[大数据]MapReduce实现HBase的批量导入

1、业务上在hdfs上生成了批量的数据，现在我们需要将这些数据导入到hbase中
首先我们需要了解buload的步骤：
a、生成HFile文件
b、将HFile文件load到hbase中
2、生成HFile的代码

package com.xiaofei.hbase;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.HFileOutputFormat2;
import org.apache.hadoop.hbase.util.Bytes;
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.TextInputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.io.IOException;
import java.util.UUID;

/**
 * @author xxxx
 * @date 2021.07.13
 */
public class Hdfs2Hbase extends Configured implements Tool {

    static Path pathHFile = new Path("hdfs://hadoop01:9000/hbase/userClickFile");
    static TableName tableName=TableName.valueOf("userClick");

    @Override
    public int run(String[] args) throws Exception {
        Job job=Job.getInstance(super.getConf(), Hdfs2Hbase.class.getSimpleName());
        job.setJarByClass(Hdfs2Hbase.class);

        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("hdfs://hadoop01:9000/dataclean/input/"));

        job.setMapperClass(Hdfs2HbaseMapper.class);
        job.setMapOutputKeyClass(ImmutableBytesWritable.class);
        job.setMapOutputValueClass(Put.class);

        Connection conn = ConnectionFactory.createConnection(super.getConf());
        Table table = conn.getTable(tableName);

        HFileOutputFormat2.configureIncrementalLoad(
                job,
                table,
                conn.getRegionLocator(tableName)
        );

        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS","hdfs://hadoop01:9000/dataclean/userClickFile");
        FileSystem fileSystem = FileSystem.get(configuration);
        if(fileSystem.exists(pathHFile)){
            fileSystem.delete(pathHFile,true);
        }
        HFileOutputFormat2.setOutputPath(job,pathHFile);

        return (job.waitForCompletion(true)?0:1);
    }

    public static void main(String[] args)  throws Exception{
        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum","hadoop01:2181,hadoop02:2181,hadoop03:2181");
        System.setProperty("HADOOP_USER_NAME","root");

        int run = ToolRunner.run(conf, new Hdfs2Hbase(), args);

        System.exit(run);
    }

    public static class Hdfs2HbaseMapper extends Mapper<LongWritable, Text, ImmutableBytesWritable, Put>{
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] splits = value.toString().split("\t");
            String uuid = UUID.randomUUID().toString();
            if(splits.length==6) {
                //不能使用userId做为rowkey，很多userid的操作时重复的
                //String userId = splits[1];
                byte[] rk = Bytes.toBytes(uuid);
                ImmutableBytesWritable immutableBytesWritable = new ImmutableBytesWritable();
                immutableBytesWritable.set(rk);

                Put put = new Put(rk);
                put.addColumn("info".getBytes(),"datatime".getBytes(),splits[0].getBytes());
                put.addColumn("info".getBytes(),"userid".getBytes(),splits[1].getBytes());
                put.addColumn("info".getBytes(),"searchkwd".getBytes(),splits[2].getBytes());
                put.addColumn("info".getBytes(),"retorder".getBytes(),splits[3].getBytes());
                put.addColumn("info".getBytes(),"cliorder".getBytes(),splits[4].getBytes());
                put.addColumn("info".getBytes(),"cliurl".getBytes(),splits[5].getBytes());

                context.write(immutableBytesWritable,put);
            }
        }
    }

}

3、将HFile文件load到HBase中

package com.xiaofei.hbase;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.tool.LoadIncrementalHFiles;

/**
 * @author xxxx
 * @date 2021.-7.13
 */
public class LoadData {
    public static void main(String[] args) throws Exception{
        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum","hadoop01:2181,hadoop02:2181,hadoop03:2181");
        System.setProperty("HADOOP_USER_NAME","root");
        Connection conn = ConnectionFactory.createConnection(conf);
        Table table=conn.getTable(TableName.valueOf("userClick"));
        Admin admin = conn.getAdmin();
        LoadIncrementalHFiles loadIncrementalHFiles = new LoadIncrementalHFiles(conf);

        loadIncrementalHFiles.doBulkLoad(
                new Path("hdfs://hadoop01:9000/hbase/userClickFile/"),
                admin,
                table,
                conn.getRegionLocator(TableName.valueOf("userClick"))
        );

    }
}