spark与MR读取HBase snapshot

最新推荐文章于 2022-09-26 19:39:33 发布

原创

最新推荐文章于 2022-09-26 19:39:33 发布 · 1.5k 阅读

1 ·

CC 4.0 BY-SA版权

import com.suning.recmmentation.content.video.online.habse.HbaseDaoImpl;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
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.util.Bytes;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
import java.net.URISyntaxException;

/**
 * mr读HBase snapshot，由于yarn和HBase用的是两个hadoop集群，所以需要配置值HBase集群的hdfs地址
 */
public class MrSnapshot {
    private static final String JOB_NAME = "XXX";
    /**
     * HBase表快照名
     */
    private static String snapshotName = "XXX";