Answers:
试试这个功能:
Create Function [dbo].[RemoveNonAlphaCharacters](@Temp VarChar(1000))
Returns VarChar(1000)
AS
Begin
Declare @KeepValues as varchar(50)
Set @KeepValues = '%[^a-z]%'
While PatIndex(@KeepValues, @Temp) > 0
Set @Temp = Stuff(@Temp, PatIndex(@KeepValues, @Temp), 1, '')
Return @Temp
End
这样称呼它:
Select dbo.RemoveNonAlphaCharacters('abc1234def5678ghi90jkl')
一旦理解了代码,就应该看到更改代码以删除其他字符也相对简单。您甚至可以使它足够动态以传递您的搜索模式。
希望能帮助到你。
CREATE FUNCTION [dbo].[fn_StripCharacters]
(
@String NVARCHAR(MAX),
@MatchExpression VARCHAR(255)
)
RETURNS NVARCHAR(MAX)
AS
BEGIN
SET @MatchExpression = '%['+@MatchExpression+']%'
WHILE PatIndex(@MatchExpression, @String) > 0
SET @String = Stuff(@String, PatIndex(@MatchExpression, @String), 1, '')
RETURN @String
END
仅按字母顺序:
SELECT dbo.fn_StripCharacters('a1!s2@d3#f4$', '^a-z')
仅数字:
SELECT dbo.fn_StripCharacters('a1!s2@d3#f4$', '^0-9')
仅字母数字:
SELECT dbo.fn_StripCharacters('a1!s2@d3#f4$', '^a-z0-9')
非字母数字:
SELECT dbo.fn_StripCharacters('a1!s2@d3#f4$', 'a-z0-9')
SELECT dbo.fn_StripCharacters('a1!s2 spaces @d3# f4$', '^a-z0-9\s')
仍会剥离空格的字符。我也尝试使用,[[:blank:]]
但这破坏了功能并且从字符串中没有删除任何内容。我得到的最接近的Ive通过使用:(SELECT dbo.fn_StripCharacters('a1!s2 spaces @d3# f4$', '^a-z0-9 ')
在正则表达式模式中硬编码一个空格)。但是,这并不能消除换行符。
SELECT dbo.fn_StripCharacters('a1!s2 spaces @d3# f4$', '^ a-z0-9')
信不信由你,在我的系统中,这个丑陋的功能比G Mastros优雅的功能要好。
CREATE FUNCTION dbo.RemoveSpecialChar (@s VARCHAR(256))
RETURNS VARCHAR(256)
WITH SCHEMABINDING
BEGIN
IF @s IS NULL
RETURN NULL
DECLARE @s2 VARCHAR(256) = '',
@l INT = LEN(@s),
@p INT = 1
WHILE @p <= @l
BEGIN
DECLARE @c INT
SET @c = ASCII(SUBSTRING(@s, @p, 1))
IF @c BETWEEN 48 AND 57
OR @c BETWEEN 65 AND 90
OR @c BETWEEN 97 AND 122
SET @s2 = @s2 + CHAR(@c)
SET @p = @p + 1
END
IF LEN(@s2) = 0
RETURN NULL
RETURN @s2
ASCII
在这里不使用整数,然后直接将输出SUBSTRING
与某些字符进行比较,则有多少不同,例如:SET @ch=SUBSTRING(@s, @p, 1)
和IF @ch BETWEEN '0' AND '9' OR @ch BETWEEN 'a' AND 'z' OR @ch BETWEEN 'A' AND 'Z' ...
