【Hadoop】HBase Java API 练习

1 环境准备

1）成功搭建Hadoop-2.2.0开发环境

2）成功启动HBase，通过HBase Shell进行测试

3）使用MyEclipse作为开发工具

4）使用Maven构建项目

2 项目创建

2.1 创建Project

由于我已经创建了项目，所以这里会报错，只要改下Artifact Id就可以。而你只需要输入没有使用过的Artifact Id。

2.2 pom.xml

<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>

<groupId>com.szh</groupId>
<artifactId>HBase</artifactId>
<version>0.0.1</version>
<packaging>jar</packaging>

<name>HBase</name>
<url>http://maven.apache.org</url>

<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<hadoop.version>2.2.0</hadoop.version>
</properties>

<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>3.8.1</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>0.98.23-hadoop2</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-common</artifactId>
<version>0.98.23-hadoop2</version>
</dependency>

<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>0.98.23-hadoop2</version>
</dependency>
<dependency>
<groupId>jdk.tools</groupId>
<artifactId>jdk.tools</artifactId>
<version>1.7</version>
<scope>system</scope>
<systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>2.4.1</version>
<executions>
<!-- Run shade goal on package phase -->
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<transformers>
<!-- add Main-Class to manifest file -->
<transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
<mainClass>com.szh.hbase.MyDriver</mainClass>
</transformer>
</transformers>
<createDependencyReducedPom>false</createDependencyReducedPom>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>

在上面的pom.xml中我们导入了hadoop和hbase开发所需要的包，待会我们还要学习如何开发MapReduce和HBase的交互，所以先做好准备，使用Maven开发最好要保证网速，下载真的很慢！！！等待下载完毕….

2.3 MyHbase实例

使用Java API和使用HBase shell本质上是没有任何区别的，都是HBase里面的DDL操作，所以我们本次使用的例子跟HBase Shell 练习里面的例子是一样的，在这里我们先贴出局部代码，大家不用着急，最后会把项目代码给大家的。

1）创建HBaseConfiguration来获取HBase的配置文件信息

static Configuration conf = null;
static {
conf = HBaseConfiguration.create();
conf.set("hbase.zookeeper.quorum", "szh");
}

2）创建表格

/**
* 创建表格
* @param tbName 表名
* @param cf 列族名
* @throws IOException
* @throws ZooKeeperConnectionException
* @throws MasterNotRunningException
*/
@SuppressWarnings({ "all" })
public static void createTable(String tbName,String[] cf) throws MasterNotRunningException, ZooKeeperConnectionException, IOException{
//用于执行操作
HBaseAdmin admin = new HBaseAdmin(conf);
HTableDescriptor desc = new HTableDescriptor(tbName);
for(int i=0;i<cf.length;i++){
desc.addFamily(new HColumnDescriptor(cf[i]));
}
//判断表格是否存在
if(admin.tableExists(tbName)){
System.out.println(tbName+" exists");
System.exit(0);
}else{
admin.createTable(desc);
System.out.println("create table success");
}
}

3）删除表格

public static void deleteTable(String tableName) throws MasterNotRunningException, ZooKeeperConnectionException, IOException{
//用于执行操作
HBaseAdmin admin = new HBaseAdmin(conf);
HTableDescriptor desc = new HTableDescriptor(tableName);
//判断表格是否存在
if(admin.tableExists(tableName)){
admin.disable(tableName);
admin.drop(tableName);
System.out.println("delete table success");
}else{
System.out.println("table is not exist");
}
}

4）插入数据

@SuppressWarnings("all")
public static void add(String tableName,String rowKey,String family,String qualifier,String value) throws IOException{
Put put = new Put(Bytes.toBytes(rowKey));
HTable table = new HTable(conf, tableName);
put.add(Bytes.toBytes(family), Bytes.toBytes(qualifier), Bytes.toBytes(value));
table.put(put);
System.out.println("add data success");
System.out.println("===========");
}

