- 浏览: 49040 次
- 性别:
- 来自: 杭州
-
文章分类
最新评论
1、搭建环境
新建JAVA项目,添加的包有:
有关Hadoop的hadoop-core-0.20.204.0.jar
有关Hbase的hbase-0.90.4.jar、hbase-0.90.4-tests.jar以及Hbase资源包中lib目录下的所有jar包
2、主要程序
Java代码 [img]http://yangling00.iteye.com/images/icon_copy.gif" alt="复制代码[/img]
package com.wujintao.hbase.test;
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.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.SingleColumnValueFilter;
import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp;
import org.apache.hadoop.hbase.util.Bytes;
public class JinTaoTest {
public static Configuration configuration;
static {
configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.property.clientPort", "2181");
configuration.set("hbase.zookeeper.quorum", "192.168.1.100");
configuration.set("hbase.master", "192.168.1.100:600000");
}
public static void main(String[] args) {
// createTable("wujintao");
// insertData("wujintao");
// QueryAll("wujintao");
// QueryByCondition1("wujintao");
// QueryByCondition2("wujintao");
//QueryByCondition3("wujintao");
//deleteRow("wujintao","abcdef");
deleteByCondition("wujintao","abcdef");
}
/**
* 创建表
* @param tableName
*/
public static void createTable(String tableName) {
System.out.println("start create table ......");
try {
HBaseAdmin hBaseAdmin = new HBaseAdmin(configuration);
if (hBaseAdmin.tableExists(tableName)) {// 如果存在要创建的表,那么先删除,再创建
hBaseAdmin.disableTable(tableName);
hBaseAdmin.deleteTable(tableName);
System.out.println(tableName + " is exist,detele....");
}
HTableDescriptor tableDescriptor = new HTableDescriptor(tableName);
tableDescriptor.addFamily(new HColumnDescriptor("column1"));
tableDescriptor.addFamily(new HColumnDescriptor("column2"));
tableDescriptor.addFamily(new HColumnDescriptor("column3"));
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 ......");
HTablePool pool = new HTablePool(configuration, 1000);
HTable table = (HTable) pool.getTable(tableName);
Put put = new Put("112233bbbcccc".getBytes());// 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.add("column1".getBytes(), null, "aaa".getBytes());// 本行数据的第一列
put.add("column2".getBytes(), null, "bbb".getBytes());// 本行数据的第三列
put.add("column3".getBytes(), null, "ccc".getBytes());// 本行数据的第三列
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);
try {
ResultScanner 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();
}
}
/**
* 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);
try {
Get scan = new Get("abcdef".getBytes());// 根据rowkey查询
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);
Filter filter = new SingleColumnValueFilter(Bytes
.toBytes("column1"), null, CompareOp.EQUAL, Bytes
.toBytes("aaa")); // 当列column1的值为aaa时进行查询
Scan s = new Scan();
s.setFilter(filter);
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);
HTable table = (HTable) pool.getTable(tableName);
List filters = new ArrayList();
Filter filter1 = new SingleColumnValueFilter(Bytes
.toBytes("column1"), null, CompareOp.EQUAL, Bytes
.toBytes("aaa"));
filters.add(filter1);
Filter filter2 = new SingleColumnValueFilter(Bytes
.toBytes("column2"), null, CompareOp.EQUAL, Bytes
.toBytes("bbb"));
filters.add(filter2);
Filter filter3 = new SingleColumnValueFilter(Bytes
.toBytes("column3"), null, CompareOp.EQUAL, Bytes
.toBytes("ccc"));
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();
}
}
}
[code="java"]package com.wujintao.hbase.test;
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.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.SingleColumnValueFilter;