我知道SQL在字符串操作方面很糟糕,但是我并不认为这会很困难。这是一个简单的函数,可从字符串中去除所有数字。会有更好的方法来执行此操作,但这只是一个开始。
CREATE FUNCTION dbo.AlphaOnly (
@String varchar(100)
)
RETURNS varchar(100)
AS BEGIN
RETURN (
REPLACE(
REPLACE(
REPLACE(
REPLACE(
REPLACE(
REPLACE(
REPLACE(
REPLACE(
REPLACE(
REPLACE(
@String,
'9', ''),
'8', ''),
'7', ''),
'6', ''),
'5', ''),
'4', ''),
'3', ''),
'2', ''),
'1', ''),
'0', '')
)
END
GO
-- ==================
DECLARE @t TABLE (
ColID int,
ColString varchar(50)
)
INSERT INTO @t VALUES (1, 'abc1234567890')
SELECT ColID, ColString, dbo.AlphaOnly(ColString)
FROM @t
输出量
ColID ColString
----- ------------- ---
1 abc1234567890 abc
第二轮-数据驱动黑名单
-- ============================================
-- Create a table of blacklist characters
-- ============================================
IF EXISTS (SELECT * FROM sys.tables WHERE [object_id] = OBJECT_ID('dbo.CharacterBlacklist'))
DROP TABLE dbo.CharacterBlacklist
GO
CREATE TABLE dbo.CharacterBlacklist (
CharID int IDENTITY,
DisallowedCharacter nchar(1) NOT NULL
)
GO
INSERT INTO dbo.CharacterBlacklist (DisallowedCharacter) VALUES (N'0')
INSERT INTO dbo.CharacterBlacklist (DisallowedCharacter) VALUES (N'1')
INSERT INTO dbo.CharacterBlacklist (DisallowedCharacter) VALUES (N'2')
INSERT INTO dbo.CharacterBlacklist (DisallowedCharacter) VALUES (N'3')
INSERT INTO dbo.CharacterBlacklist (DisallowedCharacter) VALUES (N'4')
INSERT INTO dbo.CharacterBlacklist (DisallowedCharacter) VALUES (N'5')
INSERT INTO dbo.CharacterBlacklist (DisallowedCharacter) VALUES (N'6')
INSERT INTO dbo.CharacterBlacklist (DisallowedCharacter) VALUES (N'7')
INSERT INTO dbo.CharacterBlacklist (DisallowedCharacter) VALUES (N'8')
INSERT INTO dbo.CharacterBlacklist (DisallowedCharacter) VALUES (N'9')
GO
-- ====================================
IF EXISTS (SELECT * FROM sys.objects WHERE [object_id] = OBJECT_ID('dbo.StripBlacklistCharacters'))
DROP FUNCTION dbo.StripBlacklistCharacters
GO
CREATE FUNCTION dbo.StripBlacklistCharacters (
@String nvarchar(100)
)
RETURNS varchar(100)
AS BEGIN
DECLARE @blacklistCt int
DECLARE @ct int
DECLARE @c nchar(1)
SELECT @blacklistCt = COUNT(*) FROM dbo.CharacterBlacklist
SET @ct = 0
WHILE @ct < @blacklistCt BEGIN
SET @ct = @ct + 1
SELECT @String = REPLACE(@String, DisallowedCharacter, N'')
FROM dbo.CharacterBlacklist
WHERE CharID = @ct
END
RETURN (@String)
END
GO
-- ====================================
DECLARE @s nvarchar(24)
SET @s = N'abc1234def5678ghi90jkl'
SELECT
@s AS OriginalString,
dbo.StripBlacklistCharacters(@s) AS ResultString
输出量
OriginalString ResultString
------------------------ ------------
abc1234def5678ghi90jkl abcdefghijkl
我对读者的挑战:您能否提高效率?那使用递归呢?
