- 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
-
国家体育总局|脚下有力量 辽宁女足小花蓄势绽放,心中有梦想
-
-
郭碧婷|郭碧婷造型“翻车”,齐刘海配浓妆艳抹,优雅大气的好气质都没了
-
-
天猫服装类品牌官方旗舰店评价为何总比行业平均分低0.1 ~ 0.3分
-
娱乐新青年|瞪眼、撇嘴、假笑……林允这演技跟Anglababy学的吧!
-
肝脏|经常手麻的人:可能是这几种病在找你的麻烦,早知道能避免悲剧
-
-
-
中国之声微信公号|男孩被指划车坚决否认,民警追查3天还他清白
-
游戏日报|跟老八同桌吃饭是什么感受?过来人表示太难了,筷子都不敢动
-
滴滴出行|一缅甸女子从仰光返乡后被确诊,两KTV上班的男子返乡后确诊
-
魔兽世界|魔兽世界怀旧服:虫腿适合多少入手?一万左右,再高就等P6老三
-
-
龙卷风|内蒙古龙卷风致33人受伤,100余顶蒙古包倾倒受损
-
大学排名|出炉!2020莫斯科国际大学排名,你从没见过的中国大学榜单!
-
[水果]这6种小零食,正在渐渐消失,00后没见过,全吃过的孩子至少3岁了
-
-
-
青年|德云颜色评价rookie左手,一个给团队,一个给自己