1.开发环境准备及搭建
（1）构建maven工程
maven代码如下：
1) 相关依赖
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<artifactId>shadowsync</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.3.1</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>1.3.1</version>
</dependency>
</dependencies>
</project>2）添加打包和编译插件
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>1.6</source>
<target>1.6</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>3.0.0</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<transformers>
<transformer
implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
<mainClass>需要打包的类名</mainClass>
</transformer>
<transformer
implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
<mainClass>需要打包的类名</mainClass>
</transformer>
<transformer
implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
<mainClass>需要打包的类名</mainClass>
</transformer>
</transformers>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>（2） 配置windows的hosts文件，地址：C:\Windows\System32\drivers\etc（这一步非常重要，hbase对IP很敏感，否则会一直处于连接状态）
一直连接不上会出现如下所示状态：
DEBUG hconnection-0xb7dd107-metaLookup-shared--pool2-t32 org.apache.hadoop.hbase.ipc.RpcClientImpl - Use SIMPLE authentication for service ClientService, sasl=false
DEBUG hconnection-0xb7dd107-metaLookup-shared--pool2-t32 org.apache.hadoop.hbase.ipc.RpcClientImpl - Not trying to connect to bigdata4.jiaxun.com/10.0.5.14:16020 this server is in the failed servers list
DEBUG main-SendThread(10.9.1.43:2181) org.apache.zookeeper.ClientCnxn - Reading reply sessionid:0x370878cbdc400f1, packet:: clientPath:null serverPath:null finished:false header:: 795,4 replyHeader:: 795,536871130376,0 request:: '/hbase-unsecure/meta-region-server,F response:: #ffffffff0001a726567696f6e7365727665723a31363032306affffff8344ffffffca6cffffffd4ffffffaf3c50425546a1fa1362696764617461342e6a696178756e2e636f6d10ffffff947d18ffffffdaffffff99ffffffeeffffff99ffffff882e100183,s{532575944989,532575945628,1582749573464,1582749802674,1,0,0,0,72,0,532575944989}
DEBUG main-SendThread(10.9.1.43:2181) org.apache.zookeeper.ClientCnxn - Reading reply sessionid:0x370878cbdc400f1, packet:: clientPath:null serverPath:null finished:false header:: 796,8 replyHeader:: 796,536871130376,0 request:: '/hbase-unsecure,F response:: v{'replication,'meta-region-server,'rs,'splitWAL,'backup-masters,'table-lock,'flush-table-proc,'master-maintenance,'region-in-transition,'online-snapshot,'switch,'master,'running,'recovering-regions,'draining,'namespace,'hbaseid,'table}
DEBUG hconnection-0xb7dd107-metaLookup-shared--pool2-t32 org.apache.hadoop.hbase.ipc.RpcClientImpl - Use SIMPLE authentication for service ClientService, sasl=false
DEBUG hconnection-0xb7dd107-metaLookup-shared--pool2-t32 org.apache.hadoop.hbase.ipc.RpcClientImpl - Not trying to connect to bigdata4.jiaxun.com/10.0.5.14:16020 this server is in the failed servers list
DEBUG main-SendThread(10.9.1.43:2181) org.apache.zookeeper.ClientCnxn - Reading reply sessionid:0x370878cbdc400f1, packet:: clientPath:null serverPath:null finished:false header:: 797,4 replyHeader:: 797,536871130376,0 request:: '/hbase-unsecure/meta-region-server,F response:: #ffffffff0001a726567696f6e7365727665723a31363032306affffff8344ffffffca6cffffffd4ffffffaf3c50425546a1fa1362696764617461342e6a696178756e2e636f6d10ffffff947d18ffffffdaffffff99ffffffeeffffff99ffffff882e100183,s{532575944989,532575945628,1582749573464,1582749802674,1,0,0,0,72,0,532575944989}
DEBUG main-SendThread(10.9.1.43:2181) org.apache.zookeeper.ClientCnxn - Reading reply sessionid:0x370878cbdc400f1, packet:: clientPath:null serverPath:null finished:false header:: 798,8 replyHeader:: 798,536871130376,0 request:: '/hbase-unsecure,F response:: v{'replication,'meta-region-server,'rs,'splitWAL,'backup-masters,'table-lock,'flush-table-proc,'master-maintenance,'region-in-transition,'online-snapshot,'switch,'master,'running,'recovering-regions,'draining,'namespace,'hbaseid,'table}
