HBase Java API基本操作(四)

(1). 前言

前面对HBase Shell进行了学习,这一小篇,主要讲解Java API.

(2). 项目结构如下

"HBase 项目结构"

(3). 创建表和列簇信息

package help.lixin.hbase.example;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.io.compress.Compression.Algorithm;
import org.junit.Before;
import org.junit.Test;

public class CreateTableTest {

	private Connection connection = null;

	@Before
	public void init() throws Exception {
		Configuration configuration = HBaseConfiguration.create();
		configuration.addResource(new Path(ClassLoader.getSystemResource("hbase-site.xml").toURI()));
		configuration.addResource(new Path(ClassLoader.getSystemResource("core-site.xml").toURI()));
		connection = ConnectionFactory.createConnection(configuration);
	}

	@Test
	public void testCreateTable() throws Exception {
		Admin admin = connection.getAdmin();
		// 定义表名称
		TableName userTableName = TableName.valueOf("user");

		// 查看表是否存在,如果不存在,则创建
		if (!admin.tableExists(userTableName)) {
			// 定义表
			HTableDescriptor table = new HTableDescriptor(userTableName);

			// 定义列簇
			HColumnDescriptor info = new HColumnDescriptor("info");
			// 设置列簇的压缩方式
			info.setCompactionCompressionType(Algorithm.GZ);
			// 设置最大的保存的历史版本
			info.setMaxVersions(5);

			// 给表(user)添加列簇.
			table.addFamily(info);
			// 创建表和列簇.
			// create 'user','info'
			admin.createTable(table);
		}
	}
}

(4). 基本增删改查

package help.lixin.hbase.example;

import java.util.Arrays;
import java.util.List;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Delete;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.util.Bytes;
import org.junit.Before;
import org.junit.Test;

public class BaseTest {

	private Connection connection = null;

	@Before
	public void init() throws Exception {
		Configuration configuration = HBaseConfiguration.create();
		configuration.addResource(new Path(ClassLoader.getSystemResource("hbase-site.xml").toURI()));
		configuration.addResource(new Path(ClassLoader.getSystemResource("core-site.xml").toURI()));
		this.connection = ConnectionFactory.createConnection(configuration);
	}

	@Test
	public void addOrUpdate() throws Exception {
		Table table = connection.getTable(TableName.valueOf("user"));

		// row-key
		Put row1 = new Put(Bytes.toBytes("1"));
		// 列簇/列/version/cell
		row1.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name"), 1L, Bytes.toBytes("张三"));
		row1.addColumn(Bytes.toBytes("info"), Bytes.toBytes("sex"), 1L, Bytes.toBytes("男"));
		row1.addColumn(Bytes.toBytes("info"), Bytes.toBytes("pwd"), 1L, Bytes.toBytes("123"));
		table.put(row1);

		Put row2 = new Put(Bytes.toBytes("2"));
		row2.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name"), 1L, Bytes.toBytes("李四"));
		row2.addColumn(Bytes.toBytes("info"), Bytes.toBytes("sex"), 1L, Bytes.toBytes("男"));
		row2.addColumn(Bytes.toBytes("info"), Bytes.toBytes("pwd"), 1L, Bytes.toBytes("321"));
		table.put(row2);
	}
	
	
	/**
	 * info:name 张三 	info:pwd 123 	info:sex 男 	
	 * info:name 李四 	info:pwd 321 	info:sex 男 
	 * @throws Exception
	 */
	@Test
	public void batchGet() throws Exception {
		Table table = connection.getTable(TableName.valueOf("user"));
		Get getOne = new Get(Bytes.toBytes("1"));
		Get getTwo = new Get(Bytes.toBytes("2"));
		List<Get>  gets = Arrays.asList(getOne,getTwo);
		Result[] results = table.get(gets);
		for(Result result : results) {
			List<Cell> cells = result.listCells();
			for(Cell cell : cells) {
				// 列簇
				 byte[] columnFamilyBytes = CellUtil.cloneFamily(cell);
				 String columnFamily = Bytes.toString(columnFamilyBytes);
				 
				 // 列
				 byte[] columnQualifierBytes = CellUtil.cloneQualifier(cell);
				 String columnQualifier = Bytes.toString(columnQualifierBytes);
				 
				 // 列值
				 byte[] columnCellValue = CellUtil.cloneValue(cell);
				 String cennValue = Bytes.toString(columnCellValue);
				 String format = String.format("%s %s \t", (columnFamily + ":" + columnQualifier) , cennValue );
				 System.out.print(format);
			}
			System.out.println();
		}
	}
	
	@Test
	public void testDelete() throws Exception {
		Table table = connection.getTable(TableName.valueOf("user"));
		Delete delete = new Delete(Bytes.toBytes("2"));
		table.delete(delete);
		System.out.println();
	}
}

(5). core-site.xml(拷贝自hadoop)

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>

<!-- 指定集群的文件系统类型:分布式文件系统 -->
    <property>
        <name>fs.default.name</name>
        <value>hdfs://localhost:9000</value>
    </property>

    <!-- 指定临时文件存储目录 -->
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/Users/lixin/Developer/hadoop/hadoopDatas/tmpDatas</value>
    </property>

    <!-- 缓冲区大小,实际工作中根据服务器性能动态调整 -->
    <property>
        <name>io.file.buffer.size</name>
        <value>4096</value>
    </property>

   <!-- 开启HDFS的垃圾桶机制,删除掉的数据可以从垃圾桶中回收,单位分钟 -->
    <property>
        <name>fs.trash.interval</name>
        <value>10080</value>
    </property>

</configuration>

(6). hbase-site.xml(拷贝自hbase)

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
  <!-- 开启集群模式 -->
<property>
  <name>hbase.cluster.distributed</name>
  <value>true</value>
</property>

<!-- HDFS存储路径 -->
<property>
  <name>hbase.rootdir</name>
  <value>hdfs://lixin-macbook.local:9000/hbase</value>
</property>
</configuration>

(7). 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>help.lixin.hbase.example</groupId>
	<artifactId>hbase-client-example</artifactId>
	<version>1.0.0-SNAPSHOT</version>
	<packaging>jar</packaging>

	<name>hbase-client-example</name>
	<url>http://maven.apache.org</url>

	<properties>
		<maven.compiler.source>8</maven.compiler.source>
		<maven.compiler.target>8</maven.compiler.target>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
	</properties>

	<dependencies>
		<dependency>
			<groupId>org.apache.hbase</groupId>
			<artifactId>hbase-client</artifactId>
    		<version>1.4.13</version>
		</dependency>
	</dependencies>
</project>

(8). 总结

这一小节,通过HBase client进行了简单的增删改查.相对来说是比较简单的.