Hbase 过滤器API

最新推荐文章于 2022-03-02 20:10:00 发布
最新推荐文章于 2022-03-02 20:10:00 发布
阅读量310 收藏 1
点赞数
分类专栏： hadoop HBase

filter ==> SQL 中的Where

filter的执行流程：

过滤器在客户端创建,然后通过RPC发送到服务器上,由服务器执行

 
基础过滤器：

 
比较器：

Comparator 

Description 

LongComparator

Assumes the given value array is a Java Long number and uses Bytes.toLong() to convert it. 

BinaryComparator

Uses Bytes.compareTo() to compare 当前值与阀值

BinaryPrefixComparator

Bytes.compareTo() 进行匹配，但是从左端开始前缀匹配

NullComparator

判断当前值是否为null

BitComparator

Performs a bitwise comparison, providing a BitwiseOp enumeration with AND, OR, and XOR operators. 

RegexStringComparator

正则表达式匹配

SubstringComparator

子字符串比对

  •  RowFilter 行键过滤器：
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
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.*;
import  org.apache.hadoop.hbase.util.Bytes;
 
import  java.io.IOException;
 
/**
  * 基于行键上的过滤器
  */
public  class  FilterInHbase {
     public  static  void  main(String[] args)  throws  IOException{
         Configuration configuration = HBaseConfiguration.create();
         Connection connection = ConnectionFactory.createConnection(configuration);
         //建立user表的连接
         Table table =connection.getTable(TableName.valueOf( "user" ));
         Scan scan= new  Scan();
         //扫描列族info 列age
         scan.addColumn(Bytes.toBytes( "info" ),Bytes.toBytes( "age" ));
 
         System.out.println( "行过滤器" );
         //比较过滤器
         //这儿是指找出行小于或者等于"510824118261011172"的所有行
         Filter filter1 =  new  RowFilter(CompareFilter.CompareOp.LESS_OR_EQUAL,  new  BinaryComparator(Bytes.toBytes( "813782218261011172" )));
         //添加过滤器到扫描器中
         scan.setFilter(filter1);
         ResultScanner scanner1 = table.getScanner(scan);
         for (Result res:scanner1){
             System.out.println(res);
         }
         scanner1.close();
 
         System.out.println( "正则过滤器" );
         //正则过滤器
         //过滤行键以2结束的
         Filter filter2 =  new  RowFilter(CompareFilter.CompareOp.EQUAL,
                 new  RegexStringComparator( ".*2$" )
                 );
         scan.setFilter(filter2);
         ResultScanner scanner2 = table.getScanner(scan);
         for  (Result res:scanner2){
             System.out.println(res);
         }
         scanner2.close();
 
         //子串过滤器
         //过滤行键中包含了"61826"这个字符串
         System.out.println( "子串过滤器" );
         Scan scan3= new  Scan();
         //扫描列族info 列age
         scan3.addColumn(Bytes.toBytes( "info" ),Bytes.toBytes( "age" ));
         Filter filter3= new  RowFilter(CompareFilter.CompareOp.EQUAL,
                 new  SubstringComparator( "61826" )
                 );
         scan3.setFilter(filter3);
         ResultScanner scanner3=table.getScanner(scan3);
         for (Result res:scanner3){
             System.out.println(res);
         }
         scanner3.close();
 
         table.close();
         connection.close();
     }
}
 
/**
Result:
 
  行过滤器 < 813782218261011172
  keyvalues={224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0}
  keyvalues={510824118261011172/info:age/1472196213020/Put/vlen=2/seqid=0}
  keyvalues={524382618264914241/info:age/1472196193913/Put/vlen=2/seqid=0}
  keyvalues={673782618261019142/info:age/1472196211733/Put/vlen=2/seqid=0}
  keyvalues={813782218261011172/info:age/1472196212550/Put/vlen=2/seqid=0}
  正则过滤器 已2结尾的行键
  keyvalues={510824118261011172/info:age/1472196213020/Put/vlen=2/seqid=0}
  keyvalues={673782618261019142/info:age/1472196211733/Put/vlen=2/seqid=0}
  keyvalues={813782218261011172/info:age/1472196212550/Put/vlen=2/seqid=0}
  子串过滤器 包含了"61826"的行键
  keyvalues={224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0}
  keyvalues={524382618264914241/info:age/1472196193913/Put/vlen=2/seqid=0}
  keyvalues={673782618261019142/info:age/1472196211733/Put/vlen=2/seqid=0}
  **/

 

  • FamilyFilter列族过滤器：
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
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.FamilyFilter;
import  org.apache.hadoop.hbase.filter.Filter;
import  org.apache.hadoop.hbase.util.Bytes;
import  java.io.IOException;
/**
  * 列族过滤器
  * 比较列族来返回结果
  * 用户可以在列族一级筛选所需数据
  */
public  class  FamilyFilterInHbase {
     public  static  void  main(String[] args)  throws  IOException {
         Configuration configuration = HBaseConfiguration.create();
         Connection connection = ConnectionFactory.createConnection(configuration);
         //建立表的连接
         Table table = connection.getTable(TableName.valueOf( "user" ));
 
         //比较过滤器 现在表有2个列族 info  ship 当然实际有可能很多哦
         //取info < "kiss" <ship < "wings"
         Filter filter1 =  new  FamilyFilter(CompareFilter.CompareOp.GREATER,  new  BinaryComparator(Bytes.toBytes( "kiss" )));
         Scan scan =  new  Scan();
         scan.setFilter(filter1);
         ResultScanner scanner = table.getScanner(scan);
         for  (Result result : scanner){
            System.out.println(result);
         }
         scanner.close();
 
         Get get1 =  new  Get(Bytes.toBytes( "673782618261019142" ));
         get1.setFilter(filter1);
         Result result1=table.get(get1);
         System.out.println( "Result of get1(): "  + result1);
 
         //添加列族过滤器 info
         Filter filter2=  new  FamilyFilter(CompareFilter.CompareOp.EQUAL, new  BinaryComparator(Bytes.toBytes( "info" )));
         //获取一行数据
         Get get2 =  new  Get(Bytes.toBytes( "673782618261019142" ));
         //但是get列族ship 那么==>> Result of get():keyvalues=NONE  [本身冲突 所以无数据]
         //如果get列族info 那么==>> Result of get2():keyvalues={673782618261019142/...
         get2.addFamily(Bytes.toBytes( "ship" ));
         get2.setFilter(filter2);
         Result result2 =table.get(get2);
         System.out.println( "Result of get2():" +result2);
 
         scanner.close();
         table.close();
         connection.close();
 
     }
}
/**
  LESS "kiss"
  keyvalues={224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, 224382618261914241/info:phone/1472196211427/Put/vlen=11/seqid=0, 224382618261914241/info:weight/1472196211386/Put/vlen=3/seqid=0}
  keyvalues={510824118261011172/info:age/1472196213020/Put/vlen=2/seqid=0, 510824118261011172/info:height/1472196213056/Put/vlen=3/seqid=0, 510824118261011172/info:name/1472196212942/Put/vlen=8/seqid=0, 510824118261011172/info:phone/1472196213237/Put/vlen=11/seqid=0, 510824118261011172/info:weight/1472196213169/Put/vlen=3/seqid=0}
  keyvalues={524382618264914241/info:age/1472196193913/Put/vlen=2/seqid=0, 524382618264914241/info:height/1472196194783/Put/vlen=3/seqid=0, 524382618264914241/info:name/1472196193255/Put/vlen=8/seqid=0, 524382618264914241/info:phone/1472196195125/Put/vlen=11/seqid=0, 524382618264914241/info:weight/1472196194970/Put/vlen=3/seqid=0}
  keyvalues={673782618261019142/info:age/1472196211733/Put/vlen=2/seqid=0, 673782618261019142/info:height/1472196211761/Put/vlen=3/seqid=0, 673782618261019142/info:name/1472196211678/Put/vlen=7/seqid=0, 673782618261019142/info:phone/1472196211956/Put/vlen=11/seqid=0, 673782618261019142/info:weight/1472196211841/Put/vlen=3/seqid=0}
  keyvalues={813782218261011172/info:age/1472196212550/Put/vlen=2/seqid=0, 813782218261011172/info:height/1472196212605/Put/vlen=3/seqid=0, 813782218261011172/info:name/1472196212480/Put/vlen=8/seqid=0, 813782218261011172/info:phone/1472196212713/Put/vlen=11/seqid=0, 813782218261011172/info:weight/1472196212651/Put/vlen=3/seqid=0}
 
  GREATER "kiss"
  keyvalues={224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, 224382618261914241/ship:email/1472196211530/Put/vlen=11/seqid=0, 224382618261914241/ship:salary/1472196211594/Put/vlen=4/seqid=0}
  keyvalues={510824118261011172/ship:addr/1472196213328/Put/vlen=8/seqid=0, 510824118261011172/ship:email/1472196213422/Put/vlen=12/seqid=0, 510824118261011172/ship:salary/1472196214963/Put/vlen=5/seqid=0}
  keyvalues={524382618264914241/ship:addr/1472196195270/Put/vlen=7/seqid=0, 524382618264914241/ship:email/1472196195371/Put/vlen=13/seqid=0, 524382618264914241/ship:salary/1472196195485/Put/vlen=4/seqid=0}
  keyvalues={673782618261019142/ship:addr/1472196212059/Put/vlen=8/seqid=0, 673782618261019142/ship:email/1472196212176/Put/vlen=12/seqid=0, 673782618261019142/ship:salary/1472196212284/Put/vlen=4/seqid=0}
  keyvalues={813782218261011172/ship:addr/1472196212762/Put/vlen=4/seqid=0, 813782218261011172/ship:email/1472196212802/Put/vlen=12/seqid=0, 813782218261011172/ship:salary/1472196212840/Put/vlen=5/seqid=0}
 
