Hadoop Mapper 阶段将数据直接从 HDFS 导入 Hbase

数据源格式如下：

20130512   1   -1 -1 13802   1   2013-05-1207:26:22
20130512   1   -1 -1 13802   1   2013-05-1211:18:24

?

我们期待的结果是数据直接从 hdfs 读取后 写入 hbase，没有 reduce 阶段，

代码如下：

package WebsiteAnalysis;
 
import java.io.IOException;
 
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.KeyValue;
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.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
 
public class Map2Hdfs {
    public static final String NAME = "ImportFromFile";
 
    public enum Counters {
        LINES
    }
 
    static class ImportMapper extends Mapper<LongWritable, Text, ImmutableBytesWritable, Writable> {
        private byte[] family = null;
        private byte[] qualifier = null;
 
        @Override
        protected void setup(Context context) throws IOException, InterruptedException {
            String column = context.getConfiguration().get("conf.column");
            byte[][] colkey = KeyValue.parseColumn(Bytes.toBytes(column));
            family = colkey[0];
            if (colkey.length > 1) {
                qualifier = colkey[1];
            }
        }
 
        @Override
        public void map(LongWritable offset, Text line, Context context) throws IOException {
            try {
                String[] lineArr = line.toString().split("\t");
                Put put = new Put(Bytes.toBytes(offset + ""));
                put.add(family, Bytes.toBytes("time"), Bytes.toBytes(lineArr[lineArr.length - 1]));
                context.write(new ImmutableBytesWritable(Bytes.toBytes(offset + "")), put);
                context.getCounter(Counters.LINES).increment(1);
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
    }
 
    public static void main(String[] args) throws Exception {
        Configuration conf = HBaseConfiguration.create();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        conf.set("conf.column", "cf");
        String inputPath = "/dsap/middata/lj/ooxx/pv";
        Job job = new Job(conf, "TestMap2Hdfs");
 
        job.setJarByClass(Map2Hdfs.class);
        job.setMapperClass(ImportMapper.class);
        job.setOutputFormatClass(TableOutputFormat.class);
        job.getConfiguration().set(TableOutputFormat.OUTPUT_TABLE, "TestMap2Hdfs");
        job.setOutputKeyClass(ImmutableBytesWritable.class);
        job.setOutputValueClass(Writable.class);
        job.setNumReduceTasks(0);
        FileInputFormat.addInputPath(job, new Path(inputPath + "/" + otherArgs[0]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

REF：

http://stackoverflow.com/questions/11061854/hadoop-writing-to-hbase-directly-from-the-mapper

http://blog.sina.com.cn/s/blog_62a9902f0101904h.html  新建表的方式写入

hbase-hdfs MapReduce 数据读写总结

http://blog.pureisle.net/archives/1938.html  hbase hdfs MR 读写的几种情况总结

http://blog.youkuaiyun.com/kirayuan/article/details/7001278  hbase表拷贝样例代码