T-SQL选择查询以删除非数字字符

问题描述 投票:49回答:15

我在具有可变alpha长度的列中有脏数据。我只想删除任何不是0-9的东西。

我不想运行函数或proc。我有一个类似于在文本之后抓取数值的脚本,它看起来像这样:

Update TableName
set ColumntoUpdate=cast(replace(Columnofdirtydata,'Alpha #','') as int)
where Columnofdirtydata like 'Alpha #%'
And ColumntoUpdate is Null

我认为它会工作得很好,直到我发现我认为只有Alpha#12345789格式的某些数据字段不...

需要剥离的数据示例

AB ABCDE # 123
ABCDE# 123
AB: ABC# 123

我只想要123.确实所有数据字段都具有#之前的数字。

我尝试了substring和PatIndex,但我的语法不正确或者其他东西。任何人对解决这个问题的最佳方法有任何建议吗?

谢谢!

tsql sql-server-2008-r2 substring patindex
15个回答
63
投票

有关从SQL Server中的字符串中提取数字,请参阅此blog post。下面是您的示例中使用字符串的示例:

DECLARE @textval NVARCHAR(30)
SET @textval = 'AB ABCDE # 123'

SELECT LEFT(SUBSTRING(@textval, PATINDEX('%[0-9.-]%', @textval), 8000),
           PATINDEX('%[^0-9.-]%', SUBSTRING(@textval, PATINDEX('%[0-9.-]%', @textval), 8000) + 'X') -1)

0
投票

这是答案:

DECLARE @t TABLE (tVal VARCHAR(100))

INSERT INTO @t VALUES('123')
INSERT INTO @t VALUES('123S')
INSERT INTO @t VALUES('A123,123')
INSERT INTO @t VALUES('a123..A123')


;WITH cte (original, tVal, n)
     AS
     (
         SELECT t.tVal AS original,
                LOWER(t.tVal)  AS tVal,
                65             AS n
         FROM   @t             AS t
         UNION ALL
         SELECT tVal AS original,
                CAST(REPLACE(LOWER(tVal), LOWER(CHAR(n)), '') AS VARCHAR(100)),
                n + 1
         FROM   cte
         WHERE  n <= 90
     )

SELECT t1.tVal  AS OldVal,
       t.tval   AS NewVal
FROM   (
           SELECT original,
                  tVal,
                  ROW_NUMBER() OVER(PARTITION BY tVal + original ORDER BY original) AS Sl
           FROM   cte
           WHERE  PATINDEX('%[a-z]%', tVal) = 0
       ) t
       INNER JOIN @t t1
            ON  t.original = t1.tVal
WHERE  t.sl = 1

0
投票
Create function fn_GetNumbersOnly(@pn varchar(100))
    Returns varchar(max)
    AS
    BEGIN
      Declare @r varchar(max) ='', @len int ,@c char(1), @x int = 0
      Select @len = len(@pn)
      while @x <= @len 
      begin
        Select @c = SUBSTRING(@pn,@x,1)
        if ISNUMERIC(@c) = 1 and @c <> '-'
         Select @r = @r + @c
       Select @x = @x +1
      end
    return @r
End

0
投票

这对我有用:

  1. 我删除了单引号。
  2. 然后我用","替换"."

当然,这将有助于某人:

" & txtFinalscore.Text.Replace(",", ".") & "

0
投票

在你的情况下似乎#将始终在teh#符号之后,所以使用CHARINDEX()与LTRIM()和RTRIM()可能会表现最佳。但这是一个摆脱任何非数字的有趣方法。它利用一个计数表和数字表来限制接受哪些字符,然后使用XML技术连接回一个不带非数字字符的字符串。关于这种技术的巧妙之处在于它可以扩展为包含任何允许的字符并删除任何不允许的内容。

DECLARE @ExampleData AS TABLE (Col VARCHAR(100))
INSERT INTO @ExampleData (Col) VALUES ('AB ABCDE # 123'),('ABCDE# 123'),('AB: ABC# 123')

DECLARE @Digits AS TABLE (D CHAR(1))
INSERT INTO @Digits (D) VALUES ('0'),('1'),('2'),('3'),('4'),('5'),('6'),('7'),('8'),('9')

;WITH cteTally AS (
SELECT
    I = ROW_NUMBER() OVER (ORDER BY (SELECT NULL))
FROM
    @Digits d10
    CROSS APPLY @Digits d100
    --add more cross applies to cover longer fields this handles 100
)

SELECT *
FROM
    @ExampleData e
    OUTER APPLY (
    SELECT CleansedPhone = CAST((
    SELECT TOP 100
       SUBSTRING(e.Col,t.I,1)
    FROM
       cteTally t
       INNER JOIN @Digits d
       ON SUBSTRING(e.Col,t.I,1) = d.D
    WHERE
       I <= LEN(e.Col)
    ORDER BY
       t.I
    FOR XML PATH('')) AS VARCHAR(100))) o

