Question

如何自定义mapreduce在输出的key和value之间自动添加的分隔符

Answer 1

package com.panguoyuan.mapreduce;  
  
import java.io.IOException;  
import java.util.StringTokenizer;  
  
import org.apache.hadoop.conf.Configuration;  
import org.apache.hadoop.fs.Path;  
import org.apache.hadoop.io.IntWritable;  
import org.apache.hadoop.io.Text;  
import org.apache.hadoop.mapreduce.Job;  
import org.apache.hadoop.mapreduce.Mapper;  
import org.apache.hadoop.mapreduce.Reducer;  
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;  
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;  
import org.apache.hadoop.util.GenericOptionsParser;  
  
public class WordCount {  
  
    public static class TokenizerMapper extends  
            Mapper<Object, Text, Text, IntWritable> {  
  
        private final static IntWritable one = new IntWritable(1);  
        private Text word = new Text();  
  
        public void map(Object key, Text value, Context context)  
                throws IOException, InterruptedException {  
            StringTokenizer itr = new StringTokenizer(value.toString());  
            while (itr.hasMoreTokens()) {  
                word.set(itr.nextToken());  
                context.write(word, one);  
            }  
        }  
    }  
  
    public static class IntSumReducer extends  
            Reducer<Text, IntWritable, Text, IntWritable> {  
        private IntWritable result = new IntWritable();  
  
        public void reduce(Text key, Iterable<IntWritable> values,  
                Context context) throws IOException, InterruptedException {  
            int sum = 0;  
            for (IntWritable val : values) {  
                sum += val.get();  
            }  
            result.set(sum);  
            context.write(key, result);  
        }  
    }  
  
    public static void main(String[] args) throws Exception{  
        System.out.println(2);  
        Configuration conf = new Configuration();  
        conf.set("mapred.textoutputformat.ignoreseparator", "true");  
        conf.set("mapred.textoutputformat.separator", ",");  
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();  
        if (otherArgs.length != 2) {  
          System.err.println("Usage: wordcount <in> <out>");  
          System.exit(2);  
        }  
//      conf.set("fs.hdfs.impl",   
//              org.apache.hadoop.hdfs.DistributedFileSystem.class.getName()  
//              );  
        Job job = new Job(conf, "word count");  
        job.setJarByClass(WordCount.class);  
        job.setMapperClass(TokenizerMapper.class);  
        job.setCombinerClass(IntSumReducer.class);  
        job.setReducerClass(IntSumReducer.class);  
        job.setOutputKeyClass(Text.class);  
        job.setOutputValueClass(IntWritable.class);  
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));  
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));  
        System.exit(job.waitForCompletion(true) ? 0 : 1);  
    }  
}

Answer 2

http://blog.csdn.net/panguoyuan/article/details/38062303