import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp;
import org.apache.hadoop.hbase.util.Bytes;
public class JinTaoTest {
public static Configuration configuration;
static {
configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.property.clientPort", "2181");
configuration.set("hbase.zookeeper.quorum", "192.168.1.100");
configuration.set("hbase.master", "192.168.1.100:600000");
}
public static void main(String[] args) {
// createTable("wujintao");
// insertData("wujintao");
// QueryAll("wujintao");
// QueryByCondition1("wujintao");
// QueryByCondition2("wujintao");
//QueryByCondition3("wujintao");
//deleteRow("wujintao","abcdef");
deleteByCondition("wujintao","abcdef");
}
/**
* 创建表
* @param tableName
*/
public static void createTable(String tableName) {
System.out.println("start create table ......");
try {
HBaseAdmin hBaseAdmin = new HBaseAdmin(configuration);
if (hBaseAdmin.tableExists(tableName)) {// 如果存在要创建的表,那么先删除,再创建
hBaseAdmin.disableTable(tableName);
hBaseAdmin.deleteTable(tableName);
System.out.println(tableName + " is exist,detele....");
}
HTableDescriptor tableDescriptor = new HTableDescriptor(tableName);
tableDescriptor.addFamily(new HColumnDescriptor("column1"));
tableDescriptor.addFamily(new HColumnDescriptor("column2"));
tableDescriptor.addFamily(new HColumnDescriptor("column3"));
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 ......");
HTablePool pool = new HTablePool(configuration, 1000);
HTable table = (HTable) pool.getTable(tableName);
Put put = new Put("112233bbbcccc".getBytes());// 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.add("column1".getBytes(), null, "aaa".getBytes());// 本行数据的第一列
put.add("column2".getBytes(), null, "bbb".getBytes());// 本行数据的第三列
put.add("column3".getBytes(), null, "ccc".getBytes());// 本行数据的第三列
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);
try {
ResultScanner 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();
}
}
/**
* 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);
try {
Get scan = new Get("abcdef".getBytes());// 根据rowkey查询
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);
Filter filter = new SingleColumnValueFilter(Bytes
.toBytes("column1"), null, CompareOp.EQUAL, Bytes
.toBytes("aaa")); // 当列column1的值为aaa时进行查询
Scan s = new Scan();
s.setFilter(filter);
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);
HTable table = (HTable) pool.getTable(tableName);
List filters = new ArrayList();
Filter filter1 = new SingleColumnValueFilter(Bytes
.toBytes("column1"), null, CompareOp.EQUAL, Bytes
.toBytes("aaa"));
filters.add(filter1);
Filter filter2 = new SingleColumnValueFilter(Bytes
.toBytes("column2"), null, CompareOp.EQUAL, Bytes
.toBytes("bbb"));
filters.add(filter2);
Filter filter3 = new SingleColumnValueFilter(Bytes
.toBytes("column3"), null, CompareOp.EQUAL, Bytes
.toBytes("ccc"));
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();
}
}
}
注意:可能大家没看到更新数据的操作,其实更新的操作跟添加完全一致,只不过是添加呢rowkey不存在,更新呢rowkey已经存在,并且timstamp相同的情况下,还有就是目前好像还没办法实现hbase数据的分页查询,不知道有没有人知道怎么做
HBase性能优化建议:
针对前面的代码,有很多不足之处,在此我就不修改上面的代码了,只是提出建议的地方,大家自己加上
1)配置
当你调用create方法时将会加载两个配置文件:hbase-default.xml and hbase-site.xml,利用的是当前的java类路径, 代码中configuration设置的这些配置将会覆盖hbase-default.xml和hbase-site.xml中相同的配置,如果两个配置文件都存在并且都设置好了相应参上面的属性下面的属性即可
2)关于建表
setMaxFileSize,指定最大的region size
增加family通过 addFamily方法
setTimeToLive:指定最大的TTL,单位是ms,过期数据会被自动删除。
setBloomFilter:指定是否使用BloomFilter,可提高随机查询效率。默认关闭
setMaxVersions:指定数据最大保存的版本个数。默认为3。
注意的是,一般我们不去setInMemory为true,默认是关闭的
