import java.io.IOException;
import java.util.HashMap;
import java.util.Map;
import java.util.Set;

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.MultiTableOutputFormat;
import org.apache.hadoop.hbase.mapreduce.TableInputFormat;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.util.GenericOptionsParser;

public class IndexBuilder {

    private class MyMapper extends TableMapper {
        private Map indexes = new HashMap();
        private String columnFamily;

        @Override
        protected void map(ImmutableBytesWritable key, Result value,
                Context context) throws IOException, InterruptedException {

            Set keys = indexes.keySet();
            for (byte[] k : keys) {

                ImmutableBytesWritable indexTableName = indexes.get(k);
                byte[] val = value.getValue(Bytes.toBytes(columnFamily), k);
                Put put = new Put(val);// 索引表的rowkey为原始表的值
                put.add(Bytes.toBytes("f1"), Bytes.toBytes("id"), key.get());// 索引表的内容为原始表的rowkey
                context.write(indexTableName, put);

            }

        }

        @Override
        protected void setup(Context context) throws IOException,
                InterruptedException {
            Configuration conf = context.getConfiguration();
            String tableName = conf.get("tableName");
            columnFamily = conf.get("columnFamily");
            String[] qualifiers = conf.getStrings("qualifiers");
            // indexes的key为列名，value为索引表名
            for (String q : qualifiers) {
                indexes.put(
                        Bytes.toBytes(q),
                        new ImmutableBytesWritable(Bytes.toBytes(tableName
                                + "-" + q)));

            }

        }

    }

    public static void main(String[] args) throws IOException,
            ClassNotFoundException, InterruptedException {
        Configuration conf = HBaseConfiguration.create();

        String[] otherargs = new GenericOptionsParser(conf, args)
                .getRemainingArgs();// 去除掉没有用的命令行参数
        // 输入参数：表名，列族名，列名
        if (otherargs.length < 3) {
            System.exit(-1);
        }
        String tableName = otherargs[0];
        String columnFamily = otherargs[1];

        conf.set("tableName", tableName);
        conf.set("columnFamily", columnFamily);

        String[] qualifiers = new String[otherargs.length - 2];
        for (int i = 0; i < qualifiers.length; i++) {

            qualifiers[i] = otherargs[i + 2];
        }
        conf.setStrings("qualifiers", qualifiers);
        Job job = new Job(conf, tableName);
        job.setJarByClass(IndexBuilder.class);
        job.setMapperClass(MyMapper.class);
        job.setNumReduceTasks(0);
        job.setInputFormatClass(TableInputFormat.class);
        // 可以输出多张表
        job.setOutputFormatClass(MultiTableOutputFormat.class);
        Scan scan = new Scan();
        scan.setCaching(1000);
        TableMapReduceUtil.initTableMapperJob(tableName, scan, MyMapper.class,
                ImmutableBytesWritable.class, Put.class, job);
        job.waitForCompletion(true);

    }

}

网站标题：Mapreduce构建hbase二级索引
本文链接：http://ybzwz.com/article/jgcspp.html