DEBUG hconnection-0xb7dd107-metaLookup-shared--pool2-t32 org.apache.hadoop.hbase.ipc.RpcClientImpl - Use SIMPLE authentication for service ClientService, sasl=false
DEBUG hconnection-0xb7dd107-metaLookup-shared--pool2-t32 org.apache.hadoop.hbase.ipc.RpcClientImpl - Not trying to connect to bigdata4.jiaxun.com/10.0.5.14:16020 this server is in the failed servers list
DEBUG main-SendThread(10.9.1.43:2181) org.apache.zookeeper.ClientCnxn - Reading reply sessionid:0x370878cbdc400f1, packet:: clientPath:null serverPath:null finished:false header:: 799,4 replyHeader:: 799,536871130376,0 request:: '/hbase-unsecure/meta-region-server,F response:: #ffffffff0001a726567696f6e7365727665723a31363032306affffff8344ffffffca6cffffffd4ffffffaf3c50425546a1fa1362696764617461342e6a696178756e2e636f6d10ffffff947d18ffffffdaffffff99ffffffeeffffff99ffffff882e100183,s{532575944989,532575945628,1582749573464,1582749802674,1,0,0,0,72,0,532575944989}
DEBUG main-SendThread(10.9.1.43:2181) org.apache.zookeeper.ClientCnxn - Reading reply sessionid:0x370878cbdc400f1, packet:: clientPath:null serverPath:null finished:false header:: 800,8 replyHeader:: 800,536871130376,0 request:: '/hbase-unsecure,F response:: v{'replication,'meta-region-server,'rs,'splitWAL,'backup-masters,'table-lock,'flush-table-proc,'master-maintenance,'region-in-transition,'online-snapshot,'switch,'master,'running,'recovering-regions,'draining,'namespace,'hbaseid,'table}
DEBUG hconnection-0xb7dd107-metaLookup-shared--pool2-t32 org.apache.hadoop.hbase.ipc.RpcClientImpl - Use SIMPLE authentication for service ClientService, sasl=false
.......配置虚拟机的ip对应的主机名：注意此处一定是绑定的真实IP地址而不是虚拟IP。
# Copyright (c) 1993-2009 Microsoft Corp.
#
# This is a sample HOSTS file used by Microsoft TCP/IP for Windows.
#
# This file contains the mappings of IP addresses to host names. Each
# entry should be kept on an individual line. The IP address should
# be placed in the first column followed by the corresponding host name.
# The IP address and the host name should be separated by at least one
# space.
#
# Additionally, comments (such as these) may be inserted on individual
# lines or following the machine name denoted by a '#' symbol.
#
# For example:
#
# 102.54.94.97 rhino.acme.com # source server
# 38.25.63.10 x.acme.com # x client host
10.9.1.50 bigdata6
10.9.1.49 bigdata5
10.9.1.48 bigdata4
10.9.1.47 bigdata3
10.9.1.46 bigdata2
10.9.1.45 bigdata1（3）在集群中下载hbase的hbase-site.xml文件及log4j.properties文件（通过远程工具的ftp功能来进行下载）
如下图所示：
（4） 使用开发工具创建hbase客户端工程，并将hbase-site.xml以及log4j.properties文件放入工程的resources资源下。
如下图所示：
将hbase-site.xml放入该目下，可在代码工程中直接使用其配置中hostname等信息（前提windows中已经配好ip映射关系）
2.HbaseUtils工具类编写
（1）构建utils包，代码如下
package HbaseUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.client.coprocessor.AggregationClient;
import org.apache.hadoop.hbase.client.coprocessor.LongColumnInterpreter;
import org.apache.hadoop.hbase.util.Bytes;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
public class HbaseUtils {
/*封装共用模块*/
private static Configuration conf = null;
private static Connection conn = null;
static {
conf = HBaseConfiguration.create();
//配置hbase的zookeeper及相关环境
conf.set("hbase.zookeeper.quorum", "bigdata1.jiaxun.com,bigdata2.jiaxun.com,bigdata3.jiaxun.com");
conf.set("hbase.zookeeper.property.clientPort", "2181");
conf.set("hbase.master", "10.9.1.16:16000");
conf.set("zookeeper.znode.parent", "/hbase-unsecure");
//conn
try {
conn = ConnectionFactory.createConnection(conf);
} catch (Exception e) {
e.printStackTrace();
}
}
//添加一条数据
public static void addOneData(String tablename, String rowkey, String cf, String column, String value) throws Exception {
//创建hbase表对象
Table htable = conn.getTable(TableName.valueOf(tablename));
try {
//创建put对象
//创建rowkey
