一：函数操作
1.介绍
Tuple本身是不可变的
Function只是在原有的基础上追加新的tuple
2.说明
如果原来的字段是log，flag
新增之后的tuple可以访问这些字段，log,flag,orderId,orderAmt,memberId
3.先写驱动类
增加了解析
然后再将解析的日志进行打印
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.operation.Function;
import storm.trident.operation.TridentCollector;
import storm.trident.operation.TridentOperationContext;
import storm.trident.testing.FixedBatchSpout;
import storm.trident.tuple.TridentTuple; import java.util.Map; 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)
//过滤
.each(new Fields("log"),new ValidLogFilter())
//解析
.each(new Fields("log"), new LogParserFunction(),new Fields("orderId","orderTime","orderAmtStr","memberId"))
//不添加log了，日志太长，不方便看控制台的现象
.each(new Fields("flag","orderId","orderTime","orderAmtStr","memberId"),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.解析方法类
package com.jun.trident; import backtype.storm.tuple.Values;
import storm.trident.operation.Function;
import storm.trident.operation.TridentCollector;
import storm.trident.operation.TridentOperationContext;
import storm.trident.tuple.TridentTuple; import java.util.HashMap;
import java.util.Map; public class LogParserFunction implements Function {
@Override
public void execute(TridentTuple tridentTuple, TridentCollector tridentCollector) {
//function对传进来的tuple子集
String log=tridentTuple.getStringByField("log");
//解析
int splitIndex=log.indexOf("IBEIfeng.gif")+13;
String orderInfo=log.substring(splitIndex).split(" ")[0];
String[] kvs=orderInfo.split("\\&");
Map<String,String> orderInfos=new HashMap<>();
for(String kv:kvs){
String[] keyValues=kv.split("=");
if(keyValues.length==2){
orderInfos.put(keyValues[0],keyValues[1]);
}
}
String orderId=getValue(orderInfos,"order_id","");//注意这个在日志中是这个字段
String orderTime=getValue(orderInfos,"orderTime","");
String orderAmtStr=getValue(orderInfos,"orderAmt","");
String memberId=getValue(orderInfos,"memberId","");
tridentCollector.emit(new Values(orderId,orderTime,orderAmtStr,memberId));
} @Override
public void prepare(Map map, TridentOperationContext tridentOperationContext) { } @Override
public void cleanup() { } public String getValue(Map<String,String> map,String key,String defaultValue){
if(map.containsKey(key)){
return map.get(key);
}else{
return defaultValue;
}
}
}
5.效果
二：投影操作
1.说明
可以对tuple进行裁剪操作。
2.驱动类
先投影
然后打印
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.operation.Function;
import storm.trident.operation.TridentCollector;
import storm.trident.operation.TridentOperationContext;
import storm.trident.testing.FixedBatchSpout;
import storm.trident.tuple.TridentTuple; import java.util.Map; 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)
//过滤
.each(new Fields("log"),new ValidLogFilter())
//解析
.each(new Fields("log"), new LogParserFunction(),new Fields("orderId","orderTime","orderAmtStr","memberId"))
//投影
.project(new Fields("orderId","orderTime","orderAmtStr","memberId"))
.each(new Fields("orderId","orderTime","orderAmtStr","memberId"),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());
}
}
}
3.效果
三：解析
1.说明
这个部分在解析之后，进入分流阶段。涉及到全局分流与局部分流，现在先使用全局分流，进行打印验证。
2.聚合操作
部分删除，部分增加
3.驱动类
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.Stream;
import storm.trident.TridentState;
import storm.trident.TridentTopology;
import storm.trident.operation.Function;
import storm.trident.operation.TridentCollector;
import storm.trident.operation.TridentOperationContext;
import storm.trident.operation.builtin.Count;
import storm.trident.testing.FixedBatchSpout;
import storm.trident.testing.MemoryMapState;
import storm.trident.tuple.TridentTuple; import java.util.Map; 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);
//流处理
Stream stream=tridentTopology.newStream("orderAnalyse",spout)
//过滤
.each(new Fields("log"),new ValidLogFilter())
//解析
.each(new Fields("log"), new LogParserFunction(),new Fields("orderId","orderTime","orderAmtStr","memberId"))
//投影
.project(new Fields("orderId","orderTime","orderAmtStr","memberId"))
//时间解析
.each(new Fields("orderTime"),new DateTransFormerFunction(),new Fields("day","hour","minter"))
;
//分流
//1.基于minter统计订单数量，分组统计
TridentState state=stream.groupBy(new Fields("minter"))
//全局聚合，使用内存存储状态信息
.persistentAggregate(new MemoryMapState.Factory(),new Count(),new Fields("orderNumByMinter"));
state.newValuesStream().each(new Fields("minter","orderNumByMinter"),new PrintFilter()); //提交
Config config=new Config();
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.时间解析方法
package com.jun.trident; import backtype.storm.tuple.Values;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import storm.trident.operation.Function;
import storm.trident.operation.TridentCollector;
import storm.trident.operation.TridentOperationContext;
import storm.trident.tuple.TridentTuple; import java.text.DateFormat;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Map; public class DateTransFormerFunction implements Function {
private static final Logger logger = LoggerFactory.getLogger(DateTransFormerFunction.class);
@Override
public void execute(TridentTuple tridentTuple, TridentCollector tridentCollector) {
String orderTime=tridentTuple.getStringByField("orderTime");
// 处理时间
try {
long timestamp = Long.parseLong(orderTime);
Date date = new Date();
date.setTime(timestamp);
DateFormat df = new SimpleDateFormat("yyyyMMddHHmm");
String dateStr = df.format(date);
String day = dateStr.substring(0,8);
String hour = dateStr.substring(0,10);
String minute = dateStr ;
//发射
tridentCollector.emit(new Values(day,hour,minute));
}catch (Exception e){
logger.error("日期解析出错"+orderTime);
}
} @Override
public void prepare(Map map, TridentOperationContext tridentOperationContext) { } @Override
public void cleanup() { }
}
5.效果