如果您像我一样,并且无权仅向生产数据中添加功能,但仍然希望执行这种过滤,那么这是一个纯SQL解决方案,使用PIVOT表将过滤后的片段重新放在一起。
注意:我将表格硬编码为40个字符,如果要过滤的字符串较长,则必须添加更多字符。
SET CONCAT_NULL_YIELDS_NULL OFF;
with
ToBeScrubbed
as (
select 1 as id, '*SOME 222@ !@* #* BOGUS !@*&! DATA' as ColumnToScrub
),
Scrubbed as (
select
P.Number as ValueOrder,
isnull ( substring ( t.ColumnToScrub , number , 1 ) , '' ) as ScrubbedValue,
t.id
from
ToBeScrubbed t
left join master..spt_values P
on P.number between 1 and len(t.ColumnToScrub)
and type ='P'
where
PatIndex('%[^a-z]%', substring(t.ColumnToScrub,P.number,1) ) = 0
)
SELECT
id,
[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] as ScrubbedData
FROM (
select
*
from
Scrubbed
)
src
PIVOT (
MAX(ScrubbedValue) FOR ValueOrder IN (
[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]
)
) pvt
看完所有给定的解决方案后,我认为必须有一种纯SQL方法,该函数不需要函数或CTE / XML查询,并且不涉及难以维护嵌套的REPLACE语句。这是我的解决方案:
SELECT
x
,CASE WHEN a NOT LIKE '%' + SUBSTRING(x, 1, 1) + '%' THEN '' ELSE SUBSTRING(x, 1, 1) END
+ CASE WHEN a NOT LIKE '%' + SUBSTRING(x, 2, 1) + '%' THEN '' ELSE SUBSTRING(x, 2, 1) END
+ CASE WHEN a NOT LIKE '%' + SUBSTRING(x, 3, 1) + '%' THEN '' ELSE SUBSTRING(x, 3, 1) END
+ CASE WHEN a NOT LIKE '%' + SUBSTRING(x, 4, 1) + '%' THEN '' ELSE SUBSTRING(x, 4, 1) END
+ CASE WHEN a NOT LIKE '%' + SUBSTRING(x, 5, 1) + '%' THEN '' ELSE SUBSTRING(x, 5, 1) END
+ CASE WHEN a NOT LIKE '%' + SUBSTRING(x, 6, 1) + '%' THEN '' ELSE SUBSTRING(x, 6, 1) END
-- Keep adding rows until you reach the column size
AS stripped_column
FROM (SELECT
column_to_strip AS x
,'ABCDEFGHIJKLMNOPQRSTUVWXYZ' AS a
FROM my_table) a
这样做的好处是,有效字符包含在子查询的一个字符串中,从而可以轻松地为另一组字符重新配置。
缺点是您必须为每个字符添加一行SQL,直到列的大小为止。为了简化该任务,我仅使用下面的Powershell脚本,该示例用于VARCHAR(64):
1..64 | % {
" + CASE WHEN a NOT LIKE '%' + SUBSTRING(x, {0}, 1) + '%' THEN '' ELSE SUBSTRING(x, {0}, 1) END" -f $_
} | clip.exe
这是使用删除非字母字符的另一种方法iTVF
。首先,您需要一个基于模式的字符串拆分器。这是摘自德恩·坎普的文章:
-- PatternSplitCM will split a string based on a pattern of the form
-- supported by LIKE and PATINDEX
--
-- Created by: Chris Morris 12-Oct-2012
CREATE FUNCTION [dbo].[PatternSplitCM]
(
@List VARCHAR(8000) = NULL
,@Pattern VARCHAR(50)
) RETURNS TABLE WITH SCHEMABINDING
AS
RETURN
WITH numbers AS (
SELECT TOP(ISNULL(DATALENGTH(@List), 0))
n = ROW_NUMBER() OVER(ORDER BY (SELECT NULL))
FROM
(VALUES (0),(0),(0),(0),(0),(0),(0),(0),(0),(0)) d (n),
(VALUES (0),(0),(0),(0),(0),(0),(0),(0),(0),(0)) e (n),
(VALUES (0),(0),(0),(0),(0),(0),(0),(0),(0),(0)) f (n),
(VALUES (0),(0),(0),(0),(0),(0),(0),(0),(0),(0)) g (n)
)
SELECT
ItemNumber = ROW_NUMBER() OVER(ORDER BY MIN(n)),
Item = SUBSTRING(@List,MIN(n),1+MAX(n)-MIN(n)),
[Matched]
FROM (
SELECT n, y.[Matched], Grouper = n - ROW_NUMBER() OVER(ORDER BY y.[Matched],n)
FROM numbers
CROSS APPLY (
SELECT [Matched] = CASE WHEN SUBSTRING(@List,n,1) LIKE @Pattern THEN 1 ELSE 0 END
) y
) d
GROUP BY [Matched], Grouper
现在您有了基于模式的拆分器,您需要拆分与模式匹配的字符串:
[a-z]
然后将它们串联起来以获得所需的结果:
SELECT *
FROM tbl t
CROSS APPLY(
SELECT Item + ''