Put put = new Put(Bytes.toBytes(rowkey));
put.addColumn(Bytes.toBytes(cf), Bytes.toBytes(column), Bytes.toBytes(value));
//添加put到表对象
htable.put(put);
} catch (Exception e) {
e.printStackTrace();
} finally {
//关闭资源
htable.close();
conn.close();
System.out.println("===========数据插入成功===========");
}
}
//批量添加数据
public static void addBatchData(String tablename, List<Put> puts) throws Exception {
Table htable = conn.getTable(TableName.valueOf(tablename));
try {
htable.put(puts);
} catch (Exception e) {
e.printStackTrace();
}finally {
//关闭资源
htable.close();
conn.close();
System.out.println("===========数据插入成功===========");
}
}
//批量创建数据
public static void putBachData(String tablename, String rowKey, String cf, String column, String value,int num) throws IOException {
Table htable = conn.getTable(TableName.valueOf(tablename));
List<Put> puts = new ArrayList<Put>(2048);
int count=0;
try {
for (int i = 0; i < num; i++) {
Put put = new Put(Bytes.toBytes(rowKey+"_"+i));
put.addColumn(Bytes.toBytes(cf), Bytes.toBytes(column), Bytes.toBytes(value + i));
puts.add(put);
count++;
if (count % 3000 == 0) {
System.out.println("count:" + count);
htable.put(puts);
puts = new ArrayList<Put>(2048);
}
}
// 提交最后的内容
System.out.println("Total count:" + count);
htable.put(puts);
}catch(Exception e){
e.printStackTrace();
}finally {
htable.close();
conn.close();
System.out.println("===========数据插入成功===========");
}
}
//获得表描述方法
public static void getTableDesc(String tableName) throws Exception {
Table htable = conn.getTable(TableName.valueOf(tableName));//HTable htable = new HTable(conf, "people") ; //获得表对象
try {
HTableDescriptor htabledesc = htable.getTableDescriptor(); //获得表描述对象
HColumnDescriptor[] hcd = htabledesc.getColumnFamilies(); //获得列描述对象数组
for (HColumnDescriptor hd : hcd) {
String name = hd.getNameAsString(); //列族名
int bs = hd.getBlocksize(); //块大小
int minVers = hd.getMinVersions(); //最小版本号
int maxVers = hd.getMaxVersions(); //最大版本号
int defVers = HColumnDescriptor.DEFAULT_VERSIONS; //默认版本号
System.out.println("name : " + name +
" blocksize : " + bs +
" minVers : " + minVers +
" maxVers : " + maxVers + " defVers : " + defVers);
}
} catch (Exception e) {
e.printStackTrace();
}finally {
//释放资源
htable.close();
conn.close();
}
}
//扫描表的所有数据
public static void scanTable(String tableName) throws Exception{
Table htable = conn.getTable(TableName.valueOf(tableName)) ;
try {
Scan scan = new Scan() ;
//ResultScanner是客户端获取值的接口
ResultScanner scanner = htable.getScanner(scan);
//每行的数据就是Result，存储GET获得SCAN操作后获得单行的值
for(Result res : scanner){
for(Cell cell : res.listCells()){
System.out.println("================================================");
System.out.println("行键：rowkey ===========" + Bytes.toString(res.getRow()));
System.out.println("列族：columnFam ========" + Bytes.toString(CellUtil.cloneFamily(cell)));
System.out.println("列：column ============" + Bytes.toString(CellUtil.cloneQualifier(cell)));
System.out.println("时间戳：timestamp =======" + cell.getTimestamp());
System.out.println("值：value ==============" + Bytes.toString(CellUtil.cloneValue(cell)));
}
}
} catch (Exception e) {
e.printStackTrace();
}finally {
htable.close();
conn.close();
}
}
//获得多行的scan数据
public static void scanForRange(String tableName,String rowKey1,String rowKey2,String cf,String colmun) throws Exception{
Table htable = conn.getTable(TableName.valueOf(tableName)) ;
try {
Scan scan = new Scan(Bytes.toBytes(rowKey1), Bytes.toBytes(rowKey2)) ;
ResultScanner scanner = htable.getScanner(scan);
for(Result rs : scanner){
//获得某个列的值
String res = Bytes.toString(rs.getValue(Bytes.toBytes(cf), Bytes.toBytes(colmun))) ;
System.out.println(res);
}
} catch (Exception e) {
e.printStackTrace();
} finally {
htable.close();
conn.close();
}
}
//获得单行的数据
public static void getForRowKey(String tableName,String rowkey) throws Exception{
