mapreduce流量汇总程序

Demo地址

flow.log文件

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

  • FlowcountMapper.java
static class FlowcountMapper extends Mapper<LongWritable, Text, Text, FlowBean>{
        @Override
        protected void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            //输入为1234    23455   33333   33333(中间是制表符)
            //第二列为手机号,倒数第二列为下行流量,倒数第三列为上行流量
            String line = value.toString();
            String[] values = line.split("\t");
            //获取手机号
            String phoneNum = values[1];
            //获取上行流量下行流量
            long upFlow = new Long(values[values.length-3]);
            long downFlow = new Long(values[values.length-2]);
            //封装好后写出到输出收集器
            context.write(new Text(phoneNum), new FlowBean(upFlow,downFlow));
        }
    }
  • FlowcountReducer.java
 static class FlowcountReducer extends Reducer<Text, FlowBean, Text, FlowBean>{
        @Override
        protected void reduce(Text key, Iterable<FlowBean> beans,Context context)
                throws IOException, InterruptedException {
            //传进来的实例<13345677654,beans>,即多个该电话的键值对
            //取出values获得上下行和总流量求和
            long upFlow = 0;
            long downFlow = 0;
            for (FlowBean flowBean : beans) {
                upFlow += flowBean.getUpFlow();
                downFlow += flowBean.getDownFlow();
            }
            context.write(key, new FlowBean(upFlow,downFlow));
        }
    }
  • FlowcountDriver.java
public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(Flowcount.class);
        //指定本业务job要使用的mapper,reducer业务类
        job.setMapperClass(FlowcountMapper.class);
        job.setReducerClass(FlowcountReducer.class);
        //虽然指定了泛型,以防框架使用第三方的类型
                //指定mapper输出数据的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        //指定最终输出的数据的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //指定job输入原始文件所在位置
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        //指定job输入原始文件所在位置
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //将job中配置的相关参数以及job所用的java类所在的jar包,提交给yarn去运行
        boolean b = job.waitForCompletion(true);
        System.exit(b?0:1);
    }
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值