Sql 如何替换字符串中的所有特殊字符_Sql_Sql Server_String_Tsql

Sql 如何替换字符串中的所有特殊字符

sql sql-server string tsql

Sql 如何替换字符串中的所有特殊字符,sql,sql-server,string,tsql,Sql,Sql Server,String,Tsql,我有一个包含以下列的表： dbo.SomeInfo - Id - Name - InfoCode 现在我需要将上表的InfoCode更新为 Update dbo.SomeInfo Set InfoCode= REPLACE(Replace(RTRIM(LOWER(Name)),' ','-'),':','') 这会将所有空格替换为名称的-&小写当我检查信息代码时，我看到一些名称带有一些特殊字符，如 Cathe Friedrich''s Low Impact coffeyfit

我有一个包含以下列的表：

dbo.SomeInfo
  - Id
  - Name
  - InfoCode

现在我需要将上表的InfoCode更新为

Update  dbo.SomeInfo
Set InfoCode= REPLACE(Replace(RTRIM(LOWER(Name)),' ','-'),':','')

这会将所有空格替换为名称的

&小写

当我检查信息代码时，我看到一些名称带有一些特殊字符，如

Cathe Friedrich''s Low Impact
coffeyfit-cardio-box-&-burn
Jillian Michaels: Cardio

然后，我将根据以下内容手动编写更新sql

 Update dbo.SomeInfo
 SET InfoCode= 'cathe-friedrichs-low-impact'
 where Name ='Cathe Friedrich''s Low Impact '

现在，这个解决方案对我来说不现实。我查看了以下与Regex和其他相关的链接

但它们都没有达到要求

我需要的是，如果存在[a-z0-9]以外的任何字符，请将其替换-&而且信息代码中不应存在连续字符

上述更新sql已将InfoCode的一些值设置为

The dancer's-workout®----starter package

有些名称具有相同的价值

Sleek Technique™
The Dancer's-workout®

如何编写能够处理所有此类特殊字符的更新sql？

使用可以将字符串拆分为字符，然后只保留某些字符，而不是替换每个不可接受的字符：

SELECT (SELECT '' + CASE WHEN N.token COLLATE Latin1_General_BIN LIKE '[A-z0-9]'THEN token ELSE '-' END
        FROM dbo.NGrams8k(V.S,1) N
        ORDER BY position
        FOR XML PATH(''))
FROM (VALUES('Sleek Technique™'),('The Dancer''s-workout®'))V(S);

我在这里使用

COLLATE

作为我实例中的默认排序规则

™'被忽略，因此我使用二进制排序规则。您可能希望使用COLLATE
将字符串切换回子查询之外的原始排序规则。
使用可以将字符串拆分为字符，然后只保留某些字符，而不是替换每个不可接受的字符：
SELECT (SELECT '' + CASE WHEN N.token COLLATE Latin1_General_BIN LIKE '[A-z0-9]'THEN token ELSE '-' END
        FROM dbo.NGrams8k(V.S,1) N
        ORDER BY position
        FOR XML PATH(''))
FROM (VALUES('Sleek Technique™'),('The Dancer''s-workout®'))V(S);

我在这里使用COLLATE
作为我实例中的默认排序规则™'被忽略，因此我使用二进制排序规则。您可能需要使用COLLATE
将字符串切换回子查询之外的原始排序规则。
您可以为类似的内容创建一个用户定义的函数
然后在更新中使用UDF
CREATE FUNCTION [dbo].LowerDashString (@str varchar(255))
RETURNS varchar(255)
AS
BEGIN
    DECLARE @result varchar(255);
    DECLARE @chr varchar(1);
    DECLARE @pos int;
    SET @result = '';
    SET @pos = 1;

    -- lowercase the input and remove the single-quotes
    SET @str = REPLACE(LOWER(@str),'''','');

    -- loop through the characters 
    -- while replacing anything that's not a letter to a dash
    WHILE @pos <= LEN(@str)
    BEGIN

      SET @chr = SUBSTRING(@str, @pos, 1)

      IF @chr LIKE '[a-z]' SET @result += @chr;
      ELSE SET @result += '-';

      SET @pos += 1;
    END;

    -- SET @result = TRIM('-' FROM @result); -- SqlServer 2017 and beyond

    -- multiple dashes to one dash
    WHILE @result LIKE '%--%' SET @result = REPLACE(@result,'--','-');

    RETURN @result;
END;
GO

结果：
Id  InfoCode
--  -----------------------------
1   cathe-friedrichs-low-impact
2   coffeyfit-cardio-box-burn
3   jillian-michaels-cardio
4   sleek-technique-
5   the-dancers-workout-

您可以为类似的内容创建一个用户定义的函数
然后在更新中使用UDF
CREATE FUNCTION [dbo].LowerDashString (@str varchar(255))
RETURNS varchar(255)
AS
BEGIN
    DECLARE @result varchar(255);
    DECLARE @chr varchar(1);
    DECLARE @pos int;
    SET @result = '';
    SET @pos = 1;

    -- lowercase the input and remove the single-quotes
    SET @str = REPLACE(LOWER(@str),'''','');

    -- loop through the characters 
    -- while replacing anything that's not a letter to a dash
    WHILE @pos <= LEN(@str)
    BEGIN