FROM dbo.PatternSplitCM(t.str, '[a-z]')
WHERE Matched = 1
ORDER BY ItemNumber
FOR XML PATH('')
) x (a)
结果:
| Id | str | a |
|----|------------------|----------------|
| 1 | test“te d'abc | testtedabc |
| 2 | anr¤a | anra |
| 3 | gs-re-C“te d'ab | gsreCtedab |
| 4 | M‚fe, DF | MfeDF |
| 5 | R™temd | Rtemd |
| 6 | ™jad”ji | jadji |
| 7 | Cje y ret¢n | Cjeyretn |
| 8 | J™kl™balu | Jklbalu |
| 9 | le“ne-iokd | leneiokd |
| 10 | liode-Pyr‚n‚ie | liodePyrnie |
| 11 | V„s G”ta | VsGta |
| 12 | Sƒo Paulo | SoPaulo |
| 13 | vAstra gAtaland | vAstragAtaland |
| 14 | ¥uble / Bio-Bio | ubleBioBio |
| 15 | U“pl™n/ds VAsb-y | UplndsVAsby |
此解决方案受艾伦先生的解决方案启发,需要一个Numbers
整数表(如果要进行性能良好的严肃查询操作,则应具有整数表)。它不需要CTE。您可以更改NOT IN (...)
表达式以排除特定字符,或者将其更改为IN (...)
OR LIKE
表达式以仅保留某些字符。
SELECT (
SELECT SUBSTRING([YourString], N, 1)
FROM dbo.Numbers
WHERE N > 0 AND N <= CONVERT(INT, LEN([YourString]))
AND SUBSTRING([YourString], N, 1) NOT IN ('(',')',',','.')
FOR XML PATH('')
) AS [YourStringTransformed]
FROM ...
这是一个不需要创建函数或列出所有要替换字符实例的解决方案。它结合使用递归WITH语句和PATINDEX来查找不需要的字符。它将替换列中所有不需要的字符-任何给定的字符串中最多包含100个唯一的坏字符。(例如,EG“ ABC123DEF234”将包含4个错误字符1、2、3和4)。100的限制是WITH语句中允许的最大递归数,但这并不对要处理的行数施加限制。仅受可用内存的限制。
如果您不想获得DISTINCT结果,则可以从代码中删除这两个选项。
-- Create some test data:
SELECT * INTO #testData
FROM (VALUES ('ABC DEF,K.l(p)'),('123H,J,234'),('ABCD EFG')) as t(TXT)
-- Actual query:
-- Remove non-alpha chars: '%[^A-Z]%'
-- Remove non-alphanumeric chars: '%[^A-Z0-9]%'
DECLARE @BadCharacterPattern VARCHAR(250) = '%[^A-Z]%';
WITH recurMain as (
SELECT DISTINCT CAST(TXT AS VARCHAR(250)) AS TXT, PATINDEX(@BadCharacterPattern, TXT) AS BadCharIndex
FROM #testData
UNION ALL
SELECT CAST(TXT AS VARCHAR(250)) AS TXT, PATINDEX(@BadCharacterPattern, TXT) AS BadCharIndex
FROM (
SELECT
CASE WHEN BadCharIndex > 0
THEN REPLACE(TXT, SUBSTRING(TXT, BadCharIndex, 1), '')
ELSE TXT
END AS TXT
FROM recurMain
WHERE BadCharIndex > 0
) badCharFinder
)
SELECT DISTINCT TXT
FROM recurMain
WHERE BadCharIndex = 0;
-首先创建一个功能
CREATE FUNCTION [dbo].[GetNumericonly]
(@strAlphaNumeric VARCHAR(256))
RETURNS VARCHAR(256)
AS
BEGIN
DECLARE @intAlpha INT
SET @intAlpha = PATINDEX('%[^0-9]%', @strAlphaNumeric)
BEGIN
WHILE @intAlpha > 0
BEGIN
SET @strAlphaNumeric = STUFF(@strAlphaNumeric, @intAlpha, 1, '' )
SET @intAlpha = PATINDEX('%[^0-9]%', @strAlphaNumeric )
END
END
RETURN ISNULL(@strAlphaNumeric,0)
END
现在像这样调用此函数
select [dbo].[GetNumericonly]('Abhi12shek23jaiswal')
其结果像
1223
从性能角度来看,我将使用内联函数:
SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO
CREATE FUNCTION [dbo].[udf_RemoveNumericCharsFromString]
(
@List NVARCHAR(4000)
)
RETURNS TABLE
AS RETURN
WITH GetNums AS (
SELECT TOP(ISNULL(DATALENGTH(@List), 0))
n = ROW_NUMBER() OVER(ORDER BY (SELECT NULL))
FROM
(VALUES (0),(0),(0),(0)) d (n),
(VALUES (0),(0),(0),(0),(0),(0),(0),(0),(0),(0)) e (n),
(VALUES (0),(0),(0),(0),(0),(0),(0),(0),(0),(0)) f (n),
(VALUES (0),(0),(0),(0),(0),(0),(0),(0),(0),(0)) g (n)
)
SELECT StrOut = ''+
(SELECT Chr
FROM GetNums
