Flink学习笔记：1、Flink快速入门

[root@centos ~]# wget http://mirrors.tuna.tsinghua.edu.cn/apache/flink/flink-1.3.2/flink-1.3.2-bin-hadoop27-scala_2.10.tgz
--2017-11-19 08:46:47--  http://mirrors.tuna.tsinghua.edu.cn/apache/flink/flink-1.3.2/flink-1.3.2-bin-hadoop27-scala_2.10.tgz
Resolving mirrors.tuna.tsinghua.edu.cn (mirrors.tuna.tsinghua.edu.cn)... 101.6.6.178, 2402:f000:1:416:101:6:6:178
Connecting to mirrors.tuna.tsinghua.edu.cn (mirrors.tuna.tsinghua.edu.cn)|101.6.6.178|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 146881599 (140M) [application/octet-stream]
Saving to: ‘flink-1.3.2-bin-hadoop27-scala_2.10.tgz.1’

100%[=======================================================================================>] 146,881,599 1.40MB/s   in 1m 44s 

2017-11-19 08:48:30 (1.35 MB/s) - ‘flink-1.3.2-bin-hadoop27-scala_2.10.tgz.1’ saved [146881599/146881599]

[root@centos ~]# ls
anaconda-ks.cfg                          
flink-1.3.2-bin-hadoop27-scala_2.10.tgz 
[root@centos ~]# 

[root@node1 ~]# tar -zxvf flink-1.3.2-bin-hadoop27-scala_2.10.tgz -C /opt

[root@node1 ~]# cd /opt/flink-1.3.2/
[root@node1 flink-1.3.2]# bin/start-local.sh
Starting jobmanager daemon on host node1.
[root@node1 flink-1.3.2]#

[root@node1 flink-1.3.2]# tail log/flink-*-jobmanager-*.log
2017-11-19 08:59:40,788 INFO  org.apache.flink.runtime.taskmanager.TaskManager              - TaskManager data connection information: b1c3d16b52d0245feac840080ee1f387 @ localhost (dataPort=37405)
2017-11-19 08:59:40,788 INFO  org.apache.flink.runtime.taskmanager.TaskManager              - TaskManager has 1 task slot(s).
2017-11-19 08:59:40,790 INFO  org.apache.flink.runtime.taskmanager.TaskManager              - Memory usage stats: [HEAP: 262/1963/1963 MB, NON HEAP: 36/37/-1 MB (used/committed/max)]
2017-11-19 08:59:40,820 INFO  org.apache.flink.runtime.taskmanager.TaskManager              - Trying to register at JobManager akka.tcp://flink@localhost:6123/user/jobmanager (attempt 1, timeout: 500 milliseconds)
2017-11-19 08:59:40,832 INFO  org.apache.flink.runtime.clusterframework.standalone.StandaloneResourceManager  - TaskManager b1c3d16b52d0245feac840080ee1f387 has started.
2017-11-19 08:59:40,840 INFO  org.apache.flink.runtime.clusterframework.standalone.StandaloneResourceManager  - Resource Manager associating with leading JobManager Actor[akka://flink/user/jobmanager#235294181] - leader session 00000000-0000-0000-0000-000000000000
2017-11-19 08:59:40,845 INFO  org.apache.flink.runtime.instance.InstanceManager             - Registered TaskManager at localhost (akka://flink/user/taskmanager) as a3cda67b9b60ece3c5da03afb128c2d8. Current number of registered hosts is 1. Current number of alive task slots is 1.
2017-11-19 08:59:40,854 INFO  org.apache.flink.runtime.taskmanager.TaskManager              - Successful registration at JobManager (akka://flink/user/jobmanager), starting network stack and library cache.
2017-11-19 08:59:40,862 INFO  org.apache.flink.runtime.taskmanager.TaskManager              - Determined BLOB server address to be localhost/127.0.0.1:39996. Starting BLOB cache.
2017-11-19 08:59:40,865 INFO  org.apache.flink.runtime.blob.BlobCache                       - Created BLOB cache storage directory /tmp/blobStore-5bb19dd1-7cb5-45fc-8007-8eb6f6908868
[root@node1 flink-1.3.2]#

