hbase rowkey 查询

一、hbase查询方式

    hbase的查询实现只提供两种方式：

• 按指定rowkey获取唯一一条记录：get方法。
• 按指定条件获取一批记录：scan方法。

    实现条件查询功能使用的就是scan方式，scan在使用时有以下几点值的注意：

• scan可以通过setCaching与setBatch方法提高速度（以空间换时间）
• scan可以通过setStartRow与setEndRow来限定范围。范围越小，性能越高。
• scan可以通过setFilter方法添加过滤器，这也是分页、多条件查询的基础。

二、RowFilter使用

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.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.BinaryComparator;
import org.apache.hadoop.hbase.filter.BinaryPrefixComparator;
import org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.Filter;
import org.apache.hadoop.hbase.filter.RegexStringComparator;
import org.apache.hadoop.hbase.filter.RowFilter;
import org.apache.hadoop.hbase.filter.SubstringComparator;
 
public class TestHbaseRowFilter {
        String tableName = "test_row_filter";
        Configuration config = HBaseConfiguration.create();
 
        /**
         * 部分代码来自hbase权威指南
         * @throws IOException
         */
        public void testRowFilter() throws IOException {
 
                HTable table = new HTable(config, tableName);
                Scan scan = new Scan();
 
                System.out.println("小于等于row010的行");
                Filter filter1 = new RowFilter(CompareFilter.CompareOp.LESS_OR_EQUAL,
                                new BinaryComparator("row010".getBytes()));
                scan.setFilter(filter1);
                ResultScanner scanner1 = table.getScanner(scan);
                for (Result res : scanner1) {
                        System.out.println(res);
                }
                scanner1.close();
 
                System.out.println("正则获取结尾为5的行");
                Filter filter2 = new RowFilter(CompareFilter.CompareOp.EQUAL,
                                new RegexStringComparator(".*5[        DISCUZ_CODE_0        ]quot;));
                scan.setFilter(filter2);
                ResultScanner scanner2 = table.getScanner(scan);
                for (Result res : scanner2) {
                        System.out.println(res);
                }
                scanner2.close();
 
                System.out.println("包含有5的行");
                Filter filter3 = new RowFilter(CompareFilter.CompareOp.EQUAL,
                                new SubstringComparator("5"));
                scan.setFilter(filter3);
                ResultScanner scanner3 = table.getScanner(scan);
                for (Result res : scanner3) {
                        System.out.println(res);
                }
                scanner3.close();
 
                System.out.println("开头是row01的");
                Filter filter4 = new RowFilter(CompareFilter.CompareOp.EQUAL,
                                new BinaryPrefixComparator("row01".getBytes()));
                scan.setFilter(filter4);
                ResultScanner scanner4 = table.getScanner(scan);
                for (Result res : scanner4) {
                        System.out.println(res);
                }
                scanner3.close();
        }
 
        /**
         * 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("data");
                                htd.addFamily(hcd1);
                                HColumnDescriptor hcd2 = new HColumnDescriptor("url");
                                htd.addFamily(hcd2);
 
                                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("data".getBytes(), String.format("col%01d", i % 10)
                                                .getBytes(), String.format("data%03d", i).getBytes());
                                p.add("url".getBytes(), String.format("col%01d", i % 10)
                                                .getBytes(), String.format("url%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 {
                TestHbaseRowFilter test = new TestHbaseRowFilter();
                test.init();
                test.testRowFilter();
        }
 
}

小于等于row010的行
keyvalues={row001/data:col1/1364133382268/Put/vlen=7, row001/url:col1/1364133382268/Put/vlen=6}
keyvalues={row002/data:col2/1364133382268/Put/vlen=7, row002/url:col2/1364133382268/Put/vlen=6}
keyvalues={row003/data:col3/1364133382268/Put/vlen=7, row003/url:col3/1364133382268/Put/vlen=6}
keyvalues={row004/data:col4/1364133382268/Put/vlen=7, row004/url:col4/1364133382268/Put/vlen=6}
keyvalues={row005/data:col5/1364133382268/Put/vlen=7, row005/url:col5/1364133382268/Put/vlen=6}
keyvalues={row006/data:col6/1364133382268/Put/vlen=7, row006/url:col6/1364133382268/Put/vlen=6}
keyvalues={row007/data:col7/1364133382268/Put/vlen=7, row007/url:col7/1364133382268/Put/vlen=6}
keyvalues={row008/data:col8/1364133382268/Put/vlen=7, row008/url:col8/1364133382268/Put/vlen=6}
keyvalues={row009/data:col9/1364133382268/Put/vlen=7, row009/url:col9/1364133382268/Put/vlen=6}
keyvalues={row010/data:col0/1364133382268/Put/vlen=7, row010/url:col0/1364133382268/Put/vlen=6}
正则获取结尾为5的行
keyvalues={row005/data:col5/1364133382268/Put/vlen=7, row005/url:col5/1364133382268/Put/vlen=6}
keyvalues={row015/data:col5/1364133382268/Put/vlen=7, row015/url:col5/1364133382268/Put/vlen=6}
keyvalues={row025/data:col5/1364133382268/Put/vlen=7, row025/url:col5/1364133382268/Put/vlen=6}
keyvalues={row035/data:col5/1364133382268/Put/vlen=7, row035/url:col5/1364133382268/Put/vlen=6}
keyvalues={row045/data:col5/1364133382268/Put/vlen=7, row045/url:col5/1364133382268/Put/vlen=6}
包行有5的行
keyvalues={row005/data:col5/1364133382268/Put/vlen=7, row005/url:col5/1364133382268/Put/vlen=6}
keyvalues={row015/data:col5/1364133382268/Put/vlen=7, row015/url:col5/1364133382268/Put/vlen=6}
keyvalues={row025/data:col5/1364133382268/Put/vlen=7, row025/url:col5/1364133382268/Put/vlen=6}
keyvalues={row035/data:col5/1364133382268/Put/vlen=7, row035/url:col5/1364133382268/Put/vlen=6}
keyvalues={row045/data:col5/1364133382268/Put/vlen=7, row045/url:col5/1364133382268/Put/vlen=6}
keyvalues={row050/data:col0/1364133382268/Put/vlen=7, row050/url:col0/1364133382268/Put/vlen=6}
开头是row01的
keyvalues={row010/data:col0/1364133382268/Put/vlen=7, row010/url:col0/1364133382268/Put/vlen=6}
keyvalues={row011/data:col1/1364133382268/Put/vlen=7, row011/url:col1/1364133382268/Put/vlen=6}
keyvalues={row012/data:col2/1364133382268/Put/vlen=7, row012/url:col2/1364133382268/Put/vlen=6}
keyvalues={row013/data:col3/1364133382268/Put/vlen=7, row013/url:col3/1364133382268/Put/vlen=6}
keyvalues={row014/data:col4/1364133382268/Put/vlen=7, row014/url:col4/1364133382268/Put/vlen=6}
keyvalues={row015/data:col5/1364133382268/Put/vlen=7, row015/url:col5/1364133382268/Put/vlen=6}
keyvalues={row016/data:col6/1364133382268/Put/vlen=7, row016/url:col6/1364133382268/Put/vlen=6}
keyvalues={row017/data:col7/1364133382268/Put/vlen=7, row017/url:col7/1364133382268/Put/vlen=6}
keyvalues={row018/data:col8/1364133382268/Put/vlen=7, row018/url:col8/1364133382268/Put/vlen=6}
keyvalues={row019/data:col9/1364133382268/Put/vlen=7, row019/url:col9/1364133382268/Put/vlen=6}