执行main函数：

public static void main(String[] args) {
// TODO Auto-generated method stub
String tablebName = "student";
String rowKey = "xiaoming";
String[] family = {"info","address","score"};
try {
//          createTable(tablebName, family);
add(tablebName,rowKey,family[0],"age","18");
add(tablebName,rowKey,family[0],"birthday","1990-12-12");
add(tablebName,rowKey,family[0],"school","beijingdaxue");
add(tablebName,rowKey,family[1],"country","china");
add(tablebName,rowKey,family[1],"province","guangdong");
add(tablebName,rowKey,family[1],"city","shenzhen");
add(tablebName,rowKey,family[1],"yuwen","99");
add(tablebName,rowKey,family[1],"shuxue","98");
add(tablebName,rowKey,family[1],"yingyu","100");
} catch (MasterNotRunningException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (ZooKeeperConnectionException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}

使用HBase Shell查询结果，如下：



5）删除数据

public static void deleteAppointColumn(String tableName,String rowKey,String family,String qualifier) throws IOException{
HTable table = new HTable(conf,Bytes.toBytes(tableName));
Delete delete = new Delete(Bytes.toBytes(rowKey));
delete.deleteColumn(Bytes.toBytes(family), Bytes.toBytes(qualifier));
table.delete(delete);
System.out.println("delete data success");
System.out.println("===========");
}

执行main函数：

public static void main(String[] args) {
// TODO Auto-generated method stub
String tablebName = "student";
String rowKey = "xiaoming";
String[] family = {"info","address","score"};
try {
deleteAppointColumn(tablebName,rowKey,family[1],"yuwen");
deleteAppointColumn(tablebName,rowKey,family[1],"shuxue");
deleteAppointColumn(tablebName,rowKey,family[1<
f312
/span>],"yingyu");
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}

使用 HBase Shell 查询结果，如下：



6）更新数据

public static void update(String tableName,String rowKey,String family,String qualifier,String value) throws IOException{
Put put = new Put(Bytes.toBytes(rowKey));
HTable table = new HTable(conf, tableName);
put.add(Bytes.toBytes(family), Bytes.toBytes(qualifier), Bytes.toBytes(value));
table.put(put);
System.out.println("update data success");
System.out.println("===========");
}

执行main函数：

public static void main(String[] args) {
// TODO Auto-generated method stub
String tablebName = "student";
String rowKey = "xiaoming";
String[] family = {"info","address","score"};
try {
update(tablebName,rowKey,family[0],"age","100");
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}

使用HBase Shell查询，结果如下：



7）查询数据

7.1）全盘扫描

public static void scanAll(String tableName,String startRow,String stopRow) throws IOException{

HTable table = new HTable(conf, tableName);
Scan scan = new Scan();
scan.setStartRow(Bytes.toBytes(startRow));
scan.setStopRow(Bytes.toBytes(stopRow));
ResultScanner rs = null;
try{
System.out.println("全盘扫描");
rs = table.getScanner(scan);
for(Result r:rs){
for(KeyValue kv:r.list()){
System.out.println("rowKey: "+ Bytes.toString(kv.getRow())
+" family: "+ Bytes.toString(kv.getFamily())
+" qualifiter: "+Bytes.toString(kv.getQualifier())
+" value "+Bytes.toString(kv.getValue())
);
}

}

}finally{
if(rs!=null){
rs.close();
}
}
System.out.println("===========");
}

7.2）查询某一列族

public static void scanByFamily(String tableName,String startRow,String stopRow,String family) throws IOException{

HTable table = new HTable(conf, tableName);
Scan scan = new Scan();
scan.setStartRow(Bytes.toBytes(startRow));
scan.setStopRow(Bytes.toBytes(stopRow));
scan.addFamily(Bytes.toBytes(family));
ResultScanner rs = null;
try{
System.out.println("查询某一列族");
rs = table.getScanner(scan);
for(Result r:rs){
for(KeyValue kv:r.list()){
System.out.println("rowKey: "+ Bytes.toString(kv.getRow())
+" family: "+ Bytes.toString(kv.getFamily())
+" qualifiter: "+Bytes.toString(kv.getQualifier())
+" value "+Bytes.toString(kv.getValue())
);
}