0
投票

您可以创建SQL CLR标量函数,以便能够使用替换模式等正则表达式。

Here你可以找到如何创建这样的功能的例子。

拥有这样的功能将只用以下几行解决问题:

SELECT [dbo].[fn_Utils_RegexReplace] ('AB ABCDE # 123', '[^0-9]', '');
SELECT [dbo].[fn_Utils_RegexReplace] ('ABCDE# 123', '[^0-9]', '');
SELECT [dbo].[fn_Utils_RegexReplace] ('AB: ABC# 123', '[^0-9]', '');

更重要的是,您将能够解决更复杂的问题,因为正则表达式将直接在您的T-SQL语句中带来全新的选项世界。


0
投票
CREATE FUNCTION FN_RemoveNonNumeric (@Input NVARCHAR(512))
RETURNS NVARCHAR(512)
AS
BEGIN
DECLARE @Trimmed NVARCHAR(512)

SELECT @Trimmed = @Input

WHILE PATINDEX('%[^0-9]%', @Trimmed) > 0
    SELECT @Trimmed = REPLACE(@Trimmed, SUBSTRING(@Trimmed, PATINDEX('%[^0-9]%', @Trimmed), 1), '')

RETURN @Trimmed
END

GO

SELECT dbo.FN_RemoveNonNumeric('ABCDE# 123')

34
投票

你可以使用stuffpatindex

stuff(Col, 1, patindex('%[0-9]%', Col)-1, '')

SQL Fiddle


20
投票

如果数字之间可能存在某些字符(例如千位分隔符),您可以尝试以下操作:

declare @table table (DirtyCol varchar(100))
insert into @table values
    ('AB ABCDE # 123')
    ,('ABCDE# 123')
    ,('AB: ABC# 123')
    ,('AB#')
    ,('AB # 1 000 000')
    ,('AB # 1`234`567')
    ,('AB # (9)(876)(543)')

;with tally as (select top (100) N=row_number() over (order by @@spid) from sys.all_columns),
data as (
    select DirtyCol, Col
    from @table
        cross apply (
            select (select C + ''
            from (select N, substring(DirtyCol, N, 1) C from tally where N<=datalength(DirtyCol)) [1]
            where C between '0' and '9'
            order by N
            for xml path(''))
        ) p (Col)
    where p.Col is not NULL
)
select DirtyCol, cast(Col as int) IntCol
from data

输出是:

DirtyCol              IntCol
--------------------- -------
AB ABCDE # 123        123
ABCDE# 123            123
AB: ABC# 123          123
AB # 1 000 000        1000000
AB # 1`234`567        1234567
AB # (9)(876)(543)    9876543

要进行更新,请添加ColToUpdate以选择data cte的列表:

;with num as (...),
data as (
    select ColToUpdate, /*DirtyCol, */Col
    from ...
)
update data
set ColToUpdate = cast(Col as int)

13
投票

这适合我:

CREATE FUNCTION [dbo].[StripNonNumerics]
(
  @Temp varchar(255)
)
RETURNS varchar(255)
AS
Begin

    Declare @KeepValues as varchar(50)
    Set @KeepValues = '%[^0-9]%'
    While PatIndex(@KeepValues, @Temp) > 0
        Set @Temp = Stuff(@Temp, PatIndex(@KeepValues, @Temp), 1, '')

    Return @Temp
End

然后像这样调用函数来查看清理过的东西旁边的原始内容:

SELECT Something, dbo.StripNonNumerics(Something) FROM TableA

9
投票

如果您的服务器支持TRANSLATE功能,那么这是一个优雅的解决方案(在sql server上它可以在sql server 2017+以及sql azure上使用)。

首先,它用@字符替换任何非数字字符。然后,它删除所有@字符。您可能需要添加您知道可能存在于TRANSLATE调用的第二个参数中的其他字符。

select REPLACE(TRANSLATE([Col], 'abcdefghijklmnopqrstuvwxyz+()- ,#+', '@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@'), '@', '')

1
投票

要添加到Ken's答案,这将处理逗号和空格和括号

--Handles parentheses, commas, spaces, hyphens..
declare @table table (c varchar(256))
insert into @table
values
('This is a test 111-222-3344'),
('Some Sample Text (111)-222-3344'),
('Hello there 111222 3344 / How are you?'),
('Hello there 111 222 3344 ? How are you?'),
('Hello there 111 222 3344. How are you?')

