storm学习篇（二）—— 单词计数实例

小灰灰 2021-05-12 11:55 468阅读 0赞

# 利用storm实现简单的单词统计 #

添加依赖pom.xml

<?xml version="1.0" encoding="UTF-8"?>
    <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>4.0.0</modelVersion>
        <artifactId>storm-wordcount</artifactId>
        <packaging>jar</packaging>
    
        <properties>
            <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
            <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
            <java.version>1.8</java.version>
        </properties>
    
        <dependencies>
            <dependency>
                <groupId>org.apache.storm</groupId>
                <artifactId>storm-core</artifactId>
                <version>1.1.1</version>
                
            </dependency>
            <dependency>
                <groupId>junit</groupId>
                <artifactId>junit</artifactId>
                <version>4.12</version>
                <scope>test</scope>
            </dependency>
        </dependencies>
    
        <build>
            <plugins>
                <plugin>
                    <artifactId>maven-assembly-plugin</artifactId>
                    <configuration>
                        <descriptorRefs>
                            <descriptorRef>jar-with-dependencies</descriptorRef>
                        </descriptorRefs>
                        <archive>
                            <manifest>
                                <mainClass>cn.ljh.storm.helloworld.ExclamationTopology</mainClass>
                            </manifest>
                        </archive>
                    </configuration>
                </plugin>
            </plugins>
        </build>
    
    </project>

创建SentenceSpout.java

package com.storm.demo;
    
    import org.apache.storm.spout.SpoutOutputCollector;
    import org.apache.storm.task.TopologyContext;
    import org.apache.storm.topology.OutputFieldsDeclarer;
    import org.apache.storm.topology.base.BaseRichSpout;
    import org.apache.storm.tuple.Fields;
    import org.apache.storm.tuple.Values;
    
    import java.util.Map;
    
    /**
     * 路径：com.storm.demo
     * 类名：
     * 功能：《用一句话描述一下》
     * 备注：
     * 创建人：typ
     * 创建时间：2018/7/24 21:44
     * 修改人：
     * 修改备注：
     * 修改时间：
     */
    public class SentenceSpout extends BaseRichSpout {
    
        private SpoutOutputCollector collector;
    
        //初始化方法
        public void open(Map map, TopologyContext topologyContext, SpoutOutputCollector spoutOutputCollector) {
            this.collector = spoutOutputCollector;
        }
    
        //storm框架在while(true) 调用nextTuple
        public void nextTuple() {
            collector.emit(new Values("i am love storm"));
        }
    
        public void declareOutputFields(OutputFieldsDeclarer declarer) {
            declarer.declare(new Fields("love"));
        }
    }

创建SplitSentenceBolt.java

package com.storm.demo;
    
    import org.apache.storm.task.OutputCollector;
    import org.apache.storm.task.TopologyContext;
    import org.apache.storm.topology.OutputFieldsDeclarer;
    import org.apache.storm.topology.base.BaseRichBolt;
    import org.apache.storm.tuple.Fields;
    import org.apache.storm.tuple.Tuple;
    import org.apache.storm.tuple.Values;
    
    import java.util.Map;
    
    /**
     * 路径：com.storm.demo
     * 类名：
     * 功能：《用一句话描述一下》
     * 备注：
     * 创建人：typ
     * 创建时间：2018/7/24 21:48
     * 修改人：
     * 修改备注：
     * 修改时间：
     */
    public class SplitSentenceBolt extends BaseRichBolt {
    
        private OutputCollector collector;
    
        //初始化方法
        public void prepare(Map map, TopologyContext topologyContext, OutputCollector outputCollector) {
            this.collector = outputCollector;
        }
    
        //被storm框架while(true) 循环调用 传入参数tuple
        public void execute(Tuple tuple) {
            String line = tuple.getString(0);
            String[] words = line.split(" ");
            for(String word : words){
                this.collector.emit(new Values(word,1));
            }
    
        }
    
        public void declareOutputFields(OutputFieldsDeclarer declarer) {
            declarer.declare(new Fields("word","count"));
        }
    }

创建WordCountBolt.java

package com.storm.demo;
    
    import org.apache.storm.task.OutputCollector;
    import org.apache.storm.task.TopologyContext;
    import org.apache.storm.topology.OutputFieldsDeclarer;
    import org.apache.storm.topology.base.BaseRichBolt;
    import org.apache.storm.tuple.Tuple;
    
    import java.util.HashMap;
    import java.util.Map;
    
    /**
     * 路径：com.storm.demo
     * 类名：
     * 功能：《用一句话描述一下》
     * 备注：
     * 创建人：typ
     * 创建时间：2018/7/24 21:52
     * 修改人：
     * 修改备注：
     * 修改时间：
     */
    public class WordCountBolt extends BaseRichBolt {
    
        private OutputCollector collector;
    
        private HashMap<String,Integer> map = new HashMap<String, Integer>();
    
        public void prepare(Map map, TopologyContext topologyContext, OutputCollector outputCollector) {
            this.collector = outputCollector;
        }
    
        public void execute(Tuple tuple) {
            String word = tuple.getString(0);
            Integer num = tuple.getInteger(1);
            if(map.containsKey(word)){
                Integer count = map.get(word);
                map.put(word,count+num);
            }else{
                map.put(word,1);
            }
            System.out.println("count"+map);
        }
    
        public void declareOutputFields(OutputFieldsDeclarer declarer) {
    //        declarer.declare(new Fields("word","count"));
        }
    }

创建WordCountTopology.java

package com.storm.demo;
    
    import org.apache.storm.Config;
    import org.apache.storm.LocalCluster;
    import org.apache.storm.topology.TopologyBuilder;
    import org.apache.storm.tuple.Fields;
    
    /**
     * 路径：com.storm.demo
     * 类名：
     * 功能：《用一句话描述一下》
     * 备注：
     * 创建人：typ
     * 创建时间：2018/7/24 22:02
     * 修改人：
     * 修改备注：
     * 修改时间：
     */
    public class WordCountTopology {
    
        public static void main(String[] args) throws Exception {
    
            //定义一个TopologyBuilder
            TopologyBuilder builder = new TopologyBuilder();
            builder.setSpout("spout",new SentenceSpout(),1);
            builder.setBolt("myBolt1",new SplitSentenceBolt(),10).shuffleGrouping("spout");
            builder.setBolt("myBolt2",new WordCountBolt(),2).fieldsGrouping("myBolt1",new Fields("word"));
    
            //创建一个Config，用来指定当前topology需要的worker的数量
            Config config = new Config();
            config.setNumWorkers(2);
    
            //提交任务的两种模式：本地模式和远程模式
    
            //1.远程模式
    //        StormSubmitter.submitTopology("mywordcount",config,builder.createTopology());
            //2.本地模式
            LocalCluster localCluster = new LocalCluster();
            localCluster.submitTopology("mywordcount",config,builder.createTopology());
        }
    }

运行结果：

![70][]

[70]: /images/20210511/9eadc1b9392c4b2f8a992955f0fc135d.png