  APPEND(LESS "kiss")
  Result of get(): keyvalues={673782618261019142/info:age/1472196211733/Put/vlen=2/seqid=0, 673782618261019142/info:height/1472196211761/Put/vlen=3/seqid=0, 673782618261019142/info:name/1472196211678/Put/vlen=7/seqid=0, 673782618261019142/info:phone/1472196211956/Put/vlen=11/seqid=0, 673782618261019142/info:weight/1472196211841/Put/vlen=3/seqid=0}
  APPEND(GREATER "kiss")
  Result of get1(): keyvalues={673782618261019142/ship:addr/1472196212059/Put/vlen=8/seqid=0, 673782618261019142/ship:email/1472196212176/Put/vlen=12/seqid=0, 673782618261019142/ship:salary/1472196212284/Put/vlen=4/seqid=0}
 
  //filter "info" get "ship"  
  Result of get():keyvalues=NONE
  //filter "info" get "info"
  Result of get2():keyvalues={673782618261019142/info:age/1472196211733/Put/vlen=2/seqid=0, 673782618261019142/info:height/1472196211761/Put/vlen=3/seqid=0, 673782618261019142/info:name/1472196211678/Put/vlen=7/seqid=0, 673782618261019142/info:phone/1472196211956/Put/vlen=11/seqid=0, 673782618261019142/info:weight/1472196211841/Put/vlen=3/seqid=0}
 
  **/

 

  •  ValueFilter值过滤器：
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
import  org.apache.hadoop.conf.Configuration;
import  org.apache.hadoop.hbase.Cell;
import  org.apache.hadoop.hbase.HBaseConfiguration;
import  org.apache.hadoop.hbase.TableName;
import  org.apache.hadoop.hbase.client.*;
import  org.apache.hadoop.hbase.filter.*;
import  org.apache.hadoop.hbase.util.Bytes;
import  java.io.IOException;
 
/**
  * 值过滤器
  * 根据值进行筛选 可以联合RegexStringComparator 进行设计
  */
public  class  FilterOfValue {
     public  static  void  main(String[] args)  throws  IOException {
         Configuration configuration = HBaseConfiguration.create();
         Connection connection = ConnectionFactory.createConnection(configuration);
         //建立表的连接
         Table table = connection.getTable(TableName.valueOf( "user" ));
 
         //值中包含了177的过滤器
         Filter filter =  new  ValueFilter(CompareFilter.CompareOp.EQUAL,
                 new  SubstringComparator( "1771392142" )
                 );
 
         Scan scan =  new  Scan();
         scan.setFilter(filter);
         ResultScanner scanner = table.getScanner(scan);
         for  (Result result : scanner){
             for  (Cell cell:result.rawCells()){
                 System.out.println( "Cell: " +cell+ ", Value: " +Bytes.toString(cell.getValueArray(),cell.getValueLength()));
             }
         }
         scanner.close();
 
         Get get1 =  new  Get(Bytes.toBytes( "673782618261019142" ));
         get1.setFilter(filter);
         Result result1=table.get(get1);
         for  (Cell cell : result1.rawCells()) {
             System.out.println( "Get1 Cell: "  + cell +  ", Value: "  +
                     Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                             cell.getValueLength()));
         }
 
         Get get2 =  new  Get(Bytes.toBytes( "813782218261011172" ));
         get2.setFilter(filter);
         Result result2=table.get(get2);
         for  (Cell cell : result2.rawCells()) {
             System.out.println( "Get2 Cell: "  + cell +  ", Value: "  +
                     Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                             cell.getValueLength()));
         }
 
         table.close();
         connection.close();
 
     }
}
 
 
/**
  原数据:                                                                               
  673782618261019142                              column=info:phone, timestamp=1472196211956, value=17713921424                                                                               
  813782218261011172                              column=info:phone, timestamp=1472196212713, value=12713921424
  *输出结果:
  Cell: 673782618261019142/info:phone/1472196211956/Put/vlen=11/seqid=0, Value: 73782618261019142infophoneVŻt�17713921424
  Get1 Cell: 673782618261019142/info:phone/1472196211956/Put/vlen=11/seqid=0, Value: 17713921424
**/

 

  • DependentColumnFilter 参考列过滤器
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
import  org.apache.hadoop.conf.Configuration;
import  org.apache.hadoop.hbase.Cell;
import  org.apache.hadoop.hbase.HBaseConfiguration;
import  org.apache.hadoop.hbase.TableName;
import  org.apache.hadoop.hbase.client.*;
import  org.apache.hadoop.hbase.filter.*;
import  org.apache.hadoop.hbase.util.Bytes;
 
import  java.io.IOException;
 
 
/**
  * 参考列过滤器
  * 根据列名进行筛选
  */
public  class  FilterOfDependentColumnFilter {
     private  static  Table table= null ;
     public  static  Table getTable() {
         if (table== null ){
             try  {
                 Configuration configuration = HBaseConfiguration.create();
                 Connection connection = ConnectionFactory.createConnection(configuration);
                 //建立表的连接
                 return  connection.getTable(TableName.valueOf( "user" ));
             } catch  (IOException e){
                 return  table;
             }
         }
         return  table;
     }
 
     public  static  void  filter( boolean  drop,CompareFilter.CompareOp oper,ByteArrayComparable comparable)  throws  IOException {
         Filter filter;
         if  (comparable !=  null ) {
             filter =  new  DependentColumnFilter(Bytes.toBytes( "info" ), Bytes.toBytes( "phone" ), drop, oper, comparable);
         }  else  {
             filter =  new  DependentColumnFilter(Bytes.toBytes( "info" ), Bytes.toBytes( "phone" ), drop);
         }
         Scan scan =  new  Scan();
         scan.setFilter(filter);
         ResultScanner scanner = getTable().getScanner(scan);
         for  (Result result : scanner) {
             for  (Cell cell : result.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
         }
         scanner.close();
         Get get =  new  Get(Bytes.toBytes( "673782618261019142" ));
         get.setFilter(filter);
         Result result = getTable().get(get);
         for  (Cell cell : result.rawCells()) {
             System.out.println( "Cell: "  + cell +  ", Value: "  +
                     Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                             cell.getValueLength()));
         }
     }
 
 
 
 
     public  static  void  main(String[] args)  throws  IOException {
         filter( true , CompareFilter.CompareOp.NO_OP,  null );
         filter( false , CompareFilter.CompareOp.NO_OP,  null );
         filter( true , CompareFilter.CompareOp.EQUAL,
                 new  BinaryPrefixComparator(Bytes.toBytes( "17713921424" )));
         filter( false , CompareFilter.CompareOp.EQUAL,
                 new  BinaryPrefixComparator(Bytes.toBytes( "17713921424" )));
         filter( true , CompareFilter.CompareOp.EQUAL,
                 new  RegexStringComparator( ".*\\.5" ));
         filter( false , CompareFilter.CompareOp.EQUAL,
                 new  RegexStringComparator( ".*\\.5" ));
     }
}
/**
 
  **/

 

  • PrefixFilter 前缀过滤器：
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
import  org.apache.hadoop.conf.Configuration;
import  org.apache.hadoop.hbase.Cell;
import  org.apache.hadoop.hbase.HBaseConfiguration;
import  org.apache.hadoop.hbase.TableName;
import  org.apache.hadoop.hbase.client.*;
import  org.apache.hadoop.hbase.filter.*;
import  org.apache.hadoop.hbase.util.Bytes;
 
import  java.io.IOException;
 
 
/**
  * 前缀过滤器
  * 根据行键的前缀进行过滤
  */
public  class  FilterOfPrefixFilter {
     public  static  void  main(String[] args)  throws  IOException {
         Configuration configuration = HBaseConfiguration.create();
         Connection connection = ConnectionFactory.createConnection(configuration);
         //建立表的连接
         Table table = connection.getTable(TableName.valueOf( "user" ));
         Filter filter =  new  PrefixFilter(Bytes.toBytes( "510824" ));
 
         Scan scan =  new  Scan();
         scan.setFilter(filter);
         ResultScanner scanner = table.getScanner(scan);
         for  (Result result : scanner) {
             for  (Cell cell : result.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             } }
         scanner.close();
         Get get =  new  Get(Bytes.toBytes( "row-5" ));
         get.setFilter(filter);
         Result result = table.get(get);
         for  (Cell cell : result.rawCells()) {
             System.out.println( "Cell: "  + cell +  ", Value: "  +
                     Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                             cell.getValueLength()));
         }
 
         scanner.close();
         table.close();
         connection.close();
 
     }
}
/**
  Cell: 510824118261011172/info:height/1472196213056/Put/vlen=3/seqid=0, Value: 188
  Cell: 510824118261011172/info:name/1472196212942/Put/vlen=8/seqid=0, Value: yangyang
  Cell: 510824118261011172/info:phone/1472196213237/Put/vlen=11/seqid=0, Value: 18013921626
  Cell: 510824118261011172/info:weight/1472196213169/Put/vlen=3/seqid=0, Value: 138
  Cell: 510824118261011172/ship:addr/1472196213328/Put/vlen=8/seqid=0, Value: shanghai
  Cell: 510824118261011172/ship:email/1472196213422/Put/vlen=12/seqid=0, Value: 199@sina.com
  Cell: 510824118261011172/ship:salary/1472196214963/Put/vlen=5/seqid=0, Value: 50000
**/

 

