Effective Apache Flink（四）入门

Effective Apache Flink（四）入门

目录

Effective Apache Flink（四）入门

教程

安装

本地安装

API教程

示例

 Docker Playgrounds

---

教程

安装

本地安装

• Java 8.x
• 根据你的系统下载相应版本的安装包(Linux,Mac OS X和Windows)http://flink.apache.org/downloads.html

启动

./bin/start-cluster.sh  # Start Flink

web管理台

http://localhost:8081 

编写代码（完整版Scala，Java）

object SocketWindowWordCount {

    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", 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), 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)
}

public class SocketWindowWordCount {

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

        // the port to connect to
        final int port;
        try {
            final ParameterTool params = ParameterTool.fromArgs(args);
            port = params.getInt("port");
        } catch (Exception e) {
            System.err.println("No port specified. Please run 'SocketWindowWordCount --port <port>'");
            return;
        }

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

        // get input data by connecting to the socket
        DataStream<String> text = env.socketTextStream("localhost", 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), Time.seconds(1))
            .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;
        }
    }
}

运行

现在，我们要运行这个Flink应用程序。它将从Socket中读取文本，并每5秒打印前5秒内每个不同单词出现的次数，即处理时间的滚动窗口，只要单词是浮动的。

1.使用netstat启动本地服务器

nc -l 9000

2.提交flink程序

./bin/flink run examples/streaming/SocketWindowWordCount.jar --port 9000
Starting execution of program

3.单词以5秒的时间窗口(处理时间、翻转窗口)计算，并打印到stdout。监控TaskManager的输出文件，用nc写一些文本(输入按下后逐行发送到Flink):

$ nc -l 9000
lorem ipsum
ipsum ipsum ipsum
bye

4.停止集群

./bin/stop-cluster.sh

Windows上安装参考

https://ci.apache.org/projects/flink/flink-docs-release-1.9/zh/getting-started/tutorials/flink_on_windows.html

API教程

DataStream API

1.Maven构建工程

mvn archetype:generate \
    -DarchetypeGroupId=org.apache.flink \
    -DarchetypeArtifactId=flink-quickstart-java \
    -DarchetypeVersion=1.9.0 \
    -DgroupId=wiki-edits \
    -DartifactId=wiki-edits \
    -Dversion=0.1 \
    -Dpackage=wikiedits \
    -DinteractiveMode=false

2.增加依赖

<dependencies>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-java</artifactId>
        <version>${flink.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-streaming-java_2.11</artifactId>
        <version>${flink.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-clients_2.11</artifactId>
        <version>${flink.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-connector-wikiedits_2.11</artifactId>
        <version>${flink.version}</version>
    </dependency>
</dependencies>

3.编写代码

package wikiedits;

import org.apache.flink.api.common.functions.AggregateFunction;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.streaming.connectors.wikiedits.WikipediaEditEvent;
import org.apache.flink.streaming.connectors.wikiedits.WikipediaEditsSource;

public class WikipediaAnalysis {

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

    StreamExecutionEnvironment see = StreamExecutionEnvironment.getExecutionEnvironment();

    DataStream<WikipediaEditEvent> edits = see.addSource(new WikipediaEditsSource());

    KeyedStream<WikipediaEditEvent, String> keyedEdits = edits
      .keyBy(new KeySelector<WikipediaEditEvent, String>() {
        @Override
        public String getKey(WikipediaEditEvent event) {
          return event.getUser();
        }
      });

    DataStream<Tuple2<String, Long>> result = keyedEdits
      .timeWindow(Time.seconds(5))
      .aggregate(new AggregateFunction<WikipediaEditEvent, Tuple2<String, Long>, Tuple2<String, Long>>() {
        @Override
      	public Tuple2<String, Long> createAccumulator() {
      	  return new Tuple2<>("", 0L);
      	}

      	@Override
      	public Tuple2<String, Long> add(WikipediaEditEvent value, Tuple2<String, Long> accumulator) {
      	  accumulator.f0 = value.getUser();
      	  accumulator.f1 += value.getByteDiff();
          return accumulator;
      	}

      	@Override
      	public Tuple2<String, Long> getResult(Tuple2<String, Long> accumulator) {
      	  return accumulator;
      	}

      	@Override
      	public Tuple2<String, Long> merge(Tuple2<String, Long> a, Tuple2<String, Long> b) {
      	  return new Tuple2<>(a.f0, a.f1 + b.f1);
      	}
      });

    result.print();

    see.execute();
  }
}

4.打包执行

mvn clean package
mvn exec:java -Dexec.mainClass=wikiedits.WikipediaAnalysis

另附一例

<dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-connector-kafka-0.11_2.11</artifactId>
    <version>${flink.version}</version>
</dependency>

import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer011;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.api.common.functions.MapFunction;

result
    .map(new MapFunction<Tuple2<String,Long>, String>() {
        @Override
        public String map(Tuple2<String, Long> tuple) {
            return tuple.toString();
        }
    })
    .addSink(new FlinkKafkaProducer011<>("localhost:9092", "wiki-result", new SimpleStringSchema()));

Python API

详见https://ci.apache.org/projects/flink/flink-docs-release-1.9/zh/tutorials/python_table_api.html

示例

https://ci.apache.org/projects/flink/flink-docs-release-1.9/zh/getting-started/examples/

 Docker Playgrounds

https://ci.apache.org/projects/flink/flink-docs-release-1.9/zh/getting-started/docker-playgrounds/flink-operations-playground.html