HBase 总结之HBase作为共享源

简介：HBase作为共享源，即HBase作为输入源，同时作为输出源。通俗的讲，就是从HBase中读取数据，使用MapReduce处理过后，再将处理的结果存入HBase中去。

---

下面直接上代码：

---

package apache.org.myhbase.asshare;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
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.Text;
import org.apache.hadoop.mapreduce.Job;

/**
 * hbase作为数据共享源，即从hbase中读取数据后做处理再插入回hbase
 * 
 * @author 13277
 *
 */
public class HBaseMR {

    final static String inTable = "access-log";
    final static String inFamily = "info";
    final static String inColumn = "url";

    final static  String outTable="total-access";
    final static  String outFamily="url";
    final static  String outColumn="count";

    public static class Mapper extends TableMapper<Text,Text> {
        public Mapper() {}
        @Override
        public void map(ImmutableBytesWritable row, Result values,Context context) 
                throws IOException, InterruptedException {

            byte[] b = values.getValue(inFamily.getBytes(), inColumn.getBytes());

            if (b != null) {
                String v = new String(b);
                String r = new String(values.getRow());
                String[] strs = r.split("-");
                String ip = strs[0];
                System.out.println("iamhere"+r);
                context.write(new Text(ip), new Text(v));
            }
        }
    }

    public static class Reducer extends TableReducer<Text, Text, Text> {
        @Override
        public void reduce(Text key, Iterable<Text> values, Context context) 
                throws IOException, InterruptedException {

            int count = 0;
            String sum = null;
            for (Text val : values) {
                count++;
            }
            sum = String.valueOf(count);

            Put put = new Put(Bytes.toBytes(key.toString()));

            put.add(outFamily.getBytes(), outColumn.getBytes(), sum.getBytes());
            context.write(key, put);
        }
    }

    public static void main(String[] args) 
            throws IOException, ClassNotFoundException, InterruptedException {

        System.out.println("iamherestart");
        Configuration conf = HBaseConfiguration.create();
        Job job = Job.getInstance(conf, "HbaseMR");

        job.setJarByClass(HBaseMR.class);
        Scan scan = new Scan();

        TableMapReduceUtil.initTableMapperJob("access-log", scan, Mapper.class, Text.class, Text.class, job);

        TableMapReduceUtil.initTableReducerJob("total-access", Reducer.class, job);

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

---

PS：
从access-log中读取所有访问记录数据，然后计算出每个ip的访问次数存储到total-access表中。