  •  PageFilter 分页过滤器
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
import  org.apache.hadoop.conf.Configuration;
import  org.apache.hadoop.hbase.Cell;
import  org.apache.hadoop.hbase.HBaseConfiguration;
import  org.apache.hadoop.hbase.TableName;
import  org.apache.hadoop.hbase.client.*;
import  org.apache.hadoop.hbase.filter.Filter;
import  org.apache.hadoop.hbase.filter.PageFilter;
import  org.apache.hadoop.hbase.filter.PrefixFilter;
import  org.apache.hadoop.hbase.util.Bytes;
import  java.io.IOException;
/**
  * 分页过滤器
  */
public  class  FilterOfPage {
     private  static  final  byte [] POSTFIX =  new  byte [] {  0x00  };
 
 
     public  static  void  main(String[] args)  throws  IOException {
         Configuration configuration = HBaseConfiguration.create();
         Connection connection = ConnectionFactory.createConnection(configuration);
         //建立表的连接
         Table table = connection.getTable(TableName.valueOf( "user" ));
         //分页大小
         Filter filter =  new  PageFilter( 3 );
 
         int  totalRows =  0 ;
         byte [] lastRow =  null ;
 
         while  ( true ) {
             Scan scan =  new  Scan();
             scan.setFilter(filter);
             if  (lastRow !=  null ) {
                 byte [] startRow = Bytes.add(lastRow, POSTFIX);
                 System.out.println( "start row: "  +
                         Bytes.toStringBinary(startRow));
                 scan.setStartRow(startRow);
             }
             ResultScanner scanner = table.getScanner(scan);
             int  localRows =  0 ;
             Result result;
             while  ((result = scanner.next()) !=  null ) {
                 System.out.println(localRows++ +  ": "  + result);
                 totalRows++;
                 lastRow = result.getRow();
             }
             scanner.close();
             if  (localRows ==  0 )  break ;
         }
         System.out.println( "total rows: "  + totalRows);
 
         table.close();
         connection.close();
 
     }
}
/**
  0: keyvalues={224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, 224382618261914241/info:phone/1472196211427/Put/vlen=11/seqid=0, 224382618261914241/info:weight/1472196211386/Put/vlen=3/seqid=0, 224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, 224382618261914241/ship:email/1472196211530/Put/vlen=11/seqid=0, 224382618261914241/ship:salary/1472196211594/Put/vlen=4/seqid=0}
  1: keyvalues={510824118261011172/info:age/1472196213020/Put/vlen=2/seqid=0, 510824118261011172/info:height/1472196213056/Put/vlen=3/seqid=0, 510824118261011172/info:name/1472196212942/Put/vlen=8/seqid=0, 510824118261011172/info:phone/1472196213237/Put/vlen=11/seqid=0, 510824118261011172/info:weight/1472196213169/Put/vlen=3/seqid=0, 510824118261011172/ship:addr/1472196213328/Put/vlen=8/seqid=0, 510824118261011172/ship:email/1472196213422/Put/vlen=12/seqid=0, 510824118261011172/ship:salary/1472196214963/Put/vlen=5/seqid=0}
  2: keyvalues={524382618264914241/info:age/1472196193913/Put/vlen=2/seqid=0, 524382618264914241/info:height/1472196194783/Put/vlen=3/seqid=0, 524382618264914241/info:name/1472196193255/Put/vlen=8/seqid=0, 524382618264914241/info:phone/1472196195125/Put/vlen=11/seqid=0, 524382618264914241/info:weight/1472196194970/Put/vlen=3/seqid=0, 524382618264914241/ship:addr/1472196195270/Put/vlen=7/seqid=0, 524382618264914241/ship:email/1472196195371/Put/vlen=13/seqid=0, 524382618264914241/ship:salary/1472196195485/Put/vlen=4/seqid=0}
  start row: 524382618264914241\x00
  0: keyvalues={673782618261019142/info:age/1472196211733/Put/vlen=2/seqid=0, 673782618261019142/info:height/1472196211761/Put/vlen=3/seqid=0, 673782618261019142/info:name/1472196211678/Put/vlen=7/seqid=0, 673782618261019142/info:phone/1472196211956/Put/vlen=11/seqid=0, 673782618261019142/info:weight/1472196211841/Put/vlen=3/seqid=0, 673782618261019142/ship:addr/1472196212059/Put/vlen=8/seqid=0, 673782618261019142/ship:email/1472196212176/Put/vlen=12/seqid=0, 673782618261019142/ship:salary/1472196212284/Put/vlen=4/seqid=0}
  1: keyvalues={813782218261011172/info:age/1472196212550/Put/vlen=2/seqid=0, 813782218261011172/info:height/1472196212605/Put/vlen=3/seqid=0, 813782218261011172/info:name/1472196212480/Put/vlen=8/seqid=0, 813782218261011172/info:phone/1472196212713/Put/vlen=11/seqid=0, 813782218261011172/info:weight/1472196212651/Put/vlen=3/seqid=0, 813782218261011172/ship:addr/1472196212762/Put/vlen=4/seqid=0, 813782218261011172/ship:email/1472196212802/Put/vlen=12/seqid=0, 813782218261011172/ship:salary/1472196212840/Put/vlen=5/seqid=0}
  start row: 813782218261011172\x00
  2016-08-29 17:17:57,197 INFO  [main] client.ConnectionManager$HConnectionImplementation: Closing zookeeper sessionid=0x56c13890bf003a
  total rows: 5
**/
  • KeyOnlyFilter 行键过滤器

  • FirstKeyOnlyFilter 首次行键过滤器

  • FirstKeyValueMatchingQualifiersFilter 

  • InclusiveStopFilter 包含结束的过滤器

  • FuzzyRowFilter 模糊行匹配过滤器

  • ColumnCountGetFilter 列计数过滤器
    可以使用这个过滤器来限制每行最多取回多少列，

    当一行的列数到设定的最大值，这个过滤器会停止整个扫描操作。

    适合在get方法中使用

    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
    import  org.apache.hadoop.conf.Configuration;
    import  org.apache.hadoop.hbase.Cell;
    import  org.apache.hadoop.hbase.HBaseConfiguration;
    import  org.apache.hadoop.hbase.TableName;
    import  org.apache.hadoop.hbase.client.*;
    import  org.apache.hadoop.hbase.filter.ColumnCountGetFilter;
    import  org.apache.hadoop.hbase.util.Bytes;
    import  java.io.IOException;
     
    /**
      * ColumnCountGetFilter 列数过滤器
      */
    public  class  FilterOfColumnCountGetFilter {
         public  static  void  main(String args[])  throws  IOException{
             Configuration configuration = HBaseConfiguration.create();
             Connection connection = ConnectionFactory.createConnection(configuration);
             Table table = connection.getTable(TableName.valueOf( "user" ));
     
             //限制返回的列数
             ColumnCountGetFilter columnCountGetFilter =  new  ColumnCountGetFilter( 3 );
             // column=info:age,column=info:height,column=info:name,column=info:phone,column=info:weight,
             Get get =  new  Get(Bytes.toBytes( "224382618261914241" ));
             get.setFilter(columnCountGetFilter);
             Result result = table.get(get);
             System.out.println( "Result of columnCountGetFilter get: " );
             for  (Cell cell : result.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
             Get get1 =  new  Get(Bytes.toBytes( "224382618261914241" ));
             Result result1 = table.get(get1);
             System.out.println( "Result of get: " );
             for  (Cell cell : result1.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
             table.close();
             connection.close();
         }
    }
     
    /**
      Result of columnCountGetFilter get:
      Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      Cell: 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, Value: 158
      Cell: 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, Value: lisi
      Result of get:
      Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      Cell: 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, Value: 158
      Cell: 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, Value: lisi
      Cell: 224382618261914241/info:phone/1472196211427/Put/vlen=11/seqid=0, Value: 13213921424
      Cell: 224382618261914241/info:weight/1472196211386/Put/vlen=3/seqid=0, Value: 128
      Cell: 224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, Value: chengdu
      Cell: 224382618261914241/ship:email/1472196211530/Put/vlen=11/seqid=0, Value: qq@sina.com
      Cell: 224382618261914241/ship:salary/1472196211594/Put/vlen=4/seqid=0, Value: 5000
    **/

     

  • ColumnPaginationFilter 列分页过滤
    HBase 的列可以很多，所以出现了列分页
    该过滤器可以对一行的所有列进行分页
    构造函数：
    ColumnPaginationFilter(int limit, int offset)
    ColumnPaginationFilter(int limit, byte[] columnOffset)
    limit 限制取回来列数  offset 偏移位就是开始位置 byte[] 字符串/书签偏移从哪里开始分页。
    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
    import  org.apache.hadoop.conf.Configuration;
    import  org.apache.hadoop.hbase.Cell;
    import  org.apache.hadoop.hbase.HBaseConfiguration;
    import  org.apache.hadoop.hbase.TableName;
    import  org.apache.hadoop.hbase.client.*;
    import  org.apache.hadoop.hbase.filter.ColumnPaginationFilter;
    import  org.apache.hadoop.hbase.util.Bytes;
     
    import  java.io.IOException;
     
    /**
      * ColumnPageFilter 列分页过滤器
      */
    public  class  FilterOColumnPageFilter {
         public  static  void  main(String args[])  throws  IOException{
             Configuration configuration = HBaseConfiguration.create();
             Connection connection = ConnectionFactory.createConnection(configuration);
             Table table = connection.getTable(TableName.valueOf( "user" ));
             //限制返回的列数 从第4列开始取 取3列数据
             ColumnPaginationFilter columnPaginationFilter =  new  ColumnPaginationFilter( 3 , 4 );
             Get get =  new  Get(Bytes.toBytes( "224382618261914241" ));
             get.setFilter(columnPaginationFilter);
             Result result = table.get(get);
             System.out.println( "Result of ColumnPageFilter get: " );
             for  (Cell cell : result.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
     
             //限制返回的列数 从第name列开始取 取3列数据
             ColumnPaginationFilter columnPaginationFilter2 =  new  ColumnPaginationFilter( 3 ,Bytes.toBytes( "name" ));
             Get get2 =  new  Get(Bytes.toBytes( "224382618261914241" ));
             get2.setFilter(columnPaginationFilter2);
             Result result2 = table.get(get2);
             System.out.println( "Result of ColumnPageFilter get: " );
             for  (Cell cell : result2.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
     
             Get get1 =  new  Get(Bytes.toBytes( "224382618261914241" ));
             Result result1 = table.get(get1);
             System.out.println( "Result of get: " );
             for  (Cell cell : result1.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
             table.close();
             connection.close();
         }
    }
     
