MapReduce 之 ---自定义全局计数器，将信息输出到控制台

package jishuqi;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
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;
/*
 * 统计不合法的数据条数   通过全局计数器  全局计数器都在控制台输出
 * ------用于统计数据中特定的信息
 */
public class MissFileds {
    static class MyMapper extends Mapper<LongWritable, Text, NullWritable, NullWritable>{
        /**
         * LongWritable key,偏移量
         *  Text value,一行内容
            Context context  上下文对象   传输   job运行过程中上文传参数
         */
        @Override
        protected void map(LongWritable key, Text value,
                Mapper<LongWritable, Text, NullWritable, NullWritable>.Context context)
                throws IOException, InterruptedException {
            //取出你每一条数据
            String[] split = value.toString().split(",");
            //进行判断    如果长度为3  证明  数据完美   否则数据残缺
            if(split.length<3){
                //将残缺的数据记录在全局计数器中
                //取出全局计数器
                Counter counter = context.getCounter(MissCounter.Miss_Field_Lines);
                /*
                   Increment this counter by the given value
                   * @param incr the value to increase this counter by
                   */
                 //void increment(long incr);  参数代表需要增加的值  类似于   +=incr
                counter.increment(1L);
            }
        }

    }

    //Driver
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        System.setProperty("HADOOP_USER_NAME", "hadoop");
        Configuration conf=new Configuration();
        conf.set("fs.defaultFS", "hdfs://hadoop02:9000");

        Job job=Job.getInstance(conf);

        job.setJarByClass(MissFileds.class);
        //只需一个mapper就可以了
        job.setMapperClass(MyMapper.class);

        //设置map的输出
        job.setOutputKeyClass(NullWritable.class);  //没有数据输出
        job.setOutputValueClass(NullWritable.class);

        //如果不需要reducetask   这里请设置为0   否则默认执行一个reducetask任务
        job.setNumReduceTasks(0);
        //可以指定多个输入路径
        FileInputFormat.setInputPaths(job, new Path("/friendout_01"));
        //输出路径需要吗？    不设置  报错Output directory not set.
        FileOutputFormat.setOutputPath(job, new Path("/counter_out01"));
        job.waitForCompletion(true);
    }
}

自定义一个枚举类

package jishuqi;
/**
 * 枚举类定义全局变量
 * @author Administrator
 */
public enum MissCounter {
    Miss_Field_Lines
}