        //这行代码一定要实现，否则程序不执行
        env.execute("Socket window count");
    }

    public static class WordWithCount{
        public String word;
        public long count;
        public WordWithCount(){}
        public WordWithCount(String word,long count){
            this.word = word;
            this.count = count;
        }
        @Override
        public  String toString(){
             return  "WordWithCount{" +
                     "word='" + word + '\''+
                     ",count =" + count +
                     '}';
        }

    }
}

 

注意这里的API 是:

StreamExecutionEnvironment

返回类型:

DataStream

 

流处理的时候，要在服务器端输入 nc -l 9000

然后此时就可以输入 words了

 

pom.xml 如下:

<?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>liangde.tech</groupId>
    <artifactId>FlinkExample</artifactId>
    <version>1.0-SNAPSHOT</version>

    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-java -->
    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>1.6.1</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-streaming-java -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.11</artifactId>
            <version>1.6.1</version>
            <!--<scope>provided</scope>-->
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-scala -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-scala_2.11</artifactId>
            <version>1.6.1</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-streaming-scala -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-scala_2.11</artifactId>
            <version>1.6.1</version>
        </dependency>

        <dependency>
            <groupId>org.scalatest</groupId>
            <artifactId>scalatest_2.11</artifactId>
            <version>2.2.4</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.scalamock</groupId>
            <artifactId>scalamock-scalatest-support_2.11</artifactId>
            <version>3.2</version>
            <scope>test</scope>
        </dependency>
    </dependencies>


</project>