hbase的基本操作

1. shell操作

常见命令：

[root@hadoop01 ~]# hbase shell      #进入HBASE客户端
hbase(main):001:0> help “dml”    #获取一组命令的提示hbase(main):001:0> help "put" 获取一个单独命令的提示帮助
hbase(main):001:0> exit    #退出客户端

 #查看hbase中的所有表
hbase(main):001:0>list       

创建表：
语法：create ‘表名’,’列簇1’,’ 列簇2’,’ 列簇3’….

# 例1:创建一张表，名称为user,该表有info和data两个列簇
hbase(main):001:0>create 'user' ,'info','data'
hbase(main):001:0>create 'user' ,{NAME=>'info'},{NAME=>'data'}

#例2:创建一张表叫做 user_info，包含两个列簇 base_info 和 extra_info，并且分别指定这两个列簇 的数据的版本数为 3 和 1
hbase(main):001:0>create 'user_info',{NAME=>'base_info',VERSIONS=>3},{NAME=>'extra_info',VERSIONS=>1}

查看表的详细信息

#desc 或者 describe
hbase(main):001:0>desc 'user_info'
hbase(main):001:0>describe 'user_info'

插入数据
#put table ,rowkey, 列簇:列 ,value
hbase(main):001:0>put ‘user’,’rowkey01′,’info:age’,’18’

查询数据
#get

#获取 user 表中 row key 为 rk0001 的所有信息
hbase(main):001:0>get 'user' ,'rk0001'

#获取 user 表中 row key 为 rk0001，info 列簇的所有信息
hbase(main):001:0>get 'user','rk0001','info'

#获取 user 表中 row key 为 rk0001，info 列簇的 name、age 列标示符的信息
hbase(main):001:0>get ‘user’,’rk0001′,’info:name’,’info:age’

#获取 user 表中 row key 为 rk0001，列簇为 info，版本号最新 5 个的信息
hbase(main):001:0>create 'USER','rk0001',{COLUMN=>'info',VERSIONS=>5}

#获取 user 表中 row key 为 rk0001，cell 的值为 zhangsan 的信息
hbase(main):001:0>get 'user', 'rk0001', {FILTER => "ValueFilter(=, 'binary:zhangsan')"}

#获取 user 表中 row key 为 rk0001，列标示符中含有 a 的信息
hbase(main):001:0>get 'user','rk0001',{FILTER=>"(QualifierFilter(=,'substring:a'))"}

查询数据
#scan

查询 user_info 表中的所有信息
hbase(main):001:0>scan 'user_info'

#查询 user_info 表中的指定列簇的所有信息
hbase(main):001:0>scan 'user_info',{COLUMNS=>'base_info'}
hbase(main):001:0>scan 'user_info',{COLUMNS=>'base_info:name'}
hbase(main):001:0>scan 'user_info',{COLUMNS=>['base_info','extra_info']}

#查询 user_info 表中的指定列簇为 base_info 的所有版本信息
hbase(main):001:0>scan 'user_info',{COLUMNS=>'base_info',VERSIONS=>5}

#查询 user 表中列簇为 info 和 data 且列标示符中含有 a 字符的信息
hbase(main):001:0>scan 'user', {COLUMNS => ['info', 'data'], FILTER => "(QualifierFilter(=,'substring:a'))"}

#rowkey的范围查询
hbase(main):001:0>scan 'user_info', {COLUMNS => 'base_info', STARTROW => 'baiyc_20150716_0003', ENDROW =>
'baiyc_20150716_0006'}

#查询 user 表中 rowkey 以 rk 字符开头的
hbase(main):001:0>scan 'user',{FILTER=>"PrefixFilter('rk')"}

#查询 user_info 表中指定时间戳范围的数据
hbase(main):001:0>scan 'user_info',{TIMERANGE=>[1540882871681,1540882888540]}

删除数据
#delete

#删除记录
hbase(main):001:0>delete 'user', 'rk0001' 
#删除字段
hbase(main):001:0>delete 'user','rk0001','info:name'
#删除 user 表 rowkey 为 rk0001，列标示符为 info:name，timestamp 为 1392383705316 的数据
hbase(main):001:0>delete 'user','rk0001','info:name',1392383705316

