Hadoop学习记录（十五、HBase的安装与使用）

一、概述

HBase是一种Hadoop数据库，经常被描述为一种稀疏的，分布式的，持久化的，多维有序映射，它基于行键、列键和时间戳建立索引，是一个可以随机访问的存储和检索数据的平台。HBase不限制存储的数据的种类，允许动态的、灵活的数据模型，不用SQL语言，也不强调数据之间的关系。HBase被设计成在一个服务器集群上运行，可以相应地横向扩展。

二、安装

2.1下载并解压

2.2配置环境变量

vim /etc/profile

export HBASE_HOME=/usr/local/hbase-1.4.9
export PATH=$PATH:$HBASE_HOME/bin

source /etc/profile

2.3验证

2.4配置hbase-env.sh

export JAVA_HOME=/usr/lib/jvm/java-1.8.0-openjdk-1.8.0.191.b12-0.el7_5.x86_64

export HBASE_CLASSPATH=/usr/local/hadoop-2.9.2/conf
#使用HBASE自带的zookeeper管理集群
export HBASE_MANAGES_ZK=true

 2.5配置hbase-site.xml

<property>
<name>hbase.rootdir</name>
<value>hdfs://hadoop:9000/hbase</value>
</property>

<property>
<name>hbase.cluster.distributed</name>
<value>true</value>
</property>

<property>
<name>hbase.zookeeper.quorum</name>
<value>hadoop1</value>
</property>

2.6启动hbase

三、举例

3.1启动Hbase shell环境

3.2命令

新建一个名为test的表，其只包含一个名为data的列，表和列族属性为默认值
create 'test','data'
输出空间的所有表
list
输入表内容
put 'test','row1','data:1','value1'
put 'test','row2','data:2','value2'
put 'test','row3','data:3','value3'
禁用表
disable 'test'
删除表
drop 'test'

四、结合Java 

//创建表并添加数据
public class ExampleClient {

  public static void main(String[] args) throws IOException {
    Configuration config = HBaseConfiguration.create();
    // Create table
    HBaseAdmin admin = new HBaseAdmin(config);
    try {
      TableName tableName = TableName.valueOf("test");
      HTableDescriptor htd = new HTableDescriptor(tableName);
      HColumnDescriptor hcd = new HColumnDescriptor("data");
      htd.addFamily(hcd);
      admin.createTable(htd);
      HTableDescriptor[] tables = admin.listTables();
      if (tables.length != 1 &&
          Bytes.equals(tableName.getName(), tables[0].getTableName().getName())) {
        throw new IOException("Failed create of table");
      }
      // Run some operations -- three puts, a get, and a scan -- against the table.
      HTable table = new HTable(config, tableName);
      try {
        for (int i = 1; i <= 3; i++) {
          byte[] row = Bytes.toBytes("row" + i);
          Put put = new Put(row);
          byte[] columnFamily = Bytes.toBytes("data");
          byte[] qualifier = Bytes.toBytes(String.valueOf(i));
          byte[] value = Bytes.toBytes("value" + i);
          put.add(columnFamily, qualifier, value);
          table.put(put);
        }
        Get get = new Get(Bytes.toBytes("row1"));
        Result result = table.get(get);
        System.out.println("Get: " + result);
        Scan scan = new Scan();
        ResultScanner scanner = table.getScanner(scan);
        try {
          for (Result scannerResult : scanner) {
            System.out.println("Scan: " + scannerResult);
          }
        } finally {
          scanner.close();
        }
        // Disable then drop the table
        admin.disableTable(tableName);
        admin.deleteTable(tableName);
      } finally {
        table.close();
      }
    } finally {
      admin.close();
    }
  }
}

//检索HBase表中某范围内气象站观测数据行
public class HBaseTemperatureQuery extends Configured implements Tool {
  static final byte[] DATA_COLUMNFAMILY = Bytes.toBytes("data");
  static final byte[] AIRTEMP_QUALIFIER = Bytes.toBytes("airtemp");
  
  public NavigableMap<Long, Integer> getStationObservations(HTable table,
      String stationId, long maxStamp, int maxCount) throws IOException {
    byte[] startRow = RowKeyConverter.makeObservationRowKey(stationId, maxStamp);
    NavigableMap<Long, Integer> resultMap = new TreeMap<Long, Integer>();
    Scan scan = new Scan(startRow);
    scan.addColumn(DATA_COLUMNFAMILY, AIRTEMP_QUALIFIER);
    ResultScanner scanner = table.getScanner(scan);
    try {
      Result res;
      int count = 0;
      while ((res = scanner.next()) != null && count++ < maxCount) {
        byte[] row = res.getRow();
        byte[] value = res.getValue(DATA_COLUMNFAMILY, AIRTEMP_QUALIFIER);
        Long stamp = Long.MAX_VALUE -
          Bytes.toLong(row, row.length - Bytes.SIZEOF_LONG, Bytes.SIZEOF_LONG);
        Integer temp = Bytes.toInt(value);
        resultMap.put(stamp, temp);
      }
    } finally {
      scanner.close();
    }
    return resultMap;
  }

  public int run(String[] args) throws IOException {
    if (args.length != 1) {
      System.err.println("Usage: HBaseTemperatureQuery <station_id>");
      return -1;
    }
    
    HTable table = new HTable(HBaseConfiguration.create(getConf()), "observations");
    try {
      NavigableMap<Long, Integer> observations =
          getStationObservations(table, args[0], Long.MAX_VALUE, 10).descendingMap();
      for (Map.Entry<Long, Integer> observation : observations.entrySet()) {
        // Print the date, time, and temperature
        System.out.printf("%1$tF %1$tR\t%2$s\n", observation.getKey(),
            observation.getValue());
      }
      return 0;
    } finally {
      table.close();
    }
  }

  public static void main(String[] args) throws Exception {
    int exitCode = ToolRunner.run(HBaseConfiguration.create(),
        new HBaseTemperatureQuery(), args);
    System.exit(exitCode);
  }
}