sort

2020-03-30  本文已影响0人  还闹不闹

1、需求:将多个文件合并后排序。

file1.txt
2
32
654
32
15
756
65223

file2.txt
5956
22
650
92

file3.txt
54
6

2、代码设计

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 Sort {
    //map将输入中的value转化成IntWritable类型,作为输出的key
    public static class Map extends Mapper<Object,Text,IntWritable,IntWritable>{
        private static IntWritable data=new IntWritable();
        //实现map函数
        public void map(Object key,Text value,Context context) throws IOException,InterruptedException{
            String line = value.toString();
            data.set(Integer.parseInt(line));
            context.write(data, new IntWritable(1));
        }
    }
    
    //reduce将输入中的key复制到输出数据的key上,
    //然后根据输入的value-list中元素的个数决定key的输出次数
    //用全局linenum来代表key的位次
    public static class Reduce extends Reducer<IntWritable,IntWritable,IntWritable,IntWritable>{
        private static IntWritable linenum = new IntWritable(1);
        //实现reduce函数
        public void reduce(IntWritable key,Iterable<IntWritable> values,Context context) throws IOException,InterruptedException{
            for(IntWritable val:values){
                context.write(linenum, key);
                linenum = new IntWritable(linenum.get()+1);
            }
        }
    }
    
    public static void main(String[] args) throws Exception{
//      权限问题 设置hadoop用户
//      System.setProperty("HADOOP_USER_NAME", "root");
//      创建配置对象
        Configuration conf = new Configuration();
//      这句话很关键
//      conf.set("mapred.job.tracker", "192.168.1.2:9001");
        
//      设置输入输出参数
        String[] ioArgs=new String[]{"sort_test_in","sort_test_out"};
//      设置其它参数
        String[] otherArgs = new GenericOptionsParser(conf, ioArgs).getRemainingArgs();
//      校验输入参数
        if (otherArgs.length != 2) {
        System.err.println("Usage: Data Sort <in> <out>");
             System.exit(2);
        }
        
//      创建Job对象
        Job job = Job.getInstance(conf, "Data sort");
//      Job job = new Job(conf, "Data Sort");
//      指定reduce数量
        job.setNumReduceTasks(1);
//      设置运行job的类
        job.setJarByClass(Sort.class);
        //设置Map和Reduce处理类;不用配置Combiner、因为仅使用map和reduce就能够完成任务
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
//      设置map输出的key value;类型须与前面的map类一致,如IntWritable类型对应IntWritable类型
//      job.setMapOutputKeyClass(Text.class);
        job.setMapOutputKeyClass(IntWritable.class);
        job.setMapOutputValueClass(IntWritable.class);
//      设置reduce输出类型
        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(IntWritable.class);
//      设置输入和输出目录
//      FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
//      FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
//      提交job
        System.exit(job.waitForCompletion(true) ? 0 : 1);
     }
}

3、输出结果

1 2
2 6
3 15
4 22
5 32
6 32
7 54
8 92
9 650
10 654
11 756
12 5956
13 65223

上一篇下一篇

猜你喜欢

热点阅读