HDFS - HBSE -MR

最新推荐文章于 2023-01-02 15:50:11 发布

原创最新推荐文章于 2023-01-02 15:50:11 发布 · 163 阅读

0 ·

CC 4.0 BY-SA版权

hbase 专栏收录该内容

5 篇文章

订阅专栏

本文介绍了如何使用Hadoop的MapReduce框架将HDFS中的数据批量导入HBase，包括Mapper和Reducer的实现，以及配置细节。重点在于HDFS到HBase的数据转换和批量写入过程。

HDFS - HBASE

package com.ws.hbaseMr;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import java.io.IOException;

public class Hdfs2Hbase {

    public static class M extends Mapper<LongWritable, Text,Text,IntWritable>{
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] split = value.toString().split(",");
            for (String s : split) {
                context.write(new Text(s),new IntWritable(1));
            }
        }
    }

    public static class R extends TableReducer<Text,IntWritable, ImmutableBytesWritable>{
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            Put put = new Put(key.getBytes());
            int i=0;
            for (IntWritable value : values) {
                i+=value.get();
            }
            put.addColumn("f".getBytes(),"n".getBytes(),(i+"").getBytes());
            context.write(null,put);
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum","dream1:2181,dream2:2181");
        Job job = Job.getInstance(conf);

        job.setJarByClass(Hdfs2Hbase.class);
        job.setMapperClass(M.class);
        job.setReducerClass(R.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job,new Path("hdfs://dream1:9000/hd2hb/input"));

        TableMapReduceUtil.initTableReducerJob("hd2hb",R.class,job);

        job.waitForCompletion(true);

    }
}

HBASE-HDFS

package com.ws.hbaseMr;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;
import java.util.Collections;

public class HBase2Hdfs {

    public static class M extends TableMapper<Text,IntWritable> {
        @Override
        protected void map(ImmutableBytesWritable key, Result value, Context context) throws IOException, InterruptedException {
            byte[] value1 = value.getValue("f".getBytes(), "n".getBytes());
            byte[] bytes = key.get();
            context.write(new Text(new String(bytes)),new IntWritable(Integer.parseInt(new String(value1))));
        }
    }

    public static class R extends Reducer<Text,IntWritable,Text,IntWritable> {
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            for (IntWritable value : values) {
                context.write(key,value);
            }
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum","dream1:2181,dream2:2181");
        System.setProperty("HADOOP_USER_NAME","root");
        Job job = Job.getInstance(conf);
        job.setJarByClass(HBase2Hdfs.class);
        job.setReducerClass(R.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        Scan scan = new Scan();
        TableMapReduceUtil.initTableMapperJob("hd2hb",scan,M.class,Text.class,IntWritable.class,job);

        FileOutputFormat.setOutputPath(job,new Path("hdfs://dream1:9000/hd2hb/out"));
        job.waitForCompletion(true);
    }
}

HBASE-MR-HBASE

package com.ws.hbaseMr;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class HBase2HBaseMr {

    public static class M extends TableMapper<Text,IntWritable> {
        @Override
        protected void map(ImmutableBytesWritable key, Result value, Context context) throws IOException, InterruptedException {
            byte[] value1 = value.getValue("f".getBytes(), "n".getBytes());
            byte[] bytes = key.get();
            context.write(new Text(new String(bytes)),new IntWritable(Integer.parseInt(new String(value1))));
        }
    }

    public static class R extends TableReducer<Text,IntWritable,ImmutableBytesWritable> {
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            Put put = new Put((values.iterator().next().get()+"").getBytes());
            put.addColumn("f".getBytes(),"n".getBytes(),key.getBytes());
            context.write(null,put);
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum","dream1:2181,dream2:2181");
        Job job = Job.getInstance(conf);
        job.setJarByClass(HBase2HBaseMr.class);
        Scan scan = new Scan();
        TableMapReduceUtil.initTableMapperJob("hd2hb",scan,M.class,Text.class,IntWritable.class,job);
        TableMapReduceUtil.initTableReducerJob("hb2hb",R.class,job);

        job.waitForCompletion(true);
    }
}