java操作HBase

创建一个学生信息表，用来存储学生的姓名（姓名作为行键，且假设姓名不会重复）以及考试成绩，其中考试成绩（score）是一个列族，存储了各个科目的考试成绩。然后向student中添加数据

1、HBase依赖

<dependency>
	<groupId>org.apache.hbase</groupId>
	<artifactId>hbase-server</artifactId>
	<version>2.2.0</version>
</dependency>
<dependency>
	<groupId>org.apache.hbase</groupId>
	<artifactId>hbase-client</artifactId>
	<version>2.2.0</version>
</dependency>

2、HBase数据源

package com.example.demo.config;
 
import com.example.demo.service.ICodeService;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.ApplicationArguments;
import org.springframework.boot.ApplicationRunner;
import org.springframework.core.annotation.Order;
import org.springframework.stereotype.Component;
 
import java.util.HashMap;
import java.util.List;
import java.util.Map;
 
@Component
@Order(1) 
public class NmsHBaseSource implements ApplicationRunner {
 
	// 管理HBase的配置信息
    public static Configuration conf;
	// 管理HBase的连接
    public static Connection conn;
	// 管理HBase数据库的连接
    public static Admin admin;
 
    @Override
    public void run(ApplicationArguments args) throws Exception {
		conf = HBaseConfiguration.create();
        System.setProperty("HADOOP_USER_NAME", "hadoop");
        conf.set("HADOOP_USER_NAME", "hadoop");
        conf.set("hbase.root.dir", "hdfs://master:9000/hbase");
        conf.set("hbase.zookeeper.quorum", "master");//配置Zookeeper的ip地址
        conf.set("hbase.zookeeper.property.clientPort", "2181");//配置zookeeper的端口
 
        conn = ConnectionFactory.createConnection(conf);
        admin = conn.getAdmin();
    }
	
	 /**
     * 关闭所有连接
     *
     * @throws IOException 可能出现的异常
     */
    public static void close() throws IOException {
        if (admin != null)
            admin.close();
        if (conn != null)
            conn.close();
    }
	
	/**
     * 创建表
     * @param myTableName 表名
     * @param colFamily 列族名的数组
     * @throws IOException 可能出现的异常
     */
    public static void createTable(String myTableName, String[] colFamily) throws IOException {
        TableName tableName = TableName.valueOf(myTableName);
        if (admin.tableExists(tableName)) {
            logger.info(myTableName + "表已经存在");
        } else {
            //HTableDescriptor hTableDescriptor = new HTableDescriptor(tableName);
            //for (String str : colFamily) {
               // HColumnDescriptor hColumnDescriptor = new HColumnDescriptor(str);
               // hTableDescriptor.addFamily(hColumnDescriptor);
            //}
            //admin.createTable(hTableDescriptor);
 
            TableDescriptorBuilder tableDescriptor = TableDescriptorBuilder.newBuilder(tableName);    
            for (String str : colFamily) {
	            ColumnFamilyDescriptor columnFamily = ColumnFamilyDescriptorBuilder.newBuilder(Bytes.toBytes(str)).build();// 构建列族对象                 
	            tableDescriptor.setColumnFamily(columnFamily); // 设置列族
            }
            admin.createTable(tableDescriptor.build()); // 创建表
 
            
        }
    }
	
	 /**
     * 添加数据
     * @param tableName 表名
     * @param rowkey 行键
     * @param colFamily 列族
     * @param col 列
     * @param value 值
     * @throws IOException 可能出现的异常
     */
    public static void insertData(String tableName,String rowkey,String colFamily,String col,String value) throws IOException {
        Table table = conn.getTable(TableName.valueOf(tableName));
        Put put = new Put(rowkey.getBytes());
        put.addColumn(colFamily.getBytes(),col.getBytes(),value.getBytes());
        table.put(put);
        table.close();
    }
	
	/**
     * 根据行键删除数据
     * @param tableName 表名
     * @param rowkey 行键
     * @throws IOException 可能出现的异常
     */
    public static void deleteData(String tableName,String rowkey) throws IOException {
        Table table = conn.getTable(TableName.valueOf(tableName));
        Delete delete = new Delete(rowkey.getBytes());
        table.delete(delete);
        table.close();
    }
 
