一、下载开发环境的zip文件,将storm相关jar包导入编辑器。注意是zip文件,不是gz运行linux文件。
http://storm.apache.org/downloads.html
二、创建数据文件
storm有Tail属性,只适合文本源,会对文本文件内容进行监听。
public class GetData { /** * 生成数据 * @param args */ public static void main(String[] args) { File logFile = new File("track.log"); Random random = new Random(); String[] hosts = { "www.baidu.com" }; String[] session_id = { "ABYH6Y4V4SCVXTG6DPB4VH9U123", "XXYH6YCGFJYERTT834R52FDXV9U34", "BBYH61456FGHHJ7JL89RG5VV9UYU7", "CYYH6Y2345GHI899OFG4V9U567", "VVVYH6Y4V4SFXZ56JIPDPB4V678" }; String[] time = { "2014-01-07 08:40:50", "2014-01-07 08:40:51", "2014-01-07 08:40:52", "2014-01-07 08:40:53", "2014-01-07 09:40:49", "2014-01-07 10:40:49", "2014-01-07 11:40:49", "2014-01-07 12:40:49" }; StringBuffer sbBuffer = new StringBuffer() ; for (int i = 0; i < 50; i++) { sbBuffer.append(hosts[0]+"\t"+session_id[random.nextInt(5)]+"\t"+time[random.nextInt(8)]+"\n"); } if(! logFile.exists()) { try { logFile.createNewFile(); } catch (IOException e) { System.out.println("Create logFile fail !"); } } byte[] b = (sbBuffer.toString()).getBytes(); FileOutputStream fs; try { fs = new FileOutputStream(logFile); fs.write(b); fs.close(); } catch (Exception e) { e.printStackTrace(); } } }
文件格式如下:
引用
www.baidu.com XXYH6YCGFJYERTT834R52FDXV9U34 2014-01-07 12:40:49
www.baidu.com ABYH6Y4V4SCVXTG6DPB4VH9U123 2014-01-07 08:40:51
www.baidu.com ABYH6Y4V4SCVXTG6DPB4VH9U123 2014-01-07 08:40:53
www.baidu.com BBYH61456FGHHJ7JL89RG5VV9UYU7 2014-01-07 11:40:49
www.baidu.com XXYH6YCGFJYERTT834R52FDXV9U34 2014-01-07 11:40:49
www.baidu.com XXYH6YCGFJYERTT834R52FDXV9U34 2014-01-07 12:40:49
www.baidu.com ABYH6Y4V4SCVXTG6DPB4VH9U123 2014-01-07 08:40:53
www.baidu.com CYYH6Y2345GHI899OFG4V9U567 2014-01-07 12:40:49
www.baidu.com ABYH6Y4V4SCVXTG6DPB4VH9U123 2014-01-07 10:40:49
www.baidu.com ABYH6Y4V4SCVXTG6DPB4VH9U123 2014-01-07 08:40:52
www.baidu.com BBYH61456FGHHJ7JL89RG5VV9UYU7 2014-01-07 12:40:49
www.baidu.com VVVYH6Y4V4SFXZ56JIPDPB4V678 2014-01-07 12:40:49
www.baidu.com VVVYH6Y4V4SFXZ56JIPDPB4V678 2014-01-07 10:40:49
二、编写读取数据源类MySpout
Open(配置文件,上下文,发射topology类)是初始化方法
nextTuple()循环发射数据
ack() 成功处理tuple回调方法
Fail()处理失败tuple回调方法
activate和deactivate :spout可以被暂时激活和关闭
close方法在该spout关闭当前执行,但是并不能得到保证其一定被执行。kill -9时不执行,
Storm kill {topoName} 时执行。
superviser、numberis 用Kill -9。Topology一般不用Kill -9。
public class MySpout implements IRichSpout{ /** * */ private static final long serialVersionUID = 1L; FileInputStream fis; InputStreamReader isr; BufferedReader br; SpoutOutputCollector collector = null; String str = null; public void nextTuple() { try { while ((str = this.br.readLine()) != null) { // 过滤动作 collector.emit(new Values(str)); // Thread.sleep(3000); //to do } } catch (Exception e) { // TODO: handle exception } } public void open(Map conf, TopologyContext context, SpoutOutputCollector collector) { try { this.collector = collector; this.fis = new FileInputStream("track.log"); this.isr = new InputStreamReader(fis, "UTF-8"); this.br = new BufferedReader(isr); } catch (Exception e) { e.printStackTrace(); } // 打开文件 } public void declareOutputFields(OutputFieldsDeclarer declarer) { // 发射数据格式,与bolt接收数据一致 declarer.declare(new Fields("loog")); } public Map<String, Object> getComponentConfiguration() { // 与ope方法中的map对应 return null; } public void ack(Object msgId) { // TODO Auto-generated method stub } public void activate() { // TODO Auto-generated method stub } public void close() { // TODO Auto-generated method stub } public void deactivate() { // TODO Auto-generated method stub } public void fail(Object msgId) { // TODO Auto-generated method stub } }
三、编写数据处理类
prepare方法进行初始化,传入当前执行的上下文,与Spout的open方法一样
execute接受一个tuple进行处理,也可emit数据到下一级组件
cleanup 同ISpout的close方法,在关闭前调用,不保证其一定执行。
