Trident的过滤操作

1.过滤操作

　　只是判断某个tuple是否保留

　　无需跨网络，无需跨分区

　　不会改变tuple的结构，只是改变tuple的数量

2.需求

　　过滤掉不是订单的tuple。

　　其中订单中包含“IBEIfeng.gif”。

3.主驱动类

　　先过滤

　　后打印

 package com.jun.trident;

 import backtype.storm.Config;
 import backtype.storm.LocalCluster;
 import backtype.storm.StormSubmitter;
 import backtype.storm.generated.AlreadyAliveException;
 import backtype.storm.generated.InvalidTopologyException;
 import backtype.storm.tuple.Fields;
 import backtype.storm.tuple.Values;
 import storm.trident.TridentTopology;
 import storm.trident.testing.FixedBatchSpout;

 public class TridentDemo {
     public static void main(String[] args) throws AlreadyAliveException, InvalidTopologyException {
         TridentTopology tridentTopology=new TridentTopology();
         //模拟数据
         Fields field=new Fields("log","flag");
         FixedBatchSpout spout=new FixedBatchSpout(field,5,
             new Values("168.214.187.214 - - [1481953616092] \"GET /view.php HTTP/1.1\" 200 0 \"http://cn.bing.com/search?q=spark mllib\" \"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1\" \"-\"","A"),
             new Values("168.187.202.202 - - [1481953537038] \"GET /IBEIfeng.gif?order_id=1063&orderTime=1481953537038&memberId=4000012340500607&productInfos=10005-2099.48-B-1|10004-1886.62-A-2|10001-961.99-A-1&orderAmt=6834.70 HTTP/1.1\" 200 0 \"-\" \"Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2;Tident/6.0)\" \"-\"","A"),
             new Values("61.30.167.187 - - [1481953539039] \"GET /IBEIfeng.gif?order_id=1064&orderTime=1481953539039&memberId=4000930409959999&productInfos=10007-3329.13-B-1|10009-2607.71-B-1|10002-390.62-A-1|10006-411.00-B-2&orderAmt=7149.46 HTTP/1.1\" 200 0 \"-\" \"Mozilla/5.0 (Linux; Android 4.2.1; Galaxy Nexus Build/JOP40D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Mobile Safari/535.19\" \"-\"","A"),
             new Values("30.29.132.190 - - [1481953544042] \"GET /IBEIfeng.gif?order_id=1065&orderTime=1481953544043&memberId=1234568970080798&productInfos=10005-2099.48-B-1|10001-3242.40-C-2|10006-411.00-B-1&orderAmt=8995.28 HTTP/1.1\" 200 0 \"-\" \"Mozilla/5.0 (iPhone; CPU iPhone OS 7_)_3 like Mac OS X) AppleWebKit/537.51.1 (KHTML, like Gecko) Version/7.0 Mobile/11B511 Safari/9537.53\" \"-\"","B"),
             new Values("222.190.187.201 - - [1481953578068] \"GET /IBEIfeng.gif?order_id=1066&orderTime=1481953578068&memberId=3488586887970809&productInfos=10005-2099.48-B-1|10001-2774.16-C-2&orderAmt=7647.80 HTTP/1.1\" 200 0 \"-\" \"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1\" \"-\"","B"),
             new Values("72.202.43.53 - - [1481953579069] \"GET /IBEIfeng.gif?order_id=1067&orderTime=1481953579069&memberId=2084859896989877&productInfos=10007-3329.13-B-1|10001-961.99-A-2&orderAmt=5253.10 HTTP/1.1\" 200 0 \"-\" \"Mozilla/5.0 (Linux; Android 4.2.1; Galaxy Nexus Build/JOP40D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Mobile Safari/535.19\" \"-\"","B")
         );
         //多次循环
         spout.setCycle(true);
         //提交
         Config config=new Config();
         tridentTopology.newStream("orderAnalyse",spout)
 //            .each(new Fields("log","flag"),new PrintFilter());
             .each(new Fields("log"),new ValidLogFilter())
             .each(new Fields("log","flag"),new PrintFilter());
         if(args==null || args.length<=0){
             LocalCluster localCluster=new LocalCluster();
             localCluster.submitTopology("tridentDemo",config,tridentTopology.build());
         }else {
             config.setNumWorkers(2);
             StormSubmitter.submitTopology(args[0],config,tridentTopology.build());
         }
     }
 }

4.过滤类

 package com.jun.trident;

 import storm.trident.operation.Filter;
 import storm.trident.operation.TridentOperationContext;
 import storm.trident.tuple.TridentTuple;

 import java.util.Map;

 public class ValidLogFilter implements Filter {
     //定义如何过滤的逻辑
     @Override
     public boolean isKeep(TridentTuple tridentTuple) {
         String log=tridentTuple.getStringByField("log");
         boolean isKepp=true;
         if(log==null || "".equals(log)){
             isKepp=false;
         }else {
             //含有IBEIfeng.gif才是订单
             if (log.contains("IBEIfeng.gif")){
                 isKepp=true;
             }else {
                 isKepp=false;
             }
         }
         return isKepp;
     }

     @Override
     public void prepare(Map map, TridentOperationContext tridentOperationContext) {

     }

     @Override
     public void cleanup() {

     }
 }

5.效果