修改表结构
#alter

#添加两个列簇 f2 和 f3
hbase(main):001:0>alter 'user_info',NAME=>'f2'
hbase(main):001:0>alter 'user_info',NAME=>'f2'

#删除一个列簇 f1
hbase(main):001:0>alter 'user_info',NAME=>'f1',METHOD=>'delete'

#将 user_info 表的 base_info 列簇版本号改为 5
hbase(main):001:0>alter 'user_info',NAME=>'base_info',VERSIONS=>5

清空表
#truncate

#清空 user 表中的数据
hbase(main):001:0>truncate 'user_info'

停用表/启用表

#disable 和 enable
hbase(main):001:0>disable 'user'
hbase(main):001:0>enable 'user'

删除表
#drop

#删除一张表
hbase(main):001:0>disable 'user   #需要先停用这张表，在删除
hbase(main):001:0>drop 'user'

2. API操作（javaAPI）

这里实现基本的增删改查：
pom依赖

<dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>1.2.6</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>1.2.6</version>
        </dependency>

代码实现：

package com.zy.hbase;
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.KeyValue;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;
import org.junit.Test;
import java.io.IOException;
public class HbaseTest {
// 声明静态配置
static Configuration conf = null;
private static final String ZK_CONNECT_STR = "hadoop01:2181,hadoop02:2181,hadoop03:2181";
static {
conf = HBaseConfiguration.create();
conf.set("hbase.zookeeper.quorum", ZK_CONNECT_STR);
}
/**
* 1.创建表
*/
@Test
public void creatTable() {
//表名
String tableName = "stu_info";
//列簇名
String[] cf = {"base_info", "extra_info"};
try {
//创建HBaseAdmin对象
HBaseAdmin admin = new HBaseAdmin(conf);
//创建表的描述信息对象
HTableDescriptor des = new HTableDescriptor(tableName);
for (int i = 0; i < cf.length; i++) {
des.addFamily(new HColumnDescriptor(cf[i]));
}
if (admin.tableExists(tableName)) {
System.out.println("table Exists!");
System.exit(0);
} else {
admin.createTable(des);
System.out.println("create table Success!");
}
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 为表添加数据
*/
@Test
public void addData() {
//表名
String tableName = "user_info";
//行键
String rowkey = "rk0011";
//列簇
String cf = "base_info";
Put put = new Put(rowkey.getBytes());
try {
//创建操作hbase表的对象
HTable table = new HTable(conf, tableName.getBytes());
//列簇  列  值
put.addColumn(cf.getBytes(), "name".getBytes(), "zs".getBytes());
table.put(put);
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 根据 rwokey 查询
*/
@Test
public void getResult() {
//表名
String tableName = "user_info";
//行键
String rowKey = "rk0001";
Get get = new Get(Bytes.toBytes(rowKey));
try {
//创建操作hbase表的对象
HTable table = new HTable(conf, tableName.getBytes());
Result result = table.get(get);
for (KeyValue kv : result.list()) {
System.out.println("rowkey:" + kv.getRow());  //行键
System.out.println("family" + kv.getFamily()); //列簇
System.out.println("qualifier" + kv.getQualifier());  //列
System.out.println("value:" + new String(kv.getValue())); //值
System.out.println("Timestamp" + kv.getTimestamp());  //时间戳
}
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 遍历查询 hbase 表
*/
@Test
public void getResultScann() {
String tableName = "user_info";
Scan scan = new Scan();
try {
HTable table = new HTable(conf, tableName.getBytes());
ResultScanner scanner = table.getScanner(scan);
for (Result rs : scanner) {
for (KeyValue kv : rs.list()) {
System.out.println("rowkey:" + kv.getRow());  //行键
System.out.println("family" + kv.getFamily()); //列簇
System.out.println("qualifier" + kv.getQualifier());  //列
System.out.println("value:" + new String(kv.getValue())); //值
System.out.println("Timestamp" + kv.getTimestamp());  //时间戳
}
}
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 遍历查询 hbase 表  指定rowkey的查询范围
*/
@Test
public void getResultScannRange() {
String tableName = "user_info";
Scan scan = new Scan();
scan.setStartRow("rk001".getBytes());
scan.setStopRow("rk005".getBytes());
try {
HTable table = new HTable(conf, tableName.getBytes());
