HBase学习之路 (六)过滤器
目录
正文
过滤器(Filter)
基础API中的查询操作在面对大量数据的时候是非常苍白的,这里Hbase提供了高级的查询方法:Filter。Filter可以根据簇、列、版本等更多的条件来对数据进行过滤,基于Hbase本身提供的三维有序(主键有序、列有序、版本有序),这些Filter可以高效的完成查询过滤的任务。带有Filter条件的RPC查询请求会把Filter分发到各个RegionServer,是一个服务器端(Server-side)的过滤器,这样也可以降低网络传输的压力。
要完成一个过滤的操作,至少需要两个参数。一个是抽象的操作符,Hbase提供了枚举类型的变量来表示这些抽象的操作符:LESS/LESS_OR_EQUAL/EQUAL/NOT_EUQAL等;另外一个就是具体的比较器(Comparator),代表具体的比较逻辑,如果可以提高字节级的比较、字符串级的比较等。有了这两个参数,我们就可以清晰的定义筛选的条件,过滤数据。
抽象操作符(比较运算符)
LESS <
LESS_OR_EQUAL <=
EQUAL =
NOT_EQUAL <>
GREATER_OR_EQUAL >=
GREATER >
NO_OP 排除所有
比较器(指定比较机制)
BinaryComparator 按字节索引顺序比较指定字节数组,采用 Bytes.compareTo(byte[])
BinaryPrefixComparator 跟前面相同,只是比较左端的数据是否相同
NullComparator 判断给定的是否为空
BitComparator 按位比较
RegexStringComparator 提供一个正则的比较器,仅支持 EQUAL 和非 EQUAL
SubstringComparator 判断提供的子串是否出现在 value 中
HBase过滤器的分类
比较过滤器
1、行键过滤器 RowFilter
Filter rowFilter = new RowFilter(CompareOp.GREATER, new BinaryComparator("95007".getBytes()));
scan.setFilter(rowFilter);


1 public class HbaseFilterTest {
2
3 private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";
4 private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";
5
6 private static Connection conn = null;
7 private static Admin admin = null;
8
9 public static void main(String[] args) throws Exception {
10
11 Configuration conf = HBaseConfiguration.create();
12 conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);
13 conn = ConnectionFactory.createConnection(conf);
14 admin = conn.getAdmin();
15 Table table = conn.getTable(TableName.valueOf("student"));
16
17 Scan scan = new Scan();
18
19 Filter rowFilter = new RowFilter(CompareOp.GREATER, new BinaryComparator("95007".getBytes()));
20 scan.setFilter(rowFilter);
21 ResultScanner resultScanner = table.getScanner(scan);
22 for(Result result : resultScanner) {
23 List<Cell> cells = result.listCells();
24 for(Cell cell : cells) {
25 System.out.println(cell);
26 }
27 }
28
29
30 }

运行结果部分截图

2、列簇过滤器 FamilyFilter
Filter familyFilter = new FamilyFilter(CompareOp.EQUAL, new BinaryComparator("info".getBytes()));
scan.setFilter(familyFilter);


1 public class HbaseFilterTest {
2
3 private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";
4 private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";
5
6 private static Connection conn = null;
7 private static Admin admin = null;
8
9 public static void main(String[] args) throws Exception {
10
11 Configuration conf = HBaseConfiguration.create();
12 conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);
13 conn = ConnectionFactory.createConnection(conf);
14 admin = conn.getAdmin();
15 Table table = conn.getTable(TableName.valueOf("student"));
16
17 Scan scan = new Scan();
18
19 Filter familyFilter = new FamilyFilter(CompareOp.EQUAL, new BinaryComparator("info".getBytes()));
20 scan.setFilter(familyFilter);
21 ResultScanner resultScanner = table.getScanner(scan);
22 for(Result result : resultScanner) {
23 List<Cell> cells = result.listCells();
24 for(Cell cell : cells) {
25 System.out.println(cell);
26 }
27 }
28
29
30 }
31
32
33 }


3、列过滤器 QualifierFilter
Filter qualifierFilter = new QualifierFilter(CompareOp.EQUAL, new BinaryComparator("name".getBytes()));
scan.setFilter(qualifierFilter);


1 public class HbaseFilterTest {
2
3 private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";
4 private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";
5
6 private static Connection conn = null;
7 private static Admin admin = null;
8
9 public static void main(String[] args) throws Exception {
10
11 Configuration conf = HBaseConfiguration.create();
12 conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);
13 conn = ConnectionFactory.createConnection(conf);
14 admin = conn.getAdmin();
15 Table table = conn.getTable(TableName.valueOf("student"));
16
17 Scan scan = new Scan();
18
19 Filter qualifierFilter = new QualifierFilter(CompareOp.EQUAL, new BinaryComparator("name".getBytes()));
20 scan.setFilter(qualifierFilter);
21 ResultScanner resultScanner = table.getScanner(scan);
22 for(Result result : resultScanner) {
23 List<Cell> cells = result.listCells();
24 for(Cell cell : cells) {
25 System.out.println(cell);
26 }
27 }
28
29
30 }
31
32
33 }


