Flink 本地执行入门

一、maven依赖

<properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <flink.version>1.6.3</flink.version>
    <java.version>1.8</java.version>
    <scala.version>2.11.8</scala.version>
    <hbase.version>1.2.4</hbase.version>
    <scala.binary.version>2.11</scala.binary.version>
    <maven.compiler.source>${java.version}</maven.compiler.source>
    <maven.compiler.target>${java.version}</maven.compiler.target>
</properties>

<dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-clients_${scala.binary.version}</artifactId>
    <version>${flink.version}</version>
</dependency>

二、本地执行

import org.apache.flink.api.common.functions.FilterFunction;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.common.JobExecutionResult;
import org.apache.flink.api.java.ExecutionEnvironment;

public class FlinkReadTextFile {

    public static void main(String[] args) throws Exception {
        ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();

        DataSet<String> data = env.readTextFile("file:///Users/***/Documents/test.txt");

        data.filter(new FilterFunction<String>() {
            @Override
            public boolean filter(String value) throws Exception {

                return value.startsWith("五芳斋美");
            }

        })
                .writeAsText("file:///Users/***/Documents/test01.txt");
        JobExecutionResult res = env.execute();

    }
}

 

 

三、

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

 

object SocketWindowWordCount {
  /** Main program method */
  def main(args: Array[String]): Unit ={ // the port to connect to
//  val port: Int = try {
//    ParameterTool.fromArgs(args).getInt("port")
//  } catch {
//    case e: Exception => {
//      System.err.println("No port specified. Please run 'SocketWindowWordCount --port <port>'")
//      return
//    }
//  }

  // get the execution environment
  val env: StreamExecutionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment

  // get input data by connecting to the socket
  val text = env.socketTextStream("localhost", 9000, '\n')

  // parse the data, group it, window it, and aggregate the counts
  val windowCounts = text
    .flatMap { w => w.split("\\s") }
    .map { w => WordWithCount(w, 1) }
    .keyBy("word")
    .timeWindow(Time.seconds(5), Time.seconds(1))
    .sum("count")

  // print the results with a single thread, rather than in parallel
  windowCounts.print().setParallelism(1)

  env.execute("Socket Window WordCount")
}

// Data type for words with count
case class WordWithCount(word: String, count: Long)
}