通过Java Api与HBase交互

出处：http://www.taobaotest.com/blogs/qa?bid=13894

引言

HBase提供了Java Api的访问接口，掌握这个就跟Java应用使用RDBMS时需要JDBC一样重要，本文将继续前两篇文章中blog表的示例，介绍常用的Api。

练习前的准备工作

创建一个Maven工程，加入以下依赖：

<dependency>

<groupId>org.apache.hbase</groupId>

<artifactId>hbase</artifactId>

<version>0.90.2</version>

</dependency>

如果你的Maven库里还没有hbase，还需要配置下repository

<repositories>

<repository>

<id>cloudera</id>

<url>https://repository.cloudera.com/content/groups/public</url>

</repository>

</repositories>

确保HBase环境已启动且能连接到，将HBase环境的hbase-site.xml文件拷贝到上述工程的src/test/resources目录

加载配置

Configuration conf = new Configuration();

// conf.addResource("hbase-site-cluster.xml");//可以指定文件加载

conf = HBaseConfiguration.create(conf);

创建表

/**========创建表=========*/

HTableDescriptor desc = new HTableDescriptor("blog");

desc.addFamily(new HColumnDescriptor("article"));

desc.addFamily(new HColumnDescriptor("author"));

admin.createTable(desc );

增加记录

/**=========插入数据=========*/

Put put = new Put(Bytes.toBytes("1"));

put.add(Bytes.toBytes("article"), Bytes.toBytes("title"), Bytes.toBytes("Head First HBase"));

put.add(Bytes.toBytes("article"), Bytes.toBytes("content"), Bytes.toBytes("HBase is the Hadoop database. Use it when you need random, realtime read/write access to your Big Data."));

put.add(Bytes.toBytes("article"), Bytes.toBytes("tags"), Bytes.toBytes("Hadoop,HBase,NoSQL"));

put.add(Bytes.toBytes("author"), Bytes.toBytes("name"), Bytes.toBytes("hujinjun"));

put.add(Bytes.toBytes("author"), Bytes.toBytes("nickname"), Bytes.toBytes("一叶渡江"));

table.put(put);

知识点回顾：RowKey 和 ColumnName 是二进制值（Java 类型 byte[]），value 是一个字节数组（Java类型 byte[]）

根据RowKey查询

/**=========根据rowkey

Get get = new Get(Bytes.toBytes("1")); 查询数据=========*/

Result result = table.get(get);

for(KeyValue kv :result.list()){

  System.out.println("family:" +Bytes.toString(kv.getFamily()));

  System.out.println("qualifier:" +Bytes.toString(kv.getQualifier()));

  System.out.println("value:" +Bytes.toString(kv.getValue()));

  System.out.println("Timestamp:" +kv.getTimestamp());

}

遍历查询与迭代

/**=========遍历查询=========*/

Scan scan = new Scan();

ResultScanner rs =null;

try {

  rs = table.getScanner(scan);

  for (Result r : rs) {

    for(KeyValue kv :r.list()){

      System.out.println("family:" +Bytes.toString(kv.getFamily()));

      System.out.println("qualifier:" +Bytes.toString(kv.getQualifier()));

    System.out.println("value:" +Bytes.toString(kv.getValue()));

    }

  }

} finally {

  rs.close();

}

知识点回顾：HTable的存储结构

可以看到上面代码我们用了两次for循环来遍历迭代。

更新练习

/**=========更新=========*/

//查询更新前的值

Get get2 = new Get(Bytes.toBytes("1"));

get2.addColumn(Bytes.toBytes("author"), Bytes.toBytes("nickname"));

assertThat(Bytes.toString(table.get(get2).list().get(0).getValue()),is("一叶渡江"));

//更新nickname为yedu

Put put2 = new Put(Bytes.toBytes("1")); :

put2.add(Bytes.toBytes("author"), Bytes.toBytes("nickname"), Bytes.toBytes("yedu"));

table.put(put2);

//查询更新结果

Get get3 = new Get(Bytes.toBytes("1"));

get3.addColumn(Bytes.toBytes("author"), Bytes.toBytes("nickname"));

assertThat(Bytes.toString(table.get(get3).list().get(0).getValue()),is("yedu"));

//查询nickname的多个(本示例为2个)版本值

Get get4 = new Get(Bytes.toBytes("1"));

get4.addColumn(Bytes.toBytes("author"), Bytes.toBytes("nickname"));

get4.setMaxVersions(2);

List results = table.get(get4).list();

assertThat(results.size(),is(2));

assertThat(Bytes.toString(results.get(0).getValue()),is("yedu"));

assertThat(Bytes.toString(results.get(1).getValue()),is("一叶渡江"));

删除记录

/**=========删除记录=========*/

//删除指定column

Delete deleteColumn = new Delete(Bytes.toBytes("1"));

deleteColumn.deleteColumns(Bytes.toBytes("author"),Bytes.toBytes("nickname"));

table.delete(deleteColumn);

assertThat( table.get(get4).list(),nullValue());

