hadoop自定义counter简单java Demo

1.hadoop的counter可以是用枚举和字符串两种方式定义

枚举:

//先定义枚举
public static enum LOG_COUNTER{
        BAD_RECORDS;
}
//使用counter
Counter counter = context.getCounter(LOG_COUNTER.BAD_RECORDS);
counter.increment(1);

字符串

Counter counter2 = context.getCounter("log_counter", "bad_records");
counter2.increment(1);


综合demo如下
mapreduce程序

package com.lijie.conter;

import java.io.IOException;
import java.util.List;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapreduce.Counter;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class CounterMapReduce extends Configured implements Tool{

    public static void main(String[] args) throws Exception {
        String[] args1 = {"hdfs://lijie:9000/middle/*","hdfs://lijie:9000/middle/out"};
        int run = ToolRunner.run(new Configuration(), new CounterMapReduce(), args1);
        System.exit(run);
    }

    public static enum LOG_COUNTER{
        BAD_RECORDS;
    }

    public static class CounterMap extends Mapper<LongWritable, Text, Text, Text>{
        @Override
        protected void map( LongWritable key, Text value,
                            Mapper<LongWritable, Text, Text, Text>.Context context) throws IOException,
                                                                                    InterruptedException {
            List<String> list = ParseTVData.transData(value.toString());

            if(list == null || list.size() == 0){
                Counter counter = context.getCounter(LOG_COUNTER.BAD_RECORDS);
                counter.increment(1);

                Counter counter2 = context.getCounter("log_counter", "bad_records");
                counter2.increment(1);

            }else{
                for (String string : list) {
                    context.write(new Text(string), new Text(""));
                }
            }

        }
    }

    @Override
    public int run(String[] arg0) throws Exception {
        // TODO Auto-generated method stub

        Configuration conf = new Configuration();
        Path path = new Path(arg0[1]);
        FileSystem fs = path.getFileSystem(conf);
        if(fs.isDirectory(path)){
            fs.delete(path, true);
        }

        Job job = new Job(conf,"counter");
        job.setJarByClass(CounterMapReduce.class);

        FileInputFormat.addInputPath(job, new Path(arg0[0]));
        FileOutputFormat.setOutputPath(job, path);

        job.setMapperClass(CounterMap.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);

        //yasuo
        FileOutputFormat.setCompressOutput(job, true);
        FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);

        job.waitForCompletion(true);

        return 0;
    }

}

其中ParseTVData.transData(value.toString());只是对json的解析具体如下:

package com.lijie.conter;

import java.util.ArrayList;
import java.util.List;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class ParseTVData {
    public static List< String> transData(String text) {
        List< String> list = new ArrayList< String>();
        Document doc;
        String rec = "";
        try {
            doc = Jsoup.parse(text);//jsoup解析数据
            Elements content = doc.getElementsByTag("WIC");
            String num = content.get(0).attr("cardNum");//记录编号
            if(num==null||num.equals("")){
                num=" ";
            }

            String stbNum = content.get(0).attr("stbNum");//机顶盒号
            if(stbNum.equals("")){
                return list;
            }

            String date = content.get(0).attr("date");//日期

            Elements els = doc.getElementsByTag("A");
            if (els.isEmpty()) {
                return list;
            }

            for (Element el : els) {
                String e = el.attr("e");//结束时间

                String s = el.attr("s");//开始时间

                String sn = el.attr("sn");//频道名称

                rec =  stbNum + "@" + date + "@" + sn + "@" + s+ "@" + e ;
                list.add(rec);
            }
        } catch (Exception e) {
            System.out.println(e.getMessage());
            return list;
        }
        return list;
    }
}
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
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