    /**
     * 获取数据
     * @param tableName 表名
     * @param rowkey 行键
     * @param colFamily 列族
     * @param col 列
     * @throws IOException 可能出现的异常
     */
    public static void getData(String tableName,String rowkey,String colFamily,String col) throws IOException {
        Table table = conn.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.getBytes())));
        table.close();
    }
 
    public static void main(String[] args) throws IOException {
        init();
        createTable("student",new String[]{"score"});
        insertData("student","zhangsan","score","English","69");
        insertData("student","zhangsan","score","Math","86");
        insertData("student","zhangsan","score","Computer","77");
        getData("student","zhangsan","score","Computer");
        close();
    }
}

3、Hbase过滤器查询

过滤器可以分为两种：比较过滤器和专用过滤器

比较过滤器 

LESS —— 小于

LESS_OR_EQUAL —— 小于等于

EQUAL —— 等于

NOT_EQUAL —— 不等于

GREATER_OR_EQUAL —— 大于等于

GREATER —— 大于

NO_OP —— 排除所有

专用过滤器

BinaryComparator —— 匹配完整字节数组，Bytes.compareTo(byte[])

BinaryPrefixComparator —— 匹配字节数组前缀
NullComparator —— 判断给定的是否为空
BitComparator —— 按位比较
RegexStringComparator —— 提供一个正则的比较器，仅支持 EQUAL 和非EQUAL
SubstringComparator —— 判断提供的子串是否出现在value中

• 3.1、ResultScanner结果处理handleResultScanner

/**
 *	ResultScanner结果解析
 */
public void handleResultScanner(ResultScanner scanner) throws IOException {
	//因为ResultScanner类继承了迭代器
	//使用增强for循环遍历
	for (Result rs : scanner) {
	String id = Bytes.toString(rs.getRow());
	System.out.println("当前行的rowkey为：" + id);
	//继续增强for循环得到每一行中的每一个单元格（列）
	//获取一行中的所有单元格
	for (Cell cell : rs.listCells()) {
		//获取该单元格属于的列簇
		String family = Bytes.toString(CellUtil.cloneFamily(cell));
		//获取该单元格的列名
		String colName = Bytes.toString(CellUtil.cloneQualifier(cell));
		//获取该单元格的列值
		String value = Bytes.toString(CellUtil.cloneValue(cell));
		System.out.println(family + ":" + colName + "的值为：" + value);
	}
​
	String name = Bytes.toString(rs.getValue("info".getBytes(), "name".getBytes()));
	String age = Bytes.toString(rs.getValue("info".getBytes(), "age".getBytes()));
	String gender = Bytes.toString(rs.getValue("info".getBytes(), "gender".getBytes()));
	String clazz = Bytes.toString(rs.getValue("info".getBytes(), "clazz".getBytes()));
	System.out.println("学号：" + id + ",姓名：" + name + ",年龄：" + age + ",性别：" + gender + ",班级：" + clazz);
	
}

3.2、rowKey过滤器RowFilter

/**
 *  行键过滤器
 *  通过RowFilter与BinaryComparator过滤比rowKey 1500100010小的所有值出来
 */
@Test
public void RowFilter1(){
	try {
		//获取表的实例
        TableName students = TableName.valueOf("students");
        Table studentTable = conn.getTable(students);
​
		BinaryComparator binaryComparator = new BinaryComparator("1500100010".getBytes());
​
		//创建一个行键过滤器的对象
		RowFilter rowFilter = new RowFilter(CompareOperator.LESS, binaryComparator);
​
		Scan scan = new Scan();
		scan.setFilter(rowFilter);
​
		ResultScanner scanner = studentTable.getScanner(scan);
		handleResultScanner(scanner);
​
	} catch (IOException e) {
		e.printStackTrace();
	}
}