CROSS APPLY (SELECT SUBSTRING(@List , n,1)) X(Chr)
WHERE Chr LIKE '%[^0-9]%'
ORDER BY N
FOR XML PATH (''),TYPE).value('.','NVARCHAR(MAX)')
/*How to Use
SELECT StrOut FROM dbo.udf_RemoveNumericCharsFromString ('vv45--9gut')
Result: vv--gut
*/
这里还有一个递归CTE的解决方案,基于@Gerhard魏斯的答案在这里。您应该能够将整个代码块复制并粘贴到SSMS中,然后在其中运行。结果包括一些额外的列,以帮助我们了解发生了什么。我花了一段时间才了解PATINDEX(RegEx)和递归CTE的所有功能。
DECLARE @DefineBadCharPattern varchar(30)
SET @DefineBadCharPattern = '%[^A-z]%' --Means anything NOT between A and z characters (according to ascii char value) is "bad"
SET @DefineBadCharPattern = '%[^a-z0-9]%' --Means anything NOT between a and z characters or numbers 0 through 9 (according to ascii char value) are "bad"
SET @DefineBadCharPattern = '%[^ -~]%' --Means anything NOT between space and ~ characters (all non-printable characters) is "bad"
--Change @ReplaceBadCharWith to '' to strip "bad" characters from string
--Change to some character if you want to 'see' what's being replaced. NOTE: It must be allowed accoring to @DefineBadCharPattern above
DECLARE @ReplaceBadCharWith varchar(1) = '#' --Change this to whatever you want to replace non-printable chars with
IF patindex(@DefineBadCharPattern COLLATE Latin1_General_BIN, @ReplaceBadCharWith) > 0
BEGIN
RAISERROR('@ReplaceBadCharWith value (%s) must be a character allowed by PATINDEX pattern of %s',16,1,@ReplaceBadCharWith, @DefineBadCharPattern)
RETURN
END
--A table of values to play with:
DECLARE @temp TABLE (OriginalString varchar(100))
INSERT @temp SELECT ' 1hello' + char(13) + char(10) + 'there' + char(30) + char(9) + char(13) + char(10)
INSERT @temp SELECT '2hello' + char(30) + 'there' + char(30)
INSERT @temp SELECT ' 3hello there'
INSERT @temp SELECT ' tab' + char(9) + ' character'
INSERT @temp SELECT 'good bye'
--Let the magic begin:
;WITH recurse AS (
select
OriginalString,
OriginalString as CleanString,
patindex(@DefineBadCharPattern COLLATE Latin1_General_BIN, OriginalString) as [Position],
substring(OriginalString,patindex(@DefineBadCharPattern COLLATE Latin1_General_BIN, OriginalString),1) as [InvalidCharacter],
ascii(substring(OriginalString,patindex(@DefineBadCharPattern COLLATE Latin1_General_BIN, OriginalString),1)) as [ASCIICode]
from @temp
UNION ALL
select
OriginalString,
CONVERT(varchar(100),REPLACE(CleanString,InvalidCharacter,@ReplaceBadCharWith)),
patindex(@DefineBadCharPattern COLLATE Latin1_General_BIN,CleanString) as [Position],
substring(CleanString,patindex(@DefineBadCharPattern COLLATE Latin1_General_BIN,CleanString),1),
ascii(substring(CleanString,patindex(@DefineBadCharPattern COLLATE Latin1_General_BIN,CleanString),1))
from recurse
where patindex(@DefineBadCharPattern COLLATE Latin1_General_BIN,CleanString) > 0
)
SELECT * FROM recurse
--optionally comment out this last WHERE clause to see more of what the recursion is doing:
WHERE patindex(@DefineBadCharPattern COLLATE Latin1_General_BIN,CleanString) = 0
使用CTE生成的数字表检查每个字符,然后使用FOR XML连接到一串保留值,您可以...
