Trident实战之计算网站PV

1、Trident实战之计算网站PV

/**
 * Trident实战之计算网站PV
 */
public class TridentPVTopo {

	public static StormTopology buildTopology(LocalDRPC drpc) {

		Random random = new Random();
		String[] hosts = { "www.taobao.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" };

		FixedBatchSpout spout = new FixedBatchSpout(new Fields("eachLog"), 3, // 第一个参数表示输出类型，与topo的输入类型对应，第二个参数表示以三行作为一个批次
				new Values(hosts[0] + "\t" + session_id[random.nextInt(5)] + "\t" + time[random.nextInt(8)]),
				new Values(hosts[0] + "\t" + session_id[random.nextInt(5)] + "\t" + time[random.nextInt(8)]),
				new Values(hosts[0] + "\t" + session_id[random.nextInt(5)] + "\t" + time[random.nextInt(8)]));
		spout.setCycle(false);

		/**
		 * topo处理数据，存入中间存储
		 */
		TridentTopology topology = new TridentTopology();
		TridentState wordCounts = topology.newStream("spout1", spout)// 获取数据源
				.each(new Fields("eachLog"), new Mysplit("\t"), new Fields("date", "session_id"))// 第一参数是输入数据类型，第二参数是实现“分割”功能，第三个参数是输出数据类型
				.groupBy(new Fields("date"))// 按日期分组

				// 持久化到内存，传入session_id分组,输出pv数据类型
				.persistentAggregate(new MemoryMapState.Factory(), new Fields("session_id"), new Count(),
						new Fields("pv"));

		        // .parallelismHint(16);

		/**
		 * 读取中间存储数据
		 */
		topology.newDRPCStream("GetPV", drpc)// 输入函数名称
				.each(new Fields("args"), new Split(" "), new Fields("date"))// 对传入参数进行“分割”处理，
				.groupBy(new Fields("date"))// 用日期进行查询
				.stateQuery(wordCounts, new Fields("date"), new MapGet(), new Fields("PV"))// 第一个参数是中间存储。第二个参数是查询参数，可以不输入默认是传入流的值。
				.each(new Fields("PV"), new FilterNull());// 查询结果过滤
		return topology.build();
	}

	public static void main(String[] args) throws Exception {
		// 客户端调用topo
		Config conf = new Config();
		conf.setMaxSpoutPending(20);
		if (args.length == 0) {
			LocalDRPC drpc = new LocalDRPC();
			LocalCluster cluster = new LocalCluster();
			cluster.submitTopology("wordCounter", conf, buildTopology(drpc));
			for (int i = 0; i < 100; i++) {
				System.err.println("DRPC RESULT: " + drpc.execute("GetPV", "2014-01-07 2014-01-08"));
				Thread.sleep(1000);
			}
		} else {
			conf.setNumWorkers(3);
			StormSubmitter.submitTopologyWithProgressBar(args[0], conf, buildTopology(null));
		}
	}
}

2、自定义分割数据

public class Mysplit extends BaseFunction {

	/**
	 * 自定义分割数据
	 */
	private static final long serialVersionUID = 1L;

	String patton = null;

	public Mysplit(String patton) {
		this.patton = patton;
	}

	public void execute(TridentTuple tuple, TridentCollector collector) {
		String log = tuple.getString(0);
		String logArr[] = log.split(patton);
		if (logArr.length == 3) {
			collector.emit(new Values(DateFmt.getCountDate(logArr[2], DateFmt.date_short), logArr[1]));
		}

	}

}

public class Split extends BaseFunction {
    /**
	 * 分割数据
	 */
	private static final long serialVersionUID = 1L;

	String patton = null;

	public Split(String patton)
	{
		this.patton = patton;
	}
	
	
	public void execute(TridentTuple tuple, TridentCollector collector) {
      String sentence = tuple.getString(0);
      for (String word : sentence.split(patton)) {
        collector.emit(new Values(word));
      }
    }
  }

3、日期处理类

public class DateFmt {
	/*
	 * 日期处理类
	 */
	public static final String date_long = "yyyy-MM-dd HH:mm:ss" ;
	public static final String date_short = "yyyy-MM-dd" ;
	
	public static SimpleDateFormat sdf = new SimpleDateFormat(date_short);
	
	public static String getCountDate(String date,String patton)
	{
		SimpleDateFormat sdf = new SimpleDateFormat(patton);
		Calendar cal = Calendar.getInstance(); 
		if (date != null) {
			try {
				cal.setTime(sdf.parse(date)) ;
			} catch (ParseException e) {
				e.printStackTrace();
			}
		}
		return sdf.format(cal.getTime());
	}
	
	public static Date parseDate(String dateStr) throws Exception
	{
		return sdf.parse(dateStr);
	}
	
	public static void main(String[] args) throws Exception{

//		System.out.println(DateFmt.getCountDate("2014-03-01 12:13:14", DateFmt.date_short));
		System.out.println(parseDate("2014-05-02").after(parseDate("2014-05-01")));
	}

}

4、pom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>


<dependency>
    <groupId>org.apache.zookeeper</groupId>
    <artifactId>zookeeper</artifactId>
    <version>3.4.10</version>
</dependency>



  </dependencies>
  <build>
    <finalName>StormMavenProject</finalName>
  </build>
</project>

5、测试结果

引用

DRPC RESULT: [["2014-01-07 2014-01-08","2014-01-07",3]]
DRPC RESULT: [["2014-01-07 2014-01-08","2014-01-07",3]]
DRPC RESULT: [["2014-01-07 2014-01-08","2014-01-07",3]]