hbase表导入导出数据

hbase表导入导出数据

1.使用 HBase Shell 导入导出数据
导出数据
假设你有一个 HBase 表 my_table，你可以使用 hbase shell 导出数据到一个文件中。
hbase org.apache.hadoop.hbase.mapreduce.Export my_table /user/hadoop/exported_data

导入数据
你可以使用 hbase shell 将数据从文件导入到 HBase 表中。
hbase org.apache.hadoop.hbase.mapreduce.Import my_table /user/hadoop/exported_data

2.使用 HBase Java API 导入导出数据
导出数据
下面是一个使用 HBase Java API 导出数据的示例。
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.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableInputFormat;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
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 org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

import java.io.IOException;

public class HBaseExport {

    public static class HBaseExportMapper extends TableMapper<ImmutableBytesWritable, Text> {
        private static final byte[] FAMILY = Bytes.toBytes("cf");
        private static final byte[] QUALIFIER = Bytes.toBytes("column1");

        @Override
        protected void map(ImmutableBytesWritable key, Result value, Context context) throws IOException, InterruptedException {
            String rowKey = Bytes.toString(key.get());
            String valueStr = Bytes.toString(value.getValue(FAMILY, QUALIFIER));
            context.write(key, new Text(rowKey + "\t" + valueStr));
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration config = HBaseConfiguration.create();
        config.set("hbase.zookeeper.quorum", "your_zookeeper_quorum");
        config.set("hbase.zookeeper.property.clientPort", "2181");

        Job job = Job.getInstance(config, "HBase Export");
        job.setJarByClass(HBaseExport.class);

        TableMapReduceUtil.initTableMapperJob(
                "my_table", // 表名
                new Scan(), // 扫描配置
                HBaseExportMapper.class, // Mapper 类
                ImmutableBytesWritable.class, // 输出 key 类型
                Text.class, // 输出 value 类型
                job);

        FileOutputFormat.setOutputPath(job, new Path("/user/hadoop/exported_data"));
        job.setOutputFormatClass(TextOutputFormat.class);

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

导入数据
下面是一个使用 HBase Java API 导入数据的示例。
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.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;

import java.io.IOException;

public class HBaseImport {

    public static class HBaseImportMapper extends Mapper<LongWritable, Text, ImmutableBytesWritable, Put> {
        private static final byte[] FAMILY = Bytes.toBytes("cf");
        private static final byte[] QUALIFIER = Bytes.toBytes("column1");

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] parts = value.toString().split("\t");
            if (parts.length == 2) {
                String rowKey = parts[0];
                String valueStr = parts[1];
                Put put = new Put(Bytes.toBytes(rowKey));
                put.addColumn(FAMILY, QUALIFIER, Bytes.toBytes(valueStr));
                context.write(new ImmutableBytesWritable(Bytes.toBytes(rowKey)), put);
            }
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration config = HBaseConfiguration.create();
        config.set("hbase.zookeeper.quorum", "your_zookeeper_quorum");
        config.set("hbase.zookeeper.property.clientPort", "2181");

        Job job = Job.getInstance(config, "HBase Import");
        job.setJarByClass(HBaseImport.class);

        FileInputFormat.addInputPath(job, new Path("/user/hadoop/exported_data"));
        job.setInputFormatClass(TextInputFormat.class);

        TableMapReduceUtil.initTableReducerJob(
                "my_table", // 表名
                null, // Reducer 类，这里不需要 Reducer
                job);

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