头歌 HBase高级特性：过滤器（一）

头歌 HBase高级特性：过滤器（一）

第1关：使用过滤器查询指定行的数据

编程要求
请补全函数query(String tName)，需要你查询的数据如下，表名会作为方法的参数传入：

1、查询basic_info列族gender列，且行键为2018的值；

2、查询school_info列族college列，且行键大于2018的值；

3、查询basic_info列族name列，且行键小于等于2020的值。

代码行：

package step1;
 
import java.io.IOException;
 
import org.apache.hadoop.cli.util.*;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.*;
import org.apache.hadoop.hbase.util.*;
 
public class Task {
 
	public void query(String tName) throws Exception {
		/********* Begin *********/
		Configuration config = new Configuration();
		Connection conn = ConnectionFactory.createConnection(config);
		TableName tableName = TableName.valueOf(tName);
        Table table = conn.getTable(tableName);
 
        Scan scan1=new Scan();
        scan1.addColumn(Bytes.toBytes("basic_info"), Bytes.toBytes("gender"));
		Filter filter1 = new RowFilter(CompareOperator.EQUAL,new BinaryComparator(Bytes.toBytes("2018")));
        scan1.setFilter(filter1);
        ResultScanner scanner1 = table.getScanner(scan1);
 		System.out.println("row:2018");
 		for (Result result : scanner1) {
 			for(Cell cell : result.listCells()){
 				System.out.println("basic_info:gender " + new String(CellUtil.cloneValue(cell),"utf-8") );
 			}
 		}
        scanner1.close();
		
		Scan scan2=new Scan();
        scan2.addColumn(Bytes.toBytes("school_info"), Bytes.toBytes("college"));
		Filter filter2 = new RowFilter(CompareOperator.GREATER,new BinaryComparator(Bytes.toBytes("2018")));
        scan2.setFilter(filter2);
        ResultScanner scanner2 = table.getScanner(scan2);
 		for (Result result : scanner2) {
            System.out.println("row:" + new String(result.getRow(),"utf-8"));
 			for(Cell cell : result.listCells()){
 				System.out.println("school_info:college " + new String(CellUtil.cloneValue(cell),"utf-8") );
 			}
 		}
        scanner2.close();
		
        Scan scan3=new Scan();
        scan3.addColumn(Bytes.toBytes("basic_info"), Bytes.toBytes("name"));
		Filter filter3 = new RowFilter(CompareOperator.LESS_OR_EQUAL,new BinaryComparator(Bytes.toBytes("2020")));
        scan3.setFilter(filter3);
        ResultScanner scanner3 = table.getScanner(scan3);
 		for (Result result : scanner3) {
            System.out.println("row:" + new String(result.getRow(),"utf-8"));
 			for(Cell cell : result.listCells()){
 				System.out.println("basic_info:name " + new String(CellUtil.cloneValue(cell),"utf-8") );
 			}
 		}
        scanner3.close();
		
		conn.close();
		/********* End *********/
	}
}

 如果能解决您的问题，麻烦您点个赞，一键三连！！！

第2关：使用正则表达式与子字符串匹配行键

编程要求：

1、查询表t2_student_table中的数据。 要求如下：

2、查询以1开头，并以9结尾的行键，并输出该行所有列的值；

3、查询包含231的行键，并输出该行所有列的值。

代码行：

package step2;
 
import java.io.IOException;
 
import org.apache.hadoop.cli.util.*;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.*;
import org.apache.hadoop.hbase.util.*;
import org.apache.hadoop.hbase.filter.SubstringComparator;
 
public class Task {
 
	public void query() throws Exception {
		/********* Begin *********/
		Configuration config = new Configuration();
		Connection conn = ConnectionFactory.createConnection(config);
		TableName tablename=TableName.valueOf("t2_student_table");
        Table table=conn.getTable(tablename);
 
        Scan scan1=new Scan();
        Filter filter1 = new RowFilter(CompareOperator.EQUAL,new RegexStringComparator("1.*9$")); //查询以1开头，并以9结尾的行键
        scan1.setFilter(filter1);
        ResultScanner scanner1 = table.getScanner(scan1);
        for (Result result : scanner1) {
 			System.out.println("row:" + new String(result.getRow(),"utf-8"));
 			for(Cell cell : result.listCells()){
 				String family = Bytes.toString(CellUtil.cloneFamily(cell));
 				String qualifier = Bytes.toString(CellUtil.cloneQualifier(cell));
 				String value = Bytes.toString(CellUtil.cloneValue(cell));
 				System.out.println(family + ":" + qualifier + " " + value);
 			}
 		}
 		scanner1.close();
		