3.3、列族过滤器FamilyFilter

/**
 * 	通过FamilyFilter与SubstringComparator查询列簇名包含in的所有列簇下面的数据
 */
@Test
public void FamilyFilter1(){
	try {
		//获取表的实例
		TableName students = TableName.valueOf("students");
        Table studentTable = conn.getTable(students);
​
		//创建一个比较器对象
		//只要列簇名中包含了in，就把该列簇下的所有列查询出来
		SubstringComparator substringComparator = new SubstringComparator("in");
​
		//创建列簇过滤器
		FamilyFilter familyFilter = new FamilyFilter(CompareOperator.EQUAL, substringComparator);
​
		Scan scan = new Scan();
		scan.setFilter(familyFilter);
​
		//获取数据
		ResultScanner scanner = studentTable.getScanner(scan);
		handleResultScanner(scanner);
​
​
	} catch (IOException e) {
		e.printStackTrace();
	}
}
 
/**
 *	通过FamilyFilter与 BinaryPrefixComparator 过滤出列簇以i开头的列簇下的所有数据
 *
 */
@Test
public void FamilyFilter2(){
	try {
		//获取表的实例
		TableName students = TableName.valueOf("students");
        Table studentTable = conn.getTable(students);
​
		//创建前缀比较器
		BinaryPrefixComparator binaryPrefixComparator = new BinaryPrefixComparator("i".getBytes());
​
		//创建列簇过滤器
		FamilyFilter familyFilter = new FamilyFilter(CompareOperator.EQUAL, binaryPrefixComparator);
​
		Scan scan = new Scan();
		scan.setFilter(familyFilter);
​
		ResultScanner scanner = studentTable.getScanner(scan);
		handleResultScanner(scanner);
​
	} catch (IOException e) {
		e.printStackTrace();
	}
}

3.4、列过滤器QualifierFilter

/**
 * 通过QualifierFilter与SubstringComparator查询列名包含ge的列的值
 *
 */
@Test
public void QualifierFilter1(){
	try {
		//获取表的实例
		TableName students = TableName.valueOf("students");
        Table studentTable = conn.getTable(students);
​
		//创建包含比较器
		//age
		//gender
		SubstringComparator substringComparator = new SubstringComparator("ge");
​
		//创建一个列过滤器
		QualifierFilter qualifierFilter = new QualifierFilter(CompareOperator.EQUAL, substringComparator);
​
		Scan scan = new Scan();
		scan.setFilter(qualifierFilter);
​
		ResultScanner scanner = studentTable.getScanner(scan);
		handleResultScanner(scanner);
​
​
	} catch (IOException e) {
		e.printStackTrace();
	}
}
 
/**
 *
 * 通过QualifierFilter与SubstringComparator查询列名包含ge的列的值
 */
@Test
public void QualifierFilter2(){
	try {
		//获取表的实例
		TableName students = TableName.valueOf("students");
        Table studentTable = conn.getTable(students);
​
		SubstringComparator substringComparator = new SubstringComparator("am");
​
		//创建列过滤器
		QualifierFilter qualifierFilter = new QualifierFilter(CompareOperator.EQUAL, substringComparator);
​
		Scan scan = new Scan();
		scan.setFilter(qualifierFilter);
​
		ResultScanner scanner = studentTable.getScanner(scan);
		handleResultScanner(scanner);
​
	} catch (IOException e) {
		e.printStackTrace();
	}
}

3.5、列值过滤器ValueFilter

/**
 *	通过ValueFilter与BinaryPrefixComparator过滤出所有的cell中值以 "张" 开头的学生
 */
@Test
public void ValueFilter1() {
	try {
		//获取表的实例
		TableName students = TableName.valueOf("students");
        Table studentTable = conn.getTable(students);
​
		//创建前缀比较器
		BinaryPrefixComparator binaryPrefixComparator = new BinaryPrefixComparator("张".getBytes());
​
		//创建列值过滤器的对象
		ValueFilter valueFilter = new ValueFilter(CompareOperator.EQUAL, binaryPrefixComparator);
​
		Scan scan = new Scan();
		scan.setFilter(valueFilter);
​
		ResultScanner scanner = studentTable.getScanner(scan);
​
		//因为ResultScanner类继承了迭代器
		//使用增强for循环遍历
//            for (Result rs : scanner) {
//                String id = Bytes.toString(rs.getRow());
//                System.out.println("当前行的rowkey为：" + id);
//                //继续增强for循环得到每一行中的每一个单元格（列）
//                //获取一行中的所有单元格
//                for (Cell cell : rs.listCells()) {
//                    //获取该单元格属于的列簇
//                    String family = Bytes.toString(CellUtil.cloneFamily(cell));
//                    //获取该单元格的列名
//                    String colName = Bytes.toString(CellUtil.cloneQualifier(cell));
//                    //获取该单元格的列值
//                    String value = Bytes.toString(CellUtil.cloneValue(cell));
//                    System.out.println(family + ":" + colName + "的值为：" + value);
//                }
//            }
​
		handleResultScanner(scanner);
	} catch (IOException e) {
		e.printStackTrace();
	}
}
 
