HBase提供了Java Api的访问接口,掌握这个就跟Java应用使用RDBMS时需要JDBC一样重要,下面看一下Java api创建、删除表,及记录的增删改查操作:
package com;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
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.MasterNotRunningException;
import org.apache.hadoop.hbase.ZooKeeperConnectionException;
import org.apache.hadoop.hbase.client.Delete;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.HBaseAdmin;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.HTableInterface;
import org.apache.hadoop.hbase.client.HTablePool;
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.filter.Filter;
import org.apache.hadoop.hbase.filter.FilterList;
import org.apache.hadoop.hbase.filter.PrefixFilter;
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter;
import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp;
import org.apache.hadoop.hbase.util.Bytes;
/**
*
* @author zhang
*
*/
public class zhangTest
{
/**
* class Configuration 被HbaseConfiguration继承
*/
private static Configuration configuration;
static
{
/*
* HbaseConfiguration
关系:org.apache.hadoop.hbase.HBaseConfiguration 继承Configuration
作用:通过此类可以对HBase进行配置
*/
configuration = HBaseConfiguration.create();
//与hbase/conf/hbase-site.xml中hbase.zookeeper.property.clientPort配置的值相同
configuration.set("hbase.zookeeper.property.clientPort", "2181");
//与hbase/conf/hbase-site.xml中hbase.zookeeper.quorum配置的值相同
configuration.set("hbase.zookeeper.quorum", "192.168.0.145");
configuration.set("hbase.master", "192.168.0.145:600000");
}
/**
* 创建表
* @param tableName
*/
public static void createTable(String tableName)
{
System.out.println("start create table ......");
try
{
/*
* .HBaseAdmin
关系:org.apache.hadoop.hbase.client.HBaseAdmin
作用:提供一个接口来管理HBase数据库中的表信息。它提供创建表、删除表等方法。
*/
HBaseAdmin hBaseAdmin = new HBaseAdmin(configuration);
// 如果存在要创建的表,那么先删除,再创建
if (hBaseAdmin.tableExists(tableName))
{
hBaseAdmin.disableTable(tableName);
hBaseAdmin.deleteTable(tableName);
System.out.println(tableName + " is exist,detele....");
}
/*
* HTableDescriptor
关系:org.apache.hadoop.hbase.client.HTableDescriptor
作用:包含了表的名字及其对应列族。 提供的方法有
void addFamily(HColumnDescriptor) 添加一个列族
HColumnDescriptor removeFamily(byte[] column) 移除一个列族
byte[] getName() 获取表的名字
byte[] getValue(byte[] key) 获取属性的值
void setValue(String key,String value) 设置属性的值
*/
//获取表的信息
HTableDescriptor tableDescriptor = new HTableDescriptor(tableName);
/*HColumnDescriptor
关系:org.apache.hadoop.hbase.client.HColumnDescriptor
作用:维护关于列的信息。提供的方法有
byte[] getName() 获取列族的名字
byte[] getValue() 获取对应的属性的值
void setValue(String key,String value) 设置对应属性的值
*/
//添加列
//tableDescriptor.addFamily(new HColumnDescriptor("id"));
//tableDescriptor.addFamily(new HColumnDescriptor("username"));
//tableDescriptor.addFamily(new HColumnDescriptor("hostelid"));
tableDescriptor.addFamily(new HColumnDescriptor("hostelname"));
tableDescriptor.addFamily(new HColumnDescriptor("time"));
tableDescriptor.addFamily(new HColumnDescriptor("roomid"));
tableDescriptor.addFamily(new HColumnDescriptor("address"));
tableDescriptor.addFamily(new HColumnDescriptor("userid"));
hBaseAdmin.createTable(tableDescriptor);
} catch (MasterNotRunningException e) {
e.printStackTrace();
} catch (ZooKeeperConnectionException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
System.out.println("end create table ......");
}
/**
* 插入数据
* @param tableName
*/
public static void insertData(String tableName)
{
System.out.println("start insert data ......");
Put put = null;
HTablePool pool = new HTablePool(configuration, 1000);
/*
* HTable
关系:org.apache.hadoop.hbase.client.HTable
作用:用户与HBase表进行通信。此方法对于更新操作来说是非线程安全的,
如果启动多个线程尝试与单个HTable实例进行通信,那么写缓冲器可能会崩溃。
*/
//zj
HTableInterface table = pool.getTable(tableName);
// 一个PUT代表一行数据,再NEW一个PUT表示第二行数据,每行一个唯一的ROWKEY,
//此处rowkey为put构造方法中传入的值
/*
* Put
关系:org.apache.hadoop.hbase.client.Put
作用:用于对单个行执行添加操作
*/
for(int i=1;i<100;i++)
{
//id_username_hostelid
put = new Put( ("id"+i+"_"+"username"+i+"_"+"hostelid"+i).getBytes());
