源码：一个涉及MR、Bytes、Hbase的简单程序-优快云博客

本文链接：https://blog.youkuaiyun.com/weew_pp/article/details/43524457

本文介绍了一个使用Hadoop MapReduce对HBase中的文档内容进行字符频率统计的程序。该程序通过Map阶段读取HBase表中的记录，并将文档内容和标题组合起来，对每个字符计数；Reduce阶段汇总每个字符的出现次数并将结果写回HBase。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

源码：一个涉及MR、Bytes、Hbase的简单程序

---------------------------------------------------------------------------------------------------------

package com.inspur.hadoop;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;

public class CharCount {
   private static Log log=LogFactory.getLog(CharCount.class);
   static class CharMap extends TableMapper<Text, IntWritable>{
       private static final IntWritable one = new IntWritable(1);
       private Text word = new Text();
       public void map(ImmutableBytesWritable row, Result value, Context context){
           try{
               String content=new String(value.getValue(Bytes.toBytes("doccontent"), Bytes.toBytes("dealedcontent")));
               String title=new String(value.getValue(Bytes.toBytes("docattr"), Bytes.toBytes("dealedtitle")));
               content+=title;
               for(int i=0;i<content.length();i++){
                   word.set(String.valueOf(content.charAt(i)));
                   context.write(word, one);
                   context.progress();
               }
           }catch(Exception e){
               log.error("----------wrong--------------");
           }
       }
   }
   static class CharReduce extends TableReducer<Text,IntWritable, ImmutableBytesWritable>{
       public void reduce(Text key, Iterable<IntWritable> values, Context context){
           try{
               int sum=0;
               for(IntWritable i:values){
                   sum=sum+i.get();
               }
               Put put = new Put(Bytes.toBytes(key.toString()));
               put.add(Bytes.toBytes("charattr"), Bytes.toBytes("count"), Bytes.toBytes(String.valueOf(sum)));
               context.write(null, put);
           }catch(Exception e){
               e.printStackTrace();
           }
       }
   }
   public static void main(String[] args) throws Exception {

       Job job = Job.getInstance(HBaseConfiguration.create());
       job.setJarByClass(CharCount.class);
       Scan scan = new Scan();
       scan.setCaching(500);
       scan.setCacheBlocks(false);
       TableMapReduceUtil.initTableMapperJob("documents_crawl", scan, CharMap.class, Text.class, IntWritable.class, job);
       TableMapReduceUtil.initTableReducerJob("globaldocchar_test", CharReduce.class, job);
       job.setNumReduceTasks(20);
       job.setMapOutputKeyClass(Text.class);
       job.setMapOutputValueClass(IntWritable.class);
       System.exit(job.waitForCompletion(true) ? 0 : 1);
   }
}