数据行去重

最新推荐文章于 2021-12-28 10:27:54 发布

weixin_34124577

最新推荐文章于 2021-12-28 10:27:54 发布

阅读量128

点赞数

文章标签：大数据 python java

原文链接：https://my.oschina.net/yulongblog/blog/739459

版权

2019独角兽企业重金招聘Python工程师标准>>>

Dedup

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class Dedup {
  public static class DedupMapper 
       extends Mapper<Object, Text, Text, Text>{
    private Text word = new Text();    
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
    	word = value;
//把每一行作为key，然后map输出
    	context.write(word,new Text(""));
    }
  }
  
  public static class DedupReducer 
       extends Reducer<Text,Text,Text,Text> {
    public void reduce(Text key, Iterable<Text> values, 
                       Context context
                       ) throws IOException, InterruptedException {
//Shuffle过程中相同key值的进行合并，然后作为reduce输出即可
      context.write(key, new Text(""));
    }
  }

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    //String HADOOP_HOME = System.getenv("HADOOP_HOME");
    //String HADOOP_CONF_DIR = HADOOP_HOME + "/etc/hadoop";
    //conf.addResource(new Path(HADOOP_CONF_DIR + "/core-site.xml" ));
    //conf.addResource(new Path(HADOOP_CONF_DIR + "/hdfs-site.xml" ));
    //conf.addResource(new Path(HADOOP_CONF_DIR + "/yarn-site.xml" ));
    //conf.set("mapreduce.job.ubertask.enable", "true");
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length < 2) {
      System.err.println("Usage: Dedup <in> [<in>...] <out>");
      System.exit(2);
    }
    Job job = Job.getInstance(conf, "Dedup");
    job.setJarByClass(Dedup.class);
    job.setMapperClass(DedupMapper.class);
    job.setCombinerClass(DedupReducer.class);
    job.setReducerClass(DedupReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    for (int i = 0; i < otherArgs.length - 1; ++i) {
      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }
    FileOutputFormat.setOutputPath(job,
      new Path(otherArgs[otherArgs.length - 1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

转载于:https://my.oschina.net/yulongblog/blog/739459