[root@node1 flink-1.3.2]# nc -l 9000

[root@node1 flink-1.3.2]# bin/flink run examples/streaming/SocketWindowWordCount.jar --port 9000
Cluster configuration: Standalone cluster with JobManager at localhost/127.0.0.1:6123
Using address localhost:6123 to connect to JobManager.
JobManager web interface address http://localhost:8081
Starting execution of program
Submitting job with JobID: 7250da9a40999a17046c65c68c164e97. Waiting for job completion.
Connected to JobManager at Actor[akka.tcp://flink@localhost:6123/user/jobmanager#235294181] with leader session id 00000000-0000-0000-0000-000000000000.
11/19/2017 09:07:13 Job execution switched to status RUNNING.
11/19/2017 09:07:13 Source: Socket Stream -> Flat Map(1/1) switched to SCHEDULED 
11/19/2017 09:07:13 TriggerWindow(TumblingProcessingTimeWindows(5000), ReducingStateDescriptor{serializer=org.apache.flink.api.java.typeutils.runtime.PojoSerializer@ab644855, reduceFunction=org.apache.flink.streaming.examples.socket.SocketWindowWordCount$1@60f00693}, ProcessingTimeTrigger(), WindowedStream.reduce(WindowedStream.java:300)) -> Sink: Unnamed(1/1) switched to SCHEDULED 
11/19/2017 09:07:13 Source: Socket Stream -> Flat Map(1/1) switched to DEPLOYING 
11/19/2017 09:07:13 TriggerWindow(TumblingProcessingTimeWindows(5000), ReducingStateDescriptor{serializer=org.apache.flink.api.java.typeutils.runtime.PojoSerializer@ab644855, reduceFunction=org.apache.flink.streaming.examples.socket.SocketWindowWordCount$1@60f00693}, ProcessingTimeTrigger(), WindowedStream.reduce(WindowedStream.java:300)) -> Sink: Unnamed(1/1) switched to DEPLOYING 
11/19/2017 09:07:13 Source: Socket Stream -> Flat Map(1/1) switched to RUNNING 
11/19/2017 09:07:13 TriggerWindow(TumblingProcessingTimeWindows(5000), ReducingStateDescriptor{serializer=org.apache.flink.api.java.typeutils.runtime.PojoSerializer@ab644855, reduceFunction=org.apache.flink.streaming.examples.socket.SocketWindowWordCount$1@60f00693}, ProcessingTimeTrigger(), WindowedStream.reduce(WindowedStream.java:300)) -> Sink: Unnamed(1/1) switched to RUNNING 

[root@node1 flink-1.3.2]# nc -l 9000
hello
hello,flink
bye

[root@node1 flink-1.3.2]# tail -f log/flink-*-jobmanager-*.out
hello: 1
hello,flink : 1
bye : 1

[root@node1 flink-1.3.2]# bin/stop-local.sh
Stopping jobmanager daemon (pid: 2568) on host node1.
[root@node1 flink-1.3.2]#

package org.apache.flink.streaming.scala.examples.socket

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

/**
 * Implements a streaming windowed version of the "WordCount" program.
 * 
 * This program connects to a server socket and reads strings from the socket.
 * The easiest way to try this out is to open a text sever (at port 12345) 
 * using the ''netcat'' tool via
 * {{{
 * nc -l 12345
 * }}}
 * and run this example with the hostname and the port as arguments..
 */
object SocketWindowWordCount {

  /** Main program method */
  def main(args: Array[String]) : Unit = {

    // the host and the port to connect to
    var hostname: String = "localhost"
    var port: Int = 0

    try {
      val params = ParameterTool.fromArgs(args)
      hostname = if (params.has("hostname")) params.get("hostname") else "localhost"
      port = params.getInt("port")
    } catch {
      case e: Exception => {
        System.err.println("No port specified. Please run 'SocketWindowWordCount " +
          "--hostname <hostname> --port <port>', where hostname (localhost by default) and port " +
          "is the address of the text server")
        System.err.println("To start a simple text server, run 'netcat -l <port>' " +
          "and type the input text into the command line")
        return
      }
    }

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

    // get input data by connecting to the socket
    val text: DataStream[String] = env.socketTextStream(hostname, port, '\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))
          .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)
}

package org.apache.flink.streaming.examples.socket;

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.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.util.Collector;

/**
 * Implements a streaming windowed version of the "WordCount" program.
 *
 * <p>This program connects to a server socket and reads strings from the socket.
 * The easiest way to try this out is to open a text server (at port 12345)
 * using the <i>netcat</i> tool via
 * <pre>
 * nc -l 12345
 * </pre>
 * and run this example with the hostname and the port as arguments.
 */
@SuppressWarnings("serial")
public class SocketWindowWordCount {

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

        // the host and the port to connect to
        final String hostname;
        final int port;
        try {
            final ParameterTool params = ParameterTool.fromArgs(args);
            hostname = params.has("hostname") ? params.get("hostname") : "localhost";
            port = params.getInt("port");
        } catch (Exception e) {
            System.err.println("No port specified. Please run 'SocketWindowWordCount " +
                "--hostname <hostname> --port <port>', where hostname (localhost by default) " +
                "and port is the address of the text server");
            System.err.println("To start a simple text server, run 'netcat -l <port>' and " +
                "type the input text into the command line");
            return;
        }

        // get the execution environment
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // get input data by connecting to the socket
        DataStream<String> text = env.socketTextStream(hostname, port, "\n");

        // parse the data, group it, window it, and aggregate the counts
        DataStream<WordWithCount> windowCounts = text

                .flatMap(new FlatMapFunction<String, WordWithCount>() {
                    @Override
                    public void flatMap(String value, Collector<WordWithCount> out) {
                        for (String word : value.split("\\s")) {
                            out.collect(new WordWithCount(word, 1L));
                        }
                    }
                })

                .keyBy("word")
                .timeWindow(Time.seconds(5))

