云计算于大数据入门实验三——熟悉常用的 HBase 操作
实验目的
理解HBase在Hadoop体系结构中的角色
熟练使用HBase操作常用的shell命令
熟悉HBase操作常用的Java API
实验要求
-
保存程序,并自行存档
-
最终的程序都必须经过测试,验证是正确的
-
按照实验报告格式,认真记录实验过程及结果,回答实验报告中的问题。实验报告模板在学习通的资料里面下载。学生提交的实验报告需转换成PDF文件提交
实验步骤
Hbase 常用命令
- 在 Hbase 中建表
create 'student','Sname','Ssex','Sage','Sdept','course'
- 查看表结构
describe 'student'
- 添加数据
- put 'student', '95001','Sname','LiYing'
- put 'student','95001','course:math','80'
- 查看数据
get 'student','95001'
- 删除数据
- delete 'student','95001','Sname:firstName'
- deleteall 'student','95001'
- 删除表
- disable 'student' #让表不可用
- drop 'student' #删除表
- 查询历史数据
- create 'teacher',{NAME=>'username',VERSIONS=>5}
- put 'teacher','91001','username','Mary'
- put 'teacher','91001','username','Mary1'
- put 'teacher','91001','username','Mary2'
- put 'teacher','91001','username','Mary3'
- put 'teacher','91001','username','Mary4'
- put 'teacher','91001','username','Mary5'
- get 'teacher','91001',{COLUMN=>'username',VERSIONS=>3}
- 退出 HBase
exit
编程实践
例子:创建表,插入数据,查看表中数据
- import org.apache.hadoop.conf.Configuration;
- import org.apache.hadoop.hbase.*;
- import org.apache.hadoop.hbase.client.*;
- import org.apache.hadoop.hbase.util.Bytes;
-
- import java.io.IOException;
- public class ExampleForHBase {
- public static Configuration configuration;
- public static Connection connection;
- public static Admin admin;
- public static void main(String[] args)throws IOException{
- init(); //主要操作就是为了连接到数据库hbase
- createTable("student",new String[]{"score"}); //创建表,shell命令:create '表名','列族名1','列族名2','列族名3' ...
- insertData("student","zhangsan","score","English","69"); //shell命令: put 'student','张三','score:English','69'
- insertData("student","zhangsan","score","Math","86");
- insertData("student","zhangsan","score","Computer","77");
- getData("student", "zhangsan", "score","English");
- close();
- }
-
- public static void init(){
- 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(){
- try{
- if(admin != null){
- admin.close();
- }
- if(null != connection){
- connection.close();
- }
- }catch (IOException e){
- e.printStackTrace();
- }
- }
-
- public static void createTable(String myTableName,String[] colFamily) throws IOException {
- TableName tableName = TableName.valueOf(myTableName);
- if(admin.tableExists(tableName)){
- System.out.println("talbe is exists!");
- }else {
- TableDescriptorBuilder tableDescriptor = TableDescriptorBuilder.newBuilder(tableName);
- for(String str:colFamily){
- ColumnFamilyDescriptor family =
- ColumnFamilyDescriptorBuilder.newBuilder(Bytes.toBytes(str)).build();
- tableDescriptor.setColumnFamily(family);
- }
- admin.createTable(tableDescriptor.build());
- }
- }
-
- public static void insertData(String tableName,String rowKey,String colFamily,String col,String val) throws IOException {
- Table table = connection.getTable(TableName.valueOf(tableName));
- Put put = new Put(rowKey.getBytes());
- put.addColumn(colFamily.getBytes(),col.getBytes(), val.getBytes());
- table.put(put);
- table.close();
- }
-
- public static void getData(String tableName,String rowKey,String colFamily, String col)throws IOException{
- Table table = connection.getTable(TableName.valueOf(tableName));
- Get get = new Get(rowKey.getBytes());
- get.addColumn(colFamily.getBytes(),col.getBytes());
- Result result = table.get(get);
- System.out.println(new String(result.getValue(colFamily.getBytes(),col==null?null:col.getBytes())));
- table.close();
- }
- }
实验三 熟悉常用的HBase 操作
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:
-
列出 HBase 所有的表的相关信息,例如表名;
-
在终端打印出指定的表的所有记录数据;
-