CREATE FUNCTION [dbo].[PatRemove](
@pattern varchar(50),
@expression varchar(8000)
)
RETURNS varchar(8000)
AS
BEGIN
WITH
d(d) AS (SELECT d FROM (VALUES (0),(1),(2),(3),(4),(5),(6),(7),(8),(9)) digits(d)),
nums(n) AS (SELECT ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) FROM d d1, d d2, d d3, d d4),
chars(c) AS (SELECT SUBSTRING(@expression, n, 1) FROM nums WHERE n <= LEN(@expression))
SELECT
@expression = (SELECT c AS [text()] FROM chars WHERE c NOT LIKE @pattern FOR XML PATH(''));
RETURN @expression;
END
DECLARE @vchVAlue NVARCHAR(255) = 'SWP, Lettering Position 1: 4 Ω, 2: 8 Ω, 3: 16 Ω, 4: , 5: , 6: , Voltage Selector, Solder, 6, Step switch, : w/o fuseholder '
WHILE PATINDEX('%?%' , CAST(@vchVAlue AS VARCHAR(255))) > 0
BEGIN
SELECT @vchVAlue = STUFF(@vchVAlue,PATINDEX('%?%' , CAST(@vchVAlue AS VARCHAR(255))),1,' ')
END
SELECT @vchVAlue
这种方式对我不起作用,因为我试图保留阿拉伯字母以替换正则表达式,但也无效。我写了另一种在ASCII级别上工作的方法,因为这是我唯一的选择,而且行得通。
Create function [dbo].[RemoveNonAlphaCharacters] (@s varchar(4000)) returns varchar(4000)
with schemabinding
begin
if @s is null
return null
declare @s2 varchar(4000)
set @s2 = ''
declare @l int
set @l = len(@s)
declare @p int
set @p = 1
while @p <= @l begin
declare @c int
set @c = ascii(substring(@s, @p, 1))
if @c between 48 and 57 or @c between 65 and 90 or @c between 97 and 122 or @c between 165 and 253 or @c between 32 and 33
set @s2 = @s2 + char(@c)
set @p = @p + 1
end
if len(@s2) = 0
return null
return @s2
end
走
尽管帖子有些陈旧,但我想说以下内容。上述解决方案的问题在于它不会过滤掉ç,ë,ï等字符。我按如下方式修改了函数(我仅使用80 varchar字符串来节省内存):
create FUNCTION dbo.udf_Cleanchars (@InputString varchar(80))
RETURNS varchar(80)
AS
BEGIN
declare @return varchar(80) , @length int , @counter int , @cur_char char(1)
SET @return = ''
SET @length = 0
SET @counter = 1
SET @length = LEN(@InputString)
IF @length > 0
BEGIN WHILE @counter <= @length
BEGIN SET @cur_char = SUBSTRING(@InputString, @counter, 1) IF ((ascii(@cur_char) in (32,44,46)) or (ascii(@cur_char) between 48 and 57) or (ascii(@cur_char) between 65 and 90) or (ascii(@cur_char) between 97 and 122))
BEGIN SET @return = @return + @cur_char END
SET @counter = @counter + 1
END END
RETURN @return END