文件合并与去重

最新推荐文章于 2024-07-17 10:37:21 发布

Life-HJT

最新推荐文章于 2024-07-17 10:37:21 发布

阅读量728

点赞数 3

文章标签： mapreduce hadoop hdfs

本文链接：https://blog.csdn.net/weixin_46002654/article/details/124534992

版权

package com.chenbo.cn.mapreduce;

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.util.GenericOptionsParser;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; 

public class Merge {

    /**
     * @param args
     * 对A,B两个文件进行合并，并剔除其中重复的内容，得到一个新的输出文件C
     */
    //在这重载map函数，直接将输入中的value复制到输出数据的key上 注意在map方法中要抛出异常：throws IOException,InterruptedException
    public static class Map extends Mapper<Object, Text, Text, Text> {  
        private static Text text = new Text();
        public void map(Object key, Text value, Context content) throws IOException, InterruptedException {  

            text = value;  
            content.write(text, new Text(""));  
        }  
    }  
    //在这重载reduce函数，直接将输入中的key复制到输出数据的key上  注意在reduce方法上要抛出异常：throws IOException,InterruptedException
        public static class Reduce extends Reducer<Text, Text, Text, Text> {  
        public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {  
            context.write(key, new Text(""));  
        }  
    }

        public static void main(String[] args) throws Exception{

        // TODO Auto-generated method stub
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","hdfs://localhost:9000");
        String[] otherArgs = new String[]{"input","output"}; /* 直接设置输入参数 */
       if (otherArgs.length != 2) {
            System.err.println("Usage: wordcount <in> <out>");
            System.exit(2); 
            }
        Job job = Job.getInstance(conf,"Merge and duplicate removal");
        job.setJarByClass(Merge.class);
        job.setMapperClass(Map.class);
        job.setCombinerClass(Reduce.class);
        job.setReducerClass(Reduce.class); 
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
     // 判断output文件夹是否存在，如果存在则删除
        Path path = new Path(otherArgs[1]);// 取第1个表示输出目录参数（第0个参数是输入目录）
        FileSystem fileSystem = path.getFileSystem(conf);// 根据path找到这个文件
        if (fileSystem.exists(path)) {
            fileSystem.delete(path, true);// true的意思是，就算output有东西，也一带删除
        }
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}