- 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
-
「虎皮青椒」饭店大厨透露:做虎皮青椒,别直接下油锅!否则不“起皮”不入味
-
-
[App小胖子]火影手游:决斗场因为直购通灵出现失衡情况?这应该是正常现象
-
-
-
小米|4K屏加持!小米新机现身:16GB RAM、支持虹膜识别
-
-
明月生海上@世界上最“重口味”的五种蔬菜,全都吃过的,请收下我的“膝盖”
-
-
-
最后推翻秦朝的是刘邦领导的起义军吗?刘邦项羽为何能打败秦军
-
-
-
快资讯|连学习时间都没了,卸妆后吓坏众人!,9岁“网红宝宝”天天化妆
-
翁静晶|在刘家良葬礼上哭到昏厥的娇妻,转身嫁进赌王家,如今怎样了
-
-
-
星座人缘|好运将陪伴这些星座到最后!,6月的坏心情全都消失
-
-
时尚迪科|穿白色长裙腰线提老高,比例不输小姑娘,60岁惠英红真是不服老