HBase API(新版本)

以下API均為HBase API 3.0版本。

API3.0與API2.0對比

Put、Delete、Scan類的API沒有發生太多改變

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

Hbase的import

參考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;

連接HBase

public static Configuration configuration;
public static Connection connection;
public static Admin admin;
    //建立連接
    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();
        }
    }

創建表

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);//刪除原來的表
        }

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

添加數據Put

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

刪除操作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));
        //刪除指定列族
        delete.addFamily(Bytes.toBytes(colFamily));
        //刪除指定列
        delete.addColumn(Bytes.toBytes(colFamily),Bytes.toBytes(col));
        table.delete(delete);
        table.close();
        close();
    }

全表掃描

scan可以掃描多條記錄。

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);//獲取行的遍歷器
        for (Result result:scanner){
            printRecoder(result);
        }
        close();
    }

Cell輸出

通過Result.rawCells()可以得到Cell，一個RowKey有多個單元格，一個單元格一個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("時間戳: "+cell.getTimestamp());
            /*
            CellUtil在HBase2.0被棄用，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("時間戳: "+cell.getTimestamp());
            */
        }
    }

指定列族的信息

get獲取一個單元格的多個版本信息

public static void getData(String tableName)throws  IOException{
        init();
        Table table = connection.getTable(TableName.valueOf(tableName));
        //創建一個Get對象
        Get get = new Get(Bytes.toBytes(rowKey));
        //獲取數據的操作
        Result result = table.get(get);
        Cell[] cells = result.rawCells();
        for (Cell cell:cells){
            print(cell);
        }
        close();
    }

Admin接口

Admin接口用於管理HBase數據庫的表信息，包括創建刪除表，列出表等。

返回值	方法	介紹
void	createTable(TableDescriptor tabledescriptor)	創建表
void	deleteTable(TableName tableName)	刪除表
void	disableTable(TableName tableName)	使表無效
boolean	tableExists(TableName tableName)	檢查表是否存在
TableDescriptor	listTableDescriptors()	列出所有表

TableDescriptorBuilder接口

該接口用於構建TableDescriptorBuilder類，主要方法如下：

返回值	方法	介紹
TableDescriptor	build()	構建TableDescriptor
TableDescriptorBuilder	newBuilder(byte[] name)	構建TableDescriptorBuilder
TableDescriptorBuilder	setColumnFamily(ColumnFamilyDescriptor family)	設置某個列族
TableDescriptorBuilder	removeColumnFamily(byte[] name)	刪除某個列族

ColumnFamilyDescriptor接口

該接口用於構建ColumnFamilyDescriptor，其主要方法如下：

返回值	方法	介紹
ColumnFamilyDescriptor	build()	構建ColumnFamilyDescriptor
ColumnFamilyDescriptorBuilder	newBuilder(byte[] name)	構建ColumnFamilyDescriptorBuilder