hbase java 建表_hbase java API跟新数据，创建表

package hbaseCURD;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.hbase.HBaseConfiguration;

import org.apache.hadoop.hbase.client.Get;

import org.apache.hadoop.hbase.client.HTable;

import org.apache.hadoop.hbase.client.Put;

import org.apache.hadoop.hbase.client.Result;

import org.apache.hadoop.hbase.util.Bytes;

public class test {

public static void main(String[] args) throws IOException {

TableManager tm = new TableManager();

tm.getConf();

// tm.createTable("testtable","cf1","cf2");

HTable mytable=tm.getTableObj("testtable");

// Put put = new Put(Bytes.toBytes("row1"));

// put.add(Bytes.toBytes("cf1"), Bytes.toBytes("c1"), Bytes.toBytes("cf1ddfddvalue"));

// put.add(Bytes.toBytes("cf2"), Bytes.toBytes("c2"), Bytes.toBytes("cf2v3333alue"));

// mytable.put(put);

//查询

Get get = new Get(Bytes.toBytes("row1"));

Result result = mytable.get(get);

System.out.println("get result:" + Bytes.toString(result.getValue(Bytes.toBytes("cf1"), Bytes.toBytes("c1"))));

//Result[] result = table.get(List);//查询指定Rowkey的多条记录

}

}

package hbaseCURD;

import java.io.IOException;

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.MasterNotRunningException;

import org.apache.hadoop.hbase.ZooKeeperConnectionException;

import org.apache.hadoop.hbase.client.HBaseAdmin;

import org.apache.hadoop.hbase.client.HTable;

import org.apache.hadoop.hbase.util.Bytes;

public class TableManager {

private static Configuration conf;

// 设置集群的配置信息

public void getConf() {

conf = HBaseConfiguration.create();

conf.set("hbase.zookeeper.quorum", "master,slave1,slave2");

conf.set("hbase.master", "master:60000");

}

// 获取表对象

public HTable getTableObj(String tablename) {

HTable mytable = null;

try {

mytable = new HTable(conf, tablename);

} catch (IOException e) {

e.printStackTrace();

}

return mytable;

}

//

public void createTable(String tableName, String... args) throws MasterNotRunningException, ZooKeeperConnectionException {

// args数组保存的是列族

HBaseAdmin admin = new HBaseAdmin(conf);

// 创建表

HTableDescriptor htd = new HTableDescriptor(tableName);

for (String st : args) {

htd.addFamily(new HColumnDescriptor(st));

}

try {

admin.createTable(htd);

} catch (IOException e) {

e.printStackTrace();

}

}

public void deleteTable(String tableName) {

try {

HBaseAdmin admin = new HBaseAdmin(conf);

// 创建表

HTableDescriptor htd = new HTableDescriptor(tableName);

admin.disableTable(Bytes.toBytes(tableName));

admin.deleteTable(Bytes.toBytes(tableName));

} catch (IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

}

public void modifyTable(String tableName,String newcoloumf) {

try {

HBaseAdmin admin = new HBaseAdmin(conf);

// 创建表

HTableDescriptor htd = new HTableDescriptor(tableName);

admin.disableTable(Bytes.toBytes(tableName));

admin.modifyColumn(tableName, new HColumnDescriptor("cf1"));

admin.enableTable(tableName);

} catch (IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

}

}

Hbase的访问方式

1、Native Java API：最常规和高效的访问方式；

2、HBase Shell：HBase的命令行工具，最简单的接口，适合HBase管理使用；

3、Thrift Gateway：利用Thrift序列化技术，支持C++，PHP，Python等多种语言，适合其他异构系统在线访问HBase表数据；

4、REST Gateway：支持REST 风格的Http API访问HBase, 解除了语言限制；

5、MapReduce：直接使用MapReduce作业处理Hbase数据；

6、使用Pig/hive处理Hbase数据。

常用Java API的用法：

1、加载配置

[java] view plaincopy在CODE上查看代码片派生到我的代码片

Configuration config = HBaseConfiguration.create();

