HBase API(新版本)

以下API均为HBase API 3.0版本。

API3.0与API2.0对比

Put、Delete、Scan类的API没有发生太多改变

HTableDescriptor类被TableDescriptorBuilder替代，HColumnDescriptor被ColumnFamilyDescriptor替代，CellUtil类被淘汰。

Hbase的import

参考https://blog.csdn.net/qq_38899342/article/details/97540118。

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.TableNotFoundException;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.ColumnFamilyDescriptor;
import org.apache.hadoop.hbase.client.ColumnFamilyDescriptorBuilder;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Delete;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.ResultScanner;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.client.TableDescriptor;
import org.apache.hadoop.hbase.client.TableDescriptorBuilder;
import org.apache.hadoop.hbase.client.coprocessor.Batch.Call;
import org.apache.hadoop.hbase.util.Bytes;

连接HBase

public static Configuration configuration;
public static Connection connection;
public static Admin admin;
    //建立连接
    public static void init(){
        configuration  = HBaseConfiguration.create();
        configuration.set("hbase.master", "master:60000");
        configuration.set("hbase.zookeeper.quorum", "master");
        configuration.set("hbase.rootdir","hdfs://localhost:9000/hbase");
        try{
            connection = ConnectionFactory.createConnection(configuration);
            admin = connection.getAdmin();
        }catch (IOException e){
            e.printStackTrace();
        }
    }

创建表

public static void createTable(String tableName,String[] fields) throws IOException {

        init();
        TableName tablename = TableName.valueOf(tableName);

        if(admin.tableExists(tablename)){
            System.out.println("table is exists!");
            admin.disableTable(tablename);
            admin.deleteTable(tablename);//删除原来的表
        }

        TableDescriptorBulider tableDescriptor = TableDescriptorBuilder.newBuilder(tablename);
        for(String str : fields){
            tableDescriptor.setColumnFamily(ColumnFamilyDescriptorBuilder.newBuilder(Bytes.toBytes(str)).build());
        admin.createTable(tableDescriptor.build());

添加数据Put

public static void putData(String tableName,String rowKey,String colFamily,String col,String val) throws IOException {
        init();
        //获取表对象
        Table table = connection.getTable(TableName.valueOf(tableName));
        //创建Put对象
        Put put = new Put(Bytes.toBytes(rowKey));
        put.addColumn(Bytes.toBytes(colFamily), Bytes.toBytes(col), Bytes.toBytes(val));
        table.put(put);
        table.close();
        close();
    }

删除操作Delete

public static void deleteData(String tableName,String rowKey,String colFamily,String col) throws IOException {
        init();
        Table table = connection.getTable(TableName.valueOf(tableName));
        Delete delete = new Delete(Bytes.toBytes(rowKey));
        //删除指定列族
        delete.addFamily(Bytes.toBytes(colFamily));
        //删除指定列
        delete.addColumn(Bytes.toBytes(colFamily),Bytes.toBytes(col));
        table.delete(delete);
        table.close();
        close();
    }

全表扫描

scan可以扫描多条记录。

public static void scanData(String tableName)throws  IOException{
        init();
        Table table = connection.getTable(TableName.valueOf(tableName));
        Scan scan = new Scan();
        ResultScanner scanner = table.getScanner(scan);//获取行的遍历器
        for (Result result:scanner){
            printRecoder(result);
        }
        close();
    }

Cell输出

通过Result.rawCells()可以得到Cell，一个RowKey有多个单元格，一个单元格一个Cell。

public  static void printRecoder(Result result)throws IOException{
        for(Cell cell:result.rawCells()){
            System.out.print("行健: "+new String(Bytes.toString(cell.getRowArray(),cell.getRowOffset(), cell.getRowLength())));
            System.out.print("列簇: "+new String( Bytes.toString(cell.getFamilyArray(),cell.getFamilyOffset(), cell.getFamilyLength()) ));
            System.out.print(" 列: "+new String(Bytes.toString(cell.getQualifierArray(),cell.getQualifierOffset(), cell.getQualifierLength())));
            System.out.print(" 值: "+new String(Bytes.toString(cell.getValueArray(),cell.getValueOffset(), cell.getValueLength())));
            System.out.println("时间戳: "+cell.getTimestamp());
            /*
            CellUtil在HBase2.0被弃用，在HBase3.0被移除，因此它的cloneRow，cloneFamily等都被淘汰
            System.out.print("行健: "+new String(CellUtil.cloneRow(cell)));
            System.out.print("列簇: "+new String(CellUtil.cloneFamily(cell)));
            System.out.print(" 列: "+new String(CellUtil.cloneQualifier(cell)));
            System.out.print(" 值: "+new String(CellUtil.cloneValue(cell)));
            System.out.println("时间戳: "+cell.getTimestamp());
            */
        }
    }

指定列族的信息

get获取一个单元格的多个版本信息

public static void getData(String tableName)throws  IOException{
        init();
        Table table = connection.getTable(TableName.valueOf(tableName));
        //创建一个Get对象
        Get get = new Get(Bytes.toBytes(rowKey));
        //获取数据的操作
        Result result = table.get(get);
        Cell[] cells = result.rawCells();
        for (Cell cell:cells){
            print(cell);
        }
        close();
    }

Admin接口

Admin接口用于管理HBase数据库的表信息，包括创建删除表，列出表等。

返回值	方法	介绍
void	createTable(TableDescriptor tabledescriptor)	创建表
void	deleteTable(TableName tableName)	删除表
void	disableTable(TableName tableName)	使表无效
boolean	tableExists(TableName tableName)	检查表是否存在
TableDescriptor	listTableDescriptors()	列出所有表

TableDescriptorBuilder接口

该接口用于构建TableDescriptorBuilder类，主要方法如下：

返回值	方法	介绍
TableDescriptor	build()	构建TableDescriptor
TableDescriptorBuilder	newBuilder(byte[] name)	构建TableDescriptorBuilder
TableDescriptorBuilder	setColumnFamily(ColumnFamilyDescriptor family)	设置某个列族
TableDescriptorBuilder	removeColumnFamily(byte[] name)	删除某个列族

ColumnFamilyDescriptor接口

该接口用于构建ColumnFamilyDescriptor，其主要方法如下：

返回值	方法	介绍
ColumnFamilyDescriptor	build()	构建ColumnFamilyDescriptor
ColumnFamilyDescriptorBuilder	newBuilder(byte[] name)	构建ColumnFamilyDescriptorBuilder