- 主页 > 生活百科 > >
package cn.mr.dedup;
import JAVA.io.IOException;
import org.Apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.MApper;
public class DedupMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
private static Text field = new Text();
// <0,2018-3-3 c><11,2018-3-4 d>
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
field = value;
context.write(field, NullWritable.get());
}
// <2018-3-3 c,null> <2018-3-4 d,null>
}
package cn.mr.dedup;
import java.io.IOException;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class DedupReducer extends Reducer<Text, NullWritable, Text, NullWritable> {
// <2018-3-3 c,null> <2018-3-4 d,null><2018-3-4 d,null>
@Override
protected void reduce(Text key, Iterable<NullWritable> values, Context context)
【Hadoop数据去重】throws IOException, InterruptedException {
context.write(key, NullWritable.get());
}
}
package cn.mr.dedup;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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;
public class DedupRunner {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(DedupRunner.class);
job.setMapperClass(DedupMapper.class);
job.setReducerClass(DedupReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
FileInputFormat.setInputPaths(job, new Path("D:\Dedup\input"));
// 指定处理完成之后的结果所保存的位置
FileOutputFormat.setOutputPath(job, new Path("D:\Dedup\output"));
job.waitForCompletion(true);
}
}
推荐阅读
-
-
会穿罢了|为你的成片效果加分,拍照不知道手放哪?像这样摆pose
-
-
-
一步之遥1990|四次称王,在他的带领下,魏国义无反顾走向衰亡,二十年间
-
-
行星|宇宙万物不是自然演化而来?诸多疑点,让人细思极恐
-
美国迈阿密警察局隔离140名雇员 其中68名新冠病毒检测结果呈阳性
-
央视新闻客户端|陕西高考志愿填报系统崩溃致考生过时未交?官方回应
-
-
大众途昂|铁了心要取代途昂!276马力标配10AT,30.98万起比Q7还霸气
-
-
为什么有些高颜值的女生,从不在朋友圈发自拍,也不喜欢照相?
-
英雄联盟|LOL新版本改动一览:月男,卡牌大削,女警大加强,新版蝎子乌鸦上线
-
-
-
【中国经济网】第二届进博会:一场顶级装备制造商的嘉年华
-
-
证券日报|下半年以来57家公司登陆科创板 硬科技独角兽联袂亮相
-
曝周华健为保晚节,不惜赔偿1000万违约金,已退出《中国好声音》