                .reduce(new ReduceFunction<WordWithCount>() {
                    @Override
                    public WordWithCount reduce(WordWithCount a, WordWithCount b) {
                        return new WordWithCount(a.word, a.count + b.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.
     */
    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 word + " : " + count;
        }
    }
}

package org.apache.flink.streaming.scala.examples.wordcount

import org.apache.flink.api.java.utils.ParameterTool
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.examples.wordcount.util.WordCountData

/**
 * Implements the "WordCount" program that computes a simple word occurrence
 * histogram over text files in a streaming fashion.
 *
 * The input is a plain text file with lines separated by newline characters.
 *
 * Usage:
 * {{{
 * WordCount --input <path> --output <path>
 * }}}
 *
 * If no parameters are provided, the program is run with default data from
 * {@link WordCountData}.
 *
 * This example shows how to:
 *
 *  - write a simple Flink Streaming program,
 *  - use tuple data types,
 *  - write and use transformation functions.
 *
 */
object WordCount {

  def main(args: Array[String]) {

    // Checking input parameters
    val params = ParameterTool.fromArgs(args)

    // set up the execution environment
    val env = StreamExecutionEnvironment.getExecutionEnvironment

    // make parameters available in the web interface
    env.getConfig.setGlobalJobParameters(params)

    // get input data
    val text =
    // read the text file from given input path
    if (params.has("input")) {
      env.readTextFile(params.get("input"))
    } else {
      println("Executing WordCount example with default inputs data set.")
      println("Use --input to specify file input.")
      // get default test text data
      env.fromElements(WordCountData.WORDS: _*)
    }

    val counts: DataStream[(String, Int)] = text
      // split up the lines in pairs (2-tuples) containing: (word,1)
      .flatMap(_.toLowerCase.split("\\W+"))
      .filter(_.nonEmpty)
      .map((_, 1))
      // group by the tuple field "0" and sum up tuple field "1"
      .keyBy(0)
      .sum(1)

    // emit result
    if (params.has("output")) {
      counts.writeAsText(params.get("output"))
    } else {
      println("Printing result to stdout. Use --output to specify output path.")
      counts.print()
    }

    // execute program
    env.execute("Streaming WordCount")
  }
}

package org.apache.flink.streaming.examples.wordcount;

import org.apache.flink.api.common.functions.FlatMapFunction;
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;
import org.apache.flink.streaming.examples.wordcount.util.WordCountData;
import org.apache.flink.util.Collector;

/**
 * Implements the "WordCount" program that computes a simple word occurrence
 * histogram over text files in a streaming fashion.
 *
 * <p>The input is a plain text file with lines separated by newline characters.
 *
 * <p>Usage: <code>WordCount --input &lt;path&gt; --output &lt;path&gt;</code><br>
 * If no parameters are provided, the program is run with default data from
 * {@link WordCountData}.
 *
 * <p>This example shows how to:
 * <ul>
 * <li>write a simple Flink Streaming program,
 * <li>use tuple data types,
 * <li>write and use user-defined functions.
 * </ul>
 */
public class WordCount {

    // *************************************************************************
    // PROGRAM
    // *************************************************************************

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

        // Checking input parameters
        final ParameterTool params = ParameterTool.fromArgs(args);

        // set up the execution environment
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // make parameters available in the web interface
        env.getConfig().setGlobalJobParameters(params);

        // get input data
        DataStream<String> text;
        if (params.has("input")) {
            // read the text file from given input path
            text = env.readTextFile(params.get("input"));
        } else {
            System.out.println("Executing WordCount example with default input data set.");
            System.out.println("Use --input to specify file input.");
            // get default test text data
            text = env.fromElements(WordCountData.WORDS);
        }

        DataStream<Tuple2<String, Integer>> counts =
        // split up the lines in pairs (2-tuples) containing: (word,1)
        text.flatMap(new Tokenizer())
        // group by the tuple field "0" and sum up tuple field "1"
                .keyBy(0).sum(1);

        // emit result
        if (params.has("output")) {
            counts.writeAsText(params.get("output"));
        } else {
            System.out.println("Printing result to stdout. Use --output to specify output path.");
            counts.print();
        }

        // execute program
        env.execute("Streaming WordCount");
    }

    // *************************************************************************
    // USER FUNCTIONS
    // *************************************************************************

    /**
     * Implements the string tokenizer that splits sentences into words as a
     * user-defined FlatMapFunction. The function takes a line (String) and
     * splits it into multiple pairs in the form of "(word,1)" ({@code Tuple2<String,
     * Integer>}).
     */
    public static final class Tokenizer implements FlatMapFunction<String, Tuple2<String, Integer>> {
        private static final long serialVersionUID = 1L;

        @Override
        public void flatMap(String value, Collector<Tuple2<String, Integer>> out)
                throws Exception {
            // normalize and split the line
            String[] tokens = value.toLowerCase().split("\\W+");

            // emit the pairs
            for (String token : tokens) {
                if (token.length() > 0) {
                    out.collect(new Tuple2<String, Integer>(token, 1));
                }
            }
        }
    }

}