    /**
      Result of ColumnPageFilter get:
      Cell: 224382618261914241/info:weight/1472196211386/Put/vlen=3/seqid=0, Value: 128
      Cell: 224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, Value: chengdu
      Cell: 224382618261914241/ship:email/1472196211530/Put/vlen=11/seqid=0, Value: qq@sina.com
      Result of ColumnPageFilter get:
      Cell: 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, Value: lisi
      Cell: 224382618261914241/info:phone/1472196211427/Put/vlen=11/seqid=0, Value: 13213921424
      Cell: 224382618261914241/info:weight/1472196211386/Put/vlen=3/seqid=0, Value: 128
      Result of get:
      Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      Cell: 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, Value: 158
      Cell: 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, Value: lisi
      Cell: 224382618261914241/info:phone/1472196211427/Put/vlen=11/seqid=0, Value: 13213921424
      Cell: 224382618261914241/info:weight/1472196211386/Put/vlen=3/seqid=0, Value: 128
      Cell: 224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, Value: chengdu
      Cell: 224382618261914241/ship:email/1472196211530/Put/vlen=11/seqid=0, Value: qq@sina.com
      Cell: 224382618261914241/ship:salary/1472196211594/Put/vlen=4/seqid=0, Value: 5000
    **/

 

  • ColumnPrefixFilter 列前缀过虑器 
    该过滤器通过对列名称进行前缀匹配过滤
    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
    import  org.apache.hadoop.conf.Configuration;
    import  org.apache.hadoop.hbase.Cell;
    import  org.apache.hadoop.hbase.HBaseConfiguration;
    import  org.apache.hadoop.hbase.TableName;
    import  org.apache.hadoop.hbase.client.*;
    import  org.apache.hadoop.hbase.filter.ColumnPrefixFilter;
    import  org.apache.hadoop.hbase.filter.Filter;
    import  org.apache.hadoop.hbase.util.Bytes;
    import  java.io.IOException;
     
    /**
      * ColumnPrefixFilter 列前缀过滤器
      */
    public  class  FilterOfColumnPrefixFilter {
         public  static  void  main(String args[])  throws  IOException{
             Configuration configuration = HBaseConfiguration.create();
             Connection connection = ConnectionFactory.createConnection(configuration);
             Table table = connection.getTable(TableName.valueOf( "user" ));
             //取列名已ag开头的
             Filter columnPrefixFilter =  new  ColumnPrefixFilter(Bytes.toBytes( "a" ));
             Get get =  new  Get(Bytes.toBytes( "224382618261914241" ));
             get.setFilter(columnPrefixFilter);
             Result result = table.get(get);
             System.out.println( "Result of columnPrefixFilter get: " );
             for  (Cell cell : result.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
     
             Get get1 =  new  Get(Bytes.toBytes( "224382618261914241" ));
             Result result1 = table.get(get1);
             System.out.println( "Result of get: " );
             for  (Cell cell : result1.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
             table.close();
             connection.close();
         }
    }
     
    /**
      Result of columnPrefixFilter get:
      Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      Cell: 224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, Value: chengdu
      Result of get:
      Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      Cell: 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, Value: 158
      Cell: 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, Value: lisi
      Cell: 224382618261914241/info:phone/1472196211427/Put/vlen=11/seqid=0, Value: 13213921424
      Cell: 224382618261914241/info:weight/1472196211386/Put/vlen=3/seqid=0, Value: 128
      Cell: 224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, Value: chengdu
      Cell: 224382618261914241/ship:email/1472196211530/Put/vlen=11/seqid=0, Value: qq@sina.com
      Cell: 224382618261914241/ship:salary/1472196211594/Put/vlen=4/seqid=0, Value: 5000
    **/

  • MultipleColumnPrefixFilter 多个列前缀过滤器
    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
    import  org.apache.hadoop.conf.Configuration;
    import  org.apache.hadoop.hbase.Cell;
    import  org.apache.hadoop.hbase.HBaseConfiguration;
    import  org.apache.hadoop.hbase.TableName;
    import  org.apache.hadoop.hbase.client.*;
    import  org.apache.hadoop.hbase.filter.Filter;
    import  org.apache.hadoop.hbase.filter.MultipleColumnPrefixFilter;
    import  org.apache.hadoop.hbase.util.Bytes;
     
    import  java.io.IOException;
     
    /**
      * MultipleColumnPrefixFilter 多个列前缀过滤器
      */
    public  class  FilterOfMultipleColumnPrefixFilter {
         public  static  void  main(String args[])  throws  IOException{
             Configuration configuration = HBaseConfiguration.create();
             Connection connection = ConnectionFactory.createConnection(configuration);
             Table table = connection.getTable(TableName.valueOf( "user" ));
             //取列名已a开头的 还有已h 开头的
             Filter filter =  new  MultipleColumnPrefixFilter( new  byte [][] {Bytes.toBytes( "a" ),Bytes.toBytes( "h" )});
             Get get =  new  Get(Bytes.toBytes( "224382618261914241" ));
             get.setFilter(filter);
             Result result = table.get(get);
             System.out.println( "Result of columnPrefixFilter get: " );
             for  (Cell cell : result.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
     
             Get get1 =  new  Get(Bytes.toBytes( "224382618261914241" ));
             Result result1 = table.get(get1);
             System.out.println( "Result of get: " );
             for  (Cell cell : result1.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
             table.close();
             connection.close();
         }
    }
     
    /**
      Result of columnPrefixFilter get:
      Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      Cell: 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, Value: 158
      Cell: 224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, Value: chengdu
      Result of get:
      Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      Cell: 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, Value: 158
      Cell: 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, Value: lisi
      Cell: 224382618261914241/info:phone/1472196211427/Put/vlen=11/seqid=0, Value: 13213921424
      Cell: 224382618261914241/info:weight/1472196211386/Put/vlen=3/seqid=0, Value: 128
      Cell: 224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, Value: chengdu
      Cell: 224382618261914241/ship:email/1472196211530/Put/vlen=11/seqid=0, Value: qq@sina.com
      Cell: 224382618261914241/ship:salary/1472196211594/Put/vlen=4/seqid=0, Value: 5000
    **/

     

  • ColumnRangeFilter 列范围过滤器
    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
    import  org.apache.hadoop.conf.Configuration;
    import  org.apache.hadoop.hbase.Cell;
    import  org.apache.hadoop.hbase.HBaseConfiguration;
    import  org.apache.hadoop.hbase.TableName;
    import  org.apache.hadoop.hbase.client.*;
    import  org.apache.hadoop.hbase.filter.ColumnRangeFilter;
    import  org.apache.hadoop.hbase.filter.Filter;
    import  org.apache.hadoop.hbase.util.Bytes;
     
    import  java.io.IOException;
     
    /**
      * ColumnRangeFilter 列范围过滤器
      */
    public  class  FilterOfColumnRangeFilter {
         public  static  void  main(String args[])  throws  IOException{
             Configuration configuration = HBaseConfiguration.create();
             Connection connection = ConnectionFactory.createConnection(configuration);
             Table table = connection.getTable(TableName.valueOf( "user" ));
             //minColumn - minimum value for the column range. If if it's null, there is no lower bound.
             //minColumnInclusive - if true, include minColumn in the range. 如果是true 就要包含minColumn
             //maxColumn - maximum value for the column range. If it's null,
             //maxColumnInclusive - if true, include maxColumn in the range. there is no upper bound.
            //从email到phone范围内的所有列 第二个参数为true所以包含了email <br>　　    Filter filter = new ColumnRangeFilter(Bytes.toBytes("email"), true, Bytes.toBytes("phone"), false);
             Get get =  new  Get(Bytes.toBytes( "224382618261914241" ));
             get.setFilter(filter);
             Result result = table.get(get);
             System.out.println( "Result of ColumnRangeFilter get: " );
             for  (Cell cell : result.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
     
             Get get1 =  new  Get(Bytes.toBytes( "224382618261914241" ));
             Result result1 = table.get(get1);
             System.out.println( "Result of get: " );
             for  (Cell cell : result1.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
             table.close();
             connection.close();
         }
    }
     
    /**
      Result of ColumnRangeFilter get:
      Cell: 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, Value: 158
      Cell: 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, Value: lisi
      Cell: 224382618261914241/ship:email/1472196211530/Put/vlen=11/seqid=0, Value: qq@sina.com
      Result of get:
      Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      Cell: 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, Value: 158
      Cell: 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, Value: lisi
      Cell: 224382618261914241/info:phone/1472196211427/Put/vlen=11/seqid=0, Value: 13213921424
      Cell: 224382618261914241/info:weight/1472196211386/Put/vlen=3/seqid=0, Value: 128
      Cell: 224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, Value: chengdu
      Cell: 224382618261914241/ship:email/1472196211530/Put/vlen=11/seqid=0, Value: qq@sina.com
      Cell: 224382618261914241/ship:salary/1472196211594/Put/vlen=4/seqid=0, Value: 5000
      2016-08-31 17:53:28,394 INFO  [main] client.ConnectionManager$HConnectionImplementati
    **/

     


  • SingleColumnValueFilter 单列值过滤器
    用一列的值决定是否一行数据被过滤
    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
    import  org.apache.hadoop.conf.Configuration;
    import  org.apache.hadoop.hbase.Cell;
    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.filter.SubstringComparator;
    import  org.apache.hadoop.hbase.util.Bytes;
    import  java.io.IOException;
     
    /**
      * SingleColumnValueFilter 单列过滤器
      */
    public  class  FilterOfSingleColumnValueFilter {
         public  static  void  main(String args[])  throws  IOException{
             Configuration configuration = HBaseConfiguration.create();
             Connection connection = ConnectionFactory.createConnection(configuration);
             Table table = connection.getTable(TableName.valueOf( "user" ));
     
             //  510824118261011172 column=ship:email, timestamp=1472196213422, value=199@sina.com
             SingleColumnValueFilter singleColumnValueFilter =  new  SingleColumnValueFilter(Bytes.toBytes( "ship" ),Bytes.toBytes( "email" ), CompareFilter.CompareOp.EQUAL, new  SubstringComparator( "199@sina.com" ));
             singleColumnValueFilter.setFilterIfMissing( true );
     
