- 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
-
享趣看娱乐|汽车在行驶中突然熄火的原因是什么?只有三个原因!
-
北京晚报|广西北海发生管线着火事故,致5人遇难,1人失联,3人重伤
-
辛迪露妍@你如果抓住了ta并全心投入,你就可以赚取人生的第一桶金!,在这个红利时期
-
-
火法|魔兽世界怀旧服P5火法最强DPS配装,追求极致的散件流!
-
-
天气早知道|《哈利波特》的世界,可以迟到,但不该缺席
-
-
身体若有3个表现,说明心脏很健康,更易长寿!看看你有几个?
-
-
-
关节|孕期全身疼痛?原来这五种疼痛是正常的,第五种很多孕妇都会有
-
-
-
-
鹰之翼|就算洲际导弹打来也能安然无恙,特朗普的地下避难基地:随时加固
-
中国大学排行榜|最新:2020中国大学排行榜发布!附前300名单
-
-
-