MapReduce修改输出的文件名

MapReduce默认输出的文件名称格式如下：part-r-00000

自定义名称，比如editName，则输出的文件名称为：editName-r-0000，此方法没有彻底修改整个文件名，只修改了一部分

方法如下

重写TextOutPutFormat的setOutPutName方法，因为setOutPutName是protected方法，所以只能通过重写的方式来修改

代码如下

/**
 *
 */
package com.zhen.outPutName;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

/**
 * @author FengZhen
 * setOutputName是protected方法，所以无法直接调用，只能自定义TextOutPutFormat重写该方法
 */
public class MyOutPutFormat extends TextOutputFormat<Text, IntWritable>{

    protected static void setOutputName(JobContext job, String name) {
        job.getConfiguration().set(BASE_OUTPUT_NAME, name);
      }
}

/**
 *
 */
package com.zhen.outPutName;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

/**
 * @author FengZhen
 * hadoop jar /Users/FengZhen/Desktop/Hadoop/other/mapreduce_jar/OutPutNameTest.jar com.zhen.outPutName.OutPutNameTest /user/hadoop/mapreduce/combinerTest/input /user/hadoop/mapreduce/OutPutNameTest/output/
 */
public class OutPutNameTest {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration configuration = new Configuration();
        Job job = new Job(configuration, OutPutNameTest.class.getSimpleName());
        job.setJarByClass(OutPutNameTest.class);
        job.setMapperClass(MapTest.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setReducerClass(ReduceTest.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //设置job的输出类型
        job.setOutputFormatClass(MyOutPutFormat.class);

        job.setCombinerClass(ReduceTest.class);
        job.setPartitionerClass(PartitionTest.class);
        job.setNumReduceTasks();

        //结果名称如下：editName-r-00000，此方法只能修改part这一段
        MyOutPutFormat.setOutputName(job, "editName");

        FileInputFormat.addInputPath(job, new Path(args[]));
        FileOutputFormat.setOutputPath(job, new Path(args[]));

        System.exit(job.waitForCompletion(true)?:);
    }

}

Map Reduce两个类省略。