Hbase DependentColumnFilter

Here you have a more complex filter that does not simply filter out data based on
directly available information. Rather, it lets you specify a dependent column—or
reference column—that controls how other columns are filtered. It uses the timestamp
of the reference column and includes all other columns that have the same timestamp.

尝试找到该列所在的每一行,并返回该行具有相同时间戳的全部键值对。如果某一行不包含指定的列,则该行的任何键值对都不返回。
如果dropDependentColumn=true,则从属列不返回。

via: http://abloz.com/2012/08/22/the-hbases-content-query-2.html

package com.fatkun.filter.comparison;
 
import java.io.IOException;
 
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.HBaseAdmin;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Put;
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.BinaryPrefixComparator;
import org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.DependentColumnFilter;
import org.apache.hadoop.hbase.filter.Filter;
import org.apache.hadoop.hbase.filter.SubstringComparator;
import org.apache.hadoop.hbase.filter.ValueFilter;
import org.apache.hadoop.hbase.filter.WritableByteArrayComparable;
import org.apache.hadoop.hbase.util.Bytes;
 
public class TestHbaseDependentColumnFilter {
    String tableName = "test_value_filter";
    Configuration config = HBaseConfiguration.create();
 
    public void filter(boolean drop, CompareFilter.CompareOp operator,
            WritableByteArrayComparable comparator) throws IOException {
 
        HTable table = new HTable(config, tableName);
        //
        Filter filter;
 
        if (comparator != null) {
            // drop为true时,filter表示对"col1"列以外的所有"data1"列族数据做filter操作
            // drop为false时,表示对所有"data1"列族的数据做filter操作
            filter = new DependentColumnFilter(Bytes.toBytes("data1"),
                    Bytes.toBytes("col1"), drop, operator, comparator);
        } else {
            filter = new DependentColumnFilter(Bytes.toBytes("data1"),
                    Bytes.toBytes("col1"), drop);
        }
        // filter应用于scan
        Scan scan = new Scan();
        scan.setFilter(filter);
        ResultScanner scanner = table.getScanner(scan);
 
        for (Result result : scanner) {
            for (KeyValue kv : result.list()) {
                System.out.println("kv=" + kv.toString() + ",value="
                        + Bytes.toString(kv.getValue()));
            }
        }
        scanner.close();
        table.close();
    }
 
    /**
     * 部分代码来自hbase权威指南
     * 
     * @throws IOException
     */
    public void testFilter() throws IOException {
        // The dropDependentColumn parameter is giving you additional control
        // over how the reference column is handled: it is either included or
        // dropped by the filter
 
        // 1.获取整个"data1"列族当前Version中的所有timestamp等于参照列"data1:col1"的数据
        System.out.println("drop=false");
        filter(false, CompareFilter.CompareOp.NO_OP, null);
        // 2.获取除了"col1"列以外的"data1"列族中的所有timestamp等于参照列"data1:col1"的数据
        System.out.println("drop=true");
        filter(true, CompareFilter.CompareOp.NO_OP, null);
        // 3.获取除了"col1"列以外的"data1"列族当前Version中的所有timestamp等于参照列"data1:col1"的,value以"data100"开头的所有数据
        System.out.println("比较");
        filter(true, CompareFilter.CompareOp.EQUAL, new BinaryPrefixComparator(
                Bytes.toBytes("data100")));
 
    }
 
    /**
     * 初始化数据
     */
    public void init() {
        // 创建表和初始化数据
        try {
            HBaseAdmin admin = new HBaseAdmin(config);
            if (!admin.tableExists(tableName)) {
                HTableDescriptor htd = new HTableDescriptor(tableName);
                HColumnDescriptor hcd1 = new HColumnDescriptor("data1");
                htd.addFamily(hcd1);
                HColumnDescriptor hcd2 = new HColumnDescriptor("data2");
                htd.addFamily(hcd2);
                HColumnDescriptor hcd3 = new HColumnDescriptor("data3");
                htd.addFamily(hcd3);
                admin.createTable(htd);
            }
 
            HTable table = new HTable(config, tableName);
 
            table.setAutoFlush(false);
            int count = 50;
            for (int i = 1; i <= count; ++i) {
                Put p = new Put(String.format("row%03d", i).getBytes());
                p.add("data1".getBytes(), String.format("col%01d", i % 10)
                        .getBytes(), String.format("data1%03d", i).getBytes());
                p.add("data2".getBytes(), String.format("col%01d", i % 10)
                        .getBytes(), String.format("data2%03d", i).getBytes());
                p.add("data3".getBytes(), String.format("col%01d", i % 10)
                        .getBytes(), String.format("data3%03d", i).getBytes());
                table.put(p);
            }
            table.close();
 
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
 
    /**
     * @param args
     * @throws IOException
     */
    public static void main(String[] args) throws IOException {
        TestHbaseDependentColumnFilter test = new TestHbaseDependentColumnFilter();
        test.init();
        test.testFilter();
    }
 
}



fatkun

没有评论


You can leave the first : )



发表评论

电子邮件地址不会被公开。