             Scan scan =  new  Scan();
             scan.setFilter(singleColumnValueFilter);
             ResultScanner results = table.getScanner(scan);
             for  (Result result:results){
                 for  (Cell cell :result.rawCells()){
                     System.out.println( "Cell: " +cell+ ",Value:"  + Bytes.toString(cell.getValueArray(),cell.getValueOffset(), cell.getValueLength()));
                 }
             }
             results.close();
             // 224382618261914241 column=ship:email, timestamp=1472196211530, value=qq@sina.com
             Get get =  new  Get(Bytes.toBytes( "224382618261914241" ));
             get.setFilter(singleColumnValueFilter);
             Result result = table.get(get);
             System.out.println( "Result of get: " );
             for  (Cell cell : result.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
     
             Get get1 =  new  Get(Bytes.toBytes( "510824118261011172" ));
             get1.setFilter(singleColumnValueFilter);
             Result result1 = table.get(get1);
             System.out.println( "Result of get1: " );
             for  (Cell cell : result1.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
     
             table.close();
             connection.close();
         }
    }
     
    /**
      Cell: 510824118261011172/info:age/1472196213020/Put/vlen=2/seqid=0,Value:18
      Cell: 510824118261011172/info:height/1472196213056/Put/vlen=3/seqid=0,Value:188
      Cell: 510824118261011172/info:name/1472196212942/Put/vlen=8/seqid=0,Value:yangyang
      Cell: 510824118261011172/info:phone/1472196213237/Put/vlen=11/seqid=0,Value:18013921626
      Cell: 510824118261011172/info:weight/1472196213169/Put/vlen=3/seqid=0,Value:138
      Cell: 510824118261011172/ship:addr/1472196213328/Put/vlen=8/seqid=0,Value:shanghai
      Cell: 510824118261011172/ship:email/1472196213422/Put/vlen=12/seqid=0,Value:199@sina.com
      Cell: 510824118261011172/ship:salary/1472196214963/Put/vlen=5/seqid=0,Value:50000
      Result of get:
      Result of get1:
      Cell: 510824118261011172/info:age/1472196213020/Put/vlen=2/seqid=0, Value: 18
      Cell: 510824118261011172/info:height/1472196213056/Put/vlen=3/seqid=0, Value: 188
      Cell: 510824118261011172/info:name/1472196212942/Put/vlen=8/seqid=0, Value: yangyang
      Cell: 510824118261011172/info:phone/1472196213237/Put/vlen=11/seqid=0, Value: 18013921626
      Cell: 510824118261011172/info:weight/1472196213169/Put/vlen=3/seqid=0, Value: 138
      Cell: 510824118261011172/ship:addr/1472196213328/Put/vlen=8/seqid=0, Value: shanghai
      Cell: 510824118261011172/ship:email/1472196213422/Put/vlen=12/seqid=0, Value: 199@sina.com
      Cell: 510824118261011172/ship:salary/1472196214963/Put/vlen=5/seqid=0, Value: 50000
    **/

     

  • SingleColumnValueExcludeFilter 单列排除过滤器
    单列排除过滤器继承自SingleColumnValueFilter，过滤的方式还是按照SingleColumnValueFilter去过滤，
    但是最后的结果集去除了作为过滤条件的列
    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
             //  510824118261011172 column=ship:email, timestamp=1472196213422, value=199@sina.com
             SingleColumnValueExcludeFilter singleColumnValueExcludeFilter =  new  SingleColumnValueExcludeFilter(Bytes.toBytes( "ship" ),Bytes.toBytes( "email" ), CompareFilter.CompareOp.EQUAL, new  SubstringComparator( "199@sina.com" ));
             singleColumnValueExcludeFilter.setFilterIfMissing( true );
     
             Scan scan =  new  Scan();
             scan.setFilter(singleColumnValueExcludeFilter);
             ResultScanner results = table.getScanner(scan);
             for  (Result result:results){
                 for  (Cell cell :result.rawCells()){
                     System.out.println( "Cell: " +cell+ ",Value:"  + Bytes.toString(cell.getValueArray(),cell.getValueOffset(), cell.getValueLength()));
                 }
             }
             results.close();
             // 224382618261914241 column=ship:email, timestamp=1472196211530, value=qq@sina.com
             Get get =  new  Get(Bytes.toBytes( "224382618261914241" ));
             get.setFilter(singleColumnValueExcludeFilter);
             Result result = table.get(get);
             System.out.println( "Result of get: " );
             for  (Cell cell : result.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
     
             Get get1 =  new  Get(Bytes.toBytes( "510824118261011172" ));
             get1.setFilter(singleColumnValueExcludeFilter);
             Result result1 = table.get(get1);
             System.out.println( "Result of get1: " );
             for  (Cell cell : result1.rawCells()) {
                 System.out.println( "Cell: "  + cell +  ", Value: "  +
                         Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                 cell.getValueLength()));
             }
    /**
      * Cell: 510824118261011172/info:age/1472196213020/Put/vlen=2/seqid=0,Value:18
      Cell: 510824118261011172/info:height/1472196213056/Put/vlen=3/seqid=0,Value:188
      Cell: 510824118261011172/info:name/1472196212942/Put/vlen=8/seqid=0,Value:yangyang
      Cell: 510824118261011172/info:phone/1472196213237/Put/vlen=11/seqid=0,Value:18013921626
      Cell: 510824118261011172/info:weight/1472196213169/Put/vlen=3/seqid=0,Value:138
      Cell: 510824118261011172/ship:addr/1472196213328/Put/vlen=8/seqid=0,Value:shanghai
      Cell: 510824118261011172/ship:salary/1472196214963/Put/vlen=5/seqid=0,Value:50000
      Result of get:
      Result of get1:
      Cell: 510824118261011172/info:age/1472196213020/Put/vlen=2/seqid=0, Value: 18
      Cell: 510824118261011172/info:height/1472196213056/Put/vlen=3/seqid=0, Value: 188
      Cell: 510824118261011172/info:name/1472196212942/Put/vlen=8/seqid=0, Value: yangyang
      Cell: 510824118261011172/info:phone/1472196213237/Put/vlen=11/seqid=0, Value: 18013921626
      Cell: 510824118261011172/info:weight/1472196213169/Put/vlen=3/seqid=0, Value: 138
      Cell: 510824118261011172/ship:addr/1472196213328/Put/vlen=8/seqid=0, Value: shanghai
      Cell: 510824118261011172/ship:salary/1472196214963/Put/vlen=5/seqid=0, Value: 50000
      */

     

  • TimestampsFilter 时间过滤器
    使用时间戳的值来过滤值
    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
    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.Filter;
    import  org.apache.hadoop.hbase.filter.TimestampsFilter;
    import  java.io.IOException;
    import  java.util.ArrayList;
    import  java.util.List;
     
    /**
      * TimestampsFilter 时间过滤器
      */
    public  class  FilterOfTimestampsFilter {
     
         public  static  void  main(String args[])  throws  IOException{
             Configuration configuration = HBaseConfiguration.create();
             Connection connection = ConnectionFactory.createConnection(configuration);
             Table table = connection.getTable(TableName.valueOf( "user" ));
             List<Long> ts =  new  ArrayList<Long>();
             ts.add( new  Long( "1472196195270" ));
             ts.add( new  Long( "1472196212480" ));
             ts.add( new  Long( 15 ));
             Filter filter =  new  TimestampsFilter(ts);
             Scan scan1 =  new  Scan();
             scan1.setFilter(filter);
             ResultScanner scanner1 = table.getScanner(scan1);
             for (Result result:scanner1){
                 System.out.println(result);
             }
             scanner1.close();
             Scan scan2 =  new  Scan();
             scan2.setFilter(filter);
             //加了时间范围 故意多加了1s 1472196212480+1=1472196212481
             scan2.setTimeRange(1472196195271L, 1472196212481L);
             ResultScanner scanner2 = table.getScanner(scan2);
             System.out.println( "Add time range:" );
             for  (Result result : scanner2) {
                 System.out.println(result);
             }
             scanner2.close();
         }
    }
    /**
      keyvalues={524382618264914241/ship:addr/1472196195270/Put/vlen=7/seqid=0}
      keyvalues={813782218261011172/info:name/1472196212480/Put/vlen=8/seqid=0}
      Add time range:
      keyvalues={813782218261011172/info:name/1472196212480/Put/vlen=8/seqid=0}
    **/
  • RandomRowFilter  随机行过滤器
    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
    import  org.apache.hadoop.conf.Configuration;
    import  org.apache.hadoop.hbase.Cell;
    import  org.apache.hadoop.hbase.HBaseConfiguration;
    import  org.apache.hadoop.hbase.TableName;
    import  org.apache.hadoop.hbase.client.*;
    import  org.apache.hadoop.hbase.filter.Filter;
    import  org.apache.hadoop.hbase.filter.RandomRowFilter;
    import  org.apache.hadoop.hbase.util.Bytes;
     
    import  java.io.IOException;
     
    /**
      * RandomRowFilter 随机行过滤器
      */
    public  class  FilterOfRandomRowFilter {
         public  static  void  main(String args[])  throws  IOException{
             Configuration configuration = HBaseConfiguration.create();
             Connection connection = ConnectionFactory.createConnection(configuration);
             Table table = connection.getTable(TableName.valueOf( "user" ));
             //该构造参数0-1之间,如果为负数全部过滤,大于1全部通过 0.2f表的该行数据20%的概率通过
             Filter filter =  new  RandomRowFilter( 0 .2f);
             Scan scan =  new  Scan();
             scan.setFilter(filter);
             ResultScanner results = table.getScanner(scan);
             for  (Result result:results) {
                 for  (Cell cell : result.rawCells()) {
                     System.out.println( "Cell: "  + cell +  ", Value: "  +
                             Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                     cell.getValueLength()));
                 }
             }
             table.close();
             connection.close();
         }
    }
     