ResultScanner scanner = table.getScanner(scan);
for (Result rs : scanner) {
for (KeyValue kv : rs.list()) {
System.out.println("rowkey:" + kv.getRow());  //行键
System.out.println("family" + kv.getFamily()); //列簇
System.out.println("qualifier" + kv.getQualifier());  //列
System.out.println("value:" + new String(kv.getValue())); //值
System.out.println("Timestamp" + kv.getTimestamp());  //时间戳
}
}
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 查询表中的某一列
*/
@Test
public void getResultByColumn() {
String tableName = "user_info";  //表
String rowkey = "rk0001";   //行键
String cf = "base_info";    //列簇
String column = "name";     //列
try {
HTable table = new HTable(conf, tableName.getBytes());
Get get = new Get(rowkey.getBytes());
get.addColumn(cf.getBytes(), column.getBytes());
Result result = table.get(get);
for (KeyValue kv : result.list()) {
System.out.println("rowkey:" + kv.getRow());  //行键
System.out.println("family" + kv.getFamily()); //列簇
System.out.println("qualifier" + kv.getQualifier());  //列
System.out.println("value:" + new String(kv.getValue())); //值
System.out.println("Timestamp" + kv.getTimestamp());  //时间戳
}
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 更新表中的某一列,因为在hbase中可以以时间戳定义多个版本的值
* 所有，更新操作就是put操作
*/
@Test
public void updateTable() {
String tableName = "user_info";  //表
String rowkey = "rk0001";   //行键
String cf = "base_info";    //列簇
String column = "name";     //列
String value = "ll";       //值
try {
HTable table = new HTable(conf, Bytes.toBytes(tableName));
Put put = new Put(rowkey.getBytes());
put.addColumn(cf.getBytes(), column.getBytes(), value.getBytes());
table.put(put);
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 查询某列数据的多个版本
*/
@Test
public void getResultByVersion() {
String tableName = "user_info";  //表
String rowkey = "rk0001";   //行键
String cf = "base_info";    //列簇
String column = "name";     //列
int version = 5;          //hbase的列的版本
try {
HTable table = new HTable(conf, Bytes.toBytes(tableName));
Get get = new Get(rowkey.getBytes());
get.addColumn(cf.getBytes(), column.getBytes());
get.setMaxVersions(version);
Result result = table.get(get);
if (result.list() != null) {
for (KeyValue kv : result.list()) {
System.out.println("rowkey:" + kv.getRow());  //行键
System.out.println("family" + kv.getFamily()); //列簇
System.out.println("qualifier" + kv.getQualifier());  //列
System.out.println("value:" + new String(kv.getValue())); //值
System.out.println("Timestamp" + kv.getTimestamp());  //时间戳
}
}
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 删除指定的列
*/
@Test
public void deleteColumn() {
String tableName = "user_info";  //表
String rowkey = "rk0001";   //行键
String cf = "base_info";    //列簇
String column = "name";     //列
try {
HTable table = new HTable(conf, Bytes.toBytes(tableName));
Delete delete = new Delete(rowkey.getBytes());
delete.addColumn(cf.getBytes(), column.getBytes());
table.delete(delete);
System.out.println(cf + ":" + column + "is deleted!");
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 删除指定rowKey的所有列
*/
@Test
public void deleteAllColumn() {
String tableName = "user_info";  //表
String rowkey = "rk0001";   //行键
try {
HTable table = new HTable(conf, Bytes.toBytes(tableName));
Delete deleteAll = new Delete(rowkey.getBytes());
table.delete(deleteAll);
System.out.println("all columns are deleted!");
} catch (IOException e) {
e.printStackTrace();
}
}
/*
* 删除表
*/
@Test
public void deleteTable(){
String tableName = "user_info";  //表
try {
HBaseAdmin admin = new HBaseAdmin(conf);
admin.disableTable(tableName.getBytes());
admin.deleteTable(tableName.getBytes());
System.out.println(tableName + "is deleted!");
} catch (IOException e) {
e.printStackTrace();
}
}
}

详细的源代码：http://down.51cto.com/data/2457979