- 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
-
每天知守观|民进党却“害怕”了?,美国送上“大礼”
-
宋茜|宋茜新剧口碑不俗,演技被赞脱胎换骨,两大“男二专业户”抢镜!
-
-
汕尾市@广东最“强”的一个镇:由镇“跳级”,直接成为地级市!
-
姜文|姜文的3个子女,同个爸爸不同一个妈,颜值差距真不是一般大
-
公司|彩虹股份:第二大股东中电彩虹解除质押约9063万股
-
-
-
TOPWOMEN时髦笔记|演绎优雅俏女人风格,私服穿搭更是惹人羡,杨紫最新时尚大片曝光
-
-
-
「娇柔的柠檬」挺难!》赚钱难!做人难!求人难,交心更难!真的好难,《一辈子
-
-
潇湘大视野|美国总统川普终于:戴口罩,瘟疫肆虐近半年、夺走13万人性命之后
-
-
-
安陵容|从安陵容到浣碧,不懂得五个字,怎会有幸福?
-
公司|益生菌“第一股”——科拓生物今成功登陆创业板
-
-
杭州|新元素来了!电竞和霹雳舞成为杭州亚运会正式竞赛项目