实验三 熟悉常用的HBase操作
一、实验目的
(1)理解HBase在Hadoop体系结构中的角色; (2)熟练使用HBase操作常用的Shell命令; (3)熟悉HBase操作常用的Java API。
二、实验平台
操作系统:centos7; Hadoop版本:3.3; HBase版本:2.2.2; JDK版本:1.8; Java IDE:IDEA。
三、实验内容和要求
(一)编程实现以下指定功能,并用Hadoop提供的HBase Shell命令完成相同任务:
(1) 列出HBase所有的表的相关信息,例如表名、创建时间等;
(2) 在终端打印出指定的表的所有记录数据;
(3) 向已经创建好的表添加和删除指定的列族或列;
(4) 清空指定的表的所有记录数据;
(5) 统计表的行数。
(二)HBase数据库操作
1 现有以下关系型数据库中的表和数据,要求将其转换为适合于HBase存储的表并插入数据:
学生表(Student)
学号(S_No)姓名(S_Name)性别(S_Sex)年龄(S_Age)2015001Zhangsanmale232015003Maryfemale222015003Lisimale24
课程表(Course)
课程号(C_No)课程名(C_Name)学分(C_Credit)123001Math2.0123002Computer5.0123003English3.0
选课表(SC)
学号(SC_Sno)课程号(SC_Cno)成绩(SC_Score)201500112300186201500112300369201500212300277201500212300399201500312300198201500312300295
2 请编程实现以下功能:
(1) createTable(String tableName, String[] fields)
创建表,参数tableName为表的名称,字符串数组fields为存储记录各个字段名称的数组。要求当HBase已经存在名为tableName的表的时候,先删除原有的表,然后再创建新的表。
package Main;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.ColumnFamilyDescriptor;
import org.apache.hadoop.hbase.client.ColumnFamilyDescriptorBuilder;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.TableDescriptorBuilder;
import org.apache.hadoop.hbase.util.Bytes;
import java.io.IOException;
public class main {
public static Configuration configuration;
public static Connection connection;
public static Admin admin;
public static void init(){//建立连接
configuration = HBaseConfiguration.create();
configuration.set("hbase.rootdir","hdfs://127.0.0.1:8020/hbase");
try{
connection = ConnectionFactory.createConnection(configuration);
admin = connection.getAdmin();
}catch(IOException e){
e.printStackTrace();
}
}
public static void close(){//关闭连接
try{
if(admin != null){
admin.close();
}
if(connection != null){
connection.close();
}
}catch(IOException e){
e.printStackTrace();
}
}
public static void createTable(String tableName,String[] fields) throws IOException{
init();
TableName tablename = TableName.valueOf(tableName);//定义表名
if(admin.tableExists(tablename)){
System.out.println("table is exists!");
admin.disableTable(tablename);
admin.deleteTable(tablename);
}
TableDescriptorBuilder tableDescriptor = TableDescriptorBuilder.newBuilder(tablename);
for(int i=0;i ColumnFamilyDescriptor family = ColumnFamilyDescriptorBuilder.newBuilder(Bytes.toBytes(fields[i])).build(); tableDescriptor.setColumnFamily(family); } admin.createTable(tableDescriptor.build()); close(); } public static void main(String[] args){ String[] fields = {"id","score"}; try{ createTable("test",fields); }catch(IOException e){ e.printStackTrace(); } } } 运行结果 (2)addRecord(String tableName, String row, String[] fields, String[] values) 向表tableName、行row(用S_Name表示)和字符串数组fields指定的单元格中添加对应的数据values。其中,fields中每个元素如果对应的列族下还有相应的列限定符的话,用“columnFamily:column”表示。例如,同时向“Math”、“Computer Science”、“English”三列添加成绩时,字符串数组fields为{“Score:Math”, ”Score:Computer Science”, ”Score:English”},数组values存储这三门课的成绩。 package Main; import java.io.IOException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.hbase.HBaseConfiguration; 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.client.Put; import org.apache.hadoop.hbase.client.Table; public class main { public static Configuration configuration; public static Connection connection; public static Admin admin; public static void init(){//建立连接 configuration = HBaseConfiguration.create(); configuration.set("hbase.rootdir","hdfs://127.0.0.1:8020/hbase"); try{ connection = ConnectionFactory.createConnection(configuration); admin = connection.getAdmin(); }catch(IOException e){ e.printStackTrace(); } } public static void close(){//关闭连接 try{ if(admin != null){ admin.close(); } if(connection != null){ connection.close(); } }catch(IOException e){ e.printStackTrace(); } } public static void addRecord(String tableName,String row,String[] fields,String[] values) throws IOException{ init();//连接Hbase Table table = connection.getTable(TableName.valueOf(tableName));//表连接 Put put = new Put(row.getBytes());//创建put对象 for(int i=0;i String[] cols = fields[i].split(":"); if(cols.length == 1){ put.addColumn(fields[i].getBytes(),"".getBytes(),values[i].getBytes()); } else{ put.addColumn(cols[0].getBytes(),cols[1].getBytes(),values[i].getBytes()); } table.put(put);//向表中添加数据 } close();//关闭连接 } public static void main(String[] args){ String[] fields = {"Score:Math","Score:Computer Science","Score:English"}; String[] values = {"85","80","90"}; try{ addRecord("grade","S_Name",fields,values); }catch(IOException e){ e.printStackTrace(); } } } 3)scanColumn(String tableName, String column) 浏览表tableName某一列的数据,如果某一行记录中该列数据不存在,则返回null。