SqlServer类似正则表达式的字符处理问题（SqlServer类似正则表达式的字符处理问题）

declare @text varchar(1000)
declare @str varchar(10)
set @text = 'ABCBDBE'
set @str = 'B'
select len(@text) - len(replace(@text,@str,''))

--方法1
declare @text varchar(1000)
declare @str varchar(10)
set @text = 'ABBBCBBBDBBBE'
set @str = 'BBB'
select (len(@text) - len(replace(@text,@str,'')))/len(@str)
--方法2
declare @text varchar(1000)
declare @str varchar(10)
set @text = 'ABBBCBBBDBBBE'
set @str = 'BBB'
select len(replace(@text,@str,@str+'_')) - len(@text)

CHARINDEX ( expressionToFind , expressionToSearch [ , start_location ] )

if object_id('NthChar','FN') is not null
  drop function Nthchar
GO
create function NthChar
(
@source_string as nvarchar(4000), 
@sub_string  as nvarchar(1024),
@nth      as int
) 
returns int 
as 
begin 
  declare @postion int 
  declare @count  int 
  set @postion = CHARINDEX(@sub_string, @source_string) 
  set @count = 0 
  while @postion > 0 
  begin 
    set @count = @count + 1 
    if @count = @nth 
    begin 
      break 
    end
    set @postion = CHARINDEX(@sub_string, @source_string, @postion + 1) 
  End 
  return @postion 
end 
GO
--select dbo.NthChar('abcabc','abc',2)
--4

if object_id('tempdb..#T') is not null
  drop table #T
create table #T
(
source_string nvarchar(4000)
)
insert into #T values (N'我们我们')
insert into #T values (N'我我哦我')
declare @sub_string nvarchar(1024)
declare @nth    int
set @sub_string = N'我们'
set @nth = 2
;with T(source_string, starts, pos, nth) 
as (
  select source_string, 1, charindex(@sub_string, source_string), 1 from #t
  union all
  select source_string, pos + 1, charindex(@sub_string, source_string, pos + 1), nth+1 from T
  where pos > 0
)
select 
  source_string, pos, nth
from T
where pos <> 0
 and nth = @nth
order by source_string, starts
--source_string  pos  nth
--我们我们  3  2

--numbers/tally table
IF EXISTS (select * from dbo.sysobjects where id = object_id(N'[dbo].[Numbers]') and OBJECTPROPERTY(id, N'IsUserTable') = 1)
  DROP TABLE dbo.Numbers
--===== Create and populate the Tally table on the fly
 SELECT TOP 1000000 
    IDENTITY(int,1,1) AS number
  INTO dbo.Numbers
  FROM master.dbo.syscolumns sc1,
    master.dbo.syscolumns sc2
--===== Add a Primary Key to maximize performance
 ALTER TABLE dbo.Numbers
    ADD CONSTRAINT PK_numbers_number PRIMARY KEY CLUSTERED (number)
--===== Allow the general public to use it
 GRANT SELECT ON dbo.Numbers TO PUBLIC
--以上数字表创建一次即可，不需要每次都重复创建
DECLARE @source_string  nvarchar(4000), 
    @sub_string    nvarchar(1024), 
    @nth       int
SET @source_string = 'abcabcvvvvabc'
SET @sub_string = 'abc'
SET @nth = 2 
;WITH T 
AS
(      
SELECT ROW_NUMBER() OVER(ORDER BY number) AS nth,
    number AS [Position In String]
 FROM dbo.Numbers n 
 WHERE n.number <= LEN(@source_string)  
  AND CHARINDEX(@sub_string, @source_string, n.number)-number = 0
  ----OR
  --AND SUBSTRING(@source_string,number,LEN(@sub_string)) = @sub_string
) 
SELECT * FROM T WHERE nth = @nth

declare @T table
(
source_string nvarchar(4000)
)

insert into @T values
('abcabc'),
('abcabcvvvvabc')
declare @sub_string nvarchar(1024)
set @sub_string = 'abc'

select source_string,
    p1.pos as no1,
    p2.pos as no2,
    p3.pos as no3
from @T
cross apply (select (charindex(@sub_string, source_string))) as P1(Pos)
cross apply (select (charindex(@sub_string, source_string, P1.Pos+1))) as P2(Pos)
cross apply (select (charindex(@sub_string, source_string, P2.Pos+1))) as P3(Pos)

--FINDSTRING in SQL Server 2005 SSIS
FINDSTRING([yourColumn], "|", 2),
--TOKEN in SQL Server 2012 SSIS
TOKEN(Col1,"|",3)

--把两个连续空格替换成一个空格，然后循环，直到charindex检查不到两个连续空格
declare @str varchar(100)
set @str='abc    abc   kljlk   kljkl'
while(charindex(' ',@str)>0)
begin
  select @str=replace(@str,' ',' ')
end
select @str

Oracle 10 g
REGEXP_LIKE
REGEXP_REPLACE
REGEXP_INSTR
REGEXP_SUBSTR
Oracle 11g (新增)
REGEXP_COUNT

select length(regexp_replace('123-345-566', '[^-]', '')) from dual;
select REGEXP_COUNT('123-345-566', '-') from dual; --Oracle 11g 

instr('source_string','sub_string' [,n][,m])

select instr('abcdefghijkabc','abc', 1, 2) position from dual; 

select regexp_replace(trim('agc f  f '),'\s+',' ') from dual; 

--是否为有效IP
WITH IP
AS(
SELECT '10.20.30.40' ip_address FROM dual UNION ALL
SELECT 'a.b.c.d' ip_address FROM dual UNION ALL
SELECT '256.123.0.254' ip_address FROM dual UNION ALL
SELECT '255.255.255.255' ip_address FROM dual
)
SELECT *
FROM IP
WHERE REGEXP_LIKE(ip_address, '^(([0-9]{1}|[0-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])\.){3}([0-9]{1}|[0-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])$');
--是否为有效身份证/手机号，暂未举例

--1. 开启 CLR 
EXEC sp_configure 'show advanced options' , '1'
GO
RECONFIGURE
GO
EXEC sp_configure 'clr enabled' , '1'
GO
RECONFIGURE
GO
EXEC sp_configure 'show advanced options' , '0';
GO

--3. 创建 CLR 函数
CREATE FUNCTION [dbo].[regex_replace](@input [nvarchar](4000), @pattern [nvarchar](4000), @replacement [nvarchar](4000))
RETURNS [nvarchar](4000) WITH EXECUTE AS CALLER, RETURNS NULL ON NULL INPUT
AS 
EXTERNAL NAME [RegexUtility].[RegexUtility].[RegexReplaceDefault]
GO
--4. 使用regex_replace替换多个空格为一个空格
select dbo.regex_replace('agc f  f ','\s+',' ');