SQL - 查找重复值并在字段中删除

Question

考虑 Article 表中名为 ArticleCategories 的列。目标是从每行的 ArticleCategories 列中删除重复的数字（。

ArticleCategories
------------
3193;2867;3193;
2871;2923;2923;
3278;3337;3337;
2878;2876;2878;
3720;3680;3680;

关于如何使用 SQL Server 完成此任务的任何帮助？

想要的结果

ArticleCategories
------------
3193;2867;
2871;2923;
3278;3337;
2878;2876;
3720;3680;

如果有人可以提供帮助，请提前致谢。

Answer 1

首先创建函数SplitAndRemoveDuplicates，它将用分隔符分割给定字符串，删除重复项，并返回字符串：

CREATE FUNCTION [dbo].[SplitAndRemoveDuplicates] (@sep VARCHAR(32), @s VARCHAR(MAX))

RETURNS VARCHAR(MAX)  
AS
BEGIN

   DECLARE @t TABLE (val VARCHAR(MAX)) 

   DECLARE @xml XML
   SET @xml = N'<root><r>' + REPLACE(@s, @sep, '</r><r>') + '</r></root>'

   INSERT INTO @t(val) SELECT r.value('.','VARCHAR(MAX)') as Item FROM @xml.nodes('//root/r') AS RECORDS(r)

   ;WITH cte
    AS (SELECT ROW_NUMBER() OVER (PARTITION BY val ORDER BY val desc) RN
    FROM  @t)
    DELETE FROM cte
    WHERE  RN > 1

    RETURN (SELECT val + ';' from @t WHERE val <> '' FOR XML PATH ('') )
END

利用函数更新已有数据：

UPDATE Article
SET ArticleCategories = (SELECT dbo.[SplitAndRemoveDuplicates](';', ArticleCategories))

现在你有了一个可重用的函数。

感谢：https://stackoverflow.com/a/314917/455770 和 https://stackoverflow.com/a/3822833/455770

Answer 2

找到了解决我问题的方法，希望对其他人也有帮助。

CREATE FUNCTION dbo.DistinctList
(
@List VARCHAR(MAX),
@Delim CHAR
)
RETURNS
VARCHAR(MAX)
AS
BEGIN
DECLARE @ParsedList TABLE
(
Item VARCHAR(MAX)
)
DECLARE @list1 VARCHAR(MAX), @Pos INT, @rList VARCHAR(MAX)
SET @list = LTRIM(RTRIM(@list)) + @Delim
SET @pos = CHARINDEX(@delim, @list, 1)
WHILE @pos > 0
BEGIN
SET @list1 = LTRIM(RTRIM(LEFT(@list, @pos - 1)))
IF @list1 <> ''
INSERT INTO @ParsedList VALUES (CAST(@list1 AS VARCHAR(MAX)))
SET @list = SUBSTRING(@list, @pos+1, LEN(@list))
SET @pos = CHARINDEX(@delim, @list, 1)
END
SELECT @rlist = COALESCE(@rlist+',','') + item
FROM (SELECT DISTINCT Item FROM @ParsedList) t
RETURN @rlist
END
GO
SELECT dbo.DistinctList('342,34,456,34,3454,456,aa,bb,cc,aa',',') DistinctList
GO

在此感谢脚本的作者。 http://blog.sqlauthority.com/2009/01/15/sql-server-remove-duplicate-entry-from-comma-delimited-string-udf/

Answer 3

没有光标也没有while，是本站之前的问题的组合

1. Split Columns
2. Join The Rows Back

所以答案是创建一个string Split function

CREATE FUNCTION [dbo].[StringSplit]
(
  @delimited nvarchar(max),
  @delimiter nvarchar(100)     
) RETURNS @t TABLE
(
-- Id column can be commented out, not required for sql splitting string
  id int identity(1,1), -- I use this column for numbering splitted parts
  val nvarchar(max)
)
AS
BEGIN
  declare @xml xml
  set @xml = N'<root><r>' + replace(@delimited,@delimiter,'</r><r>') + '</r></root>'

  insert into @t(val)
  select 
    r.value('.','varchar(max)') as item
  from @xml.nodes('//root/r') as records(r)

  RETURN
END

查询看起来像：

declare @Article  table
(
  ArticleCategories varchar(100)
)

insert into @Article values
('3193;2867;3193;'),
('2871;2923;2923;'),
('3278;3337;3337;'),
('2878;2876;2878;'),
('3720;3680;3680;')