向已经创建好的表添加和删除指定的列族或列;
-
清空指定的表的所有记录数据;
-
统计表的行数。
列出 HBase 所有的表的相关信息,例如表名:
- /**
- * 同样是正常的建立 数据库连接,执行操作,然后最后关闭连接
- * 重点是:HTableDescriptor hTableDescriptors[] = admin.listTables(); 获取到 表格列表,然后遍历
- */
- import java.io.IOException;
- import org.apache.hadoop.conf.Configuration;
- import org.apache.hadoop.hbase.*;
- import org.apache.hadoop.hbase.client.*;
- import java.io.IOException;
- public class Test_1 {
- public static Configuration configuration;
- public static Connection connection;
- public static Admin admin;
- /**
- * 建立连接
- */
- public static void init() {
- configuration = HBaseConfiguration.create();
- configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
- try {
- connection = ConnectionFactory.createConnection(configuration);
- admin = connection.getAdmin();
- } catch (IOException e) {
- e.printStackTrace();
- }
- }
- /**
- * 关闭连接
- */
- public static void close() {
- try {
- if (admin != null) {
- admin.close();
- }
- if (null != connection) {
- connection.close();
- }
- } catch (IOException e) {
- e.printStackTrace();
- }
-
- }
- /**
- *
- * 查看已有表,通过方法listTables()
- *
- * @throws IOException
- *
- */
- public static void listTables() throws IOException {
- init();
- HTableDescriptor hTableDescriptors[] = admin.listTables();
- for (HTableDescriptor hTableDescriptor : hTableDescriptors) {
- System.out.println(hTableDescriptor.getNameAsString());
- }
- close();
- }
-
- public static void main(String[] args) {
- Test_1 t = new Test_1();
- try {
- System.out.println("以下为Hbase 数据库中所存的表信息");
- t.listTables();
- } catch (IOException e) {
- e.printStackTrace();
- }
- }
- }
在终端打印出指定的表的所有记录数据;
- /**
- * 同样是正常的建立 数据库连接,执行操作,然后最后关闭连接
- * 重点是:
- * Table table = connection.getTable(TableName.valueOf(tableName));获取到表格对象
- * Scan scan = new Scan(); ResultScanner scanner = table.getScanner(scan); 然后通过Scanner对象,获取到ResultScanner扫描结果对象,遍历输出
- */
- import java.io.IOException;
- import org.apache.hadoop.conf.Configuration;
- import org.apache.hadoop.hbase.*;
- import org.apache.hadoop.hbase.client.*;
- import java.io.IOException;
- import java.util.Scanner;
- public class Test_2 {
- public static Configuration configuration;
- public static Connection connection;
- public static Admin admin;
- // 建立连接
- public static void init() {
- configuration = HBaseConfiguration.create();
- configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
- try {
- connection = ConnectionFactory.createConnection(configuration);
- admin = connection.getAdmin();
- } catch (IOException e) {
- e.printStackTrace();
- }
- }
- // 关闭连接
- public static void close() {
- try {
- if (admin != null) {
- admin.close();
- }
- if (null != connection) {
- connection.close();
- }
- } catch (IOException e) {
- e.printStackTrace();
-
- }
- }
- /**
- *
- * 根据表名查找表信息
- *
- */
- public static void getData(String tableName) throws IOException {
- init();
- Table table = connection.getTable(TableName.valueOf(tableName));
- Scan scan = new Scan();
- ResultScanner scanner = table.getScanner(scan);
- for (Result result : scanner)
- {
- showCell((result));
- }
- close();
- }
-
- /**
- *
- * 格式化输出
- *
- * @param result
- *
- */
- public static void showCell(Result result) {
- Cell[] cells = result.rawCells();
- for (Cell cell : cells) {
- System.out.println("RowName(行键):" + new String(CellUtil.cloneRow(cell)) + " ");
- System.out.println("Timetamp(时间戳):" + cell.getTimestamp() + " ");
- System.out.println("column Family(列簇):" + new String(CellUtil.cloneFamily(cell)) + " ");
- System.out.println("column Name(列名):" + new String(CellUtil.cloneQualifier(cell)) + " ");