}

}finally{
if(rs!=null){
rs.close();
}
}
System.out.println("===========");
}

7.3）查询某一列

public static void scanByColumns(String tableName,String startRow,String stopRow,String family,String qualifiter) throws IOException{

HTable table = new HTable(conf, tableName);
Scan scan = new Scan();
scan.setStartRow(Bytes.toBytes(startRow));
scan.setStopRow(Bytes.toBytes(stopRow));
scan.addColumn(Bytes.toBytes(family),Bytes.toBytes(qualifiter));
ResultScanner rs = null;
try{
System.out.println("查询某一列");
rs = table.getScanner(scan);
for(Result r:rs){
for(KeyValue kv:r.list()){
System.out.println("rowKey: "+ Bytes.toString(kv.getRow())
+" family: "+ Bytes.toString(kv.getFamily())
+" qualifiter: "+Bytes.toString(kv.getQualifier())
+" value "+Bytes.toString(kv.getValue())
);
}

}

}finally{
if(rs!=null){
rs.close();
}
}
System.out.println("===========");
}

7.4）查询某一列的多个版本

public static void getByVersion(String tableName,String rowKey,String family,String qualifier) throws IOException{
HTable table = new HTable(conf, Bytes.toBytes(tableName));
Get get = new Get(Bytes.toBytes(rowKey));
get.setMaxVersions(5);
Result result = table.get(get);
System.out.println("查询某一列多版本");
List<KeyValue> list = (List<KeyValue>) result.getColumn(Bytes.toBytes(family), Bytes.toBytes(qualifier));
for (KeyValue kv : list) {
System.out.println("rowKey: "+ Bytes.toString(kv.getRow())
+" family: "+ Bytes.toString(kv.getFamily())
+" qualifiter: "+Bytes.toString(kv.getQualifier())
+" value "+Bytes.toString(kv.getValue())
+" TimeStamp: "+kv.getTimestamp()
);
}
System.out.println("===========");
}

这里需要注意的是，0.98版本的HBase默认VERSIONS为1，所以如果你想要获取某一列多个版本数据的话，首先得去修改HBase该列所属的列族的VERSIONS，举个例子：

a. 进入HBase Shell

b. 输入一下命令

alter ‘student’,NAME=>’info’,VERSIONS => 5

查询修改结果：

describe ‘student’

更多HBase Shell细节 可查看HBase Shell 练习

7.5）查询某一行的数据

public static void getByRowKey(String tableName,String rowKey) throws IOException{
HTable table = new HTable(conf,Bytes.toBytes(tableName));
Get get = new Get(Bytes.toBytes(rowKey));
Result result = table.get(get);
System.out.println("查询某一行");
for (KeyValue kv : result.list()) {
System.out.println("rowKey: "+ Bytes.toString(kv.getRow())
+" family: "+ Bytes.toString(kv.getFamily())
+" qualifiter: "+Bytes.toString(kv.getQualifier())
+" value "+Bytes.toString(kv.getValue())
+" TimeStamp: "+kv.getTimestamp()
);
}
System.out.println("===========");
}

执行main函数：

public static void main(String[] args) {
// TODO Auto-generated method stub
String tablebName = "student";
String rowKey = "xiaoming";
String[] family = {"info","address","score"};
try {
scanAll(tablebName,rowKey,rowKey);
scanByFamily(tablebName,rowKey,rowKey,family[0]);
scanByColumns(tablebName,rowKey,rowKey,family[0],"age");
getByVersion(tablebName,rowKey,family[0],"age");
getByRowKey(tablebName,rowKey);
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}

查看Console：