Apache HBase JavaAPI 過濾器查詢

過濾器查詢

過濾器的類型很多，但是可以分爲兩大類——比較過濾器，專用過濾器
過濾器的作用是在服務端判斷數據是否滿足條件，然後只將滿足條件的數據返回給客戶端；

hbase過濾器的比較運算符：

LESS  <
LESS_OR_EQUAL <=
EQUAL =
NOT_EQUAL <>
GREATER_OR_EQUAL >=
GREATER >
NO_OP 排除所有

Hbase過濾器的專用過濾器（指定比較機制）：

BinaryComparator  按字節索引順序比較指定字節數組，採用Bytes.compareTo(byte[])
BinaryPrefixComparator 跟前面相同，只是比較左端的數據是否相同
NullComparator 判斷給定的是否爲空
BitComparator 按位比較
RegexStringComparator 提供一個正則的比較器，僅支持 EQUAL 和非EQUAL
SubstringComparator 判斷提供的子串是否出現在value中。

比較過濾器

1、rowKey過濾器RowFilter
通過RowFilter過濾比rowKey 0003小的（小於等於）所有值出來

package com.czxy.demo01;

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 org.apache.hadoop.hbase.filter.BinaryComparator;
import org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.RowFilter;
import org.apache.hadoop.hbase.util.Bytes;

public class Test08 {
    /**
     * hbase行鍵過濾器RowFilter
     * @param args
     */
    public static void main(String[] args) throws Exception{

        //獲取連接
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum","hadoop01:2181,hadoop02:2181,hadoop03:2181");
        Connection connection = ConnectionFactory.createConnection(configuration);

        Table myuser = connection.getTable(TableName.valueOf("myuser"));

        Scan scan = new Scan();
        RowFilter rowFilter = new RowFilter(CompareFilter.CompareOp.LESS_OR_EQUAL, new BinaryComparator(Bytes.toBytes("0003")));

        scan.setFilter(rowFilter);
        ResultScanner resultScanner = myuser.getScanner(scan);
        for (Result result : resultScanner) {
            //獲取rowkey
            System.out.println(Bytes.toString(result.getRow()));

            //指定列族以及列打印列當中的數據出來
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "age".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
        }


        myuser.close();
        connection.close();



    }
}

列族過濾器FamilyFilter

查詢比f2列族小的所有的列族內的數據

package com.czxy.demo01;

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 org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.FamilyFilter;
import org.apache.hadoop.hbase.filter.SubstringComparator;
import org.apache.hadoop.hbase.util.Bytes;

public class Test09 {
    /**
     * hbase列族過濾器FamilyFilter
     *
     * @param args
     */
    public static void main(String[] args)throws Exception {
        //獲取連接
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum","hadoop01:2181,hadoop02:2181,hadoop03:2181");
        Connection connection = ConnectionFactory.createConnection(configuration);

        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        Scan scan = new Scan();
        FamilyFilter familyFilter = new FamilyFilter(CompareFilter.CompareOp.LESS, new SubstringComparator("f2"));
        scan.setFilter(familyFilter);
        ResultScanner resultScanner = myuser.getScanner(scan);

        for (Result result : resultScanner) {
            //獲取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列當中的數據出來
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "age".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
        }
        //關閉連接
        myuser.close();
        connection.close();
    }
}

列過濾器QualifierFilter

只查詢name列的值

package com.czxy.demo01;

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 org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.QualifierFilter;
import org.apache.hadoop.hbase.filter.SubstringComparator;
import org.apache.hadoop.hbase.util.Bytes;

public class Test10 {
    /**
     * 只查詢name列的值
     * @param args
     */
    public static void main(String[] args)throws Exception {
        //hbase列過濾器 QualifierFilter
        //獲取連接
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum","hadoop01:2181,hadoop02:2181,hadoop03:2181");
        Connection connection = ConnectionFactory.createConnection(configuration);

        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        Scan scan = new Scan();
        QualifierFilter qualifierFilter = new QualifierFilter(CompareFilter.CompareOp.EQUAL, new SubstringComparator("name"));
        scan.setFilter(qualifierFilter);
        ResultScanner resultScanner = myuser.getScanner(scan);

        for (Result result : resultScanner) {
            //獲取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列當中的數據出來
            //    System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
        }

        myuser.close();
        connection.close();
    }
}

列值過濾器ValueFilter

查詢所有列當中包含8的數據

package com.czxy.demo01;

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 org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.SubstringComparator;
import org.apache.hadoop.hbase.filter.ValueFilter;
import org.apache.hadoop.hbase.util.Bytes;

public class Test11 {

    /**
     * hbase值過濾器
     * 查詢包含8的列值
     * @param args
     * @throws Exception
     */
    public static void main(String[] args) throws Exception{

        //獲取連接
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum","hadoop01:2181,hadoop02:2181,hadoop03:2181");
        Connection connection = ConnectionFactory.createConnection(configuration);
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        Scan scan = new Scan();
        ValueFilter valueFilter = new ValueFilter(CompareFilter.CompareOp.EQUAL, new SubstringComparator("8"));

        scan.setFilter(valueFilter);
        ResultScanner resultScanner = myuser.getScanner(scan);

        for (Result result : resultScanner) {
            //獲取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列當中的數據出來
            //    System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
        }


        myuser.close();
        connection.close();

