- 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
-
-
体重|原创一龙姐姐轻松把体重80多公斤的一龙扛了起来,柔道出身,擅长实战
-
-
杨幂探班赵又廷■神仙友谊!杨幂探班赵又廷 还和郭敬明热聊不断
-
-
-
-
其他人通过作弊拿到了比你高的学分,你努力学习的意义在哪里
-
松鼠热点|徒步逆行2公里,竟为此事,司机直接将车停在高速公路隧道里
-
家乐福想摆摊吗?阿里、家乐福、步步高…宣布出场地、出货源、出政策
-
-
-
陨石|NASA检测到不明物体,正在慢慢靠近地球,科学家则表示不是陨石!
-
结婚四年,这个男人出轨两次,我提离婚,但是他却不同意,这是为啥
-
拍照摄影摄影控的福利?vivo新专利曝光或让手机拍照也能支持手动变焦
-
-
DNF阿趣|DNF:7词条又出新搭配,获取容易且伤害不输533,平民党毕业首选传统毕业搭配的获取难点防具选择洗牌,7词条新搭配出现
-
宋江怒杀阎婆惜后发生了什么?宋江杀了阎婆惜后来怎样了
-
穿搭|殷桃40岁还美的出众,牛仔衣配T恤扮嫩成功,皮肤白皙宛如少女
-
『呈良福的事』这个剧真的很尬,让43岁马伊琍演20岁年轻姑娘