4、值过滤器 ValueFilter
Filter valueFilter = new ValueFilter(CompareOp.EQUAL, new SubstringComparator("男"));
scan.setFilter(valueFilter);


1 public class HbaseFilterTest {
2
3 private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";
4 private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";
5
6 private static Connection conn = null;
7 private static Admin admin = null;
8
9 public static void main(String[] args) throws Exception {
10
11 Configuration conf = HBaseConfiguration.create();
12 conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);
13 conn = ConnectionFactory.createConnection(conf);
14 admin = conn.getAdmin();
15 Table table = conn.getTable(TableName.valueOf("student"));
16
17 Scan scan = new Scan();
18
19 Filter valueFilter = new ValueFilter(CompareOp.EQUAL, new SubstringComparator("男"));
20 scan.setFilter(valueFilter);
21 ResultScanner resultScanner = table.getScanner(scan);
22 for(Result result : resultScanner) {
23 List<Cell> cells = result.listCells();
24 for(Cell cell : cells) {
25 System.out.println(cell);
26 }
27 }
28
29
30 }
31
32
33 }


5、时间戳过滤器 TimestampsFilter
List<Long> list = new ArrayList<>(); list.add(1522469029503l); TimestampsFilter timestampsFilter = new TimestampsFilter(list); scan.setFilter(timestampsFilter);


1 public class HbaseFilterTest {
2
3 private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";
4 private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";
5
6 private static Connection conn = null;
7 private static Admin admin = null;
8
9 public static void main(String[] args) throws Exception {
10
11 Configuration conf = HBaseConfiguration.create();
12 conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);
13 conn = ConnectionFactory.createConnection(conf);
14 admin = conn.getAdmin();
15 Table table = conn.getTable(TableName.valueOf("student"));
16
17 Scan scan = new Scan();
18
19 List<Long> list = new ArrayList<>();
20 list.add(1522469029503l);
21 TimestampsFilter timestampsFilter = new TimestampsFilter(list);
22 scan.setFilter(timestampsFilter);
23 ResultScanner resultScanner = table.getScanner(scan);
24 for(Result result : resultScanner) {
25 List<Cell> cells = result.listCells();
26 for(Cell cell : cells) {
27 System.out.println(Bytes.toString(cell.getRow()) + "\t" + Bytes.toString(cell.getFamily()) + "\t" + Bytes.toString(cell.getQualifier())
28 + "\t" + Bytes.toString(cell.getValue()) + "\t" + cell.getTimestamp());
29 }
30 }
31
32
33 }
34
35
36 }


专用过滤器
1、单列值过滤器 SingleColumnValueFilter ----会返回满足条件的整行

SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter(
"info".getBytes(), //列簇
"name".getBytes(), //列
CompareOp.EQUAL,
new SubstringComparator("刘晨"));
//如果不设置为 true,则那些不包含指定 column 的行也会返回
singleColumnValueFilter.setFilterIfMissing(true);
scan.setFilter(singleColumnValueFilter);



1 public class HbaseFilterTest2 {
2
3 private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";
4 private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";
5
6 private static Connection conn = null;
7 private static Admin admin = null;
8
9 public static void main(String[] args) throws Exception {
10
11 Configuration conf = HBaseConfiguration.create();
12 conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);
13 conn = ConnectionFactory.createConnection(conf);
14 admin = conn.getAdmin();
15 Table table = conn.getTable(TableName.valueOf("student"));
16
17 Scan scan = new Scan();
18
19 SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter(
20 "info".getBytes(),
21 "name".getBytes(),
22 CompareOp.EQUAL,
23 new SubstringComparator("刘晨"));
24 singleColumnValueFilter.setFilterIfMissing(true);
25
26 scan.setFilter(singleColumnValueFilter);
27 ResultScanner resultScanner = table.getScanner(scan);
28 for(Result result : resultScanner) {
29 List<Cell> cells = result.listCells();
30 for(Cell cell : cells) {
31 System.out.println(Bytes.toString(cell.getRow()) + "\t" + Bytes.toString(cell.getFamily()) + "\t" + Bytes.toString(cell.getQualifier())
32 + "\t" + Bytes.toString(cell.getValue()) + "\t" + cell.getTimestamp());
33 }
34 }
35
36
37 }
38
39
40 }