    /**
      Cell: 510824118261011172/info:age/1472196213020/Put/vlen=2/seqid=0, Value: 18
      Cell: 510824118261011172/info:height/1472196213056/Put/vlen=3/seqid=0, Value: 188
      Cell: 510824118261011172/info:name/1472196212942/Put/vlen=8/seqid=0, Value: yangyang
      Cell: 510824118261011172/info:phone/1472196213237/Put/vlen=11/seqid=0, Value: 18013921626
      Cell: 510824118261011172/info:weight/1472196213169/Put/vlen=3/seqid=0, Value: 138
      Cell: 510824118261011172/ship:addr/1472196213328/Put/vlen=8/seqid=0, Value: shanghai
      Cell: 510824118261011172/ship:email/1472196213422/Put/vlen=12/seqid=0, Value: 199@sina.com
      Cell: 510824118261011172/ship:salary/1472196214963/Put/vlen=5/seqid=0, Value: 50000
    **/

    　　

  • Decorating Filters  装饰过滤器或附加过滤器
  • SkipFilter 跳过过滤器 根据构造器中的过滤器为基准跳过行
    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
    91
    92
    93
    94
    95
    96
    97
    98
    99
    100
    101
    102
    103
    104
    105
    106
    107
    108
    109
    110
    111
    112
    113
    114
    115
    116
    117
    118
    119
    import  org.apache.hadoop.conf.Configuration;
    import  org.apache.hadoop.hbase.Cell;
    import  org.apache.hadoop.hbase.HBaseConfiguration;
    import  org.apache.hadoop.hbase.TableName;
    import  org.apache.hadoop.hbase.client.*;
    import  org.apache.hadoop.hbase.filter.*;
    import  org.apache.hadoop.hbase.util.Bytes;
    import  java.io.IOException;
     
    /**
      * SkipFilter 跳过(忽略)过滤器
      * similarface
      * similarface@outlook.com
      */
    public  class  FilterOfSkipFilter {
         public  static  void  main(String args[])  throws  IOException{
             Configuration configuration = HBaseConfiguration.create();
             Connection connection = ConnectionFactory.createConnection(configuration);
             Table table = connection.getTable(TableName.valueOf( "user" ));
             //510824118261011172                                     column=info:height, timestamp=1472196213056, value=188
             //673782618261019142                                     column=info:weight, timestamp=1472196211841, value=188
             //如果列值中含有188这个数值,那么这列将会跳过
             Filter filter =  new  ValueFilter(CompareFilter.CompareOp.NOT_EQUAL, new  BinaryComparator(Bytes.toBytes( "188" )));
     
             Scan scan =  new  Scan();
             scan.setFilter(filter);
             ResultScanner results = table.getScanner(scan);
             for  (Result result:results) {
                 for  (Cell cell : result.rawCells()) {
                     System.out.println( "Cell: "  + cell +  ", Value: "  +
                             Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                     cell.getValueLength()));
                 }
             }
             Scan scan1 =  new  Scan();
             //skipfilter的构造参数时filter
             //  filter==>如果列值中含有188这个数值,那么这列将会跳过 filter2==>就是如果列值中含有188这个数值那么整个行都会被跳过 表示不会出现[510824118261011172,673782618261019142]
             Filter filter2 =  new  SkipFilter(filter);
             scan1.setFilter(filter2);
             ResultScanner scanner2= table.getScanner(scan1);
             for (Result result:scanner2){
                 for  (Cell cell : result.rawCells()) {
                     System.out.println( "SKIP Cell: "  + cell +  ", Value: "  +
                             Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                     cell.getValueLength()));
                 }
             }
             results.close();
             scanner2.close();
             table.close();
             connection.close();
         }
    }
     
    /**
      Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      Cell: 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, Value: 158
      Cell: 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, Value: lisi
      Cell: 224382618261914241/info:phone/1472196211427/Put/vlen=11/seqid=0, Value: 13213921424
      Cell: 224382618261914241/info:weight/1472196211386/Put/vlen=3/seqid=0, Value: 128
      Cell: 224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, Value: chengdu
      Cell: 224382618261914241/ship:email/1472196211530/Put/vlen=11/seqid=0, Value: qq@sina.com
      Cell: 224382618261914241/ship:salary/1472196211594/Put/vlen=4/seqid=0, Value: 5000
      Cell: 510824118261011172/info:age/1472196213020/Put/vlen=2/seqid=0, Value: 18
      Cell: 510824118261011172/info:name/1472196212942/Put/vlen=8/seqid=0, Value: yangyang
      Cell: 510824118261011172/info:phone/1472196213237/Put/vlen=11/seqid=0, Value: 18013921626
      Cell: 510824118261011172/info:weight/1472196213169/Put/vlen=3/seqid=0, Value: 138
      Cell: 510824118261011172/ship:addr/1472196213328/Put/vlen=8/seqid=0, Value: shanghai
      Cell: 510824118261011172/ship:email/1472196213422/Put/vlen=12/seqid=0, Value: 199@sina.com
      Cell: 510824118261011172/ship:salary/1472196214963/Put/vlen=5/seqid=0, Value: 50000
      Cell: 524382618264914241/info:age/1472196193913/Put/vlen=2/seqid=0, Value: 30
      Cell: 524382618264914241/info:height/1472196194783/Put/vlen=3/seqid=0, Value: 168
      Cell: 524382618264914241/info:name/1472196193255/Put/vlen=8/seqid=0, Value: zhangsan
      Cell: 524382618264914241/info:phone/1472196195125/Put/vlen=11/seqid=0, Value: 13212321424
      Cell: 524382618264914241/info:weight/1472196194970/Put/vlen=3/seqid=0, Value: 168
      Cell: 524382618264914241/ship:addr/1472196195270/Put/vlen=7/seqid=0, Value: beijing
      Cell: 524382618264914241/ship:email/1472196195371/Put/vlen=13/seqid=0, Value: sina@sina.com
      Cell: 524382618264914241/ship:salary/1472196195485/Put/vlen=4/seqid=0, Value: 3000
      Cell: 673782618261019142/info:age/1472196211733/Put/vlen=2/seqid=0, Value: 19
      Cell: 673782618261019142/info:height/1472196211761/Put/vlen=3/seqid=0, Value: 178
      Cell: 673782618261019142/info:name/1472196211678/Put/vlen=7/seqid=0, Value: zhaoliu
      Cell: 673782618261019142/info:phone/1472196211956/Put/vlen=11/seqid=0, Value: 17713921424
      Cell: 673782618261019142/ship:addr/1472196212059/Put/vlen=8/seqid=0, Value: shenzhen
      Cell: 673782618261019142/ship:email/1472196212176/Put/vlen=12/seqid=0, Value: 126@sina.com
      Cell: 673782618261019142/ship:salary/1472196212284/Put/vlen=4/seqid=0, Value: 8000
      Cell: 813782218261011172/info:age/1472196212550/Put/vlen=2/seqid=0, Value: 19
      Cell: 813782218261011172/info:height/1472196212605/Put/vlen=3/seqid=0, Value: 158
      Cell: 813782218261011172/info:name/1472196212480/Put/vlen=8/seqid=0, Value: wangmazi
      Cell: 813782218261011172/info:phone/1472196212713/Put/vlen=11/seqid=0, Value: 12713921424
      Cell: 813782218261011172/info:weight/1472196212651/Put/vlen=3/seqid=0, Value: 118
      Cell: 813782218261011172/ship:addr/1472196212762/Put/vlen=4/seqid=0, Value: xian
      Cell: 813782218261011172/ship:email/1472196212802/Put/vlen=12/seqid=0, Value: 139@sina.com
      Cell: 813782218261011172/ship:salary/1472196212840/Put/vlen=5/seqid=0, Value: 10000
      
      SKIP Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      SKIP Cell: 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, Value: 158
      SKIP Cell: 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, Value: lisi
      SKIP Cell: 224382618261914241/info:phone/1472196211427/Put/vlen=11/seqid=0, Value: 13213921424
      SKIP Cell: 224382618261914241/info:weight/1472196211386/Put/vlen=3/seqid=0, Value: 128
      SKIP Cell: 224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, Value: chengdu
      SKIP Cell: 224382618261914241/ship:email/1472196211530/Put/vlen=11/seqid=0, Value: qq@sina.com
      SKIP Cell: 224382618261914241/ship:salary/1472196211594/Put/vlen=4/seqid=0, Value: 5000
      SKIP Cell: 524382618264914241/info:age/1472196193913/Put/vlen=2/seqid=0, Value: 30
      SKIP Cell: 524382618264914241/info:height/1472196194783/Put/vlen=3/seqid=0, Value: 168
      SKIP Cell: 524382618264914241/info:name/1472196193255/Put/vlen=8/seqid=0, Value: zhangsan
      SKIP Cell: 524382618264914241/info:phone/1472196195125/Put/vlen=11/seqid=0, Value: 13212321424
      SKIP Cell: 524382618264914241/info:weight/1472196194970/Put/vlen=3/seqid=0, Value: 168
      SKIP Cell: 524382618264914241/ship:addr/1472196195270/Put/vlen=7/seqid=0, Value: beijing
      SKIP Cell: 524382618264914241/ship:email/1472196195371/Put/vlen=13/seqid=0, Value: sina@sina.com
      SKIP Cell: 524382618264914241/ship:salary/1472196195485/Put/vlen=4/seqid=0, Value: 3000
      SKIP Cell: 813782218261011172/info:age/1472196212550/Put/vlen=2/seqid=0, Value: 19
      SKIP Cell: 813782218261011172/info:height/1472196212605/Put/vlen=3/seqid=0, Value: 158
      SKIP Cell: 813782218261011172/info:name/1472196212480/Put/vlen=8/seqid=0, Value: wangmazi
      SKIP Cell: 813782218261011172/info:phone/1472196212713/Put/vlen=11/seqid=0, Value: 12713921424
      SKIP Cell: 813782218261011172/info:weight/1472196212651/Put/vlen=3/seqid=0, Value: 118
      SKIP Cell: 813782218261011172/ship:addr/1472196212762/Put/vlen=4/seqid=0, Value: xian
      SKIP Cell: 813782218261011172/ship:email/1472196212802/Put/vlen=12/seqid=0, Value: 139@sina.com
      SKIP Cell: 813782218261011172/ship:salary/1472196212840/Put/vlen=5/seqid=0, Value: 10000
    **/

    　　