- System.out.println("value:(值)" + new String(CellUtil.cloneValue(cell)) + " ");
- System.out.println();
- }
- }
- public static void main(String[] args) throws IOException {
- // TODO Auto-generated method stub
- Test_2 t = new Test_2();
- System.out.println("请输入要查看的表名");
- Scanner scan = new Scanner(System.in);
- String tableName = scan.nextLine();
- System.out.println("信息如下:");
- t.getData(tableName);
- }
- }
向已经创建好的表添加和删除指定的列族或列:
- put 'student','95003','Sname','wangjinxuan' (添加列)
-
- put 'student','95003','Sname:nickName','wang' (添加列族)
-
- put 'student','95003','Sname:firstName','jinxuan' (添加列族)
-
- put的反向操作的delete:
-
- delete 'student' ,’95003’,’Sname’
-
- delete 'student' ,’95003’,’Sname:nickName’
-
- deleteall 'student' ,’95003’ (删除整个行记录)
- /**
- * hbase只关注rowkey,column Family(列族),并没有说在创建表的时候指定cq(列限定修饰符)有多少,这也是hbase列式存储的特点,
- * 所以在hbase API中是没有提供delete 一个列下的所有数据的
- *
- * 同样是正常的建立 数据库连接,执行操作,然后最后关闭连接
- * 1,Table table = connection.getTable(TableName.valueOf(tableName)); 先获取到表
- * 2,插入:(① 创建Put对象,② 然后通过方法 addColumn将列、列限定符、值 放到put对象,③ 最后将put对象put到表格)
- * Put put = new Put(rowKey.getBytes());
- * put.addColumn(colFamily.getBytes(), col.getBytes(), val.getBytes());
- * table.put(put);
- * 3,删除:
- * Table table = connection.getTable(TableName.valueOf(tableName)); 同样首先获取到表
- * Delete delete = new Delete(rowKey.getBytes()); //通过传入行键,new一个删除对象
- * //删除对象添加要被删除的列或列族
- * ① 删除指定列族的所有数据(此情况是列族下无列限定符时的情况):delete.addFamily(colFamily.getBytes());
- * ② 删除指定列的数据(此列主要说的是列限定修饰符):delete.addColumn(colFamily.getBytes(), col.getBytes());
- * table.delete(delete); //最后就是表格delete掉 delete对象
- */
- import java.io.IOException;
- import java.util.Scanner;
- 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.Delete;
- import org.apache.hadoop.hbase.client.Put;
- 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;
-
- public class Test_3 {
- public static Configuration configuration;
- public static Connection connection;
- public static Admin admin;
-
- // 建立连接
- public static void init() {
- configuration = HBaseConfiguration.create();
- configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
- try {
- connection = ConnectionFactory.createConnection(configuration);
- admin = connection.getAdmin();
- } catch (IOException e) {
- e.printStackTrace();
- }
- }
-
- // 关闭连接
- public static void close() {
- try {
- if (admin != null) {
- admin.close();
- }
- if (null != connection) {
- connection.close();
- }
- } catch (IOException e) {
- e.printStackTrace();
- }
- }
-
- /**
- * 向某一行的某一列插入数据
- *
- * @param tableName 表名
- * @param rowKey 行键
- * @param colFamily 列族名
- * @param col 列名(如果其列族下没有子列,此参数可为空)
- * @param val 值
- * @throws IOException
- */
- public static void insertRow(String tableName, String rowKey, String colFamily, String col, String val)throws IOException {
- init();
- Table table = connection.getTable(TableName.valueOf(tableName));
- Put put = new Put(rowKey.getBytes());
- put.addColumn(colFamily.getBytes(), col.getBytes(), val.getBytes());
- table.put(put);
- table.close();
- close();
- }
-
- /**
- * 根据表名查找表信息
- */
- public static void getData(String tableName) throws IOException {
- init();
- Table table = connection.getTable(TableName.valueOf(tableName));
- Scan scan = new Scan();
- ResultScanner scanner = table.getScanner(scan);
- for (Result result : scanner) {
- showCell((result));
- }
- close();
- }
- /**
- *
- * 格式化输出
- *
- * @param result
- *
- */
- public static void showCell(Result result) {
- Cell[] cells = result.rawCells();
- for (Cell cell : cells) {