3)关于入库
[size=x-small;]table.setAutoFlush(false); //数据入库之前先设置此项为false[/size]
注意:
关于这一项如果不希望大量数据在存储过程中丢失,建议设置为true,如果仅是在测试演练阶段,为了节省入库时间建议设置为false
4)关于获取表实例
HTable table = (HTable) pool.getTable(tableName);
不建议使用new HTable(configuration,tableName);的方式获取表
5)关于查询
Java代码 [img]http://yangling00.iteye.com/images/icon_copy.gif" alt="复制代码[/img]
public static void QueryAll(String tableName) {
HTablePool pool = new HTablePool(configuration, Integer.MAX_VALUE);
HTable table = null;
ResultScanner rs = null;
try {
Scan scan = new Scan();
table = (HTable) pool.getTable(tableName);
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()));
}
}
} catch (IOException e) {
e.printStackTrace();
}finally{
rs.close();// 最后还得关闭
pool.putTable(table); //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)
}
}
[code="java"]public static void QueryAll(String tableName) {
HTablePool pool = new HTablePool(configuration, Integer.MAX_VALUE);
HTable table = null;
ResultScanner rs = null;
try {
Scan scan = new Scan();
table = (HTable) pool.getTable(tableName);
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()));
}
}
} catch (IOException e) {
e.printStackTrace();
}finally{
rs.close();// 最后还得关闭
pool.putTable(table); //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)
}
}
所以,以上代码有缺陷的地方,感兴趣的同学可以针对优化建议作出相应修改
新建JAVA项目,添加的包有:
有关Hadoop的hadoop-core-0.20.204.0.jar
有关Hbase的hbase-0.90.4.jar、hbase-0.90.4-tests.jar以及Hbase资源包中lib目录下的所有jar包
2、主要程序
Java代码 [img]http://yangling00.iteye.com/images/icon_copy.gif" alt="复制代码[/img]
[code="java"]package com.wujintao.hbase.test;
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.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.SingleColumnValueFilter;
import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp;
import org.apache.hadoop.hbase.util.Bytes;
public class JinTaoTest {
public static Configuration configuration;
static {
configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.property.clientPort", "2181");
configuration.set("hbase.zookeeper.quorum", "192.168.1.100");
configuration.set("hbase.master", "192.168.1.100:600000");
}
public static void main(String[] args) {
// createTable("wujintao");
// insertData("wujintao");
// QueryAll("wujintao");
// QueryByCondition1("wujintao");
// QueryByCondition2("wujintao");
//QueryByCondition3("wujintao");
//deleteRow("wujintao","abcdef");
deleteByCondition("wujintao","abcdef");
}
/**
* 创建表
* @param tableName
*/
public static void createTable(String tableName) {
System.out.println("start create table ......");
try {
HBaseAdmin hBaseAdmin = new HBaseAdmin(configuration);
if (hBaseAdmin.tableExists(tableName)) {// 如果存在要创建的表,那么先删除,再创建
hBaseAdmin.disableTable(tableName);
hBaseAdmin.deleteTable(tableName);
System.out.println(tableName + " is exist,detele....");
}
HTableDescriptor tableDescriptor = new HTableDescriptor(tableName);
tableDescriptor.addFamily(new HColumnDescriptor("column1"));
tableDescriptor.addFamily(new HColumnDescriptor("column2"));
tableDescriptor.addFamily(new HColumnDescriptor("column3"));
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 ......");
HTablePool pool = new HTablePool(configuration, 1000);
HTable table = (HTable) pool.getTable(tableName);
Put put = new Put("112233bbbcccc".getBytes());// 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.add("column1".getBytes(), null, "aaa".getBytes());// 本行数据的第一列
put.add("column2".getBytes(), null, "bbb".getBytes());// 本行数据的第三列
put.add("column3".getBytes(), null, "ccc".getBytes());// 本行数据的第三列