public class MyBolt implements IRichBolt { private static final long serialVersionUID = 1L; OutputCollector collector = null; public void cleanup() { } int num = 0; String valueString = null; public void execute(Tuple input) { // input.getValueByField("log"); // input.getValue(0); try { valueString = input.getStringByField("loog") ; if(valueString != null) { num ++ ; System.err.println("lines :"+num +" session_id:"+valueString.split("\t")[1]); } collector.ack(input); Thread.sleep(2000); } catch (Exception e) { collector.fail(input); e.printStackTrace(); } } public void prepare(Map stormConf, TopologyContext context, OutputCollector collector) { this.collector = collector ; } public void declareOutputFields(OutputFieldsDeclarer declarer) { declarer.declare(new Fields("")) ; } public Map<String, Object> getComponentConfiguration() { return null; } }
四、构建topology结构并运行
public class Main { public static void main(String[] args) { TopologyBuilder builder = new TopologyBuilder(); builder.setSpout("spout", new MySpout(), 1); builder.setBolt("bolt", new MyBolt(), 1).shuffleGrouping("spout");//与builder中的spout名称对应 Map conf = new HashMap(); conf.put(Config.TOPOLOGY_WORKERS, 4); if (args.length > 0) { try { StormSubmitter.submitTopology(args[0], conf, builder.createTopology()); } catch (AlreadyAliveException e) { e.printStackTrace(); } catch (InvalidTopologyException e) { e.printStackTrace(); }catch (AuthorizationException e) { e.printStackTrace(); } }else { LocalCluster localCluster = new LocalCluster(); localCluster.submitTopology("mytopology", conf, builder.createTopology()); } } }
六、如果maven项目的pom.xml文件
引用
<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/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.test</groupId>
<artifactId>StormMavenProject</artifactId>
<packaging>jar</packaging>
<version>0.0.1-SNAPSHOT</version>
<name>StormMavenProject</name>
<url>http://maven.apache.org</url>
<dependencies>
<dependency>
<groupId>org.ow2.asm</groupId>
<artifactId>asm</artifactId>
<version>5.0.3</version>
</dependency>
<dependency>
<groupId>org.clojure</groupId>
<artifactId>clojure</artifactId>
<version>1.7.0</version>
</dependency>
<dependency>
<groupId>com.lmax</groupId>
<artifactId>disruptor</artifactId>
<version>3.3.2</version>
</dependency>
<dependency>
<groupId>com.esotericsoftware</groupId>
<artifactId>kryo</artifactId>
<version>3.0.3</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-api</artifactId>
<version>2.8</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<version>2.8</version>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>log4j-over-slf4j</artifactId>
<version>1.6.6</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-slf4j-impl</artifactId>
<version>2.8</version>
</dependency>
<dependency>
<groupId>com.esotericsoftware</groupId>
<artifactId>minlog</artifactId>
<version>1.3.0</version>
</dependency>
<dependency>
<groupId>org.objenesis</groupId>
<artifactId>objenesis</artifactId>
<version>2.1</version>
</dependency>
<dependency>
<groupId>com.esotericsoftware</groupId>
<artifactId>reflectasm</artifactId>
<version>1.10.1</version>
</dependency>
<dependency>
<groupId>javax.servlet</groupId>
<artifactId>servlet-api</artifactId>
<version>2.5</version>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
<version>1.7.21</version>
</dependency>
<dependency>
<groupId>org.apache.storm</groupId>
<artifactId>storm-core</artifactId>
<version>1.1.0</version>
</dependency>
<dependency>
<groupId>org.apache.storm</groupId>
<artifactId>storm-rename-hack</artifactId>
<version>1.1.0</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>3.8.1</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>ring-cors</groupId>
<artifactId>ring-cors</artifactId>
<version>0.1.5</version>
</dependency>
</dependencies>
<build>
<finalName>StormMavenProject</finalName>
</build>
</project>
七、运行结果
引用
lines :2 session_id:ABYH6Y4V4SCVXTG6DPB4VH9U123
lines :3 session_id:ABYH6Y4V4SCVXTG6DPB4VH9U123
lines :4 session_id:BBYH61456FGHHJ7JL89RG5VV9UYU7
lines :5 session_id:XXYH6YCGFJYERTT834R52FDXV9U34