Storm工程创建

1.创建maven项目：

pom.xml:

<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></modelVersion>
  <groupId>storm.book</groupId>
  <artifactId>Getting-Started</artifactId>
  <version>-SNAPSHOT</version>

  <build>
   <plugins>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-compiler-plugin</artifactId>
        <version></version>
        <configuration>
          <source>1.6</source>
          <target>1.6</target>
          <compilerVersion>1.6</compilerVersion>
        </configuration>
      </plugin>
     </plugins>
  </build>

  <repositories>

        <!-- Repository where we can found the storm dependencies  -->
        <repository>
            <id>clojars.org</id>
            <url>http://clojars.org/repo</url>
        </repository>

  </repositories>

  <dependencies>

        <!-- Storm Dependency -->
        <dependency>
          <groupId>storm</groupId>
          <artifactId>storm</artifactId>
          <version></version>
       </dependency>

  </dependencies>

</project>

相关类：

WordReader：

package spouts;

import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.util.Map;
import backtype.storm.spout.SpoutOutputCollector;
import backtype.storm.task.TopologyContext;
import backtype.storm.topology.OutputFieldsDeclarer;
import backtype.storm.topology.base.BaseRichSpout;
import backtype.storm.tuple.Fields;
import backtype.storm.tuple.Values;

public class WordReader extends BaseRichSpout {

    private SpoutOutputCollector collector;
    private FileReader fileReader;
    private boolean completed = false;
    public void ack(Object msgId) {
        System.out.println("OK:"+msgId);
    }
    public void close() {}
    public void fail(Object msgId) {
        System.out.println("FAIL:"+msgId);
    }

    /**
     * The only thing that the methods will do It is emit each
     * file line
     */
    public void nextTuple() {
        /**
         * The nextuple it is called forever, so if we have been readed the file
         * we will wait and then return
         */
        if(completed){
            try {
                Thread.sleep();
            } catch (InterruptedException e) {
                //Do nothing
            }
            return;
        }
        String str;
        //Open the reader
        BufferedReader reader = new BufferedReader(fileReader);
        try{
            //Read all lines
            while((str = reader.readLine()) != null){
                /**
                 * By each line emmit a new value with the line as a their
                 */
                this.collector.emit(new Values(str),str);
            }
        }catch(Exception e){
            throw new RuntimeException("Error reading tuple",e);
        }finally{
            completed = true;
        }
    }

    /**
     * We will create the file and get the collector object
     */
    public void open(Map conf, TopologyContext context,
            SpoutOutputCollector collector) {
        try {
            this.fileReader = new FileReader(conf.get("wordsFile").toString());
        } catch (FileNotFoundException e) {
            throw new RuntimeException("Error reading file ["+conf.get("wordFile")+"]");
        }
        this.collector = collector;
    }

    /**
     * Declare the output field "word"
     */
    public void declareOutputFields(OutputFieldsDeclarer declarer) {
        declarer.declare(new Fields("line"));
    }
}

WordCounter：

package bolts;

import java.util.HashMap;
import java.util.Map;

import backtype.storm.task.TopologyContext;
import backtype.storm.topology.BasicOutputCollector;
import backtype.storm.topology.OutputFieldsDeclarer;
import backtype.storm.topology.base.BaseBasicBolt;
import backtype.storm.tuple.Tuple;

public class WordCounter extends BaseBasicBolt {

    Integer id;
    String name;
    Map<String, Integer> counters;

    /**
     * At the end of the spout (when the cluster is shutdown
     * We will show the word counters
     */
    @Override
    public void cleanup() {
        System.out.println("-- Word Counter ["+name+"-"+id+"] --");
        for(Map.Entry<String, Integer> entry : counters.entrySet()){
            System.out.println(entry.getKey()+": "+entry.getValue());
        }
    }

    /**
     * On create
     */
    @Override
    public void prepare(Map stormConf, TopologyContext context) {
        this.counters = new HashMap<String, Integer>();
        this.name = context.getThisComponentId();
        this.id = context.getThisTaskId();
    }

    @Override
    public void declareOutputFields(OutputFieldsDeclarer declarer) {}

    @Override
    public void execute(Tuple input, BasicOutputCollector collector) {
        String str = input.getString();
        /**
         * If the word dosn't exist in the map we will create
         * this, if not We will add 1
         */
        if(!counters.containsKey(str)){
            counters.put(str, );
        }else{
            Integer c = counters.;
            counters.put(str, c);
        }
    }
}

WordNormalizer：

package bolts;

import backtype.storm.topology.BasicOutputCollector;
import backtype.storm.topology.OutputFieldsDeclarer;
import backtype.storm.topology.base.BaseBasicBolt;
import backtype.storm.tuple.Fields;
import backtype.storm.tuple.Tuple;
import backtype.storm.tuple.Values;

public class WordNormalizer extends BaseBasicBolt {

    public void cleanup() {}

    /**
     * The bolt will receive the line from the
     * words file and process it to Normalize this line
     *
     * The normalize will be put the words in lower case
     * and split the line to get all words in this
     */
    public void execute(Tuple input, BasicOutputCollector collector) {
        String sentence = input.getString();
        String[] words = sentence.split(" ");
        for(String word : words){
            word = word.trim();
            if(!word.isEmpty()){
                word = word.toLowerCase();
                collector.emit(new Values(word));
            }
        }
    }

    /**
     * The bolt will only emit the field "word"
     */
    public void declareOutputFields(OutputFieldsDeclarer declarer) {
        declarer.declare(new Fields("word"));
    }
}

TopologyMain：

import spouts.WordReader;
import backtype.storm.Config;
import backtype.storm.LocalCluster;
import backtype.storm.topology.TopologyBuilder;
import backtype.storm.tuple.Fields;
import bolts.WordCounter;
import bolts.WordNormalizer;

public class TopologyMain {
    public static void main(String[] args) throws InterruptedException {

        //Topology definition
        TopologyBuilder builder = new TopologyBuilder();
        builder.setSpout("word-reader",new WordReader());
        builder.setBolt("word-normalizer", new WordNormalizer())
            .shuffleGrouping("word-reader");
        builder.setBolt()
            .fieldsGrouping("word-normalizer", new Fields("word"));

        //Configuration
        Config conf = new Config();
        conf.put(]);
        conf.setDebug(false);
        //Topology run
        conf.put(Config.TOPOLOGY_MAX_SPOUT_PENDING, );
        LocalCluster cluster = new LocalCluster();
        cluster.submitTopology("Getting-Started-Toplogie", conf, builder.createTopology());
        Thread.sleep();
        cluster.shutdown();
    }
}

工程架构

运行：

结果

强大的流处理！

github:https://github.com/super-d2/strom_demo