  • WhileMatchFilter 当匹配到就中断扫描
    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
    import  org.apache.hadoop.conf.Configuration;
    import  org.apache.hadoop.hbase.Cell;
    import  org.apache.hadoop.hbase.HBaseConfiguration;
    import  org.apache.hadoop.hbase.TableName;
    import  org.apache.hadoop.hbase.client.*;
    import  org.apache.hadoop.hbase.filter.*;
    import  org.apache.hadoop.hbase.util.Bytes;
     
    import  java.io.IOException;
     
    /**
      * WhileMatchFilter 全匹配过滤器 [当匹配到就中断扫描]
      * similarface
      * similarface@outlook.com
      */
    public  class  FilterOfWhileMatchFilter {
         public  static  void  main(String args[])  throws  IOException{
             Configuration configuration = HBaseConfiguration.create();
             Connection connection = ConnectionFactory.createConnection(configuration);
             Table table = connection.getTable(TableName.valueOf( "user" ));
             //匹配 510824118261011172 的行
             Filter filter1= new  RowFilter(CompareFilter.CompareOp.NOT_EQUAL, new  BinaryComparator(Bytes.toBytes( "510824118261011172" )));
             Scan scan =  new  Scan();
             scan.setFilter(filter1);
             ResultScanner results = table.getScanner(scan);
             for  (Result result:results) {
                 for  (Cell cell : result.rawCells()) {
                     System.out.println( "Cell: "  + cell +  ", Value: "  +
                             Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                     cell.getValueLength()));
                 }
             }
             //  匹配 510824118261011172 的行马上中断本次扫描操作
             Filter filter2 =  new  WhileMatchFilter(filter1);
             Scan scan1 =  new  Scan();
             scan1.setFilter(filter2);
             ResultScanner scanner2= table.getScanner(scan1);
             for (Result result:scanner2){
                 for  (Cell cell : result.rawCells()) {
                     System.out.println( "WhileMatchFilter Cell: "  + cell +  ", Value: "  +
                             Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                     cell.getValueLength()));
                 }
             }
             results.close();
             scanner2.close();
             table.close();
             connection.close();
         }
    }
     
    /**
      Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      Cell: 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, Value: 158
      ...
      Cell: 524382618264914241/ship:addr/1472196195270/Put/vlen=7/seqid=0, Value: beijing
      Cell: 524382618264914241/ship:email/1472196195371/Put/vlen=13/seqid=0, Value: sina@sina.com
      ...
      Cell: 813782218261011172/ship:salary/1472196212840/Put/vlen=5/seqid=0, Value: 10000
      WhileMatchFilter Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      ...
      WhileMatchFilter Cell: 224382618261914241/ship:salary/1472196211594/Put/vlen=4/seqid=0, Value: 5000
    **/

     

  • FilterList 过滤列表［多个过滤器一起起作用］
    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
    91
    92
    93
    94
    95
    96
    97
    98
    99
    100
    101
    102
    103
    104
    105
    106
    107
    108
    109
    110
    111
    112
    113
    import  org.apache.hadoop.conf.Configuration;
    import  org.apache.hadoop.hbase.Cell;
    import  org.apache.hadoop.hbase.HBaseConfiguration;
    import  org.apache.hadoop.hbase.TableName;
    import  org.apache.hadoop.hbase.client.*;
    import  org.apache.hadoop.hbase.filter.*;
    import  org.apache.hadoop.hbase.util.Bytes;
    import  java.io.IOException;
    import  java.util.ArrayList;
    import  java.util.List;
     
    /**
      * FilterList 过滤器列表[多个过滤器组合在一起]
      * similarface
      * similarface@outlook.com
      */
    public  class  FilterOfFilterList {
         public  static  void  main(String args[])  throws  IOException{
             Configuration configuration = HBaseConfiguration.create();
             Connection connection = ConnectionFactory.createConnection(configuration);
             Table table = connection.getTable(TableName.valueOf( "user" ));
             List<Filter> filters =  new  ArrayList<Filter>();
             Filter filter1= new  RowFilter(CompareFilter.CompareOp.GREATER_OR_EQUAL,
                     new  BinaryComparator(Bytes.toBytes( "524382618264914241" )));
             filters.add(filter1);
     
             Filter filter2= new  RowFilter(CompareFilter.CompareOp.LESS_OR_EQUAL,
                     new  BinaryComparator(Bytes.toBytes( "813782218261011172" )));
     
             filters.add(filter2);
             //列名过滤器
             Filter filter3= new  QualifierFilter(CompareFilter.CompareOp.EQUAL,
                     new  RegexStringComparator( "age" ));
     
             filters.add(filter3);
             //行键 Between "524382618264914241" and "813782218261011172"  and column="age"
             FilterList filterList1 =  new  FilterList(filters);
     
             Scan scan =  new  Scan();
             scan.setFilter(filterList1);
     
             ResultScanner results = table.getScanner(scan);
             for  (Result result:results) {
                 for  (Cell cell : result.rawCells()) {
                     System.out.println( "Cell: "  + cell +  ", Value: "  +
                             Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                     cell.getValueLength()));
                 }
             }
             results.close();
             //行键 Between "524382618264914241" or "813782218261011172"  or column="age"
             FilterList filterList2 =  new  FilterList(FilterList.Operator.MUST_PASS_ONE,filters);
             scan.setFilter(filterList2);
             ResultScanner scanner2= table.getScanner(scan);
             for (Result result:scanner2){
                 for  (Cell cell : result.rawCells()) {
                     System.out.println( "MUST_PASS_ONE Cell: "  + cell +  ", Value: "  +
                             Bytes.toString(cell.getValueArray(), cell.getValueOffset(),
                                     cell.getValueLength()));
                 }
             }
             scanner2.close();
             table.close();
             connection.close();
         }
    }
     
    /**
     
      Cell: 524382618264914241/info:age/1472196193913/Put/vlen=2/seqid=0, Value: 30
      Cell: 673782618261019142/info:age/1472196211733/Put/vlen=2/seqid=0, Value: 19
      Cell: 813782218261011172/info:age/1472196212550/Put/vlen=2/seqid=0, Value: 19
      MUST_PASS_ONE Cell: 224382618261914241/info:age/1472196211169/Put/vlen=2/seqid=0, Value: 24
      MUST_PASS_ONE Cell: 224382618261914241/info:height/1472196211234/Put/vlen=3/seqid=0, Value: 158
      MUST_PASS_ONE Cell: 224382618261914241/info:name/1472196211088/Put/vlen=4/seqid=0, Value: lisi
      MUST_PASS_ONE Cell: 224382618261914241/info:phone/1472196211427/Put/vlen=11/seqid=0, Value: 13213921424
      MUST_PASS_ONE Cell: 224382618261914241/info:weight/1472196211386/Put/vlen=3/seqid=0, Value: 128
      MUST_PASS_ONE Cell: 224382618261914241/ship:addr/1472196211487/Put/vlen=7/seqid=0, Value: chengdu
      MUST_PASS_ONE Cell: 224382618261914241/ship:email/1472196211530/Put/vlen=11/seqid=0, Value: qq@sina.com
      MUST_PASS_ONE Cell: 224382618261914241/ship:salary/1472196211594/Put/vlen=4/seqid=0, Value: 5000
      MUST_PASS_ONE Cell: 510824118261011172/info:age/1472196213020/Put/vlen=2/seqid=0, Value: 18
      MUST_PASS_ONE Cell: 510824118261011172/info:height/1472196213056/Put/vlen=3/seqid=0, Value: 188
      MUST_PASS_ONE Cell: 510824118261011172/info:name/1472196212942/Put/vlen=8/seqid=0, Value: yangyang
      MUST_PASS_ONE Cell: 510824118261011172/info:phone/1472196213237/Put/vlen=11/seqid=0, Value: 18013921626
      MUST_PASS_ONE Cell: 510824118261011172/info:weight/1472196213169/Put/vlen=3/seqid=0, Value: 138
      MUST_PASS_ONE Cell: 510824118261011172/ship:addr/1472196213328/Put/vlen=8/seqid=0, Value: shanghai
      MUST_PASS_ONE Cell: 510824118261011172/ship:email/1472196213422/Put/vlen=12/seqid=0, Value: 199@sina.com
      MUST_PASS_ONE Cell: 510824118261011172/ship:salary/1472196214963/Put/vlen=5/seqid=0, Value: 50000
      MUST_PASS_ONE Cell: 524382618264914241/info:age/1472196193913/Put/vlen=2/seqid=0, Value: 30
      MUST_PASS_ONE Cell: 524382618264914241/info:height/1472196194783/Put/vlen=3/seqid=0, Value: 168
      MUST_PASS_ONE Cell: 524382618264914241/info:name/1472196193255/Put/vlen=8/seqid=0, Value: zhangsan
      MUST_PASS_ONE Cell: 524382618264914241/info:phone/1472196195125/Put/vlen=11/seqid=0, Value: 13212321424
      MUST_PASS_ONE Cell: 524382618264914241/info:weight/1472196194970/Put/vlen=3/seqid=0, Value: 168
      MUST_PASS_ONE Cell: 524382618264914241/ship:addr/1472196195270/Put/vlen=7/seqid=0, Value: beijing
      MUST_PASS_ONE Cell: 524382618264914241/ship:email/1472196195371/Put/vlen=13/seqid=0, Value: sina@sina.com
      MUST_PASS_ONE Cell: 524382618264914241/ship:salary/1472196195485/Put/vlen=4/seqid=0, Value: 3000
      MUST_PASS_ONE Cell: 673782618261019142/info:age/1472196211733/Put/vlen=2/seqid=0, Value: 19
      MUST_PASS_ONE Cell: 673782618261019142/info:height/1472196211761/Put/vlen=3/seqid=0, Value: 178
      MUST_PASS_ONE Cell: 673782618261019142/info:name/1472196211678/Put/vlen=7/seqid=0, Value: zhaoliu
      MUST_PASS_ONE Cell: 673782618261019142/info:phone/1472196211956/Put/vlen=11/seqid=0, Value: 17713921424
      MUST_PASS_ONE Cell: 673782618261019142/info:weight/1472196211841/Put/vlen=3/seqid=0, Value: 188
      MUST_PASS_ONE Cell: 673782618261019142/ship:addr/1472196212059/Put/vlen=8/seqid=0, Value: shenzhen
      MUST_PASS_ONE Cell: 673782618261019142/ship:email/1472196212176/Put/vlen=12/seqid=0, Value: 126@sina.com
      MUST_PASS_ONE Cell: 673782618261019142/ship:salary/1472196212284/Put/vlen=4/seqid=0, Value: 8000
      MUST_PASS_ONE Cell: 813782218261011172/info:age/1472196212550/Put/vlen=2/seqid=0, Value: 19
      MUST_PASS_ONE Cell: 813782218261011172/info:height/1472196212605/Put/vlen=3/seqid=0, Value: 158
      MUST_PASS_ONE Cell: 813782218261011172/info:name/1472196212480/Put/vlen=8/seqid=0, Value: wangmazi
      MUST_PASS_ONE Cell: 813782218261011172/info:phone/1472196212713/Put/vlen=11/seqid=0, Value: 12713921424
      MUST_PASS_ONE Cell: 813782218261011172/info:weight/1472196212651/Put/vlen=3/seqid=0, Value: 118
      MUST_PASS_ONE Cell: 813782218261011172/ship:addr/1472196212762/Put/vlen=4/seqid=0, Value: xian
      MUST_PASS_ONE Cell: 813782218261011172/ship:email/1472196212802/Put/vlen=12/seqid=0, Value: 139@sina.com
      MUST_PASS_ONE Cell: 813782218261011172/ship:salary/1472196212840/Put/vlen=5/seqid=0, Value: 10000
    **/