//删除所有column

Delete deleteAll = new Delete(Bytes.toBytes("1"));

table.delete(deleteAll);

assertThat(table.getScanner(scan).next(),nullValue());

删除表

/**=========删除表=========*/

admin.disableTable("blog");

admin.deleteTable("blog");

assertThat(admin.tableExists("blog"),is(false));

完整代码示例

public class HBase {

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

Configuration conf = new Configuration();

// conf.addResource("hbase-site-cluster.xml");//指定文件加载

conf = HBaseConfiguration.create(conf);

HBaseAdmin admin = new HBaseAdmin(conf);//HBaseAdmin负责跟表相关的操作如create,drop等 

/**========创建表=========*/

HTableDescriptor desc = new HTableDescriptor("blog");

desc.addFamily(new HColumnDescriptor("article"));

desc.addFamily(new HColumnDescriptor("author"));

admin.createTable(desc );

HTable table = new HTable(conf, Bytes.toBytes("blog"));//HTabel负责跟记录相关的操作如增删改查等

/**=========插入数据=========*/

Put put = new Put(Bytes.toBytes("1"));

put.add(Bytes.toBytes("article"), Bytes.toBytes("title"), Bytes.toBytes("Head First HBase"));

put.add(Bytes.toBytes("article"), Bytes.toBytes("content"), Bytes.toBytes("HBase is the Hadoop database. Use it when you need random, realtime read/write access to your Big Data."));

put.add(Bytes.toBytes("article"), Bytes.toBytes("tags"), Bytes.toBytes("Hadoop,HBase,NoSQL"));

put.add(Bytes.toBytes("author"), Bytes.toBytes("name"), Bytes.toBytes("hujinjun"));

put.add(Bytes.toBytes("author"), Bytes.toBytes("nickname"), Bytes.toBytes("一叶渡江"));

table.put(put);

/**=========根据rowkey

Get get = new Get(Bytes.toBytes("1")); 查询数据=========*/

Result result = table.get(get);

  for(KeyValue kv :result.list()){

  System.out.println("family:" +Bytes.toString(kv.getFamily()));

  System.out.println("qualifier:" +Bytes.toString(kv.getQualifier()));

  System.out.println("value:" +Bytes.toString(kv.getValue()));

  System.out.println("Timestamp:" +kv.getTimestamp());

}

/**=========遍历查询=========*/

Scan scan = new Scan();

ResultScanner rs =null;

try {

  rs = table.getScanner(scan);

  for (Result r : rs) {

    for(KeyValue kv :r.list()){

      System.out.println("family:" +Bytes.toString(kv.getFamily()));

      System.out.println("qualifier:" +Bytes.toString(kv.getQualifier()));

      System.out.println("value:" +Bytes.toString(kv.getValue()));

    }

  }

} finally {

  rs.close();

}

/**=========更新=========*/

//查询更新前的值

Get get2 = new Get(Bytes.toBytes("1"));

get2.addColumn(Bytes.toBytes("author"), Bytes.toBytes("nickname"));

assertThat(Bytes.toString(table.get(get2).list().get(0).getValue()),is("一叶渡江"));

//更新nickname为yedu

Put put2 = new Put(Bytes.toBytes("1")); :

put2.add(Bytes.toBytes("author"), Bytes.toBytes("nickname"), Bytes.toBytes("yedu"));

table.put(put2);

//查询更新结果

Get get3 = new Get(Bytes.toBytes("1"));

get3.addColumn(Bytes.toBytes("author"), Bytes.toBytes("nickname"));

assertThat(Bytes.toString(table.get(get3).list().get(0).getValue()),is("yedu"));

//查询nickname的多个(本示例为2个)版本值

Get get4 = new Get(Bytes.toBytes("1"));

get4.addColumn(Bytes.toBytes("author"), Bytes.toBytes("nickname"));

get4.setMaxVersions(2);

List results = table.get(get4).list();

assertThat(results.size(),is(2));

assertThat(Bytes.toString(results.get(0).getValue()),is("yedu"));

assertThat(Bytes.toString(results.get(1).getValue()),is("一叶渡江"));

/**=========删除记录=========*/

//删除指定column

Delete deleteColumn = new Delete(Bytes.toBytes("1"));

deleteColumn.deleteColumns(Bytes.toBytes("author"),Bytes.toBytes("nickname"));

table.delete(deleteColumn);

assertThat( table.get(get4).list(),nullValue());

//删除所有column

Delete deleteAll = new Delete(Bytes.toBytes("1"));

table.delete(deleteAll);

assertThat(table.getScanner(scan).next(),nullValue());

/**=========删除表=========*/

admin.disableTable("blog");

admin.deleteTable("blog");

assertThat(admin.tableExists("blog"),is(false));

}

}

小结

本文介绍了Java api创建、删除表，及记录的增删改查，还是以练习为主，也可作为速查手册（比如看如何迭代查询结果），对HBase的基本概念及操作就介绍到这里，后面将介绍如何使用MapReduce对HBase数据进行分布式计算。