2、单列值排除器 SingleColumnValueExcludeFilter

SingleColumnValueExcludeFilter singleColumnValueExcludeFilter = new SingleColumnValueExcludeFilter(
"info".getBytes(),
"name".getBytes(),
CompareOp.EQUAL,
new SubstringComparator("刘晨"));
singleColumnValueExcludeFilter.setFilterIfMissing(true);
scan.setFilter(singleColumnValueExcludeFilter);



1 public class HbaseFilterTest2 {
2
3 private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";
4 private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";
5
6 private static Connection conn = null;
7 private static Admin admin = null;
8
9 public static void main(String[] args) throws Exception {
10
11 Configuration conf = HBaseConfiguration.create();
12 conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);
13 conn = ConnectionFactory.createConnection(conf);
14 admin = conn.getAdmin();
15 Table table = conn.getTable(TableName.valueOf("student"));
16
17 Scan scan = new Scan();
18
19 SingleColumnValueExcludeFilter singleColumnValueExcludeFilter = new SingleColumnValueExcludeFilter(
20 "info".getBytes(),
21 "name".getBytes(),
22 CompareOp.EQUAL,
23 new SubstringComparator("刘晨"));
24 singleColumnValueExcludeFilter.setFilterIfMissing(true);
25
26 scan.setFilter(singleColumnValueExcludeFilter);
27 ResultScanner resultScanner = table.getScanner(scan);
28 for(Result result : resultScanner) {
29 List<Cell> cells = result.listCells();
30 for(Cell cell : cells) {
31 System.out.println(Bytes.toString(cell.getRow()) + "\t" + Bytes.toString(cell.getFamily()) + "\t" + Bytes.toString(cell.getQualifier())
32 + "\t" + Bytes.toString(cell.getValue()) + "\t" + cell.getTimestamp());
33 }
34 }
35
36
37 }
38
39
40 }


3、前缀过滤器 PrefixFilter----针对行键
PrefixFilter prefixFilter = new PrefixFilter("9501".getBytes());
scan.setFilter(prefixFilter);


1 public class HbaseFilterTest2 {
2
3 private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";
4 private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";
5
6 private static Connection conn = null;
7 private static Admin admin = null;
8
9 public static void main(String[] args) throws Exception {
10
11 Configuration conf = HBaseConfiguration.create();
12 conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);
13 conn = ConnectionFactory.createConnection(conf);
14 admin = conn.getAdmin();
15 Table table = conn.getTable(TableName.valueOf("student"));
16
17 Scan scan = new Scan();
18
19 PrefixFilter prefixFilter = new PrefixFilter("9501".getBytes());
20
21 scan.setFilter(prefixFilter);
22 ResultScanner resultScanner = table.getScanner(scan);
23 for(Result result : resultScanner) {
24 List<Cell> cells = result.listCells();
25 for(Cell cell : cells) {
26 System.out.println(Bytes.toString(cell.getRow()) + "\t" + Bytes.toString(cell.getFamily()) + "\t" + Bytes.toString(cell.getQualifier())
27 + "\t" + Bytes.toString(cell.getValue()) + "\t" + cell.getTimestamp());
28 }
29 }
30
31
32 }
33
34
35 }


4、列前缀过滤器 ColumnPrefixFilter
ColumnPrefixFilter columnPrefixFilter = new ColumnPrefixFilter("name".getBytes());
scan.setFilter(columnPrefixFilter);


1 public class HbaseFilterTest2 {
2
3 private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";
4 private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";
5
6 private static Connection conn = null;
7 private static Admin admin = null;
8
9 public static void main(String[] args) throws Exception {
10
11 Configuration conf = HBaseConfiguration.create();
12 conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);
13 conn = ConnectionFactory.createConnection(conf);
14 admin = conn.getAdmin();
15 Table table = conn.getTable(TableName.valueOf("student"));
16
17 Scan scan = new Scan();
18
19 ColumnPrefixFilter columnPrefixFilter = new ColumnPrefixFilter("name".getBytes());
20
21 scan.setFilter(columnPrefixFilter);
22 ResultScanner resultScanner = table.getScanner(scan);
23 for(Result result : resultScanner) {
24 List<Cell> cells = result.listCells();
25 for(Cell cell : cells) {
26 System.out.println(Bytes.toString(cell.getRow()) + "\t" + Bytes.toString(cell.getFamily()) + "\t" + Bytes.toString(cell.getQualifier())
27 + "\t" + Bytes.toString(cell.getValue()) + "\t" + cell.getTimestamp());
28 }
29 }
30
31
32 }
33
34
35 }


5、分页过滤器 PageFilter
目录 返回
首页