/**
 *	过滤出文科的学生，只会返回以文科开头的数据列，其他列的数据不符合条件，不会返回
 */
@Test
public void ValueFilter12(){
	try {
		//获取表的实例
		HTableInterface students = conn.getTable("students");
​
		//创建正则比较器
		RegexStringComparator regexStringComparator = new RegexStringComparator("^文科.*");
​
		//创建列值过滤器
		ValueFilter valueFilter = new ValueFilter(CompareFilter.CompareOp.EQUAL, regexStringComparator);
​
		Scan scan = new Scan();
		scan.setFilter(valueFilter);
​
		ResultScanner scanner = students.getScanner(scan);
		handleResultScanner(scanner);
​
​
	} catch (IOException e) {
		e.printStackTrace();
	}
}

3.6、单列值过滤器 SingleColumnValueFilter

/**
 * 单列值过滤器
 * SingleColumnValueFilter会返回满足条件的cell所在行的所有cell的值（即会返回一行数据）
 *
 * 通过SingleColumnValueFilter与查询文科班所有学生信息
 */
@Test
public void SingleColumnValueFilter(){
	try {
		//获取表的实例
		TableName students = TableName.valueOf("students");
        Table studentTable = conn.getTable(students);
​
		//创建一个正则比较器
		RegexStringComparator regexStringComparator = new RegexStringComparator("^文科.*");
​
		//创建单列值过滤器对象
		SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter(
				"info".getBytes(),
				"clazz".getBytes(),
				CompareOperator.EQUAL,
				regexStringComparator
		);
​
		Scan scan = new Scan();
		scan.setFilter(singleColumnValueFilter);
​
		ResultScanner scanner = studentTable.getScanner(scan);
		handleResultScanner(scanner);
​
​
	} catch (IOException e) {
		e.printStackTrace();
	}
}

3.7、列值排除过滤器SingleColumnValueExcludeFilter

/**
 * 列值排除过滤器
 * 与SingleColumnValueFilter相反，会排除掉指定的列，其他的列全部返回
 *
 * 通过SingleColumnValueExcludeFilter与BinaryComparator查询文科一班所有学生信息，最终不返回clazz列
 */
@Test
public void SingleColumnValueExcludeFilter(){
	try {
		//获取表的实例
		TableName students = TableName.valueOf("students");
        Table studentTable = conn.getTable(students);
​
		//创建一个二进制比较器
		BinaryComparator binaryComparator = new BinaryComparator("文科一班".getBytes());
​
		//创建一个列值排除过滤器
		SingleColumnValueExcludeFilter singleColumnValueExcludeFilter = new SingleColumnValueExcludeFilter(
				"info".getBytes(),
				"clazz".getBytes(),
				CompareOperator.EQUAL,
				binaryComparator
		);
​
		Scan scan = new Scan();
		scan.setFilter(singleColumnValueExcludeFilter);
​
		ResultScanner scanner = studentTable.getScanner(scan);
		handleResultScanner(scanner);
​
​
	} catch (IOException e) {
		e.printStackTrace();
	}
}

3.8、rowKey前缀过滤器PrefixFilter

/**
 * rowkey前缀过滤器
 *
 * 通过PrefixFilter查询以150010008开头的所有前缀的rowkey
 */
@Test
public void PrefixFilter(){
	try {
		//获取表的实例
		TableName students = TableName.valueOf("students");
        Table studentTable = conn.getTable(students);
​
		//创建rowkey前缀过滤器
		PrefixFilter prefixFilter = new PrefixFilter("150010008".getBytes());
		Scan scan = new Scan();
​
		scan.setFilter(prefixFilter);
		ResultScanner scanner = studentTable.getScanner(scan);
		handleResultScanner(scanner);
​
​
	} catch (IOException e) {
		e.printStackTrace();
	}
​
}