//可以自定义配置，也可以从自定义配置文件中读取

/*config.set(“hbase.zookeeper.property.clientPort”, “4181”);

config.set(“hbase.zookeeper.quorum”, “hadoop.datanode5.com,hadoop.datanode2.com,hadoop.datanode3.com”);

config.set(“hbase.master”, “hadoop.datanode3.com\:600000”);*/

2、表的创建、表信息修改、表删除

[java] view plaincopy在CODE上查看代码片派生到我的代码片

HBaseAdmin admin = new HBaseAdmin(config);

//创建表

HTableDescriptor htd = new HTableDescriptor(tableName);

htd.addFamily(new HColumnDescriptor(“cf1”));

htd.addFamily(new HColumnDescriptor(“cf2”));

admin.createTable(htd);

//修改表信息

admin.disableTable(tableName);

// modifying existing ColumnFamily

admin.modifyColumn(tableName, new HColumnDescriptor(“cf1”));

admin.enableTable(tableName);

//删除表

admin.disableTable(Bytes.toBytes(tableName));

admin.deleteTable(Bytes.toBytes(tableName));

3、添加记录

[java] view plaincopy在CODE上查看代码片派生到我的代码片

/** 在多次使用时，建议用HTablePool

HTable table = new HTable(config, tableName);

=>

HTablePool pool = new HTablePool(config, 1000);

HTableInterface table = pool.getTable(tableName);*/

HTable table = new HTable(config, tableName);

/**

* 在插入操作时，默认不适用任何缓存

* 可自定义使用缓存，以及缓存大小

* 每个任务最后需要手工调用 flushCommits();

*/

/*table.setAutoFlush(false);

table.setWriteBufferSize(1024);*/

Put put1 = new Put(Bytes.toBytes(rowKey));

if (ts == 0) {

put1.add(Bytes.toBytes(family), Bytes.toBytes(qualifier), Bytes.toBytes(value));

} else {

//自定义版本时，从自定义的版本号，类型为long

put1.add(Bytes.toBytes(family), Bytes.toBytes(qualifier), ts,Bytes.toBytes(value));

}

table.put(put1);

//table.flushCommits();

4、查询，根据Rowkey查询

[java] view plaincopy在CODE上查看代码片派生到我的代码片

Get get1 = new Get(Bytes.toBytes(rowKey));

Result result = table.get(get1);

System.out.println(“get result:” + Bytes.toString(result.getValue(Bytes.toBytes(family), Bytes.toBytes(qualifier))));

Result[] result = table.get(List);//查询指定Rowkey的多条记录

5、查询，指定条件和rowkey区间查询

[java] view plaincopy在CODE上查看代码片派生到我的代码片

Scan scan = new Scan();

//默认缓存大小为1，设置成一个合理的值，可以减少scan过程中next()的时间开销，代价是客户端的内存

scan.setCaching(500);

scan.setCacheBlocks(false);

//根据startRowKey、endRowKey查询

//Scan scan = new Scan(Bytes.toBytes(“startRowKey”), Bytes.toBytes(“endRowKey”));

//rowKey之外的过滤条件，在List中可以add;

/**List filters = new ArrayList();

Filter filter = new SingleColumnValueFilter(“familyName”.getBytes(),

“qualifierName”.getBytes(),

CompareOp.EQUAL,

Bytes.toBytes(“value”));

filters.add(filter);

scan.setFilter(new FilterList(filters));*/

ResultScanner scanner = table.getScanner(scan);

System.out.println(“scan result list:”);

for (Result result : scanner) {

System.out.println(Bytes.toString(result.getRow()));

System.out.println(Bytes.toString(result.getValue(Bytes.toBytes(“data”), Bytes.toBytes(“data1”))));

System.out.println(Bytes.toString(result.getValue(Bytes.toBytes(“data”), Bytes.toBytes(“data2”))));

}

scanner.close();

参考：

1、http://www.taobaotest.com/blogs/1605