MapReduce结果插入Hbase

1.在HBase上创建table 'wc'

create 'wc','cf1'

2.wordcount的job

package zzw.cn;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import java.io.IOException;

public class WordCountJob
{
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException
    {
        String inputPath="hdfs://master.cn:8020/user/input/";
        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum", "master.cn,slave1.cn,slave2.cn");
        Job job = Job.getInstance(conf);
        job.setJobName("word count");
        job.setJarByClass(WordCountJob.class);
        job.setMapperClass(WordCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(inputPath));
        TableMapReduceUtil.initTableReducerJob(
                "wc",        // output table
                WordCountReduce.class,    // reducer class
                job);
        Boolean flag = job.waitForCompletion(true);
        if (flag)
        {
            System.out.println("job success");
        }
    }
}

3.Mapper类

package zzw.cn;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.util.StringUtils;

import java.io.IOException;

public class WordCountMapper extends Mapper
{
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException
    {
        String[] strs = StringUtils.split(value.toString(), ' ');
        for (int i = 0; i < strs.length; i++)
        {
            String s = strs[i];
            context.write(new Text(s), new IntWritable(1));
        }
    }
}

4.Reduce类

package zzw.cn;

import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
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 java.io.IOException;

public class WordCountReduce extends TableReducer
{
    @Override
    protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException
    {
        int i = 0;
        for (IntWritable value : values)
        {
            i += value.get();
        }
        Put put = new Put(Bytes.toBytes(key.toString()));
        put.addColumn("cf1".getBytes(), "count".getBytes(), Bytes.toBytes(i + ""));
        context.write(null, put);
    }
}

5.pom.xml

    4.0.0

    zzw.cn
    hbase.mapreduce
    1.0-SNAPSHOT

    
        
            org.apache.hadoop
            hadoop-common
            2.6.0-cdh5.15.0
        

        
            org.apache.hadoop
            hadoop-client
            2.6.0-cdh5.15.0
        

        
            org.apache.hadoop
            hadoop-hdfs
            2.6.0-cdh5.15.0
        
        
            org.apache.hbase
            hbase-common
            1.2.0-cdh5.15.0
        
        
            org.apache.hbase
            hbase-client
            1.2.0-cdh5.15.0
        
        
            org.apache.hbase
            hbase-server
            1.2.0-cdh5.15.0
        

    

    
        
            cloudera
            https://repository.cloudera.com/artifactory/cloudera-repos
        
    

6.打成jar包在hdfs上运行

hadoop jar /opt/datas/HBaseMrDemo.jar

7.查询hbase中wc的结果：

hbase(main):022:0> scan 'wc'
ROW                             COLUMN+CELL                                                                             
 hadoop                         column=cf1:count, timestamp=1543742364591, value=2                                      
 hbase                          column=cf1:count, timestamp=1543742364591, value=1                                      
 hello                          column=cf1:count, timestamp=1543742364591, value=2                                      
 name                           column=cf1:count, timestamp=1543742364591, value=3                                      
 world                          column=cf1:count, timestamp=1543742364591, value=1                                      
 zookeeper                      column=cf1:count, timestamp=1543742364591, value=1                                      
6 row(s) in 0.0250 seconds