阿豪963
关注
  • 0
    点赞
  • 踩
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
HBase学习之路(五)：理解过滤器的概念及比较过滤器的使用
萧邦主的城邦
07-31 1459
内容简介一、过滤器简介1.过滤器的基本概念2.过滤器的层次结构3.比较运算符4.运算器二、比较过滤器的使用0.比较过滤器的基本概念1.行过滤器2.列族过滤器3.列名过滤器4.值过滤器三、总结 一、过滤器简介 1.过滤器的基本概念 过滤器是HBase为客户端提供的一种高级API，是HBase的一种高级特性，它提供了非常强大的功能帮助用户处理表中的数据。HBase中读取数据的API主要是get()和...
HBASE使用注意事项
01-03
博主自己整理的一些HBASE的注意事项，可能比较LOW，大家凑活看看。
hbase过滤器 API
xianrenqiu1234的博客
05-18 186
HBase客户端API-过滤器
kongxx的专栏
02-01 620
在使用HBase的API查询数据的时候，我们经常需要设置一些过滤条件来查询数据，这个时候我们就需要使用 HBase API 的各种 Filter 来实现这一功能。 在 HBase API 中使用过滤器需要创建一个 Filter 实例，然后使用Scan.setFilter()或者Get.setFilter()来使用 Filter，如下： Table table = connection.ge
HBase 过滤器 Java API
hujieliang123的博客
03-02 2566
HBase 过滤器 Java API
常见hbase过滤器api
m0_55209699的博客
03-29 140
原文 https://www.jianshu.com/p/fb4bd7a2a23e package com.aura.hbase.test; import java.io.IOException; import org.apache.commons.lang.StringUtils; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.hbase.HBaseConfiguration; import org.apac
Hbase shell及常用命令
05-29
HBase过滤器可以根据条件过滤数据。例如，使用RowFilter过滤器来过滤Student表中的数据： scan 'Student', FILTER => "RowFilter(=, 'binary:0001')" HBase行键过滤器 ------------------ HBase行键过滤器用于...
第5章Hbase1
08-08
在Java或Python等语言中，可以使用HBase的API进行数据操作，包括增删改查，以及使用过滤器进行复杂查询。 5.2.6 HBase内部原理 HBase采用BigTable的模型，将数据存储为Region，每个Region包含多个列族。Region是...
大数据HBase之入门进阶
06-10
本次课程适合HBase入门的学员，课程首先介绍了什么是HBase ，HBase安装以及Sell入门，其次通过介绍独立zk、JavaAPI、区域操作、HBase常用功能、过滤器等一系列功能操作进行详细解析，帮助学员更好的理解，最后以HA...
hbase的安装和实践.docx
04-20
《HBase的安装与实践详解》 ...总的来说，HBase的安装和实践涉及到分布式存储原理、Shell操作、API编程以及高级特性如过滤器和Phoenix的使用。理解并熟练掌握这些知识点，将有助于构建高效的大数据存储和处理系统。
彷徨 | HBase常用过滤器API操作
彷徨的博客
09-06 476
Before Table table = null; Connection conn = null; @Before public void init() throws Exception { Configuration conf = HBaseConfiguration.create(); conn = ConnectionFactory.createConnection(c...
HBase过滤器API
chuluo6251的博客
05-09 107
简介 Hbase提供的专用过滤器直接继承自FilterBase，其中一些过滤器只能做行筛选，因此只适合于scan操作，对get操作这些过滤器限制的更苛刻：要么包含整行，要么什么都不包括。 过滤器 1. 单列值过滤器（SingleColumnValueFilter）：用一列的...
Hbase葱岭探秘--过滤器Api
王洋的专栏
12-20 2657
Hbase中提供了许多的过滤器接口，以此来对数据进行过滤，使得查询出想要的数据。行过滤器针对行信息进行过滤，参数中可以采用前缀匹配、按位与、或、异或以及子串匹配等匹配的方式。同时可以控制EQUAL、NOT_EQUAL选项进行控制筛选数据的条件。/** * 行过滤器 BinaryComparator NullComparator:是不是空值 * BitCompar
HBase过滤器基本概念
huangliuyu00的博客
08-11 431
HBase过滤器 过滤器可以根据列族、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、列、版本有序），这些过滤器可以高效地完成查询过滤的。 使用过滤器至少需要两类参数： 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_EQUAL (!=) GREATER...
Hbase API高级特性-附加过滤器
坚持到底
12-02 1303
1.   跳转过滤器（SkipFilter） 该过滤器包含了一个用户提供 过滤器，当被包装的过滤器遇到一个需要过滤的KeyValue实例时，用户可以过滤整行数据。当过滤器发现某一行中的一列需要过滤时，那么整行数据都将被过滤掉。例如：SkipFilter与ValueFilter组合起来获取不包含空列值得行。 public void skipFilter() throws IOException{
Hbase API高级特性-专用过滤器
坚持到底
12-01 2431
1.   Hbase提供的专用过滤器直接继承自FilterBase,其中一些过滤器只能做行筛选，因此只适合于扫描操作，对get（），这些过滤器限制的更苛刻：要么包含整行，要么什么都不包括。 2.   单列值过滤器（SingleColumnValueFilter） 用一列的值决定是否一行数据被过滤。 public void singleColumnValueFilter() throws IO
hbase KeyValue结构打印
tterminator的专栏
07-04 1111
一、表内容hbase(main):003:0> scan ‘tableCreateTest1’ ROW COLUMN+CELL row1 column=cf1:name, timestamp=1467639285495, value
hbase的过滤器
大数据容器
06-02 4284
hbase的过滤器 1.概述 hbase的API中可以进行查询,但是这种查询一般只能单行或者是指定行键的范围的查询,在正常需要精细查询的场合有诸多的不便,所以系统内置了很多的过滤器 2.过滤器汇总 过滤器分为两大类:比较过滤器和专用过滤器 3.比较过滤器 行键过滤器 RowFilter Filter filter1 = new RowFilter(CompareOp.LESS_OR_EQUAL...
HBase基础知识(4):批量处理操作
weixin_30725315的博客
08-26 316
之前我们学习过添加、检索和删除表中数据的操作了，不过都是基于单个实例或基于列表的操作。下边介绍一些API调用，可以批量处理跨多行的不同操作。 事实上，许多基于列表的操作，如delete(List <Delete> deletes)或者get(List <Get> gets)，都是基于batch()方法实现的。它们都是一些为了方便用户使用而保留的方法...
hbase过滤器查询列族名称含有“c”的所有数据
最新发布
06-07
您可以使用HBase Java API中的Filter来查询列族名称含有“c”的所有数据，具体代码如下： ```java import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.hbase.Cell; import org.apache.hadoop.hbase.CellUtil; import org.apache.hadoop.hbase.HBaseConfiguration; import org.apache.hadoop.hbase.TableName; import org.apache.hadoop.hbase.client.Connection; import org.apache.hadoop.hbase.client.ConnectionFactory; import org.apache.hadoop.hbase.client.Result; import org.apache.hadoop.hbase.client.Scan; import org.apache.hadoop.hbase.filter.Filter; import org.apache.hadoop.hbase.filter.QualifierFilter; import org.apache.hadoop.hbase.filter.SubstringComparator; import org.apache.hadoop.hbase.util.Bytes; public class HBaseFilterExample { public static void main(String[] args) throws Exception { Configuration config = HBaseConfiguration.create(); Connection connection = ConnectionFactory.createConnection(config); TableName tableName = TableName.valueOf("table_name"); Scan scan = new Scan(); Filter filter = new QualifierFilter( org.apache.hadoop.hbase.filter.CompareOperator.EQUAL, new SubstringComparator("c") ); scan.setFilter(filter); ResultScanner scanner = connection.getTable(tableName).getScanner(scan); for (Result result : scanner) { for (Cell cell : result.listCells()) { String rowKey = Bytes.toString(CellUtil.cloneRow(cell)); String columnFamily = Bytes.toString(CellUtil.cloneFamily(cell)); String columnQualifier = Bytes.toString(CellUtil.cloneQualifier(cell)); String value = Bytes.toString(CellUtil.cloneValue(cell)); System.out.println("rowKey=" + rowKey + ", columnFamily=" + columnFamily + ", columnQualifier=" + columnQualifier + ", value=" + value); } } } } ``` 其中，`QualifierFilter`表示按列名过滤，`SubstringComparator`表示包含子串的过滤条件，`EQUAL`表示精确匹配，而在这里是使用`SubstringComparator`过滤包含子串的列族。

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值