要求当参数column为某一列族名称时,如果底下有若干个列限定符,则要列出每个列限定符代表的列的数据;当参数column为某一列具体名称(例如“Score:Math”)时,只需要列出该列 package Main; import java.io.IOException; import org.apache.hadoop.conf.Configuration; 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.Admin; import org.apache.hadoop.hbase.client.Connection; import org.apache.hadoop.hbase.client.ConnectionFactory; import org.apache.hadoop.hbase.client.Result; import org.apache.hadoop.hbase.client.ResultScanner; import org.apache.hadoop.hbase.client.Scan; import org.apache.hadoop.hbase.client.Table; import org.apache.hadoop.hbase.util.Bytes; public class main { public static Configuration configuration; public static Connection connection; public static Admin admin; public static void init(){//建立连接 configuration = HBaseConfiguration.create(); configuration.set("hbase.rootdir","hdfs://localhost:8020/hbase"); try{ connection = ConnectionFactory.createConnection(configuration); admin = connection.getAdmin(); }catch(IOException e){ e.printStackTrace(); } } public static void close(){//关闭连接 try{ if(admin != null){ admin.close(); } if(connection != null){ connection.close(); } }catch(IOException e){ e.printStackTrace(); } } public static void showResult(Result result){ Cell[] cells = result.rawCells(); for(int i=0;i System.out.println("RowName:"+new String(CellUtil.cloneRow(cells[i])));//打印行键 System.out.println("ColumnName:"+new String(CellUtil.cloneQualifier(cells[i])));//打印列名 System.out.println("Value:"+new String(CellUtil.cloneValue(cells[i])));//打印值 System.out.println("Column Family:"+new String(CellUtil.cloneFamily(cells[i])));//打印列簇 System.out.println(); } } public static void scanColumn(String tableName,String column){ init(); try { Table table = connection.getTable(TableName.valueOf(tableName)); Scan scan = new Scan(); scan.addFamily(Bytes.toBytes(column)); ResultScanner scanner = table.getScanner(scan); for(Result result = scanner.next();result != null;result = scanner.next()){ showResult(result); } } catch (IOException e) { e.printStackTrace(); } finally{ close(); } } public static void main(String[] args){ scanColumn("test","id"); } } 运行结果 (4)modifyData(String tableName, String row, String column) 修改表tableName,行row(可以用学生姓名S_Name表示),列column指定的单元格的数据。 package Main; import java.io.IOException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.hbase.HBaseConfiguration; 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.client.Put; import org.apache.hadoop.hbase.client.Table; public class main{ public static Configuration configuration; public static Connection connection; public static Admin admin; public static void init(){//建立连接 configuration = HBaseConfiguration.create(); configuration.set("hbase.rootdir","hdfs://localhost:9000/hbase"); try{ connection = ConnectionFactory.createConnection(configuration); admin = connection.getAdmin(); }catch(IOException e){ e.printStackTrace(); } } public static void close(){//关闭连接 try{ if(admin != null){ admin.close(); } if(connection != null){ connection.close(); } }catch(IOException e){ e.printStackTrace(); } } public static void modifyData(String tableName,String row,String column,String value) throws IOException{ init(); Table table = connection.getTable(TableName.valueOf(tableName)); Put put = new Put(row.getBytes()); String[] cols = column.split(":"); if(cols.length == 1){ put.addColumn(column.getBytes(),"".getBytes(), value.getBytes()); } else{ put.addColumn(cols[0].getBytes(), cols[1].getBytes(), value.getBytes()); } table.put(put); close(); } public static void main(String[] args){ try{ modifyData("test","1","score","100"); } catch(Exception e){ e.printStackTrace(); } } } 运行结果 此时row为1的score已经改为100 (5)deleteRow(String tableName, String row) 删除表tableName中row指定的行的记录。 package Main; import java.io.IOException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.hbase.HBaseConfiguration; 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.client.Delete; import org.apache.hadoop.hbase.client.Table; public class main { public static Configuration configuration; public static Connection connection; public static Admin admin; public static void init(){//建立连接 configuration = HBaseConfiguration.create(); configuration.set("hbase.rootdir","hdfs://localhost:8020/hbase"); try{ connection = ConnectionFactory.createConnection(configuration); admin = connection.getAdmin(); }catch(IOException e){ e.printStackTrace(); } } public static void close(){//关闭连接 try{ if(admin != null){ admin.close(); } if(connection != null){ connection.close(); } }catch(IOException e){ e.printStackTrace(); } } public static void deleteRow(String tableName,String row) throws IOException{ init(); Table table = connection.getTable(TableName.valueOf(tableName)); Delete delete = new Delete(row.getBytes()); table.delete(delete); close(); } public static void main(String[] args){ try{ deleteRow("test","2"); }catch(Exception e){ e.printStackTrace(); } } } 此时row=2已经被删除 出现的问题 问题一 在安装hbase后master-status用浏览器无法打开,而此时Hmaster和HregionServer,QuorumPeerMain已经启动 问题二 解决方法 问题一 在连接Hbase后使用list命令后发现如下 发现原因是因为我启动Hbase使用的不是hbase自带的zookeeper,而是自己独立安装的,在hbase-env.sh下增加 export HBASE_DISABLE_HADOOP_CLASSPATH_LOOKUP="true" 重新启动后 问题解决 问题二 发现是maven导入包出现问题,再将hbase-client包换为2.5.3后问题解决 参考链接
发表评论