    }
}

專用過濾器

1、單列值過濾器 SingleColumnValueFilter
SingleColumnValueFilter會返回滿足條件的整列值的所有字段

package com.czxy.demo01;

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 org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter;
import org.apache.hadoop.hbase.util.Bytes;

public class Test12 {
    /**
     * 單列值過濾器，返回滿足條件的整行數據
     * @param args
     */
    public static void main(String[] args) throws Exception{
        //獲取連接
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum","hadoop01:2181,hadoop02:2181,hadoop03:2181");
        Connection connection = ConnectionFactory.createConnection(configuration);

        Table myuser = connection.getTable(TableName.valueOf("myuser"));

        Scan scan = new Scan();
        SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter("f1".getBytes(), "name".getBytes(), CompareFilter.CompareOp.EQUAL, "劉備".getBytes());
        scan.setFilter(singleColumnValueFilter);

        ResultScanner resultScanner = myuser.getScanner(scan);
        for (Result result : resultScanner) {
            //獲取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列當中的數據出來
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
        }
        myuser.close();
        connection.close();
    }
}

2、列值排除過濾器SingleColumnValueExcludeFilter
與SingleColumnValueFilter相反，會排除掉指定的列，其他的列全部返回

3、rowkey前綴過濾器PrefixFilter
查詢以00開頭的所有前綴的rowkey

package com.czxy.demo01;

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 org.apache.hadoop.hbase.filter.PrefixFilter;
import org.apache.hadoop.hbase.util.Bytes;

public class Test13 {
    /**
     * 行鍵前綴過濾器
     * @param args
     */
    public static void main(String[] args) throws Exception{
        //獲取連接
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum","hadoop01:2181,hadoop02:2181,hadoop03:2181");
        Connection connection = ConnectionFactory.createConnection(configuration);

        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        Scan scan = new Scan();
        PrefixFilter prefixFilter = new PrefixFilter("00".getBytes());
        scan.setFilter(prefixFilter);

        ResultScanner resultScanner = myuser.getScanner(scan);
        for (Result result : resultScanner) {
            //獲取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列當中的數據出來
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
        }

        myuser.close();
        connection.close();
    }
}

分頁過濾器PageFilter

通過pageFilter實現分頁過濾器

package com.czxy.demo01;

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 org.apache.hadoop.hbase.filter.PageFilter;
import org.apache.hadoop.hbase.util.Bytes;

public class Test14 {
    public static void main(String[] args)throws Exception {
        //獲取連接
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum", "hadoop01:2181,hadoop02:2181,hadoop03:2181");
        Connection connection = ConnectionFactory.createConnection(configuration);

        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        int pageNum = 2;
        int pageSize = 2;
        Scan scan = new Scan();
        if (pageNum == 1) {
            PageFilter filter = new PageFilter(pageSize);
            scan.setStartRow(Bytes.toBytes(""));
            scan.setFilter(filter);
            scan.setMaxResultSize(pageSize);
            ResultScanner scanner = myuser.getScanner(scan);
            for (Result result : scanner) {
                //獲取rowkey
                System.out.println(Bytes.toString(result.getRow()));
                //指定列族以及列打印列當中的數據出來
//            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
                System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
                //System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
            }

        }else{
            String startRowKey ="";
            PageFilter filter = new PageFilter((pageNum - 1) * pageSize + 1  );
            scan.setStartRow(startRowKey.getBytes());
            scan.setMaxResultSize((pageNum - 1) * pageSize + 1);
            scan.setFilter(filter);
            ResultScanner scanner = myuser.getScanner(scan);
            for (Result result : scanner) {
                byte[] row = result.getRow();
                startRowKey =  new String(row);
            }
            Scan scan2 = new Scan();
            scan2.setStartRow(startRowKey.getBytes());
            scan2.setMaxResultSize(Long.valueOf(pageSize));
            PageFilter filter2 = new PageFilter(pageSize);
            scan2.setFilter(filter2);

            ResultScanner scanner1 = myuser.getScanner(scan2);
            for (Result result : scanner1) {
                byte[] row = result.getRow();
                System.out.println(new String(row));
            }
        }
        myuser.close();
        connection.close();
    }
}

多過濾器綜合查詢FilterList

需求：使用SingleColumnValueFilter查詢f1列族，name爲劉備的數據，並且同時滿足rowkey的前綴以00開頭的數據（PrefixFilter）

package com.czxy.demo01;

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 org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.FilterList;
import org.apache.hadoop.hbase.filter.PrefixFilter;
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter;
import org.apache.hadoop.hbase.util.Bytes;

public class Test15 {
    /**
     * 多過濾器組合使用
     * @param args
     */
    public static void main(String[] args) throws Exception{
        //獲取連接
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum", "hadoop01:2181,hadoop02:2181,hadoop03:2181");
        Connection connection = ConnectionFactory.createConnection(configuration);

        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        Scan scan = new Scan();
        FilterList filterList = new FilterList();

        SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter("f1".getBytes(), "name".getBytes(), CompareFilter.CompareOp.EQUAL, "劉備".getBytes());
        PrefixFilter prefixFilter = new PrefixFilter("00".getBytes());

        filterList.addFilter(singleColumnValueFilter);
        filterList.addFilter(prefixFilter);

        scan.setFilter(filterList);

        ResultScanner scanner = myuser.getScanner(scan);
        for (Result result : scanner) {
            //獲取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列當中的數據出來
//            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
            //System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
        }
        myuser.close();
        connection.close();
    }
}