如何从字符串中删除所有非字母的字符?
非字母数字呢?
这必须是一个自定义函数还是也有更通用的解决方案?
当前回答
这是另一个递归CTE解决方案，基于@Gerhard Weiss的回答。您应该能够将整个代码块复制并粘贴到SSMS中，并在那里使用它。结果包括一些额外的列，以帮助我们理解发生了什么。我花了一段时间才理解了PATINDEX (RegEx)和递归CTE的全部原理。
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
其他回答
SQL Server >= 2017…
declare @text varchar(max)
-- create some sample text
select
@text=
'
Lorem @ipsum *&dolor-= sit?! amet, {consectetur } adipiscing\ elit. Vivamus commodo justo metus, sed facilisis ante
congue eget. Proin ac bibendum sem/.
'
-- the characters to be removed
declare @unwanted varchar(max)='''.,!?/<>"[]{}|`~@#$%^&*()-+=/\:;'+char(13)+char(10)
-- interim replaced with
declare @replace_with char(1)=' '
-- call the translate function that will change unwanted characters to spaces
-- in this sample
declare @translated varchar(max)
select @translated=TRANSLATE(@text,@unwanted,REPLICATE(@replace_with,len(@unwanted)))
-- In this case, I want to preserve one space
select string_agg(trim(value),' ')
from STRING_SPLIT(@translated,' ')
where trim(value)<>''
-- Result
'Lorem ipsum dolor sit amet consectetur adipiscing elit Vivamus commodo justo metus sed facilisis ante congue eget Proin ac bibendum sem'
CREATE FUNCTION remove_spc_char(@str VARCHAR(MAX))
RETURNS VARCHAR(MAX)
AS
BEGIN
DECLARE @resp VARCHAR(MAX) = '';
DECLARE @str_val VARCHAR(MAX) = UPPER(@str);
DECLARE @i INTEGER= 1;
DECLARE @v_asc INTEGER;
WHILE @i <= (LEN(@str_val))
BEGIN
SET @v_asc = (ASCII(SUBSTRING(@str_val, @i, 1)))
BEGIN
IF @v_asc in (192,193,194,195,196,65)
begin
SET @v_asc = 65;
SET @resp = concat(@resp, CHAR(@v_asc));
end;
IF @v_asc in (200,201,202,203,233,69)
begin
SET @v_asc = 69;
SET @resp = concat(@resp, CHAR(@v_asc));
end;
IF @v_asc in (204,205,206,207,296,73)
begin
SET @v_asc = 73;
SET @resp = concat(@resp, CHAR(@v_asc));
end;
IF @v_asc in (210,211,212,213,214,79)
begin
SET @v_asc = 79;
SET @resp = concat(@resp, CHAR(@v_asc));
end;
IF @v_asc in (217,218,219,220,85)
begin
SET @v_asc = 85;
SET @resp = concat(@resp, CHAR(@v_asc));
end;
IF @v_asc in (199,231,67)
begin
SET @v_asc = 67;
SET @resp = concat(@resp, CHAR(@v_asc));
end;
IF @v_asc in (209,78)
begin
SET @v_asc = 78;
SET @resp = concat(@resp, CHAR(@v_asc));
end;
IF @v_asc in (924,181,358,216,222,330,272,208,198,42,37,38,34,36,35,
64,33,39,41,40,43,61,95,45,62,60,63,47,176,183,124,166,174,359,248,254,
180,170,186,126,312,331,273,172,178,179,163,162,123,91,93,125,92,167,240,
223,230,171,187,169,185,168)
begin
SET @resp = concat(@resp, '');
end;
ELSE
begin
if @v_asc not in (65,67,69,73,78,79,85)
begin
SET @resp = concat(@resp, CHAR(@v_asc));
end;
end;
END;
SET @i = @i + 1
END;
RETURN @resp;
END;
从性能角度来看，我会使用内联函数:
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
*/
看过所有给出的解决方案后，我认为必须有一个纯SQL方法，它不需要函数或CTE / XML查询，并且不涉及难以维护的嵌套REPLACE语句。以下是我的解决方案:
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中的一个字符串中，便于为不同的字符集重新配置。
缺点是您必须为每个字符添加一行SQL，直到您的列的大小。为了让这个任务更容易，我只是使用了下面的Powershell脚本，这个例子如果是VARCHAR(64):
1..64 | % {
" + CASE WHEN a NOT LIKE '%' + SUBSTRING(x, {0}, 1) + '%' THEN '' ELSE SUBSTRING(x, {0}, 1) END" -f $_
} | clip.exe
这是另一个递归CTE解决方案，基于@Gerhard Weiss的回答。您应该能够将整个代码块复制并粘贴到SSMS中，并在那里使用它。结果包括一些额外的列，以帮助我们理解发生了什么。我花了一段时间才理解了PATINDEX (RegEx)和递归CTE的全部原理。
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