		Scan scan2=new Scan();
        Filter filter2 = new RowFilter(CompareOperator.EQUAL,new SubstringComparator("231")); //查询包含231的行键
        scan2.setFilter(filter2);
        ResultScanner scanner2 = table.getScanner(scan2);
        for (Result result : scanner2) {
 			System.out.println("row:" + new String(result.getRow(),"utf-8"));
 			for(Cell cell : result.listCells()){
 				String family = Bytes.toString(CellUtil.cloneFamily(cell));
 				String qualifier = Bytes.toString(CellUtil.cloneQualifier(cell));
 				String value = Bytes.toString(CellUtil.cloneValue(cell));
 				System.out.println(family + ":" + qualifier + " " + value);
 			}
 		}
 		scanner2.close();
	
		conn.close();
		/********* End *********/
	}
}

 创作不易，如果能解决您的问题，麻烦您点个赞，一键三连！！！

第3关：列族过滤器、值过滤器、列名过滤器
编程要求：
使用过滤器对表t3_student_table完成如下查询操作：

1、查询行键1019中列族school_info所有列，输出值；

2、查询行键2020中，列名包含字母c的所有列，输出值；

3、查询表所有行中包含张的值，并输出该值。

代码行：

package step3;
 
import java.io.IOException;
 
import org.apache.hadoop.cli.util.*;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.*;
import org.apache.hadoop.hbase.util.*;
 
import org.apache.hadoop.hbase.filter.SubstringComparator;
 
public class Task {
 
	public void query() throws Exception {
		/********* Begin *********/
		Configuration config = new Configuration();
		Connection conn = ConnectionFactory.createConnection(config);
		TableName tableName = TableName.valueOf(Bytes.toBytes("t3_student_table"));
 		Table table = conn.getTable(tableName);
		
		Filter filter1 = new FamilyFilter(CompareOperator.EQUAL,new BinaryComparator(Bytes.toBytes("school_info")));  //列族过滤器
 		Get get1 = new Get(Bytes.toBytes("1019"));
 		get1.setFilter(filter1);
 		Result result1 = table.get(get1);
 		System.out.println("row:" + new String(result1.getRow(),"utf-8"));
 		for(Cell cell : result1.listCells()){
 			String family = Bytes.toString(CellUtil.cloneFamily(cell));
 			String qualifier = Bytes.toString(CellUtil.cloneQualifier(cell));
 			String value = Bytes.toString(CellUtil.cloneValue(cell));
 			System.out.println(family + ":" + qualifier + " " + value);
 		}
 
        Filter filter2 = new QualifierFilter(CompareOperator.EQUAL,
 		new SubstringComparator("c"));   //列名过滤器
 		Get get2 = new Get(Bytes.toBytes("2020"));
 		get2.setFilter(filter2);
 		Result result2 = table.get(get2);
 		System.out.println("row:" + new String(result2.getRow(),"utf-8"));
 		for(Cell cell : result2.listCells()){
 			String family = Bytes.toString(CellUtil.cloneFamily(cell));
 			String qualifier = Bytes.toString(CellUtil.cloneQualifier(cell));
 			String value = Bytes.toString(CellUtil.cloneValue(cell));
 			System.out.println(family + ":" + qualifier + " " + value);
 		}
		
		Scan scan3 = new Scan();
 		Filter filter3 = new ValueFilter(CompareOperator.EQUAL, new SubstringComparator("张"));   //值过滤器
 		scan3.setFilter(filter3);
 		ResultScanner scanner3 = table.getScanner(scan3);
 		for (Result result : scanner3) {
 			System.out.println("row:" + new String(result.getRow(),"utf-8"));
 			for(Cell cell : result.listCells()){
 				String family = Bytes.toString(CellUtil.cloneFamily(cell));
 				String qualifier = Bytes.toString(CellUtil.cloneQualifier(cell));
 				String value = Bytes.toString(CellUtil.cloneValue(cell));
 				System.out.println(family + ":" + qualifier + " " + value);
 			}
 		}
        scanner3.close();
		conn.close();
		/********* End *********/
	}
}