- System.out.println("RowName(行键):" + new String(CellUtil.cloneRow(cell)) + " ");
- System.out.println("Timetamp(时间戳):" + cell.getTimestamp() + " ");
- System.out.println("column Family(列簇):" + new String(CellUtil.cloneFamily(cell)) + " ");
- System.out.println("column Name(列名):" + new String(CellUtil.cloneQualifier(cell)) + " ");
- System.out.println("value:(值)" + new String(CellUtil.cloneValue(cell)) + " ");
- System.out.println();
- }
- }
- /**
- *
- * 删除数据
- *
- * @param tableName 表名
- *
- * @param rowKey 行键
- *
- * @param colFamily 列族名
- *
- * @param col 列名
- *
- * @throws IOException
- *
- */
- public static void deleteRow(String tableName, String rowKey, String colFamily, String col) throws IOException {
- init();
- Table table = connection.getTable(TableName.valueOf(tableName));
- Delete delete = new Delete(rowKey.getBytes());
- if(col == null) {
- //删除指定列族的所有数据(此情况是列族下无列限定符时的情况)
- delete.addFamily(colFamily.getBytes());
- table.delete(delete);
- table.close();
- }else {
- //删除指定列的数据(此列主要说的是列限定修饰符)
- delete.addColumn(colFamily.getBytes(), col.getBytes());
- table.delete(delete);
- table.close();
- }
- close();
- }
-
- public static void main(String[] args) {
- Test_3 t = new Test_3();
- boolean flag = true;
- while (flag){
- System.out.println("------------向已经创建好的表中添加和删除指定的列簇或列--------------------");
- System.out.println(" 请输入您要进行的操作 1- 添加 2-删除 ");
- Scanner scan = new Scanner(System.in);
- String choose1 = scan.nextLine();
- switch (choose1) {
- case "1":
- try {
- //put 'student','95003','Sname','wangjinxuan' (添加列)
- //put 'student','95003','Sname:nickName','wang' (添加列族)
- //put 'student','95003','Sname:firstName','jinxuan' (添加列族)
- // t.insertRow(tableName, rowKey, colFamily, col, val);
- t.insertRow("student", "95003", "Sname",null, "wangjingxuan");
- t.insertRow("student", "95003", "Sname", "nickName", "wang");
- t.insertRow("student", "95003", "Sname", "firstName", "jingxuan");
- System.out.println("插入成功:");
- t.getData(tableName);
- } catch (IOException e) {
- e.getMessage();
- }
- break;
- case "2":
- try {
- System.out.println("----------------------删除前,表的原本信息如下---------------------");
- t.getData(tableName);
- //delete 'student' ,’95003’,’Sname’
- //delete 'student' ,’95003’,’Sname:nickName’
- // t.deleteRow(tableName, rowKey, colFamily, col);
- t.deleteRow("student", "95003", "Sname", "firstName");
- System.out.println("-----------------------删除成功-----------------------------\n");
- System.out.println("---------------------删除后,表的信息如下---------------------");
- t.getData(tableName);
- } catch (IOException e) {
- e.getMessage();
- }
- break;
- }
- System.out.println(" 你要继续操作吗? 是-true 否-false ");
- flag = scan.nextBoolean();
- }
- System.out.println(" 程序已退出! ");
- }
- }
清空指定的表的所有记录数据:
- import java.io.IOException;
- import java.util.Scanner;
- 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.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.client.HBaseAdmin;
- 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 Test_4 {
- public static Configuration configuration;
- public static Connection connection;
- public static Admin admin;
- // 建立连接
- public static void init() {
- configuration = HBaseConfiguration.create();
- configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
- try {
- connection = ConnectionFactory.createConnection(configuration);
- admin = connection.getAdmin();
- } catch (IOException e) {
- e.printStackTrace();
- }
- }
- // 关闭连接
- public static void close() {
- try {
- if (admin != null) {
- admin.close();
- }
- if (null != connection) {
