- 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
-
生日|原创赌王女儿何超盈30岁生日,终于瘦了,婚礼上胖成球身形抵两老公
-
社会大爆点|乔欣穿衣真斗胆!一袭玄色吊带透视裙大秀好身材,性感妩媚又撩人
-
长沙|中央部委又“点名”6个城市!新一轮楼市调控或许不远了
-
妻为上:景韶打架像儿戏,蹭饭人员有点多,王爷吃醋好真实
-
-
-
-
【PhoneTV】Ace2能够继续真香,看完这些配置再说,4月13日就来的OPPO
-
-
-
鲁班大师@王者荣耀S20战令皮? 一级确定鲁班大师, 云中君6元史诗原画已经确定!
-
产品|多位明星代言产品遭遇“翻车”,出问题谁该埋单?
-
退休|公司以到年龄劳动合同自动终止为由要员工自行办理退休,怎么办?
-
移动,电信,联通,哪个运营商更好 移动联通电信运营商哪个好
-
白小白的衣橱|黄圣依“套娃”打扮,上衣下装各穿两层,外搭不严实内搭也藏不住
-
-
F-35|战斗在凌晨打响!F35遭到俄制导弹攻击,美军专家称有预谋的伏击
-
-
-
FE电竞APP|【FE前瞻】欧美豪门S10初见,欧成与大师兄小组赛直面交锋