HBase 总结之HBase作为输出源

简介：HBase 作为输出源，即从其他存储介质中，使用MapReduce计算后将结果输出到HBase中。

---

下面直接上代码：

---

• 主程序

package apache.org.myhbase.asoutput;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableOutputFormat;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

/**
 * 是　HBaseASOutPutMR　的启动方法，配置作业
 * @author 13277
 *
 */
public class HBaseMR {

    public static void main(String[] args) throws Exception {

        Configuration conf = HBaseConfiguration.create();
        conf.set(TableOutputFormat.OUTPUT_TABLE, "access-log");
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

        Job job = Job.getInstance(conf, "Hbase_Mr");
        job.setNumReduceTasks(0);
        job.setJarByClass(HBaseMRTest.class);
        job.setMapperClass(HBaseASOutPutMR.class);
        job.setOutputKeyClass(ImmutableBytesWritable.class);
        job.setOutputValueClass(Put.class);
        job.setOutputFormatClass(TableOutputFormat.class);

        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }

}

---

• 主程序中设置的Mapper

package apache.org.myhbase.asoutput;

import java.io.IOException;

import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

/**
 * 从HDFS读取文件内容后，解析成要要插进HBase的记录
 * @author 13277
 *
 */
public class HBaseASOutPutMR extends Mapper<LongWritable, Text, ImmutableBytesWritable, Put> {

    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        String[] strs = value.toString().split(" ");
        String rowkey = strs[0] + "-" + strs[3].substring(1);

        byte[] row = Bytes.toBytes(rowkey);
        byte[] family = Bytes.toBytes("info");
        byte[] qualifier = Bytes.toBytes("url");
        byte[] values = Bytes.toBytes(strs[6]);
        Put put = new Put(row);
        put.add(family, qualifier, values);

        context.write(new ImmutableBytesWritable(row), put);
    }
}

---

PS：
在Hadoop任务配置中，使用FileInputFormat从HDFS读取数据，输出需要配置4项内容：输出格式为TableOutputFormat，输出表名，输出数据的Key和Value的类型。