- 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
-
乌台诗案和以下哪位人物相关-?谁记录了乌台诗案的全过程
-
-
-
中新网|中国首部动物致伤诊治规范教你如何安全“吸猫”
-
生肖|10月初,红鸾星波动,和真爱不期而遇,喜结良缘要脱单的四大生肖
-
-
福州新闻网|全球航空业因新冠肺炎疫情收入损失将达2520亿美元
-
[北京]24省开学定档!北京、上海、天津、重庆开学有何新动态?了解一下
-
王莽|他本想做御前侍卫,不料11年后却登基称帝,一说名字世人皆知
-
核武器|俄军运输机紧急出动,反隐形雷达交付印军,印专家:能锁定歼-20
-
玉亦美丽新娱乐|超商店员开无双Combo劫匪,神手速网友笑翻:手起刀落,10秒爆头9次
-
-
宋江|宋江三个决定,不光害了自己,同时也害了梁山众人!
-
龚进辉■互联网公司反腐不狠不行,喜马拉雅副总裁因受贿被开除
-
-
畅娱网络|姿态谈英雄联盟手游:AD才是大爹,上路永远都是1V1
-
DS风清|这次不是德国,中国600吨黄金何去何从,想从美国运回黄金被拒
-
-
厝火积薪|喊农民工帮忙抬车,赶回来时突然愣住了,包工头开车掉进沟里
-