- connection.close();
- }
- } catch (IOException e) {
- e.printStackTrace();
- }
- }
- /**
- *
- * 清空制定的表的所有记录数据
- *
- * @param args
- *
- * @throws IOException
- *
- */
- public static void clearRows(String tableName) throws IOException {
- init();
- HBaseAdmin admin1 = new HBaseAdmin(configuration);
- // 读取了之前表的表名 列簇等信息,然后再进行删除操作。
- HTableDescriptor tDescriptor = admin1.getTableDescriptor(Bytes.toBytes(tableName));
- // 总思想是先将原表结构保留下来,然后进行删除,再重新依据保存的信息重新创建表。
- TableName tablename = TableName.valueOf(tableName);
- // 删除表
- admin.disableTable(tablename);
- admin.deleteTable(tablename);
- // 重新建表
- admin.createTable(tDescriptor);
- close();
- }
- /**
- *
- * 根据表名查找表信息
- *
- */
- public static void getData(String tableName) throws IOException {
- init();
- Table table = connection.getTable(TableName.valueOf(tableName));
- Scan scan = new Scan();
- ResultScanner scanner = table.getScanner(scan);
- for (Result result : scanner){
- showCell((result));
- }
- close();
- }
-
- /**
- *
- * 格式化输出
- *
- * @param result
- *
- */
- public static void showCell(Result result) {
- Cell[] cells = result.rawCells();
- for (Cell cell : cells) {
- System.out.println("RowName(行键):" + new String(CellUtil.cloneRow(cell)) + " ");
- System.out.println("Timetamp(时间戳):" + cell.getTimestamp() + " ");
- System.out.println("column Family(列簇):" + new String(CellUtil.cloneFamily(cell)) + " ");
- System.out.println("column Name(列名):" + new String(CellUtil.cloneQualifier(cell)) + " ");
- System.out.println("value:(值)" + new String(CellUtil.cloneValue(cell)) + " ");
- System.out.println();
- }
- }
-
- public static void main(String[] args) {
- Test_4 test_4 = new Test_4();
- Scanner scan = new Scanner(System.in);
- System.out.println("请输入要清空的表名");
- String tableName = scan.nextLine();
- try {
- System.out.println("表原来的信息:");
- test_4.getData(tableName);
- test_4.clearRows(tableName);
- System.out.println("表已清空:");
- } catch (IOException e) {
- e.printStackTrace();
- }
- }
- }
统计表的行数:
- import java.io.IOException;
- import java.util.Scanner;
- 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.Result;
- import org.apache.hadoop.hbase.client.ResultScanner;
- import org.apache.hadoop.hbase.client.Scan;
- import org.apache.hadoop.hbase.client.Table;
- public class Test_5 {
- public static Configuration configuration;
- public static Connection connection;
- public static Admin admin;
- //建立连接
- public static void init() {
- configuration = HBaseConfiguration.create();
- configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
- try {
- connection = ConnectionFactory.createConnection(configuration);
- admin = connection.getAdmin();
- } catch (IOException e) {
- e.printStackTrace();
- }
- }
- // 关闭连接
- public static void close() {
- try {
- if (admin != null) {
- admin.close();
- }
- if (null != connection) {
- connection.close();
- }
- } catch (IOException e) {
- e.printStackTrace();
- }
- }
-
- public static void countRows(String tableName) throws IOException{
- init();
- Table table = connection.getTable(TableName.valueOf(tableName));
- Scan scan = new Scan();
- ResultScanner scanner = table.getScanner(scan);
- int num = 0;
- for (Result result = scanner.next(); result != null; result = scanner.next()){
- num++;
- }
- System.out.println("行数:" + num);
- scanner.close();
- close();
- }
- public static void main(String[] args) throws IOException {
- Test_5 test_5 = new Test_5();
- Scanner scan = new Scanner(System.in);
- System.out.println("请输入要统计行数的表名");
- String tableName = scan.nextLine();
- test_5.countRows(tableName);
- }
- }