准备工作
创建maven项目
添加依赖
在pom.xml文件中加入
<?xml version="1.0" encoding="UTF-8"?>
<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.learn.test</groupId>
<artifactId>HBase</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<maven.compiler.source>8</maven.compiler.source>
<maven.compiler.target>8</maven.compiler.target>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>2.4.1</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.12</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.testng</groupId>
<artifactId>testng</artifactId>
<version>6.14.2</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
<version>2.6</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.1</version>
<configuration>
<target>1.8</target>
<source>1.8</source>
</configuration>
</plugin>
</plugins>
</build>
</project>
等待它安装
完成状态
在resource下创建log文件,便于查看错误
log4j.rootLogger=INFO, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n
log4j.appender.logfile=org.apache.log4j.FileAppender
log4j.appender.logfile.File=target/spring.log
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n
API操作
所需要的包
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;
import org.testng.annotations.AfterTest;
import org.testng.annotations.BeforeTest;
import org.testng.annotations.Test;
import java.io.IOException;
import java.util.List;
创建HBase连接
我所用的Hadoop集群是HA集群,主节点不一定是active状态,所以IP地址得相应的改动
@BeforeTest
public void beforeTest() throws IOException {
// 1.创建hbase配置
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum", "192.168.237.146");
configuration.set("hbase.zookeeper.property.clientPort", "2181");
// 2.创建hbase的连接
connection = ConnectionFactory.createConnection(configuration);
// 3.创建admin的连接
admin = connection.getAdmin();
}
创建HBase表
在创建表之前都得先判断该表是否存在
@Test
public void createTableTest() throws IOException {
// 1.判断表是否存在
TableName tableName = TableName.valueOf("water_bill");
if (admin.tableExists(tableName)) {
return;
}
// 2.构建表描述构建器(构建器设计模式)
TableDescriptorBuilder tableDescriptorBuilder = TableDescriptorBuilder.newBuilder(tableName);
// 3.构建列族描述构建器
ColumnFamilyDescriptorBuilder columnFamilyDescriptorBuilder = ColumnFamilyDescriptorBuilder.newBuilder(Bytes.toBytes("info"));
// 4.构建表构建器和列族描述构建器建立联系
ColumnFamilyDescriptor columnFamilyDescriptor = columnFamilyDescriptorBuilder.build();
tableDescriptorBuilder.setColumnFamily(columnFamilyDescriptor);
// 5.创建表
TableDescriptor tableDescriptor = tableDescriptorBuilder.build();
admin.createTable(tableDescriptor);
}
删除表
@Test
public void deleteTableTest() throws IOException {
// 1.确认表是否存在
TableName tableName = TableName.valueOf("water_bill");
if (admin.tableExists(tableName)) {
// 禁用表
admin.disableTable(tableName);
// 删除表
admin.deleteTable(tableName);
}
}
向表中插入数据
@Test
public void putTableTest() throws IOException {
// 1.使用hbase连接获取表
TableName tableName = TableName.valueOf("water_bill");
Table table = connection.getTable(tableName);
// 2.构建rowkey,列簇名,列名
// 3.构建put对象
Put put = new Put(Bytes.toBytes("4944191"));
// 4.添加姓名列
put.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name"), Bytes.toBytes("张三"));
// 5.使用表执行put操作
table.put(put);
// 6.关闭表对象
table.close();
}
查看数据
@Test
public void getableTest() throws IOException {
// 1、使用hbase连接获取表
TableName tableName = TableName.valueOf("water_bill");
Table table = connection.getTable(tableName);
// 2、构建rowkey、列簇名、列名
// 3、构建get对象
Get get = new Get(Bytes.toBytes("4944191"));
// 4、执行get请求，获取result对象
Result result = table.get(get);
// 5、获取所有的单元格
List<Cell> cellList = result.listCells();
for (Cell cell : cellList) {
// 获取单元格的列簇名