;WITH DistinctArticles AS (
    SELECT DISTINCT ArticleCategories, Val
    FROM @article
    CROSS APPLY dbo.[StringSplit](ArticleCategories, ';')
    WHERE Val <> ''
),
Concatenated AS (
    SELECT 
        ArticleCategories,
        STUFF((
            SELECT '; ' + CAST([Val] AS VARCHAR(MAX)) 
            FROM DistinctArticles
            WHERE (ArticleCategories = Results.ArticleCategories) 
    FOR XML PATH(''),TYPE).value('(./text())[1]','VARCHAR(MAX)'),1,2,'') + ';' AS DistinctArticleCategories
    FROM DistinctArticles Results
    GROUP BY ArticleCategories
)
UPDATE @Article 
SET ArticleCategories = Concatenated.DistinctArticleCategories
FROM @Article a
INNER JOIN Concatenated ON a.ArticleCategories = Concatenated.ArticleCategories

Answer 4

尝试以下解决方案

首先创建一个UDF，如下所示

alter function dbo.SplitString2(@inputStr varchar(1000),@del varchar(5))
RETURNS varchar(max)
As
BEGIN

DECLARE @t table(col1 varchar(100))
DECLARE @table table(col1 varchar(100))
DECLARE @ret varchar(max)
Set @ret = ''
INSERT INTO @t
select @inputStr

if CHARINDEX(@del,@inputStr,1) > 0
BEGIN
    ;WITH CTE1 as (
    select ltrim(rtrim(LEFT(col1,CHARINDEX(@del,col1,1)-1))) as col,RIGHT(col1,LEN(col1)-CHARINDEX(@del,col1,1)) as rem from @t
    union all
    select ltrim(rtrim(LEFT(rem,CHARINDEX(@del,rem,1)-1))) as col,RIGHT(rem,LEN(rem)-CHARINDEX(@del,rem,1))
    from CTE1 c
    where CHARINDEX(@del,rem,1)>0
    )

        INSERT INTO @table 
        select col from CTE1
        union all
        select rem from CTE1 where CHARINDEX(@del,rem,1)=0
    END
ELSE
BEGIN
    INSERT INTO @table 
    select col1 from @t
END

Set @ret = (Select distinct col1 + ';'  from @table for xml path(''))

return @ret

END

然后您可以根据需要运行以下选择/更新查询

更新查询——这将更新您表中的记录

update ArticleCategory Set ArticleCategories = dbo.SplitString2(ArticleCategories, ';' )

选择查询——这将只选择不同的记录

Select ArticleCategories , dbo.SplitString2(ArticleCategories, ';' ) from ArticleCategory

Answer 5

如果必须保留哪些行无关紧要：

DELETE FROM Article WHERE (
    SELECT COUNT(*) FROM Article t WHERE
    t.ArticleCategories=Article.ArticleCategories AND t.%%physloc%%<Article.%%physloc%%
)>0;

这就是我在 SQLite 中的做法，不确定我是否匹配 MS SQL Server 的语法...

Answer 6

请尝试以下解决方案，它已针对您的情况进行了全面测试，希望对您有所帮助。

DECLARE @ArticleCategories varchar(500)
DECLARE Cursor_Article CURSOR FOR 
SELECT ArticleCategories from Article
OPEN Cursor_Article
FETCH NEXT FROM Cursor_Article INTO @ArticleCategories
WHILE @@FETCH_STATUS = 0
BEGIN

   DECLARE @individualNum varchar(500),@ArticleCategoriesNew varchar(500) ,@ArticleCategoriesRem varchar(500)
   SET @ArticleCategoriesNew='';
   SET @ArticleCategoriesRem=@ArticleCategories

   WHILE PATINDEX('%;%',@ArticleCategoriesRem) > 0
   BEGIN
       SET @individualNum = SUBSTRING(@ArticleCategoriesRem, 0, PATINDEX('%;%',@ArticleCategoriesRem)) 

       SET @ArticleCategoriesRem = SUBSTRING(@ArticleCategoriesRem, LEN(@individualNum + ';') + 1, LEN(@ArticleCategoriesRem))
       if(@ArticleCategoriesRem not like '%'+@individualNum+'%')
       set @ArticleCategoriesNew=CASE WHEN ISNULL(@ArticleCategoriesNew,'')='' THEN @individualNum ELSE @ArticleCategoriesNew+';'+@individualNum+';' END

   END
   --If ArticleCategories is unique then leave same condition else Fetch primary key in cursor and append in Where condition of Update query
   Update Article SET ArticleCategories=@ArticleCategoriesNew WHERE ArticleCategories=@ArticleCategories    

   FETCH NEXT FROM Cursor_Article INTO @ArticleCategories
END 
CLOSE Cursor_Article;
DEALLOCATE Cursor_Article;

Answer 7

SELECT DISTINCT ArticleCategories FROM Article

或

SELECT ArticleCategories 
FROM Article
GROUP BY ArticleCategories 

这是删除重复值

DELETE
FROM Article
WHERE ArticleCategories NOT IN
(
   SELECT MAX(ArticleCategories)
   FROM Article
   GROUP BY ArticleCategories
)