3.9、分页过滤器PageFilter

/**
 * 分页过滤器
 * 分页有两个条件
 * pageNum  第几页
 * pageSize 每页有几条
 */
@Test
public void pageFilter() throws IOException {
 
	int pageNum = 3;
	int pageSize = 2;
 
 
	/*
	分为两种情况判断：
	第一页
	其他页
	 */
	if (pageNum == 1){
		Scan scan = new Scan();
		//设置起始rowKey
		scan.setStartRow("".getBytes());
		//设置最大的返回结果，返回pageSize条
		scan.setMaxResultSize(pageSize);
		//分页过滤器
		PageFilter pageFilter = new PageFilter(pageSize);
		scan.setFilter(pageFilter);
 
		ResultScanner resultScanner = table.getScanner(scan);
		for (Result result : resultScanner) {
			byte[] row = result.getRow();
			System.out.println("数据的rowKey为" + Bytes.toString(row));
			List<Cell> cells = result.listCells();
			for (Cell cell : cells) {
				byte[] qualifier = cell.getQualifier();
				byte[] family = cell.getFamily();
				byte[] value = cell.getValue();
				//id列和age列是整型数据
				if ("f1".equals(Bytes.toString(family)) && "id".equals(Bytes.toString(qualifier)) || "age".equals(Bytes.toString(value))){
					System.out.println("列族为"+Bytes.toString(family)+"列名为"+Bytes.toString(qualifier)+"列值为"+Bytes.toInt(value));
				} else {
					System.out.println("列族为"+Bytes.toString(family)+"列名为"+Bytes.toString(qualifier)+"列值为"+Bytes.toString(value));
				}
			}
		}
	} else {
		String startRow = "";
		Scan scan = new Scan();
		/*
		第二页的起始rowKey = 第一页的结束rowKey + 1
		第三页的起始rowKey = 第二页的结束rowKey + 1
		 */
		int resultSize = (pageNum - 1) * pageSize + 1;
		scan.setMaxResultSize(resultSize);
		//设置一次性往前扫描5条，最后一个rowKey是第三页起始rowKey
		PageFilter pageFilter = new PageFilter(resultSize);
		scan.setFilter(pageFilter);
		//resultScanner里面有5条数据
		ResultScanner scanner = table.getScanner(scan);
		for (Result result : scanner) {
			//获取rowKey
			byte[] row = result.getRow();
			//最后一次循环遍历 rowKey为0005
			startRow = Bytes.toString(row);
		}
		Scan scan1 = new Scan();
		scan1.setStartRow(startRow.getBytes());
		scan1.setMaxResultSize(pageSize);
 
		PageFilter pageFilter1 = new PageFilter(pageSize);
		scan1.setFilter(pageFilter1);
 
		ResultScanner scanner1 = table.getScanner(scan1);
		for (Result result : scanner1) {
			byte[] row = result.getRow();
			System.out.println("数据的rowKey为" + Bytes.toString(row));
			List<Cell> cells = result.listCells();
			for (Cell cell : cells) {
				// byte[] qualifier = cell.getQualifier();
				// byte[] family = cell.getFamily();
				// byte[] value = cell.getValue();
				String family = Bytes.toString(CellUtil.cloneFamily(cell));
				//获取该单元格的列名
				String colName = Bytes.toString(CellUtil.cloneQualifier(cell));
				//获取该单元格的列值
				String value = Bytes.toString(CellUtil.cloneValue(cell));
				//id列和age列是整型数据
				if ("f1".equals(Bytes.toString(family)) && "id".equals(Bytes.toString(qualifier)) || "age".equals(Bytes.toString(value))){
					System.out.println("列族为"+Bytes.toString(family)+"列名为"+Bytes.toString(qualifier)+"列值为"+Bytes.toInt(value));
				} else {
					System.out.println("列族为"+Bytes.toString(family)+"列名为"+Bytes.toString(qualifier)+"列值为"+Bytes.toString(value));
				}
			}
		}
	}
}

