29
实验3
熟悉常用的HBase操作
1.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。
2.实验平台
（1）操作系统：Linux（建议Ubuntu16.04或Ubuntu18.04）；
（2）Hadoop版本：3.1.3；
（3）HBase版本：2.2.2；
（4）JDK版本：1.8；
（5）Java IDE：Eclipse。
3. 实验步骤
（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；
（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；
添加
put 'Student','s000','S_Name','Huangkaiyu'
删除
delete 'Student','s000','S_Name'
（4） 清空指定的表的所有记录数据；
truncate 'Student'
（5） 统计表的行数。
count 'Student'
（二）HBase数据库操作
1. 现有以下关系型数据库中的表和数据（见表14-3到表14-5），要求将其转换为适合于HBase存储的表并插入数据：
表14-3 学生表（Student）
|
学号（S_No） |
姓名（S_Name） |
性别（S_Sex） |
年龄（S_Age） |
|
2015001 |
Zhangsan |
male |
23 |
|
2015002 |
Mary |
female |
22 |
|
2015003 |
Lisi |
male |
24 |
create 'Student','S_No','S_Name','S_Sex','S_Age'
put 'Student','s001','S_No','2015001'
put 'Student','s001','S_Name','Zhangsan'
put 'Student','s001','S_Sex','male'
put 'Student','s001','S_Age','23'
put 'Student','s002','S_No','2015002'
put 'Student','s002','S_Name','Mary'
put 'Student','s002','S_Sex','female'
put 'Student','s002','S_Age','22'
put 'Student','s003','S_No','2015003'
put 'Student','s003','S_Name','Lisi'
put 'Student','s003','S_Sex','male'
put 'Student','s003','S_Age','24'
表14-4 课程表（Course）
|
课程号（C_No） |
课程名（C_Name） |
学分（C_Credit） |
|
123001 |
Math |
2.0 |
|
123002 |
Computer Science |
5.0 |
|
123003 |
English |
3.0 |
create 'Course','C_No','C_Name','C_Credit'
put 'Course','c001','C_No','123001'
put 'Course','c001','C_Name','Math'
put 'Course','c001','C_Credit','2.0'
put 'Course','c002','C_No','123002'
put 'Course','c002','C_Name','Computer'
put 'Course','c002','C_Credit','5.0'
put 'Course','c003','C_No','123003'
put 'Course','c003','C_Name','English'
put 'Course','c003','C_Credit','3.0'
表14-5 选课表（SC）
|
学号（SC_Sno） |
课程号（SC_Cno） |
成绩（SC_Score） |
|
2015001 |
123001 |
86 |
|
2015001 |
123003 |
69 |
|
2015002 |
123002 |
77 |
|
2015002 |
123003 |
99 |
|
2015003 |
123001 |
98 |
|
2015003 |
123002 |
95 |
put 'SC','sc001','SC_Sno','2015001'
put 'SC','sc001','SC_Cno','123001'
put 'SC','sc001','SC_Score','86'
put 'SC','sc002','SC_Sno','2015001'
put 'SC','sc002','SC_Cno','123003'
put 'SC','sc002','SC_Score','69'
put 'SC','sc003','SC_Sno','2015002'
put 'SC','sc003','SC_Cno','123002'
put 'SC','sc003','SC_Score','77'
put 'SC','sc004','SC_Sno','2015002'
put 'SC','sc004','SC_Cno','123003'
put 'SC','sc004','SC_Score','99'
put 'SC','sc005','SC_Sno','2015003'
put 'SC','sc005','SC_Cno','123001'
put 'SC','sc005','SC_Score','98'
put 'SC','sc006','SC_Sno','2015003'
put 'SC','sc006','SC_Cno','123002'
put 'SC','sc006','SC_Score','95'
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。
import org.apache.hadoop.conf.Configuration;
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 java.io.IOException;
public class CreateTable {
public static Configuration configuration;
public static Connection connection;
public static Admin admin;
public static void createTable(String tableName, String[] fields) throws IOException {
init();
TableName tablename = TableName.valueOf(tableName);
if (admin.tableExists(tablename)) {
System.out.println("table is exists!");
admin.disableTable(tablename);
admin.deleteTable(tablename);
}
HTableDescriptor hTableDescriptor = new HTableDescriptor(tablename);
for (String str : fields) {
HColumnDescriptor hColumnDescriptor = new HColumnDescriptor(str);
hTableDescriptor.addFamily(hColumnDescriptor);
}
admin.createTable(hTableDescriptor);
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 main(String[] args) {
String[] fields = {"Score"};
try {
createTable("person", fields);
} catch (IOException e) {
e.printStackTrace();
}
}
}
（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。
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import java.io.IOException;
public class AddRecord {
public static Configuration configuration;
public static Connection connection;
public static Admin admin;
