zoukankan      html  css  js  c++  java
  • Trident中使用HBase进行状态管理

    1.使用的类

      

    2.使用HBaseMapState

      

    3.使用状态管理

      使用的状态管理还要看Spout

      StateFactory factory1 = HBaseMapState.opaque(opts1);

    4.服务

      需要Kafka,zookeeper

      然后Hbase,前提需要Hadoop

      

    5.主驱动类

     1 package com.jun.tridentWithHbase;
     2 
     3 import backtype.storm.Config;
     4 import backtype.storm.LocalCluster;
     5 import backtype.storm.StormSubmitter;
     6 import backtype.storm.generated.AlreadyAliveException;
     7 import backtype.storm.generated.InvalidTopologyException;
     8 import backtype.storm.tuple.Fields;
     9 import backtype.storm.tuple.Values;
    10 import org.apache.storm.hbase.trident.state.HBaseMapState;
    11 import storm.trident.Stream;
    12 import storm.trident.TridentState;
    13 import storm.trident.TridentTopology;
    14 import storm.trident.operation.builtin.Count;
    15 import storm.trident.operation.builtin.Sum;
    16 import storm.trident.state.OpaqueValue;
    17 import storm.trident.state.StateFactory;
    18 import storm.trident.testing.FixedBatchSpout;
    19 import storm.trident.testing.MemoryMapState;
    20 
    21 public class TridentDemo {
    22     public static void main(String[] args) throws AlreadyAliveException, InvalidTopologyException {
    23         TridentTopology tridentTopology=new TridentTopology();
    24         //模拟数据
    25         Fields field=new Fields("log","flag");
    26         FixedBatchSpout spout=new FixedBatchSpout(field,5,
    27             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"),
    28             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"),
    29             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"),
    30             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"),
    31             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"),
    32             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")
    33         );
    34         //多次循环
    35         spout.setCycle(true);
    36         //流处理
    37         Stream stream=tridentTopology.newStream("orderAnalyse",spout)
    38                 //过滤
    39             .each(new Fields("log"),new ValidLogFilter())
    40                 //解析
    41             .each(new Fields("log"), new LogParserFunction(),new Fields("orderId","orderTime","orderAmtStr","memberId"))
    42                 //投影
    43             .project(new Fields("orderId","orderTime","orderAmtStr","memberId"))
    44                 //时间解析
    45             .each(new Fields("orderTime"),new DateTransFormerFunction(),new Fields("day","hour","minter"))
    46          ;
    47         //分流
    48         //1.基于minter统计订单数量,分组统计
    49         TridentState state=stream.groupBy(new Fields("minter"))
    50                 //全局聚合,使用内存存储状态信息
    51                 .persistentAggregate(new MemoryMapState.Factory(),new Count(),new Fields("orderNumByMinter"));
    52 //        state.newValuesStream().each(new Fields("minter","orderNumByMinter"),new PrintFilter());
    53 
    54         //2.另一个流,基于分钟的订单金额,局部聚合
    55         Stream partitionStream=stream.each(new Fields("orderAmtStr"),new TransforAmtToDoubleFunction(),new Fields("orderAmt"))
    56             .groupBy(new Fields("minter"))
    57                     //局部聚合
    58                 .chainedAgg()    //聚合链
    59             .partitionAggregate(new Fields("orderAmt"),new LocalSum(),new Fields("orderAmtSumOfLocal"))
    60                 .chainEnd();      //聚合链
    61 
    62         //*******************************使用Hbase存储***********************
    63             //产生Factory,而不是内存MemoryMapState.Factory()
    64         HBaseMapState.Options<OpaqueValue> opts1 = new HBaseMapState.Options<>();
    65         opts1.tableName ="orderAnalyse";       //表名称
    66         opts1.columnFamily = "cf";              // 列簇名称
    67         opts1.qualifier = "totalOrderAmt";
    68         StateFactory factory1 = HBaseMapState.opaque(opts1);
    69 
    70         //*******************************************************************
    71 
    72         //做一次全局聚合
    73         TridentState partitionState=partitionStream.groupBy(new Fields("minter"))
    74                 //全局聚合
    75                 .persistentAggregate(factory1,new Fields("orderAmtSumOfLocal"),new Sum(),new Fields("totalOrderAmt"));
    76         partitionState.newValuesStream().each(new Fields("minter","totalOrderAmt"),new PrintFilter());
    77 
    78         //提交
    79         Config config=new Config();
    80         if(args==null || args.length<=0){
    81             LocalCluster localCluster=new LocalCluster();
    82             localCluster.submitTopology("tridentDemo",config,tridentTopology.build());
    83         }else {
    84             config.setNumWorkers(2);
    85             StormSubmitter.submitTopology(args[0],config,tridentTopology.build());
    86         }
    87     }
    88 }

    6.HBase中效果

      

  • 相关阅读:
    RabbitMQ安装
    基于Linux的校园网破解思路和方法
    网络-0001-常见传输介质
    友情链接
    linux简史
    计算机的发展简史
    ArrayList&LinkedList&Vector区别
    Adobe Flash Player PPAPI 32.0.0.330
    ntoskrnl.exe导致蓝屏解决方法
    Git常用命令
  • 原文地址:https://www.cnblogs.com/juncaoit/p/9170358.html
Copyright © 2011-2022 走看看