package com.leesf.Spout;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(1000);} catch (InterruptedException e) {//Do nothing
            }return;}String str;//Open the readerBufferedReader reader = new BufferedReader(fileReader);try{//Read all lineswhile((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"));}
}

package com.leesf.Bolt;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*/@Overridepublic 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 */@Overridepublic void prepare(Map stormConf, TopologyContext context) {this.counters = new HashMap<String, Integer>();this.name = context.getThisComponentId();this.id = context.getThisTaskId();}@Overridepublic void declareOutputFields(OutputFieldsDeclarer declarer) {}@Overridepublic void execute(Tuple input, BasicOutputCollector collector) {String str = input.getString(0);/*** 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, 1);}else{Integer c = counters.get(str) + 1;counters.put(str, c);}}
}

package com.leesf.Bolt;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(0);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"));}
}

package com.leesf.Main;
import backtype.storm.Config;
import backtype.storm.LocalCluster;
import backtype.storm.topology.TopologyBuilder;
import backtype.storm.tuple.Fields;
import com.leesf.Bolt.*;
import com.leesf.Spout.*;public class Main {public static void main(String[] args) throws InterruptedException {//Topology definitionTopologyBuilder builder = new TopologyBuilder();builder.setSpout("word-reader",new WordReader());builder.setBolt("word-normalizer", new WordNormalizer()).shuffleGrouping("word-reader");builder.setBolt("word-counter", new WordCounter(),1).fieldsGrouping("word-normalizer", new Fields("word"));//ConfigurationConfig conf = new Config();conf.put("wordsFile", "/home/leesf/code/eclipse/StormDemo/res/words.txt");conf.setDebug(false);//Topology runconf.put(Config.TOPOLOGY_MAX_SPOUT_PENDING, 1);LocalCluster cluster = new LocalCluster();cluster.submitTopology("Getting-Started-Toplogie", conf, builder.createTopology());Thread.sleep(10000);cluster.shutdown();}
}

storm
test
are
great
is
an
storm
simple
application
but
very
powerfull
really
StOrm
is
great