Hadoop学习(5)-HBASE的安装和命令行操作和java操作

#！/bin/bash
for host in hdp-01 hdp-02 hdp-03 hdp-04
do
echo "${host}:starting...."
ssh $host "/root/apps/zookeeper-3.4.6/bin/zkserver.sh $1"
done
sleep 2
for host in hdp-01 hdp-02 hdp-03 hdp-04
do
ssh $host "/root/apps/zookeeper-3.4.6/bin/zkserver.sh status"
done

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;


/**
 *  
 *  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);    
 *  
 * @author hunter.d
 *
 */
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", "hdp-01:2181,hdp-02:2181,hdp-03:2181,hdp-04:2181");
        
        conn = connectionfactory.createconnection(conf);
    }
    
    
    
    /**
     * ddl
     * @throws exception 
     */
    @test
    public void testcreatetable() throws exception{

        // 从连接中构造一个ddl操作器
        admin admin = conn.getadmin();
        
        // 创建一个表定义描述对象
        htabledescriptor htabledescriptor = new htabledescriptor(tablename.valueof("user_info"));
        
        // 创建列族定义描述对象
        hcolumndescriptor hcolumndescriptor_1 = new hcolumndescriptor("base_info");
        hcolumndescriptor_1.setmaxversions(3); // 设置该列族中存储数据的最大版本数,默认是1
        
        hcolumndescriptor hcolumndescriptor_2 = new hcolumndescriptor("extra_info");
        
        // 将列族定义信息对象放入表定义对象中
        htabledescriptor.addfamily(hcolumndescriptor_1);
        htabledescriptor.addfamily(hcolumndescriptor_2);
        
        
        // 用ddl操作器对象：admin 来建表
        admin.createtable(htabledescriptor);
        
        // 关闭连接
        admin.close();
        conn.close();
        
    }
    
    
    /**
     * 删除表
     * @throws exception 
     */
    @test
    public void testdroptable() throws exception{
        
        admin admin = conn.getadmin();
        
        // 停用表
        admin.disabletable(tablename.valueof("user_info"));
        // 删除表
        admin.deletetable(tablename.valueof("user_info"));
        
        
        admin.close();
        conn.close();
    }
    
    // 修改表定义--添加一个列族
    @test
    public void testaltertable() throws exception{
        
        admin admin = conn.getadmin();
        
        // 取出旧的表定义信息
        htabledescriptor tabledescriptor = admin.gettabledescriptor(tablename.valueof("user_info"));
        
        
        // 新构造一个列族定义
        hcolumndescriptor hcolumndescriptor = new hcolumndescriptor("other_info");
        hcolumndescriptor.setbloomfiltertype(bloomtype.rowcol); // 设置该列族的布隆过滤器类型
        
        // 将列族定义添加到表定义对象中
        tabledescriptor.addfamily(hcolumndescriptor);
        
        
        // 将修改过的表定义交给admin去提交
        admin.modifytable(tablename.valueof("user_info"), tabledescriptor);
        
        
        admin.close();
        conn.close();
        
    }
    
    
    /**
     * dml -- 数据的增删改查
     */
    
    

}

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{
        // 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", "hdp-01:2181,hdp-02:2181,hdp-03:2181");
        
        conn = connectionfactory.createconnection(conf);
    }
    
    
    /**
     * 增
     * 改:put来覆盖
     * @throws exception 
     */
    @test
    public void testput() throws exception{
        
        // 获取一个操作指定表的table对象,进行dml操作
        table table = conn.gettable(tablename.valueof("user_info"));
        
        // 构造要插入的数据为一个put类型(一个put对象只能对应一个rowkey)的对象
        put put = new put(bytes.tobytes("001"));
        put.addcolumn(bytes.tobytes("base_info"), bytes.tobytes("username"), bytes.tobytes("张三"));
        put.addcolumn(bytes.tobytes("base_info"), bytes.tobytes("age"), bytes.tobytes("18"));
        put.addcolumn(bytes.tobytes("extra_info"), bytes.tobytes("addr"), bytes.tobytes("北京"));
        
        
        put put2 = new put(bytes.tobytes("002"));
        put2.addcolumn(bytes.tobytes("base_info"), bytes.tobytes("username"), bytes.tobytes("李四"));
        put2.addcolumn(bytes.tobytes("base_info"), bytes.tobytes("age"), bytes.tobytes("28"));
        put2.addcolumn(bytes.tobytes("extra_info"), bytes.tobytes("addr"), bytes.tobytes("上海"));
    
        
        arraylist<put> puts = new arraylist<>();
        puts.add(put);
        puts.add(put2);
        
        
        // 插进去
        table.put(puts);
        
        table.close();
        conn.close();
        
    }
    
    
    /**
     * 循环插入大量数据
     * @throws exception 
     */
    @test
    public void testmanyputs() throws exception{
        
        table table = conn.gettable(tablename.valueof("user_info"));
        arraylist<put> puts = new arraylist<>();
        
        for(int i=0;i<100000;i++){
            put put = new put(bytes.tobytes(""+i));
            put.addcolumn(bytes.tobytes("base_info"), bytes.tobytes("username"), bytes.tobytes("张三"+i));
            put.addcolumn(bytes.tobytes("base_info"), bytes.tobytes("age"), bytes.tobytes((18+i)+""));
            put.addcolumn(bytes.tobytes("extra_info"), bytes.tobytes("addr"), bytes.tobytes("北京"));
            
            puts.add(put);
        }
        
        table.put(puts);
        
    }
    
    /**
     * 删
     * @throws exception 
     */
    @test
    public void testdelete() throws exception{
        table table = conn.gettable(tablename.valueof("user_info"));
        
        // 构造一个对象封装要删除的数据信息
        delete delete1 = new delete(bytes.tobytes("001"));
        
        delete delete2 = new delete(bytes.tobytes("002"));
        delete2.addcolumn(bytes.tobytes("extra_info"), bytes.tobytes("addr"));
        
        arraylist<delete> dels = new arraylist<>();
        dels.add(delete1);
        dels.add(delete2);
        
        table.delete(dels);
        
        
        table.close();
        conn.close();
    }
    
    /**
     * 查
     * @throws exception 
     */
    @test
    public void testget() throws exception{
        
        table table = conn.gettable(tablename.valueof("user_info"));
        
        get get = new get("001".getbytes());
        
        result result = table.get(get);
        
        // 从结果中取用户指定的某个key的value
        byte[] value = result.getvalue("base_info".getbytes(), "age".getbytes());
        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();
        
    }
    
    
    /**
     * 按行键范围查询数据
     * @throws exception 
     */
    @test
    public void testscan() throws exception{
        
        table table = conn.gettable(tablename.valueof("user_info"));
        
        // 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）
        scan scan = new scan("10".getbytes(), "10000\001".getbytes());
        
        resultscanner scanner = table.getscanner(scan);
        
        iterator<result> iterator = scanner.iterator();
        
        while(iterator.hasnext()){
            
            result result = iterator.next();
            // 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()));
            }
            system.out.println("----------------------");
        }
    }

}