3.10、多过滤器综合查询FilterList

/**
 * 通过运用4种比较器过滤出姓于，年纪大于23岁，性别为女，且是理科的学生。
 *
 * 正则比较器   RegexStringComparator
 * 包含比较器   SubstringComparator
 * 二进制前缀比较器   BinaryPrefixComparator
 * 二进制比较器      BinaryComparator
 *
 */
@Test
public void FilterData1(){
	try {
		//获取表的实例
		TableName students = TableName.valueOf("students");
        Table studentTable = conn.getTable(students);
​
		/**
		 *  第一个过滤器，过滤出是理科开头的班级
		 */
		RegexStringComparator regexStringComparator = new RegexStringComparator("^理科.*");
		//单列值过滤器
		SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter("info".getBytes(), "clazz".getBytes(),
				CompareOperator.EQUAL, regexStringComparator);
​
		/**
		 * 第二个过滤器，过滤出性别是女生的
		 */
​
		SubstringComparator substringComparator = new SubstringComparator("女");
		SingleColumnValueFilter singleColumnValueFilter1 = new SingleColumnValueFilter("info".getBytes(), "gender".getBytes(),
				CompareOperator.EQUAL, substringComparator);
​
		/**
		 * 第三个过滤器，过滤出年龄大于23岁的
		 */
		BinaryComparator binaryComparator = new BinaryComparator("20".getBytes());
		SingleColumnValueFilter singleColumnValueFilter2 = new SingleColumnValueFilter("info".getBytes(), "age".getBytes(),
				CompareOperator.GREATER, binaryComparator);
​
​
		/**
		 * 第四个过滤器，过滤出姓于的学生
		 */
		BinaryPrefixComparator binaryPrefixComparator = new BinaryPrefixComparator("于".getBytes());
		SingleColumnValueFilter singleColumnValueFilter3 = new SingleColumnValueFilter("info".getBytes(), "name".getBytes(),
				CompareOperator.EQUAL, binaryPrefixComparator);
​
​
		Scan scan = new Scan();
​
		//要想实现多个需求同时过滤，就需要创建多个过滤器，添加到一个过滤器列表中
		//然后将过滤器列表传给扫描器scan
		FilterList filterList = new FilterList();
		filterList.addFilter(singleColumnValueFilter);
		filterList.addFilter(singleColumnValueFilter1);
		filterList.addFilter(singleColumnValueFilter2);
		filterList.addFilter(singleColumnValueFilter3);
​
		scan.setFilter(filterList);
​
		ResultScanner scanner = studentTable.getScanner(scan);
​
		handleResultScanner(scanner);
​
​
	} catch (IOException e) {
		e.printStackTrace();
	}
​
}
 
/**
 * 	过滤出学号是以15001001开头的文科学生
 */
@Test
public void filterData2(){
	try {
		//获取表的实例
		TableName students = TableName.valueOf("students");
        Table studentTable = conn.getTable(students);
​
		/**
		 *  创建第一个过滤器，过滤是以15001001开头的rowkey
		 */
		BinaryPrefixComparator binaryPrefixComparator = new BinaryPrefixComparator("15001001".getBytes());
		//创建行键过滤器
		RowFilter rowFilter = new RowFilter(CompareOperator.EQUAL, binaryPrefixComparator);
​
		/**
		 * 创建第二个过滤器，过滤出文科的学生
		 */
		RegexStringComparator regexStringComparator = new RegexStringComparator("^文科.*");
		SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter("info".getBytes(), "clazz".getBytes(),
				CompareOperator.EQUAL,
				regexStringComparator);
​
​
		FilterList filterList = new FilterList();
		filterList.addFilter(rowFilter);
		filterList.addFilter(singleColumnValueFilter);
​
		Scan scan = new Scan();
		scan.setFilter(filterList);
		ResultScanner scanner = studentTable.getScanner(scan);
		handleResultScanner(scanner);
​
	} catch (IOException e) {
		e.printStackTrace();
	}
​
}