//zj
//Put put = new Put("112233bbbcccc".getBytes());
// put.add("id".getBytes(), null, (""+i).getBytes());// 本行数据的第一列
// put.add("username".getBytes(), null, ("qwe"+i).getBytes());// 本行数据的第二列
// put.add("hostelid".getBytes(), null, (""+i).getBytes());// 本行数据的第三列
put.add("hostelname".getBytes(), null, ("qwea"+i).getBytes());
put.add("time".getBytes(), null, "2013-01-25 13:12:16".getBytes());
put.add("roomid".getBytes(), null, ("10"+i).getBytes());
put.add("address".getBytes(), null, ("qweaa"+i).getBytes());
put.add("userid".getBytes(), null, ("14587965453512"+i).getBytes());
try {
table.put(put);
} catch (IOException e) {
e.printStackTrace();
}
}
System.out.println("end insert data ......");
}
/**
* 删除一张表
* @param tableName
*/
public static void dropTable(String tableName) {
try {
HBaseAdmin admin = new HBaseAdmin(configuration);
admin.disableTable(tableName);
admin.deleteTable(tableName);
} catch (MasterNotRunningException e) {
e.printStackTrace();
} catch (ZooKeeperConnectionException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 根据 rowkey删除一条记录
* @param tablename
* @param rowkey
*/
public static void deleteRow(String tablename, String rowkey) {
try {
HTable table = new HTable(configuration, tablename);
List list = new ArrayList();
Delete d1 = new Delete(rowkey.getBytes());
list.add(d1);
table.delete(list);
System.out.println("删除行成功!");
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 组合条件删除
* @param tablename
* @param rowkey
*/
public static void deleteByCondition(String tablename, String rowkey)
{
//目前还没有发现有效的API能够实现 根据非rowkey的条件删除 这个功能,
//还有清空表全部数据的API操作
}
/**
* 查询所有数据
* @param tableName
*/
public static void QueryAll(String tableName) {
HTablePool pool = new HTablePool(configuration, 1000);
//HTable table = (HTable) pool.getTable(tableName);
//zj
HTableInterface table = null;
//zj
ResultScanner rs = null;
try
{
//ResultScanner rs = table.getScanner(new Scan());
//zj
table = pool.getTable(tableName);
rs = table.getScanner(new Scan());
for (Result r : rs)
{
System.out.println("获得到rowkey:" + new String(r.getRow()));
for (KeyValue keyValue : r.raw())
{
System.out.println("列:" + new String(keyValue.getFamily())
+ "====值:" + new String(keyValue.getValue()));
}
}
}
catch (IOException e)
{
e.printStackTrace();
}
finally
{
rs.close();// 最后还得关闭
//实际应用过程中,pool获取实例的方式应该抽取为单例模式的,
//不应在每个方法都重新获取一次(单例明白?
//就是抽取到专门获取pool的逻辑类中,
//具体逻辑为如果pool存在着直接使用,如果不存在则new)
try
{
pool.putTable(table);
} catch (IOException e)
{
e.printStackTrace();
}
}
}
/**
* 单条件查询,根据rowkey查询唯一一条记录
* @param tableName
*/
public static void QueryByCondition1(String tableName) {
HTablePool pool = new HTablePool(configuration, 1000);
//HTable table = (HTable) pool.getTable(tableName);
//zj
HTableInterface table = pool.getTable(tableName);
try {
/*
* Get
关系:org.apache.hadoop.hbase.client.Get
作用:用于获取单个行的相关信息
*/
Get scan = new Get("abcdef".getBytes());// 根据rowkey查询
//zj
//Get scan = new Get("112233bbbcccc".getBytes());// 根据rowkey查询
/*
* Result
关系:org.apache.hadoop.hbase.client.Result
作用:存储Get或Scan操作后获取的单行值。
*/
Result r = table.get(scan);
System.out.println("获得到rowkey:" + new String(r.getRow()));
for (KeyValue keyValue : r.raw())
{
System.out.println("列:" + new String(keyValue.getFamily())
+ "====值:" + new String(keyValue.getValue()));
}
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 单条件按查询,查询多条记录
* @param tableName
*/
public static void QueryByCondition2(String tableName) {
try {
HTablePool pool = new HTablePool(configuration, 1000);
// HTable table = (HTable) pool.getTable(tableName);
//zj
HTableInterface table = pool.getTable(tableName);
// 当列column1的值为aaa时进行查询
Filter filter = new SingleColumnValueFilter(Bytes
.toBytes("id"), null, CompareOp.EQUAL, Bytes
.toBytes("1"));
Scan s = new Scan();
s.setFilter(filter);
/*
* ResultScanner
关系:Interface
作用:客户端获取值的接口。
*/
ResultScanner rs = table.getScanner(s);
for (Result r : rs)
{
System.out.println("获得到rowkey:" + new String(r.getRow()));
