Hadoop计数器

package com.hadoop.Counter;

import java.io.IOException;

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.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;

/**
 * @author Zimo
 *　ＭａｐＲｅｄｕｃｅ计数器
 */
public class MyCounter extends Configured implements Tool {

    /**
     * @param args
     */
    public static class MyCounterMap extends Mapper<LongWritable, Text, Text, Text> {
        //定义枚举对象
        public static enum LOG_PROCESSOR_COUNTER {
            //枚举对象BAD_RECORDS_LONG来统计长数据，枚举对象BAD_RECORDS_SHORT来统计短数据
            BAD_RECORDS_LONG, BAD_RECORDS_SHORT
        };
        
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String arr_values[] = value.toString().split("/t");
            if (arr_values.length > 3) {
                //动态自定义计数器
                context.getCounter("ErrorCounter", "toolong").increment(1);
                //枚举声明计数器
                context.getCounter(LOG_PROCESSOR_COUNTER.BAD_RECORDS_LONG).increment(1);
            } else if(arr_values.length < 3) {
                // 动态自定义计数器
                context.getCounter("ErrorCounter", "tooshort").increment(1);  
                // 枚举声明计数器
                context.getCounter(LOG_PROCESSOR_COUNTER.BAD_RECORDS_SHORT).increment(1);
            } else {
                context.write(value, new Text(""));
            }
        }
    }
    
    public int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Path myPath = new Path(args[1]);
        FileSystem hdfs = myPath.getFileSystem(conf);
        if (hdfs.isDirectory(myPath)) {
            hdfs.delete(myPath);
        }
        
        Job job = new Job(conf, "MyCounter");
        job.setJarByClass(MyCounter.class);
        job.setMapperClass(MyCounterMap.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.waitForCompletion(true);
        
        return 0;
    }
    
    public static void main(String[] args) throws Exception {
        // TODO Auto-generated method stub
        String[] arg0 = {
                "hdfs://centpy:9000/counter/counter.txt", "hdfs://centpy:9000/counter/out"
        };
        int ec = ToolRunner.run(new Configuration(), new MyCounter(), arg0);
        System.exit(ec);
    }

}

2018-05-08 16:43:45,146 INFO [org.apache.hadoop.mapreduce.Job] - Counters: 34
    File System Counters
        FILE: Number of bytes read=314
        FILE: Number of bytes written=368622
        FILE: Number of read operations=0
        FILE: Number of large read operations=0
        FILE: Number of write operations=0
        HDFS: Number of bytes read=102
        HDFS: Number of bytes written=0
        HDFS: Number of read operations=15
        HDFS: Number of large read operations=0
        HDFS: Number of write operations=6
    Map-Reduce Framework
        Map input records=5
        Map output records=0
        Map output bytes=0
        Map output materialized bytes=6
        Input split bytes=103
        Combine input records=0
        Combine output records=0
        Reduce input groups=0
        Reduce shuffle bytes=0
        Reduce input records=0
        Reduce output records=0
        Spilled Records=0
        Shuffled Maps =0
        Failed Shuffles=0
        Merged Map outputs=0
        GC time elapsed (ms)=53
        CPU time spent (ms)=0
        Physical memory (bytes) snapshot=0
        Virtual memory (bytes) snapshot=0
        Total committed heap usage (bytes)=830472192
    ErrorCounter
        tooshort=5
    com.hadoop.Counter.MyCounter$MyCounterMap$LOG_PROCESSOR_COUNTER
        BAD_RECORDS_SHORT=5
    File Input Format Counters 
        Bytes Read=51
    File Output Format Counters 
        Bytes Written=0