HBase 进阶笔记

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
package cn.lazycat.bdd.hbase.ext;

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 java.io.IOException;
import java.util.Map;
import java.util.NavigableMap;

public class HBaseAdvDemo1 {

    public static void main(String[] args) throws IOException {
        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum", "hadoop1:2181," +
                "hadoop2:2181,hadoop3:2181");
        HTable tab = new HTable(conf, "tab1".getBytes());

        // 创建scan对象
        Scan scan = new Scan();

        // 得到结果集
        ResultScanner rs = tab.getScanner(scan);

        // 遍历
        for (Result res : rs) {
            // 取得行键
            String rk = new String(res.getRow());

            // 取得每一列的数据
            // 注意三层泛型：
            // 1. byte[]表示列族的名称，Map表示列中储存的列信息
            // 2. byte[]表示列的名称，Map表示不同版本的列数据
            // 3. Long表示一个版本的时间戳，byte[]表示储存的具体数据
            NavigableMap<byte[], NavigableMap<byte[],
                    NavigableMap<Long, byte[]>>> map = res.getMap();

            // 遍历Map
            for (Map.Entry<byte[], NavigableMap<byte[],
                    NavigableMap<Long, byte[]>>> entry : map.entrySet()) {

                // 列族名称
                String cf = new String(entry.getKey());

                // 这个列族的多个列
                NavigableMap<byte[], NavigableMap<Long, byte[]>>
                        cmap = entry.getValue();

                // 遍历这个列族的所有列
                for (Map.Entry<byte[], NavigableMap<Long, byte[]>>
                        centry: cmap.entrySet()) {

                    // 列名称
                    String column = new String(centry.getKey());

                    // 这个列的多个版本
                    NavigableMap<Long, byte[]> dataMap =
                            centry.getValue();

                    // 遍历所有的数据版本
                    for (Map.Entry<Long, byte[]> dataEntry :
                            dataMap.entrySet()) {

                        long timestamp = dataEntry.getKey();
                        String data = new String(dataEntry.getValue());

                        // 打印，行键，列族，列，时间戳，具体数据
                        System.out.println("====== cell ======");
                        System.out.println("row key = " + rk);
                        System.out.println("column family = " + cf);
                        System.out.println("column = " + column);
                        System.out.println("timestamp = " + timestamp);
                        System.out.println("data = " + data);

                    }  // cell

                } // column

            }  // column family

        }  // row key

        tab.close();

    }

}

1
2
scan.setStartRow("rk2".getBytes());
scan.setStopRow("rk5".getBytes());

1
2
3
4
5
// 创建过滤器
Filter filter = new RowFilter(CompareFilter.CompareOp.EQUAL,
        new BinaryComparator("rk1".getBytes()));
// 指定过滤器
scan.setFilter(filter);

1
2
3
Filter filter = new RowFilter(CompareFilter.CompareOp.EQUAL,
        new RegexStringComparator("^.*hhh.*$"));
scan.setFilter(filter);

1
2
Filter filter = new PrefixFilter("hhh".getBytes());
scan.setFilter(filter);

1
2
3
4
5
scan.setStartRow("rk1".getBytes());
scan.setStopRow("rk3".getBytes());

Filter filter = new KeyOnlyFilter();
scan.setFilter(filter);

1
2
Filter filter = new RandomRowFilter(0.3f);
scan.setFilter(filter);

1
2
3
scan.setStartRow("rk2".getBytes());
Filter filter = new InclusiveStopFilter("rk4".getBytes());
scan.setFilter(filter);

1
2
3
4
5
scan.setStartRow("rk1".getBytes());
scan.setStopRow("rk3".getBytes());

Filter filter = new FirstKeyOnlyFilter();
scan.setFilter(filter);

1
2
3
4
5
6
7
SingleColumnValueFilter filter = new SingleColumnValueFilter(
        "cf1".getBytes(), "c1".getBytes(),
        CompareFilter.CompareOp.EQUAL,
        new BinaryComparator("val3".getBytes())
);
filter.setFilterIfMissing(true);
scan.setFilter(filter);

1
2
3
4
5
6
FilterList filters = new FilterList();
filters.addFilter(filter1);
filters.addFilter(filter2);
filters.addFilter(filter3);
...
scan.setFilter(filters);