package com.Practice.RemoveDupData;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.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 java.io.IOException;
/**
* 題目:數據去重
* 解題思路:將每行數據作爲key值,value值爲空
* 2012-3-1 a
2012-3-2 b
2012-3-3 c
2012-3-4 d
2012-3-5 a
2012-3-6 b
2012-3-7 c
2012-3-3 c
2012-3-1 b
2012-3-2 a
2012-3-3 b
2012-3-4 d
2012-3-5 a
2012-3-6 c
2012-3-7 d
2012-3-3 c
*/
public class RemoveDupData {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(conf);
Job job = Job.getInstance(conf);
job.setJar("wordcountJar/wordcount.jar");
job.setMapperClass(RemoveDupDataMapper.class);
job.setReducerClass(RemoveDupDataReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
Path inputPath = new Path("input/RemoveDupData");
Path outputPath = new Path("output/RemoveDupData");
if(fs.isDirectory(outputPath)){
fs.delete(outputPath,true);
}
FileInputFormat.setInputPaths(job,inputPath);
FileOutputFormat.setOutputPath(job,outputPath);
boolean waitForCompletion = job.waitForCompletion(true);
System.exit(waitForCompletion ? 0 : 1 );
}
public static class RemoveDupDataMapper extends Mapper<LongWritable,Text,Text,NullWritable>{
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
context.write(value,NullWritable.get());
}
}
public static class RemoveDupDataReducer extends Reducer<Text,NullWritable,Text,NullWritable>{
@Override
protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
context.write(key,NullWritable.get());
}
}
}
wordcount 數據去重
發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.