Sql server 查找并删除重复的子字符串

我在SQLServer2008表中有一列，其中部分字符串意外重复

有没有人有一个快速简单的方法来删除尾部重复的子字符串

比如说,

alpha\bravo\charlie\delta\charlie\delta

应该是

alpha\bravo\charlie\delta

---

如果您还没有数字表：

SET NOCOUNT ON;
DECLARE @UpperLimit INT;
SET @UpperLimit = 4000;

WITH n(rn) AS
(
    SELECT ROW_NUMBER() OVER (ORDER BY [object_id])
    FROM sys.all_columns
)
SELECT [Number] = rn - 1
INTO dbo.Numbers FROM n
WHERE rn <= @UpperLimit + 1;

CREATE UNIQUE CLUSTERED INDEX n ON dbo.Numbers([Number]);

示例用法：

SELECT dbo.DedupeString('alpha\bravo\bravo\charlie\delta\bravo\charlie\delta');

结果:

alpha\bravo\charlie\delta

你也可以这样说：

UPDATE dbo.MessedUpTable
  SET OopsColumn = dbo.DedupeString(OopsColumn);

@MikaelEriksson可能会用一种更有效的方法来使用XML消除重复项，但这是我在此之前可以提供的：-

create function RemoveDups(@S nvarchar(max)) returns nvarchar(max)
as
begin
  declare @R nvarchar(max)
  declare @W nvarchar(max)
  set @R = ''

  while len(@S) > 1
  begin
    -- Get the first word
    set @W = left(@S, charindex('/', @S+'/')-1)

    -- Add word to result if not already added
    if '/'+@R not like '%/'+@W+'/%'
    begin
      set @R = @R + @W + '/'
    end 

    -- Remove first word
    set @S = stuff(@S, 1, charindex('/', @S+'/'), '')
  end

  return left(@R, len(@R)- 1)
end

应秘书长的要求。然而，我不会就什么是最快的执行提出任何要求

-- Table to replace in
declare @T table
(
  ID int identity,
  Value nvarchar(max)
)

-- Add some sample data
insert into @T values ('alpha/beta/alpha/gamma/delta/gamma/delta/alpha')
insert into @T values ('delta/beta/alpha/beta/alpha/gamma/delta/gamma/delta/alpha')

-- Update the column
update T
set Value = NewValue
from (
       select T1.ID,
              Value,
              stuff((select '/' + T4.Value
                     from (
                            select T3.X.value('.', 'nvarchar(max)') as Value,
                                   row_number() over(order by T3.X) as rn
                            from T2.X.nodes('/x') as T3(X)
                          ) as T4
                     group by T4.Value
                     order by min(T4.rn)
                     for xml path(''), type).value('.',  'nvarchar(max)'), 1, 1, '') as NewValue
       from @T as T1
         cross apply (select cast('<x>'+replace(T1.Value, '/', '</x><x>')+'</x>' as xml)) as T2(X)
     ) as T

select *
from @T  

---

我假设您也要消除多个重复，例如source=alpha\bravo\alpha\bravo\alpha变为alpha\bravo？是否也要查找重复项，以及是整个字符串还是较大字符串中的子字符串？@TonyHopkinson：示例是整个字符串，而不是较大字符串的一部分。复制的长度会有所不同，例如ABCDBCD->ABCD.Oops。否我添加了常规行走字符串：。我将考虑一下XML的内容。我还添加了一个XML版本。要保留单词的顺序有点棘手。但是我不认为使用XML来拆分字符串比数字表更有效。我知道这是一篇比较老的帖子，但这让我很开心！

create function RemoveDups(@S nvarchar(max)) returns nvarchar(max)
as
begin
  declare @R nvarchar(max)
  declare @W nvarchar(max)
  set @R = ''

  while len(@S) > 1
  begin
    -- Get the first word
    set @W = left(@S, charindex('/', @S+'/')-1)

    -- Add word to result if not already added
    if '/'+@R not like '%/'+@W+'/%'
    begin
      set @R = @R + @W + '/'
    end 

    -- Remove first word
    set @S = stuff(@S, 1, charindex('/', @S+'/'), '')
  end

  return left(@R, len(@R)- 1)
end

-- Table to replace in
declare @T table
(
  ID int identity,
  Value nvarchar(max)
)

-- Add some sample data
insert into @T values ('alpha/beta/alpha/gamma/delta/gamma/delta/alpha')
insert into @T values ('delta/beta/alpha/beta/alpha/gamma/delta/gamma/delta/alpha')

-- Update the column
update T
set Value = NewValue
from (
       select T1.ID,
              Value,
              stuff((select '/' + T4.Value
                     from (
                            select T3.X.value('.', 'nvarchar(max)') as Value,
                                   row_number() over(order by T3.X) as rn
                            from T2.X.nodes('/x') as T3(X)
                          ) as T4
                     group by T4.Value
                     order by min(T4.rn)
                     for xml path(''), type).value('.',  'nvarchar(max)'), 1, 1, '') as NewValue
       from @T as T1
         cross apply (select cast('<x>'+replace(T1.Value, '/', '</x><x>')+'</x>' as xml)) as T2(X)
     ) as T

select *
from @T