select
replace(LEFT(SUBSTRING(replace(replace(replace(replace(replace(c,'(',''),')',''),'-',''),' ',''),',',''), PATINDEX('%[0-9.-]%', replace(replace(replace(replace(replace(c,'(',''),')',''),'-',''),' ',''),',','')), 8000),
           PATINDEX('%[^0-9.-]%', SUBSTRING(replace(replace(replace(replace(replace(c,'(',''),')',''),'-',''),' ',''),',',''), PATINDEX('%[0-9.-]%', replace(replace(replace(replace(replace(c,'(',''),')',''),'-',''),' ',''),',','')), 8000) + 'X') -1),'.','')
from @table

0
投票
 Declare @MainTable table(id int identity(1,1),TextField varchar(100))
  INSERT INTO @MainTable (TextField)
 VALUES
 ('6B32E')
 declare @i int=1
  Declare @originalWord varchar(100)=''
  WHile @i<=(Select count(*) from @MainTable)
  BEGIN
  Select @originalWord=TextField from @MainTable where id=@i

 Declare @r varchar(max) ='', @len int ,@c char(1), @x int = 0

    Select @len = len(@originalWord)
    declare @pn varchar(100)=@originalWord
    while @x <= @len 
    begin

      Select @c = SUBSTRING(@pn,@x,1)
    if(@c!='')
    BEGIN
            if ISNUMERIC(@c) = 0 and @c <> '-'
    BEGIN
     Select @r = cast(@r as varchar) + cast(replace((SELECT ASCII(@c)-64),'-','') as varchar)

   end
   ELSE
   BEGIN
    Select @r = @r + @c


   END

END


    Select @x = @x +1

    END
    Select @r
  Set @i=@i+1
  END

0
投票

这是一个从字符串中提取所有数字的版本;即给予I'm 35 years old; I was born in 1982. The average family has 2.4 children.这将返回35198224。也就是说你的数字数据可能被格式化为代码(例如#123,456,789 / 123-00005)很好,但是如果你想要提取特定数字(即与数字相对而不是数字)则不合适字符)来自文本。它也只处理数字;所以不会返回负号(-)或期间.)。

declare @table table (id bigint not null identity (1,1), data nvarchar(max)) 
insert @table (data) 
values ('hello 123 its 45613 then') --outputs: 12345613
,('1 some other string 98 example 4') --outputs: 1984
,('AB ABCDE # 123') --outputs: 123 
,('ABCDE# 123') --outputs: 123
,('AB: ABC# 123') --outputs: 123
; with NonNumerics as (
    select id
    , data original
    --the below line replaces all digits with blanks
    , replace(replace(replace(replace(replace(replace(replace(replace(replace(replace(data,'0',''),'1',''),'2',''),'3',''),'4',''),'5',''),'6',''),'7',''),'8',''),'9','') nonNumeric
    from @table
)
--each iteration of the below CTE removes another non-numeric character from the original string, putting the result into the numerics column
, Numerics as (
    select id
    , replace(original, substring(nonNumeric,1,1), '') numerics
    , replace(nonNumeric, substring(nonNumeric,1,1), '') charsToreplace
    , len(replace(nonNumeric, substring(nonNumeric,1,1), '')) charsRemaining
    from NonNumerics

    union all

    select id
    , replace(numerics, substring(charsToreplace,1,1), '') numerics
    , replace(charsToreplace, substring(charsToreplace,1,1), '') charsToreplace
    , len(replace(charsToreplace, substring(charsToreplace,1,1), '')) charsRemaining
    from Numerics
    where charsRemaining > 0
)
--we select only those strings with `charsRemaining=0`; i.e. the rows for which all non-numeric characters have been removed; there should be 1 row returned for every 1 row in the original data set.
select * from Numerics where charsRemaining = 0

这段代码的工作原理是从给定的字符串中删除所有数字(即我们想要的字符),方法是用空格替换它们。然后它通过原始字符串(包括数字)删除所有剩下的字符(即非数字字符),从而只留下数字。

之所以我们分两步完成,而不是仅仅删除所有非数字字符,那么只有10位数,而且有大量可能的字符;所以取代那个小名单的速度相对较快;然后给我们一个实际存在于字符串中的那些非数字字符的列表,这样我们就可以替换那个小集。

该方法使用公共表表达式(CTE)来使用递归SQL。


0
投票

我为此创建了一个函数

Create FUNCTION RemoveCharacters (@text varchar(30))
RETURNS VARCHAR(30)
AS
BEGIN
declare @index as int 
declare @newtexval as varchar(30)
set @index = (select PATINDEX('%[A-Z.-/?]%', @text))
if (@index =0)
begin 
return @text
end
else
begin 
set @newtexval  = (select STUFF ( @text , @index , 1 , '' ))
return dbo.RemoveCharacters(@newtexval)
end
return 0
END
GO
© www.soinside.com 2019 - 2024. All rights reserved.