Hadoop HIVE JavaAPI

DDL操作

表的增删改查

1、构建连接
2、从连接中取到一个表DDL操作工具admin
3、admin.createTable(表描述对象);
4、admin.disableTable(表名)
5、admin.deleteTable(表名);
6、admin.modifyTable(表名，表描述对象);

package demo;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
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.regionserver.BloomType;
import org.junit.Before;
import org.junit.Test;

public class HbaseClientDDL {
	Connection conn = null;
	@Before
	public void getConn() throws Exception{
		// 构建一个连接对象
		Configuration conf = HBaseConfiguration.create(); // 会自动加载hbase-site.xml
		conf.set("hbase.zookeeper.quorum", "ip1:2181,ip2:2181,ip3:2181"); //设置管理Hbase的zookeeper对象
		conn = ConnectionFactory.createConnection(conf);
	}
	
	@Test
	public void testCreateTable() throws Exception{//添加表
		Admin admin = conn.getAdmin();// 构造DDL操作器
		HTableDescriptor hTableDescriptor = new HTableDescriptor(TableName.valueOf("table_info"));// 表描述对象
		HColumnDescriptor hColumnDescriptor_1 = new HColumnDescriptor("column_info");// 列族定义描述对象
		hColumnDescriptor_1.setMaxVersions(3); // 设置该列族中存储数据的最大版本数,默认是1
		hTableDescriptor.addFamily(hColumnDescriptor_1);// 将列族定义信息对象放入表定义对象中
		admin.createTable(hTableDescriptor);// 建表
		admin.close();
		conn.close();
	}
	
	@Test
	public void testDropTable() throws Exception{
		Admin admin = conn.getAdmin();
		admin.disableTable(TableName.valueOf("user_info"));// 停用表
		admin.deleteTable(TableName.valueOf("user_info"));// 删除表
		admin.close();
		conn.close();
	}
	
	@Test
	public void testAlterTable() throws Exception{//修改表
		Admin admin = conn.getAdmin();
		HTableDescriptor tableDescriptor = admin.getTableDescriptor(TableName.valueOf("table_info"));// 取出旧的表定义信息
		HColumnDescriptor hColumnDescriptor = new HColumnDescriptor("another_info");// 新构造一个列族定义
		hColumnDescriptor.setBloomFilterType(BloomType.ROWCOL); // 设置该列族的布隆过滤器类型
		tableDescriptor.addFamily(hColumnDescriptor);// 将列族定义添加到表定义对象
		admin.modifyTable(TableName.valueOf("table_info"), tableDescriptor);//admin提交
		admin.close();
		conn.close();
	}
}

DML操作

数据的增删改查

package demo;

import java.util.ArrayList;
import java.util.Iterator;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellScanner;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
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.Scan;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.util.Bytes;
import org.junit.Before;
import org.junit.Test;

public class HbaseClientDML {
	Connection conn = null;
	@Before
	public void getConn() throws Exception{
		Configuration conf = HBaseConfiguration.create(); // 会自动加载hbase-site.xml
		conf.set("hbase.zookeeper.quorum", "ip1:2181,ip2:2181,ip3:2181");
		conn = ConnectionFactory.createConnection(conf);
	}

	@Test
	public void testPut() throws Exception{//插入数据
		Table table = conn.getTable(TableName.valueOf("table_info"));// 获取表格
		Put put = new Put(Bytes.toBytes("001"));// put对象既是rowkey
		put.addColumn(Bytes.toBytes("base_info"), Bytes.toBytes("username"), Bytes.toBytes("xiaowang"));
		
		Put put2 = new Put(Bytes.toBytes("002"));
		put2.addColumn(Bytes.toBytes("base_info"), Bytes.toBytes("username"), Bytes.toBytes("xiaowei"));
		
		// 插如数据
		ArrayList<Put> puts = new ArrayList<>();
		puts.add(put);
		puts.add(put2);
		table.put(puts);
		table.close();
		conn.close();
		
	}
	

	@Test
	public void testDelete() throws Exception{//删除数据
		Table table = conn.getTable(TableName.valueOf("table_info"));
		
		Delete delete1 = new Delete(Bytes.toBytes("001"));// 构造一个对象封装要删除的数据信息
		Delete delete2 = new Delete(Bytes.toBytes("002"));
		delete2.addColumn(Bytes.toBytes("table_info"), Bytes.toBytes("username"));
		
		ArrayList<Delete> dels = new ArrayList<>();
		dels.add(delete1);
		dels.add(delete2);
		table.delete(dels);
	
		table.close();
		conn.close();
	}
	
	@Test
	public void testGet() throws Exception{
		Table table = conn.getTable(TableName.valueOf("table_info"));//获得表
		Get get = new Get("002".getBytes()); //创建列簇对象
		Result result = table.get(get);//获得列簇对应数据
		byte[] value = result.getValue("base_info".getBytes(), "age".getBytes());// 从列簇中取用户指定的某个key的value
		System.out.println(new String(value));
		System.out.println("-------------------------");
		
		// 遍历整行结果中的所有kv单元格
		CellScanner cellScanner = result.cellScanner();
		while(cellScanner.advance()){
			Cell cell = cellScanner.current();
			byte[] rowArray = cell.getRowArray();  //本kv所属的行键的字节数组
			byte[] familyArray = cell.getFamilyArray();  //列族名的字节数组
			byte[] qualifierArray = cell.getQualifierArray();  //列名的字节数据
			byte[] valueArray = cell.getValueArray(); // value的字节数组
			
			System.out.println("行键: "+new String(rowArray,cell.getRowOffset(),cell.getRowLength()));
			System.out.println("列族名: "+new String(familyArray,cell.getFamilyOffset(),cell.getFamilyLength()));
			System.out.println("列名: "+new String(qualifierArray,cell.getQualifierOffset(),cell.getQualifierLength()));
			System.out.println("value: "+new String(valueArray,cell.getValueOffset(),cell.getValueLength()));
		}
		table.close();
		conn.close();
	}
	

	@Test
	public void testScan() throws Exception{
		Table table = conn.getTable(TableName.valueOf("table_info"));
		Scan scan = new Scan("10".getBytes(), "10000\001".getBytes());// 包含起始行键，不包含结束行键,但是如果真的想查询出末尾的那个行键，那么，可以在末尾行键上拼接一个不可见的字节（\000）
		ResultScanner scanner = table.getScanner(scan);
		Iterator<Result> iterator = scanner.iterator();
		while(iterator.hasNext()){
			Result result = iterator.next();
			CellScanner cellScanner = result.cellScanner();// 遍历整行结果中的所有kv单元格
			while(cellScanner.advance()){
				Cell cell = cellScanner.current();
				
				byte[] rowArray = cell.getRowArray();  //本kv所属的行键的字节数组
				byte[] familyArray = cell.getFamilyArray();  //列族名的字节数组
				byte[] qualifierArray = cell.getQualifierArray();  //列名的字节数据
				byte[] valueArray = cell.getValueArray(); // value的字节数组
				
				System.out.println("行键: "+new String(rowArray,cell.getRowOffset(),cell.getRowLength()));
				System.out.println("列族名: "+new String(familyArray,cell.getFamilyOffset(),cell.getFamilyLength()));
				System.out.println("列名: "+new String(qualifierArray,cell.getQualifierOffset(),cell.getQualifierLength()));
				System.out.println("value: "+new String(valueArray,cell.getValueOffset(),cell.getValueLength()));
			}
			System.out.println("----------------------");
		}
	}

参考:
布隆过滤器