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);
try {
ResultScanner 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();
}
}
/**
* 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);
try {
Get scan = new Get("abcdef".getBytes());// 根据rowkey查询
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);
Filter filter = new SingleColumnValueFilter(Bytes
.toBytes("column1"), null, CompareOp.EQUAL, Bytes
.toBytes("aaa")); // 当列column1的值为aaa时进行查询
Scan s = new Scan();
s.setFilter(filter);
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);
HTable table = (HTable) pool.getTable(tableName);
List filters = new ArrayList();
Filter filter1 = new SingleColumnValueFilter(Bytes
.toBytes("column1"), null, CompareOp.EQUAL, Bytes
.toBytes("aaa"));
filters.add(filter1);
Filter filter2 = new SingleColumnValueFilter(Bytes
.toBytes("column2"), null, CompareOp.EQUAL, Bytes
.toBytes("bbb"));
filters.add(filter2);
Filter filter3 = new SingleColumnValueFilter(Bytes
.toBytes("column3"), null, CompareOp.EQUAL, Bytes
.toBytes("ccc"));
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();
}
}
}
注意:可能大家没看到更新数据的操作,其实更新的操作跟添加完全一致,只不过是添加呢rowkey不存在,更新呢rowkey已经存在,并且timstamp相同的情况下,还有就是目前好像还没办法实现hbase数据的分页查询,不知道有没有人知道怎么做
HBase性能优化建议:
针对前面的代码,有很多不足之处,在此我就不修改上面的代码了,只是提出建议的地方,大家自己加上
1)配置
当你调用create方法时将会加载两个配置文件:hbase-default.xml and hbase-site.xml,利用的是当前的java类路径, 代码中configuration设置的这些配置将会覆盖hbase-default.xml和hbase-site.xml中相同的配置,如果两个配置文件都存在并且都设置好了相应参上面的属性下面的属性即可
2)关于建表
setMaxFileSize,指定最大的region size
增加family通过 addFamily方法
setTimeToLive:指定最大的TTL,单位是ms,过期数据会被自动删除。
setBloomFilter:指定是否使用BloomFilter,可提高随机查询效率。默认关闭
setMaxVersions:指定数据最大保存的版本个数。默认为3。
注意的是,一般我们不去setInMemory为true,默认是关闭的
3)关于入库
[size=x-small;]table.setAutoFlush(false); //数据入库之前先设置此项为false[/size]
注意:
关于这一项如果不希望大量数据在存储过程中丢失,建议设置为true,如果仅是在测试演练阶段,为了节省入库时间建议设置为false
4)关于获取表实例
HTable table = (HTable) pool.getTable(tableName);
不建议使用new HTable(configuration,tableName);的方式获取表
5)关于查询
Java代码 [img]http://yangling00.iteye.com/images/icon_copy.gif" alt="复制代码[/img]
[code="java"]public static void QueryAll(String tableName) {
HTablePool pool = new HTablePool(configuration, Integer.MAX_VALUE);
HTable table = null;
ResultScanner rs = null;
try {
Scan scan = new Scan();
table = (HTable) pool.getTable(tableName);
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()));
}
}
} catch (IOException e) {
e.printStackTrace();
}finally{
rs.close();// 最后还得关闭
pool.putTable(table); //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)
}
}
所以,以上代码有缺陷的地方,感兴趣的同学可以针对优化建议作出相应修改
相关推荐
Java 操作 Hbase 进行建表、删表以及对数据进行增删改查 一、Hbase 简介 Hbase 是一个开源的、分布式的、基于 column-family 的 NoSQL 数据库。它是基于 Hadoop 的,使用 HDFS 作为其存储层。Hbase 提供了高性能、...
下面将详细介绍如何在Eclipse中搭建HBase开发环境,并对HBase进行建表、增、删、改、查等操作。 一、环境准备 首先需要确定HBase和Hadoop的版本是否一致,为了避免版本不兼容问题。在本例中,我们使用的HBase版本...
表是HBase中的基本数据存储单元,每个表都属于某个命名空间。下面是关于表的一些操作: 1. **列出所有表**: 要查看所有表,可以运行`list`命令;如果只想查看特定命名空间下的表,使用`list_namespace_tables 'ns...
HTableDescriptor在HTableDescriptor中,建立了一个表结构,HTableDescriptor封装表格对象,对表格的增删改查操作主要通过它来完成。HTableDescriptor可以通过HTableDescriptor(TableName.valueOf(“表名”))方法...
建表、增删改查操作是基础,例如使用create命令创建表,put命令插入数据,alter命令修改表结构,disable和drop命令禁用和删除表,compact和major_compact命令处理Region的合并与压缩,balancer命令用于Region的均衡...
包括基本的数据操作,如建表、删表、统计(DML操作)以及数据的创建、更新、删除和查询(DDL操作)。最新版本为v1.0,由Shuyi-Lee于2013/6/21创建,旨在促进技术交流并对外公开。 1. 编写目的 本指南的目的是为...
- **DML**(Data Manipulation Language):用于数据的增删改查操作。 - **HBase命令行工具**:提供了丰富的命令来操作HBase表。 #### 五、Eclipse下开发HBase - **安装HBase插件**:使用Eclipse Marketplace...