HBase基础API(创建、插入、读取、扫描及删除)

一、添加Maven依赖

<dependency>
  <groupId>junit</groupId>
  <artifactId>junit</artifactId>
  <version>4.12</version>
  <scope>test</scope>
</dependency>
<dependency>
  <groupId>org.apache.hbase</groupId>
  <artifactId>hbase-client</artifactId>
  <version>1.2.0</version>
</dependency>
<dependency>
  <groupId>org.apache.hbase</groupId>
  <artifactId>hbase-common</artifactId>
  <version>1.2.0</version>
</dependency>
<dependency>
  <groupId>org.apache.hbase</groupId>
  <artifactId>hbase-server</artifactId>
  <version>1.2.0</version>
</dependency>
<dependency>
  <groupId>org.apache.hadoop</groupId>
  <artifactId>hadoop-common</artifactId>
  <version>2.6.0</version>
</dependency>

二、创建表

创建表主要是通过HBase的Admin类来进行的，代码如下：

@Test
public void createTable() throws IOException {
    // 1、获取hbase连接，配置
    // hbase，zookeeper，property，clientPort
    Configuration conf = HBaseConfiguration.create();
    conf.set("hbase.zookeeper.quorum","hadoop4"); // 设置zookeeper地址，若是zookeeper集群，节点名称用逗号分隔
    conf.set("hbase.zookeeper.property.clientPort","2181"); // 设置zookeeper连接端口
    
    // 2、创建连接
    Connection conn = ConnectionFactory.createConnection(conf);

    // 3、创建admin（表管理类）
    Admin admin = conn.getAdmin();

    // 4、定义表名
    HTableDescriptor student = new HTableDescriptor(TableName.valueOf("student"));

    // 5、添加列簇信息
    student.addFamily(new HColumnDescriptor("info"));
    student.addFamily(new HColumnDescriptor("score"));

    // 6、调用创建表的方法进行建表操作
    admin.createTable(student);

    // 7、关闭连接
    admin.close();
    conn.close();
}

三、插入数据

插入通过HBase的Put类完成，代码如下：

@Test
public void putDataToTable() throws IOException {
   // 1、获取hbase连接，配置
   Configuration conf = HBaseConfiguration.create();
   conf.set("hbase.zookeeper.quorum","192.168.233.146");
   conf.set("hbase.zookeeper.property.clientPort","2181");

   // 2、创建连接
   Connection conn = ConnectionFactory.createConnection(conf);

   // 3、获取table
   Table student = conn.getTable(TableName.valueOf("student"));

   // 4、用行键实例化Put，行键为rk1
   Put put = new Put(Bytes.toBytes("rk1"));
   
   // 5、指定列族、列名和值,如:info:name zhangsan
   put.addColumn(Bytes.toBytes("info"),Bytes.toBytes("name"),Bytes.toBytes("zhangsan"));
   put.addColumn(Bytes.toBytes("info"),Bytes.toBytes("gender"),Bytes.toBytes("male"));
   put.addColumn(Bytes.toBytes("info"),Bytes.toBytes("age"),Bytes.toBytes("11"));

   // 6、执行Put,插入数据
   student.put(put);

   // 7、关闭连接
   student.close();
   conn.close();
}

四、读取数据

读取通过HBase的Get类完成，代码如下：

@Test
public void getDataFromTable() throws IOException {
    // 1、配置
    Configuration conf = HBaseConfiguration.create();
    conf.set("hbase.zookeeper.quorum","192.168.233.146");
    conf.set("hbase.zookeeper.property.clientPort","2181");

    // 2、连接
    Connection conn = ConnectionFactory.createConnection(conf);

    // 3、获取table
    Table student = conn.getTable(TableName.valueOf("student"));

    // 4、用行键实例化Get
    Get get = new Get(Bytes.toBytes("rk1"));
    // 指定列族和列名
    get.addColumn("info".getBytes(),"age".getBytes());

    // 5、读取结果
    Result result = student.get(get);

    // 6、对结果进行遍历
    Cell[] cells = result.rawCells();
    for (Cell cell : cells) {
        // 获取具体的值
        System.out.println("rowKey:"+Bytes.toString(CellUtil.cloneRow(cell)));
        System.out.println("列簇："+Bytes.toString(CellUtil.cloneFamily(cell)));
        System.out.println("列名："+Bytes.toString(CellUtil.cloneQualifier(cell)));
        System.out.println("value"+Bytes.toString(CellUtil.cloneValue(cell)));
    }

    // 7、关闭
    student.close;
    conn.close();
}

五、扫描数据

HBase读取数据有两种方式，一种是读取(Get)，另一种是扫描（Scan），扫描针对的是某个行键范围

@Test
public void scanDataFromTable() throws IOException {
    // 1、配置
    Configuration conf = HBaseConfiguration.create();
    conf.set("hbase.zookeeper.quorum","192.168.233.146");
    conf.set("hbase.zookeeper.property.clientPort","2181");

    // 2、连接
    Connection conn = ConnectionFactory.createConnection(conf);

    // 3、获取table
    Table student = conn.getTable(TableName.valueOf("student"));

    // 4、初始化Scan实例
    Scan scan = new Scan();

    // 5、指定开始和结束的行键，即获取rk1~rk6之间的数据
    scan.setStartRow("rk1".getBytes());
    scan.setStopRow("rk6".getBytes());

    // 6、增加过滤条件，即指定列族和列名
    scan.addColumn("info".getBytes(),"age".getBytes());

    // 5、读取结果
    ResultScanner rs = student.getScanner(scan);

    // 6、对结果进行遍历
    for (Result r : rs) {
        Cell[] cells = r.rawCells();
        for (Cell cell : cells) {
            System.out.println("rowKey:"+Bytes.toString(CellUtil.cloneRow(cell)));
            System.out.println("列簇："+Bytes.toString(CellUtil.cloneFamily(cell)));
            System.out.println("列名："+Bytes.toString(CellUtil.cloneQualifier(cell)));
            System.out.println("value:"+Bytes.toString(CellUtil.cloneValue(cell)));
        }
    }
    
    // 7、关闭
    student.close();
    conn.close();
}

六、删除

需要注意的是删除表之前要先禁用表（disable）表

@Test
public void dropTable() throws IOException {
    //1、配置
    Configuration conf = HBaseConfiguration.create();
    conf.set("hbase.zookeeper.quorum","hadoop4");
    conf.set("hbase.zookeeper.property.clientPort","2181");

    //2、连接
    Connection conn = ConnectionFactory.createConnection(conf);

    //3、表管理类
    Admin admin = conn.getAdmin();

    //4、禁用表
    admin.disableTable(TableName.valueOf("student"));

    //5、删除表
    admin.deleteTable(TableName.valueOf("student"));

    //6、关闭资源
    admin.close();
    conn.close();
}