MapReduce实现手机上网流量分析（业务逻辑）

1363157985066 	13726230503	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	2481	24681	200
1363157995052 	13826544101	5C-0E-8B-C7-F1-E0:CMCC	120.197.40.4			4	0	264	0	200
1363157991076 	13926435656	20-10-7A-28-CC-0A:CMCC	120.196.100.99			2	4	132	1512	200
1363154400022 	13926251106	5C-0E-8B-8B-B1-50:CMCC	120.197.40.4			4	0	240	0	200
1363157993044 	18211575961	94-71-AC-CD-E6-18:CMCC-EASY	120.196.100.99	iface.qiyi.com	视频网站	15	12	1527	2106	200
1363157995074 	84138413	5C-0E-8B-8C-E8-20:7DaysInn	120.197.40.4	122.72.52.12		20	16	4116	1432	200
1363157993055 	13560439658	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			18	15	1116	954	200
1363157995033 	15920133257	5C-0E-8B-C7-BA-20:CMCC	120.197.40.4	sug.so.360.cn	信息安全	20	20	3156	2936	200
1363157983019	13719199419	68-A1-B7-03-07-B1:CMCC-EASY	120.196.100.82			4	0	240	0	200
1363157984041 	13660577991	5C-0E-8B-92-5C-20:CMCC-EASY	120.197.40.4	s19.cnzz.com	站点统计	24	9	6960	690	200
1363157973098 	15013685858	5C-0E-8B-C7-F7-90:CMCC	120.197.40.4	rank.ie.sogou.com	搜索引擎	28	27	3659	3538	200
1363157986029 	15989002119	E8-99-C4-4E-93-E0:CMCC-EASY	120.196.100.99	www.umeng.com	站点统计	3	3	1938	180	200
1363157992093 	13560439658	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			15	9	918	4938	200
1363157986041 	13480253104	5C-0E-8B-C7-FC-80:CMCC-EASY	120.197.40.4			3	3	180	180	200
1363157984040 	13602846565	5C-0E-8B-8B-B6-00:CMCC	120.197.40.4	2052.flash2-http.qq.com	综合门户	15	12	1938	2910	200
1363157995093 	13922314466	00-FD-07-A2-EC-BA:CMCC	120.196.100.82	img.qfc.cn		12	12	3008	3720	200
1363157982040 	13502468823	5C-0A-5B-6A-0B-D4:CMCC-EASY	120.196.100.99	y0.ifengimg.com	综合门户	57	102	7335	110349	200
1363157986072 	18320173382	84-25-DB-4F-10-1A:CMCC-EASY	120.196.100.99	input.shouji.sogou.com	搜索引擎	21	18	9531	2412	200
1363157990043 	13925057413	00-1F-64-E1-E6-9A:CMCC	120.196.100.55	t3.baidu.com	搜索引擎	69	63	11058	48243	200
1363157988072 	13760778710	00-FD-07-A4-7B-08:CMCC	120.196.100.82			2	2	120	120	200
1363157985066 	13726238888	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	2481	24681	200
1363157993055 	13560436666	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			18	15	1116	954	200

package cn.app.hadoop.mr.datacount;

import java.io.IOException;
import java.text.FieldPosition;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

//第一个处理文本的话一般是LongWritable  或者object
//一行一行的文本是text
//输出的key的手机号 定位Text
//结果是DataBean  一定要实现Writable接口
public class DataCountMapper extends Mapper {

	//实际处理中已经进行了数据清洗 在这就不catch
	public void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {
		String line = value.toString();
		String[] fields = line.split("\t");
		String telNo = fields[1];
		long upPayLoad = Long.parseLong(fields[8]);
		long downPayLoad = Long.parseLong(fields[9]);
		
		//封装到bean，如果格式不对那么跳过 这里不考虑，假设已经清洗
		DataBean dataBean = new DataBean(telNo,upPayLoad,downPayLoad);
		
		//但是这种方式  每行都new了一个databena下次并没有释放 很慢
		//能不能在外边new DataBean，每次修改值，如果按以前的思维是不行的，因为指向了
		//同一块内存，没法相加
		//但是在hadoop里是可以的，因为每次写入以后就已经序列化了，下次不一样了
		context.write(new Text(telNo), dataBean);
	}

}

//反序列化 deserializable  从字节流独处 赋值给内存
	public void readFields(DataInput in) throws IOException {
		// TODO Auto-generated method stub
		
		//注意顺序   类型  里面没参数 
		//this.telNo = in.readUTF(telNo);是错的

		this.telNo = in.readUTF();
		this.upPayLoad = in.readLong();
		this.downPayLoad = in.readLong();
		this.totalPayLoad = in.readLong();
		
	}
	
	//序列化serializable,从内存写入到字节流 或者通过rmi在网上传输
	public void write(DataOutput out) throws IOException {
		// TODO Auto-generated method stub
		//手机号是String，但是没有writeString，用writeUTF
		out.writeUTF(telNo);
		out.writeLong(upPayLoad);
		out.writeLong(downPayLoad);
		out.writeLong(totalPayLoad);
	}

this.telNo = on.readUTF(telNo);

	@Override
	public String toString() {
		//电话号码不要了
		return "DataBean [upPayLoad=" + upPayLoad
				+ ", downPayLoad=" + downPayLoad + ", totalPayLoad="
				+ totalPayLoad + "]";
	}