大数据从入门到实战 - HBase高级特性：过滤器（一）

叮嘟！这里是小啊呜的学习课程资料整理。好记性不如烂笔头，今天也是努力进步的一天。一起加油进阶吧！

一、关于此次实践

1、实战简介

HBase过滤器（filter）提供了非常强大的特性来帮助用户提高其处理表中数据的效率，用户不仅可以使用HBase中预定义好的过滤器，而且可以实现自定义的过滤器。

本次实训我们就来初步的了解过滤器的基本知识和开发流程。

2、全部任务

二、实践详解

1、第 1关：使用过滤器查询指定行的数据

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 *********/
 }
}

评测

2、第 2关：使用正则表达式与子字符串匹配行键

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.filter.SubstringComparator;
import org.apache.hadoop.hbase.util.*;
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$")); //匹配任意开头，以2结尾。
 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"));
 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 *********/
 }
}

评测

3、第 3关：列族过滤器、值过滤器、列名过滤器

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")));
 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"));
 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("寮 "));
 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 *********/
 }
}

评测

Ending！
更多课程知识学习记录随后再来吧！

就酱，嘎啦！

注：
人生在勤，不索何获。