public static void addRecord(String tableName, String row, String[] fields, String[] values) throws IOException {
init();
Table table = connection.getTable(TableName.valueOf(tableName));
for (int i = 0; i != fields.length; i++) {
Put put = new Put(row.getBytes());
String[] cols = fields[i].split(":");
put.addColumn(cols[0].getBytes(), cols[1].getBytes(), values[i].getBytes());
table.put(put);
}
table.close();
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 main(String[] args) {
String[] fields = {"Score:Math", "Score:Computer Science", "Score:English"};
String[] values = {"99", "80", "100"};
try {
addRecord("person", "Score", 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，只需要列出该列的数据。
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.*;
import org.apache.hadoop.hbase.util.Bytes;
import java.io.IOException;
public class ScanColumn {
public static Configuration configuration;
public static Connection connection;
public static Admin admin;
public static void scanColumn(String tableName, String column) throws IOException {
init();
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()) {
showCell(result);
}
table.close();
close();
}
public static void showCell(Result result) {
Cell[] cells = result.rawCells();
for (Cell cell : cells) {
System.out.println("RowName:" + new String(CellUtil.cloneRow(cell)) + " ");
System.out.println("Timetamp:" + cell.getTimestamp() + " ");
System.out.println("column Family:" + new String(CellUtil.cloneFamily(cell)) + " ");
System.out.println("row Name:" + new String(CellUtil.cloneQualifier(cell)) + " ");
System.out.println("value:" + new String(CellUtil.cloneValue(cell)) + " ");
}
}
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 main(String[] args) {
try {
scanColumn("person", "Score");
} catch (IOException e) {
e.printStackTrace();
}
}
}
（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。
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 java.io.IOException;
public class ModifyData {
public static long ts;
public static Configuration configuration;
public static Connection connection;
public static Admin admin;
public static void modifyData(String tableName, String row, String column, String val) throws IOException {
init();
Table table = connection.getTable(TableName.valueOf(tableName));
Put put = new Put(row.getBytes());
Scan scan = new Scan();
ResultScanner resultScanner = table.getScanner(scan);
for (Result r : resultScanner) {
for (Cell cell : r.getColumnCells(row.getBytes(), column.getBytes())) {
ts = cell.getTimestamp();
}
}
put.addColumn(row.getBytes(), column.getBytes(), ts, val.getBytes());
table.put(put);
table.close();
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 main(String[] args) {
try {
modifyData("person", "Score", "Math", "100");
} catch (IOException e) {
e.printStackTrace();
}
}
}
（5）deleteRow(String tableName, String row)
删除表tableName中row指定的行的记录。
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 java.io.IOException;
public class ModifyData {
public static long ts;
public static Configuration configuration;
public static Connection connection;
public static Admin admin;
public static void modifyData(String tableName, String row, String column, String val) throws IOException {
init();
Table table = connection.getTable(TableName.valueOf(tableName));
Put put = new Put(row.getBytes());
Scan scan = new Scan();
ResultScanner resultScanner = table.getScanner(scan);
for (Result r : resultScanner) {
for (Cell cell : r.getColumnCells(row.getBytes(), column.getBytes())) {
ts = cell.getTimestamp();
}
}
put.addColumn(row.getBytes(), column.getBytes(), ts, val.getBytes());
table.put(put);
table.close();
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 main(String[] args) {
try {
modifyData("person", "Score", "Math", "100");
} catch (IOException e) {
e.printStackTrace();
}
}
}
浙公网安备 33010602011771号