String cf = Bytes.toString(cell.getFamilyArray(), cell.getFamilyOffset(), cell.getFamilyLength());
// 获取单元格的列名
String cn = Bytes.toString(cell.getQualifierArray(), cell.getQualifierOffset(), cell.getQualifierLength());
// 获取单元格的值
String value = Bytes.toString(cell.getValueArray(), cell.getValueOffset(), cell.getValueLength());
System.out.println(cf + ":" + cn + "->" + value);
}
// 6、关闭表对象
table.close();
}
过滤器操作
数据得自己创建,用之前的插入命令多操作几次就行
@Test
public void scanFilterTest() throws IOException {
// 1.判断表是否存在
Table table = connection.getTable(tableName);
// 2.构建scanFilter对象
Scan scan = new Scan();
// 3.构建过滤器,需要构建两个日期范围的过滤器
// 开始日期
SingleColumnValueFilter startFilter = new SingleColumnValueFilter(
Bytes.toBytes("info"),//列族
Bytes.toBytes("record_date"),//列名
CompareOperator.GREATER_OR_EQUAL,//比较器
new BinaryComparator(Bytes.toBytes("2020-06-01"))//比较表达式
);
// 结束日期过滤器
SingleColumnValueFilter endFilter = new SingleColumnValueFilter(
Bytes.toBytes("info"),//列族
Bytes.toBytes("record_date"),//列名
CompareOperator.LESS_OR_EQUAL,//比较器
new BinaryComparator(Bytes.toBytes("2020-06-31"))//比较表达式
);
// 4.构建过滤器列表
FilterList filterList = new FilterList(
FilterList.Operator.MUST_PASS_ALL,//and操作
startFilter,
endFilter
);
// 5.设置scan扫描器的过滤器
scan.setFilter(filterList);
// 6.通过表的执行结果
ResultScanner resultScanner = table.getScanner(scan);
// 7.通过执行结果获取迭代器
Iterator<Result> resultIterator = resultScanner.iterator();
// 8.迭代打印result
while (resultIterator.hasNext()){
Result result = resultIterator.next();//获取result
byte[] rowkey = result.getRow();
System.out.println("rowkey->" +Bytes.toString(rowkey));
// 5、获取所有的单元格
List<Cell> cellList = result.listCells();
for (Cell cell : cellList) {
// 获取单元格的列簇名
String cf = Bytes.toString(cell.getFamilyArray(), cell.getFamilyOffset(), cell.getFamilyLength());
// 获取单元格的列名
String cn = Bytes.toString(cell.getQualifierArray(), cell.getQualifierOffset(), cell.getQualifierLength());
// 获取单元格的值
String value = Bytes.toString(cell.getValueArray(), cell.getValueOffset(), cell.getValueLength());
System.out.println(cf + ":" + cn + "->" + value);
}
System.out.println("===============================================");
}
// 9.关闭
resultScanner.close();
table.close();
}
查询六月的数据
全部代码
package cn.lenar.hbase;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;
import org.testng.annotations.AfterTest;
import org.testng.annotations.BeforeTest;
import org.testng.annotations.Test;
import java.io.IOException;
import java.util.List;
/**
* @author 公羽
* @time : 2021/4/11 15:02
* @File : HBase_test.java
*/
public class HBase_test {
private Connection connection;
private Admin admin;
@BeforeTest
public void beforeTest() throws IOException {
// 1.创建hbase配置
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum", "192.168.237.146");
configuration.set("hbase.zookeeper.property.clientPort", "2181");
// 2.创建hbase的连接
connection = ConnectionFactory.createConnection(configuration);
// 3.创建admin的连接
admin = connection.getAdmin();
}
// 测试创建表
@Test
public void createTableTest() throws IOException {
// 1.判断表是否存在
TableName tableName = TableName.valueOf("water_bill");
if (admin.tableExists(tableName)) {
return;
}
// 2.构建表描述构建器(构建器设计模式)
TableDescriptorBuilder tableDescriptorBuilder = TableDescriptorBuilder.newBuilder(tableName);
// 3.构建列族描述构建器
ColumnFamilyDescriptorBuilder columnFamilyDescriptorBuilder = ColumnFamilyDescriptorBuilder.newBuilder(Bytes.toBytes("info"));
// 4.构建表构建器和列族描述构建器建立联系
ColumnFamilyDescriptor columnFamilyDescriptor = columnFamilyDescriptorBuilder.build();
tableDescriptorBuilder.setColumnFamily(columnFamilyDescriptor);
// 5.创建表
