- 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
-
-
旅法华人战报 由机器人代替,【国际】微软开除80名记者
-
妈妈去世后感觉自己心理有问题,似乎之前也有,需要自我疗愈,我该咋办
-
雏菊西瓜Peterpan现代潜艇的探路者——“长颌须鱼”级,美国常规动力潜艇的绝唱
-
使徒行者3|《使徒行者3》林峯相隔5年回归 预告片中佘诗曼意外曝光很惊喜
-
-
新娘|新娘结婚当天,婆婆却让她卸妆,网友:颜值好高!
-
-
产业气象站|避免被陌生人盯上,很多人都忽视了,微信这4个“开关”最好关掉
-
-
[准格尔司法]人民调解化干戈,【人民调解】土地纠纷闹矛盾
-
-
老高品史|突显魅力小蛮腰,让人一眼难忘!,曼妙妩媚的打底裤女孩
-
-
-
-
-
巧百搭|寒冷冬季我有妙招!时髦保暖两手抓,轻而易举俘获气质
-
-
龙斌谈数码■最便宜的三款华为5G旗舰,其中两款搭载麒麟990处理器!