for (KeyValue keyValue : r.raw())
{
System.out.println("列:" + new String(keyValue.getFamily())
+ "====值:" + new String(keyValue.getValue()));
}
}
}
catch (Exception e)
{
e.printStackTrace();
}
}
/**
* 组合条件查询
* @param tableName
*/
public static void QueryByCondition3(String tableName)
{
try
{
HTablePool pool = new HTablePool(configuration, 1000);
//zj
HTableInterface table = pool.getTable(tableName);
List<Filter> filters = new ArrayList<Filter>();
Filter filter1 = new SingleColumnValueFilter(Bytes
.toBytes("id"), null, CompareOp.EQUAL, Bytes
.toBytes("99"));
filters.add(filter1);
Filter filter2 = new SingleColumnValueFilter(Bytes
.toBytes("address"), null, CompareOp.EQUAL, Bytes
.toBytes("qweaa99"));
filters.add(filter2);
Filter filter3 = new SingleColumnValueFilter(Bytes
.toBytes("username"), null, CompareOp.EQUAL, Bytes
.toBytes("qwe99"));
filters.add(filter3);
FilterList filterList1 = new FilterList(filters);
Scan scan = new Scan();
scan.setFilter(filterList1);
ResultScanner rs = table.getScanner(scan);
for (Result r : rs)
{
System.out.println("获得到rowkey:" + new String(r.getRow()));
for (KeyValue keyValue : r.raw()) {
System.out.println("列:" + new String(keyValue.getFamily())
+ "====值:" + new String(keyValue.getValue()));
}
}
rs.close();
} catch (Exception e) {
e.printStackTrace();
}
}
//------------------------条件 查询-------------
public static void selectFilter(String tablename,List<String> arr) throws IOException
{
HTable table=new HTable(configuration,tablename);
Scan scan = new Scan();//实例化一个遍历器
FilterList filterList = new FilterList(); //过滤器List
for(String v:arr)
{ //下标0为列簇,1为列名,2为条件
String [] wheres=v.split("_");
filterList.addFilter( new SingleColumnValueFilter(//过滤器
wheres[0].getBytes(),
wheres[1].getBytes(),
CompareOp.EQUAL,//各个条件之间是" and "的关系
wheres[2].getBytes())
);
}
scan.setFilter(filterList);
ResultScanner ResultScannerFilterList = table.getScanner(scan);
for(Result rs=ResultScannerFilterList.next(); rs!=null; rs=ResultScannerFilterList.next())
{
for(KeyValue kv:rs.list())
{
System.out.println("--------------------"+new String(kv.getRow())+"----------------------------");
System.out.println("Column Family: "+new String(kv.getFamily()));
System.out.println("Column :"+new String(kv.getQualifier())+"\t");
System.out.println("value : "+new String(kv.getValue()));
}
}
}
//hbase通过row key 的前缀查询记录
public static void scaneByPrefixFilter(String tablename, String rowPrifix)
{
try {
HTable table = new HTable(configuration, tablename);
Scan s = new Scan();
s.setFilter(new PrefixFilter(rowPrifix.getBytes()));
ResultScanner rs = table.getScanner(s);
for (Result r : rs)
{
KeyValue[] kv = r.raw();
for (int i = 0; i < kv.length; i++)
{
System.out.print(new String(kv[i].getRow()) + " ");
System.out.print(new String(kv[i].getFamily()) + ":");
System.out.print(new String(kv[i].getQualifier()) + " ");
System.out.print(kv[i].getTimestamp() + " ");
System.out.println(new String(kv[i].getValue()));
}
}
}
catch (IOException e)
{
e.printStackTrace();
}
}
/**
*主方法
*/
public static void main(String[] args) {
// createTable("wujintao");
//createTable("usera");
// insertData("wujintao");
//insertData("usera");
// QueryAll("wujintao");
//QueryAll("usera");
// QueryByCondition1("wujintao");
// QueryByCondition2("wujintao");
// QueryByCondition2("user");
//QueryByCondition3("wujintao");
//QueryByCondition3("user");
// deleteRow("wujintao","abcdef");
// deleteByCondition("wujintao","abcdef");
System.out.println("------------------------条件 查询----------------------------------");
List<String> arr=new ArrayList<String>();
arr.add("hostelname_qwe99_qwe99");
//arr.add("id98_username98_hostelid98");
try
{
selectFilter("user",arr);
} catch (IOException e)
{
// TODO Auto-generated catch block
e.printStackTrace();
}
//hbase通过row key 的前缀查询记录
scaneByPrefixFilter("usera","id98_username98_hostelid98");
}
}
>>>>>>>>>>>>>>>原创文章,小部分来自网络整理(如果有什么问题,请您及时联系我naxiaohuo@163.com),转载请标明出处。