TableDescriptor tableDescriptor = tableDescriptorBuilder.build();
admin.createTable(tableDescriptor);
}
// 测试删除表
@Test
public void deleteTableTest() throws IOException {
// 1.确认表是否存在
TableName tableName = TableName.valueOf("water_bill");
if (admin.tableExists(tableName)) {
// 禁用表
admin.disableTable(tableName);
// 删除表
admin.deleteTable(tableName);
}
}
// 测试插入数据
@Test
public void putTableTest() throws IOException {
// 1.使用hbase连接获取表
TableName tableName = TableName.valueOf("water_bill");
Table table = connection.getTable(tableName);
// 2.构建rowkey,列簇名,列名
// 3.构建put对象
Put put = new Put(Bytes.toBytes("4944191"));
// 4.添加姓名列
put.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name"), Bytes.toBytes("张三"));
// 5.使用表执行put操作
table.put(put);
// 6.关闭表对象
table.close();
}
//测试查看数据
@Test
public void getableTest() throws IOException {
// 1、使用hbase连接获取表
TableName tableName = TableName.valueOf("water_bill");
Table table = connection.getTable(tableName);
// 2、构建rowkey、列簇名、列名
// 3、构建get对象
Get get = new Get(Bytes.toBytes("4944191"));
// 4、执行get请求，获取result对象
Result result = table.get(get);
// 5、获取所有的单元格
List<Cell> cellList = result.listCells();
for (Cell cell : cellList) {
// 获取单元格的列簇名
String cf = Bytes.toString(cell.getFamilyArray(), cell.getFamilyOffset(), cell.getFamilyLength());
// 获取单元格的列名
String cn = Bytes.toString(cell.getQualifierArray(), cell.getQualifierOffset(), cell.getQualifierLength());
// 获取单元格的值
String value = Bytes.toString(cell.getValueArray(), cell.getValueOffset(), cell.getValueLength());
System.out.println(cf + ":" + cn + "->" + value);
}
// 6、关闭表对象
table.close();
}
@Test
public void scanFilterTest() throws IOException {
// 1.判断表是否存在
Table table = connection.getTable(tableName);
// 2.构建scanFilter对象
Scan scan = new Scan();
// 3.构建过滤器,需要构建两个日期范围的过滤器
// 开始日期
SingleColumnValueFilter startFilter = new SingleColumnValueFilter(
Bytes.toBytes("info"),//列族
Bytes.toBytes("record_date"),//列名
CompareOperator.GREATER_OR_EQUAL,//比较器
new BinaryComparator(Bytes.toBytes("2020-06-01"))//比较表达式
);
// 结束日期过滤器
SingleColumnValueFilter endFilter = new SingleColumnValueFilter(
Bytes.toBytes("info"),//列族
Bytes.toBytes("record_date"),//列名
CompareOperator.LESS_OR_EQUAL,//比较器
new BinaryComparator(Bytes.toBytes("2020-06-31"))//比较表达式
);
// 4.构建过滤器列表
FilterList filterList = new FilterList(
FilterList.Operator.MUST_PASS_ALL,//and操作
startFilter,
endFilter
);
// 5.设置scan扫描器的过滤器
scan.setFilter(filterList);
// 6.通过表的执行结果
ResultScanner resultScanner = table.getScanner(scan);
// 7.通过执行结果获取迭代器
Iterator<Result> resultIterator = resultScanner.iterator();
// 8.迭代打印result
while (resultIterator.hasNext()){
Result result = resultIterator.next();//获取result
byte[] rowkey = result.getRow();
System.out.println("rowkey->" +Bytes.toString(rowkey));
// 5、获取所有的单元格
List<Cell> cellList = result.listCells();
for (Cell cell : cellList) {
// 获取单元格的列簇名
String cf = Bytes.toString(cell.getFamilyArray(), cell.getFamilyOffset(), cell.getFamilyLength());
// 获取单元格的列名
String cn = Bytes.toString(cell.getQualifierArray(), cell.getQualifierOffset(), cell.getQualifierLength());
// 获取单元格的值
String value = Bytes.toString(cell.getValueArray(), cell.getValueOffset(), cell.getValueLength());
System.out.println(cf + ":" + cn + "->" + value);
}
System.out.println("===============================================");
}
// 9.关闭
resultScanner.close();
table.close();
}
@AfterTest
public void afterTest() throws IOException {
// 4.关闭admin
admin.close();
connection.close();
}
}
注意事项
遇到的延时问题的解决办法
得在windows中C:\Windows\System32\drivers\etc下加入IP映射
1219
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
