MapReduce hbaseToHdfs

HBase数据导出到HDFS

最新推荐文章于 2022-07-25 17:37:23 发布

原创最新推荐文章于 2022-07-25 17:37:23 发布 · 189 阅读

0 ·

CC 4.0 BY-SA版权

MapReduce 专栏收录该内容

12 篇文章

订阅专栏

本文介绍了一种将HBase表数据转换并导出到HDFS的方法，使用自定义的Mapper类处理HBase的KeyValue，将结果写入到HDFS中。此过程包括配置参数、创建Job实例、初始化TableMapper作业以及设置输出路径。

package sitech;

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.KeyValue;
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.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import java.io.IOException;

public class HbaseToHdfs {
    public static class HbaseToHdfsMapper extends TableMapper<NullWritable, Text> {
        private Text outPut = new Text();
        @Override
        protected void map(ImmutableBytesWritable key, Result value, Context context) throws IOException, InterruptedException {
            //
            StringBuffer value_res = new StringBuffer();
            for (KeyValue kv : value.raw()) {
                String clumn_value = new String(kv.getValue(), "utf-8");
                value_res.append(clumn_value + ",");
            }
            value_res.delete(value_res.length()-1,value_res.length());
            outPut.set(value_res.toString());
            context.write(NullWritable.get(), outPut);
        }
    }

    public static Job createSubmittableJob(Configuration conf, String[] args) throws IOException {
        String hbase_table_name = args[0];
        String outPut = args[1];
        conf.set("hbase_table_name", hbase_table_name);
        conf.set("outPut", outPut);
        Job job = Job.getInstance(conf, "HbaseToHdfs");
        job.setJarByClass(HbaseToHdfs.class);
        job.setMapperClass(HbaseToHdfsMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        job.setNumReduceTasks(0);
        TableMapReduceUtil.initTableMapperJob(hbase_table_name, new Scan(), HbaseToHdfsMapper.class, NullWritable.class, Text.class, job);
        Path path = new Path(outPut);
        FileSystem fs = FileSystem.get(conf);
        if (fs.exists(path)) {
            fs.delete(path, true);
        }
        FileOutputFormat.setOutputPath(job, path);
        return job;
    }

    public static void main(String[] args) throws InterruptedException, IOException, ClassNotFoundException {
        Configuration conf = HBaseConfiguration.create();
        //设置压缩格式
        conf.set("mapreduce.output.fileoutputformat.compress", "false");
        //设置内存
        conf.set("mapreduce.map.memory.mb", "2048");
        String[] otherArgs = new GenericOptionsParser(conf, args)
                .getRemainingArgs();
        if (otherArgs.length != 2) {
            System.exit(-1);
        }
        Job job = createSubmittableJob(conf, otherArgs);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}