Hbase 四种过滤器

最新推荐文章于 2025-02-25 09:27:21 发布

转载最新推荐文章于 2025-02-25 09:27:21 发布 · 285 阅读

1 ·

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/JBLi/p/10885155.html

文章标签：

#大数据 #java

博客介绍了四种过滤器，分别是行键过滤器、前缀过滤器、时间戳过滤器和列族过滤器，转载自https://www.cnblogs.com/JBLi/p/10885155.html 。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

四种过滤器 1、行键过滤器 2、前缀过滤器 3、时间戳过滤器 4、列族过滤器

package com.bw.hbasefilter;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.HTable;
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.filter.BinaryComparator;
import org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.Filter;
import org.apache.hadoop.hbase.filter.PrefixFilter;
import org.apache.hadoop.hbase.filter.QualifierFilter;
import org.apache.hadoop.hbase.filter.RegexStringComparator;
import org.apache.hadoop.hbase.filter.RowFilter;
import org.apache.hadoop.hbase.filter.TimestampsFilter;

public class HbaseFilter {
//静态块  连接zk   并且配置操作的表
    static HTable table;
    static {
        try {
            Configuration conf = HBaseConfiguration.create();
            conf.set("hbase.zookeeper.quorum", "linux04,linux05,linux06");
            table = new HTable(conf, "Nurse");
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    //2、前缀过滤器
    public static void prefixFilter() throws Exception {
        Scan scan = new Scan();              //过滤以 Nurse00009999  为前缀的行键
        PrefixFilter filter = new PrefixFilter("Nurse00009999".getBytes());
        scan.setFilter(filter);
        ResultScanner scanner = table.getScanner(scan);
        for (Result r : scanner) {
            System.out.println("行键row:" + new String(r.getRow()));// 行键
            System.out.println("查询数据的结果：" + new String(r.getValue("info".getBytes(), "name".getBytes())));
        }
        
    }
    //3、时间戳过滤器  两个时间之间的数据
    public static void timeFilter() throws Exception {
        Scan scan = new Scan();
        List<Long> list = new ArrayList<Long>();
        list.add(1557323272643L);
        list.add(1558146272160L);
        TimestampsFilter filter = new TimestampsFilter(list);
        scan.setFilter(filter);
        ResultScanner scanner = table.getScanner(scan);
        for (Result r : scanner) {
            System.out.println("行键row:" + new String(r.getRow()));// 行键
            System.out.println("查询数据的结果：" + new String(r.getValue("info".getBytes(), "name".getBytes())));
        }
        
    }
    //4、列族过滤器  每行数据含有这一列的
    public static void qualifierFilter() throws Exception {
        Scan scan = new Scan();
        Filter filter = new QualifierFilter(CompareFilter.CompareOp.EQUAL, new  RegexStringComparator("age"));
        scan.setFilter(filter);
        ResultScanner scanner = table.getScanner(scan);
        for (Result r : scanner) {
            System.out.println("行键row:" + new String(r.getRow()));// 行键
            System.out.println("查询数据的结果：" + new String(r.getValue("info".getBytes(), "name".getBytes())));
        }
    }
    
    // 1、行键过滤器
    public static void rowFilter() throws Exception {
        Scan scan = new Scan();
        Filter filter = new RowFilter(CompareFilter.CompareOp.LESS,
                // 要的是小于 Nurse00000100 值的行键数据
                new BinaryComparator("Nurse0000100".getBytes()));
        scan.setFilter(filter);
        ResultScanner scanner = table.getScanner(scan);
        for (Result r : scanner) {
            System.out.println("行键row:" + new String(r.getRow()));// 行键
            System.out.println("查询数据的结果：" + new String(r.getValue("info".getBytes(), "name".getBytes())));
        }
    }
//调用 过滤器方法
    public static void main(String[] args) throws Exception {
        //rowFilter();
        //prefixFilter();
        //timeFilter();
        qualifierFilter();
        
    }
}