Table htable = conn.getTable(TableName.valueOf(tableName)) ; //获得表对象
try {
Get get = new Get(Bytes.toBytes(rowkey)) ;
Result result = htable.get(get);
if( result == null || result.size() == 0){
System.out.println("没有这个rowkey");
htable.close();
return ;
}
for(Cell cell : result.listCells()){
System.out.println("================================================");
System.out.println("行键：rowkey ===========" + Bytes.toString(result.getRow()));
System.out.println("列族：columnFam ========" + Bytes.toString(CellUtil.cloneFamily(cell)));
System.out.println("列：column ============" + Bytes.toString(CellUtil.cloneQualifier(cell)));
System.out.println("时间戳：timestamp =======" + cell.getTimestamp());
System.out.println("值：value ==============" + Bytes.toString(CellUtil.cloneValue(cell)));
}
} catch (Exception e) {
e.printStackTrace();
} finally {
htable.close();
conn.close();
}
}
//删除数据
public static void deleteRow(String tableName,String rowkey) throws Exception{
Table htable = conn.getTable(TableName.valueOf(tableName)) ; //获得表对象
try {
Delete delete = new Delete(Bytes.toBytes(rowkey)) ;
htable.delete(delete);
} catch (Exception e) {
e.printStackTrace();
}finally {
htable.close();
conn.close();
}
}
//修改表，添加列族(管理员干的事)
public static void alterTableAddCls(String tableName,String cf) throws Exception {
//创建数据库管理员
Admin admin = conn.getAdmin() ;
try {
admin.disableTable(TableName.valueOf(tableName));
HColumnDescriptor hcd = new HColumnDescriptor(Bytes.toBytes(cf)) ;
//1:获得表描述对象进行修改
HTableDescriptor htd = admin.getTableDescriptor(TableName.valueOf(tableName));
htd.addFamily(hcd);
//通过admin来进行实际的修改
admin.modifyTable(TableName.valueOf((tableName)), htd);
admin.enableTable(TableName.valueOf(tableName));
} catch (Exception e) {
e.printStackTrace();
}finally {
admin.close();
conn.close();
System.out.println("====添加列族成功====");
}
}
//删除该表
public static void deleteTable(String tableName) throws Exception{
Admin admin = conn.getAdmin() ;
try {
if(admin.tableExists(TableName.valueOf(tableName))){
admin.disableTable(TableName.valueOf(tableName));
admin.deleteTable(TableName.valueOf(tableName));
System.out.println("删除表成功");
}
} catch (Exception e) {
e.printStackTrace();
} finally {
admin.close();
conn.close();
}
}
//行计数
public static long rowCount(String tableName) {
long rowCount = 0;
@SuppressWarnings("resource")
AggregationClient aggregationClient = new AggregationClient(conf);
Scan scan = new Scan();
try {
rowCount = aggregationClient.rowCount(TableName.valueOf(tableName),
new LongColumnInterpreter(), scan);
} catch (Throwable e) {
e.printStackTrace();
}
return rowCount;
}
}
（2）编写测试类
package testHbase;
import HbaseUtils.HbaseUtils;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Table;
import sun.util.calendar.LocalGregorianCalendar;
import java.util.Date;
import java.util.Random;
import static HbaseUtils.HbaseUtils.getTableDesc;
public class TestHbase {
public static void main(String[] args) throws Exception {
long startTime=System.currentTimeMillis(); //获取开始时间
HbaseUtils hb = new HbaseUtils();
String tableName="test_dd";
Random r = new Random();
int num = r.nextInt(11);
Date date = new Date();
String timestamp = String.valueOf(date.getTime()/1000);
System.out.println(timestamp);
String rowkey="138873118"+num+"_"+timestamp;
System.out.println(rowkey);
String cf="cf";
String[] columnArray = {"name","subject","score"};
String[] valuesArray = {"guozixuezhang","math","80"};
String column=columnArray[2];
String value=valuesArray[2];
//获得表描述信息
// hb.getTableDesc(tableName) ;
//批量插入数据
hb.putBachData(tableName,rowkey,cf,column,value,10000000);
long endTime=System.currentTimeMillis(); //获取结束时间
System.out.println("程序运行时间： "+(endTime-startTime)/1000+"s");
}
}3.小结
本文主要探讨了Hbase java-API的编写环境搭建及操作数据库具体方法，环境搭建中特别注意hosts文件的配置及连接hbase时hbase master地址的设置，往往这两个地方是容易被忽略的地方，API使用的时候要注意各个API的使用方法，需要不断的测试完成，最后熟练掌握。