      SET @chr = SUBSTRING(@str, @pos, 1)

      IF @chr LIKE '[a-z]' SET @result += @chr;
      ELSE SET @result += '-';

      SET @pos += 1;
    END;

    -- SET @result = TRIM('-' FROM @result); -- SqlServer 2017 and beyond

    -- multiple dashes to one dash
    WHILE @result LIKE '%--%' SET @result = REPLACE(@result,'--','-');

    RETURN @result;
END;
GO

结果：
Id  InfoCode
--  -----------------------------
1   cathe-friedrichs-low-impact
2   coffeyfit-cardio-box-burn
3   jillian-michaels-cardio
4   sleek-technique-
5   the-dancers-workout-

此方法完全可嵌入：
首先，我们需要一个带有一些测试数据的模型表：
DECLARe @SomeInfo TABLE (Id INT IDENTITY, InfoCode VARCHAR(100));
INSERT INTO @SomeInfo (InfoCode) VALUES
 ('Cathe Friedrich''s Low Impact')
,('coffeyfit-cardio-box-&-burn')
,('Jillian Michaels: Cardio')
,('Sleek Technique™')
,('The Dancer''s-workout®');

--这就是问题所在
WITH cte AS
(
    SELECT 1 AS position
          ,si.Id
          ,LOWER(si.InfoCode) AS SourceText
          ,SUBSTRING(LOWER(si.InfoCode),1,1) AS OneChar
    FROM @SomeInfo si

    UNION ALL

    SELECT cte.position +1
          ,cte.Id
          ,cte.SourceText
          ,SUBSTRING(LOWER(cte.SourceText),cte.position+1,1) AS OneChar
    FROM cte
    WHERE position < DATALENGTH(SourceText)
)
,Cleaned AS
(
    SELECT cte.Id
          ,(
            SELECT CASE WHEN ASCII(cte2.OneChar) BETWEEN 65 AND 90 --A-Z
                          OR ASCII(cte2.OneChar) BETWEEN 97 AND 122--a-z
                          OR ASCII(cte2.OneChar) BETWEEN 48 AND 57 --0-9
                          --You can easily add more ranges
                        THEN cte2.OneChar ELSE '-' 
                          --You can easily nest another CASE to deal with special characters like the single quote in your examples... 
                   END 
            FROM cte AS cte2
            WHERE cte2.Id=cte.Id
            ORDER BY cte2.position
            FOR XML PATH('')
           ) AS normalised
    FROM cte
    GROUP BY cte.Id
)
,NoDoubleHyphens AS
(
    SELECT REPLACE(REPLACE(REPLACE(normalised,'-','<>'),'><',''),'<>','-') AS normalised2
    FROM Cleaned
)
SELECT CASE WHEN RIGHT(normalised2,1)='-' THEN SUBSTRING(normalised2,1,LEN(normalised2)-1) ELSE normalised2 END AS FinalResult 
FROM NoDoubleHyphens;

此方法完全可嵌入：
首先，我们需要一个带有一些测试数据的模型表：
DECLARe @SomeInfo TABLE (Id INT IDENTITY, InfoCode VARCHAR(100));
INSERT INTO @SomeInfo (InfoCode) VALUES
 ('Cathe Friedrich''s Low Impact')
,('coffeyfit-cardio-box-&-burn')
,('Jillian Michaels: Cardio')
,('Sleek Technique™')
,('The Dancer''s-workout®');

--这就是问题所在
WITH cte AS
(
    SELECT 1 AS position
          ,si.Id
          ,LOWER(si.InfoCode) AS SourceText
          ,SUBSTRING(LOWER(si.InfoCode),1,1) AS OneChar
    FROM @SomeInfo si

    UNION ALL

    SELECT cte.position +1
          ,cte.Id
          ,cte.SourceText
          ,SUBSTRING(LOWER(cte.SourceText),cte.position+1,1) AS OneChar
    FROM cte
    WHERE position < DATALENGTH(SourceText)
)
,Cleaned AS
(
    SELECT cte.Id
          ,(
            SELECT CASE WHEN ASCII(cte2.OneChar) BETWEEN 65 AND 90 --A-Z
                          OR ASCII(cte2.OneChar) BETWEEN 97 AND 122--a-z
                          OR ASCII(cte2.OneChar) BETWEEN 48 AND 57 --0-9
                          --You can easily add more ranges
                        THEN cte2.OneChar ELSE '-' 
                          --You can easily nest another CASE to deal with special characters like the single quote in your examples... 
                   END 
            FROM cte AS cte2
            WHERE cte2.Id=cte.Id
            ORDER BY cte2.position
            FOR XML PATH('')
           ) AS normalised
    FROM cte
    GROUP BY cte.Id
)
,NoDoubleHyphens AS
(
    SELECT REPLACE(REPLACE(REPLACE(normalised,'-','<>'),'><',''),'<>','-') AS normalised2
    FROM Cleaned
)
SELECT CASE WHEN RIGHT(normalised2,1)='-' THEN SUBSTRING(normalised2,1,LEN(normalised2)-1) ELSE normalised2 END AS FinalResult 
FROM NoDoubleHyphens;