重新排列sql中的列的单词

时间:2017-01-04 15:27:23

标签: sql sql-server-2012

我必须比较以下两个数据表

表a

cust text

1 Director (Corporate Trustee)@Settlor

2 Director@Settlor@Shareholder

表b

cust text

1 Settlor@Director (Corporate Trustee)

2 Settlor@Director@Shareholder

我正在使用除了但是返回了不匹配,b'ze文本字段中的单词不是按顺序。

请问快速解决方案吗?

1 个答案:

答案 0 :(得分:1)

为了让您入门,您可以使用字符串拆分功能(假设您的值由文本中的@分隔),然后比较每个客户的值。

用于比较值

的查询
declare @a table(cust int
                ,[text] nvarchar(500)
                );
declare @b table(cust int
                ,[text] nvarchar(500)
                );
insert into @a values
 (1,'Director (Corporate Trustee)@Settlor')
,(2,'Director@Settlor@Shareholder');

insert into @b values
 (1,'Settlor@Director (Corporate Trustee)')
,(2,'Settlor@Director@Shareholder@ExtraText');    -- Note the ExtraText inserted here.

with a    -- Use derived tables to build a working dataset for both source tables.
as
(
    select *
    from @a a
        cross apply dbo.DelimitedSplit8K(a.text,'@') aa   -- This is how you use the string split function.
),b
as
(
    select *
    from @b b
        cross apply dbo.DelimitedSplit8K(b.text,'@') bb
)
select a.cust as CustA
        ,a.[text] as TextA
        ,a.ItemNumber as ItemNumberA
        ,a.Item as ItemA

        ,b.cust as CustB
        ,b.[text] as TextB
        ,b.ItemNumber as ItemNumberB
        ,b.Item as ItemB
from a
    full join b
        on(a.cust = b.cust
            and a.Item = b.Item
            )
order by 1,2,3;

查询输出

注意ExtraText为表A返回null,因为它不存在。

+-------+--------------------------------------+-------------+------------------------------+-------+----------------------------------------+-------------+------------------------------+
| CustA |                TextA                 | ItemNumberA |            ItemA             | CustB |                 TextB                  | ItemNumberB |            ItemB             |
+-------+--------------------------------------+-------------+------------------------------+-------+----------------------------------------+-------------+------------------------------+
| 1     | Director (Corporate Trustee)@Settlor | 1           | Director (Corporate Trustee) |     1 | Settlor@Director (Corporate Trustee)   |           2 | Director (Corporate Trustee) |
| 1     | Director (Corporate Trustee)@Settlor | 2           | Settlor                      |     1 | Settlor@Director (Corporate Trustee)   |           1 | Settlor                      |
| 2     | Director@Settlor@Shareholder         | 1           | Director                     |     2 | Settlor@Director@Shareholder@ExtraText |           2 | Director                     |
| 2     | Director@Settlor@Shareholder         | 2           | Settlor                      |     2 | Settlor@Director@Shareholder@ExtraText |           1 | Settlor                      |
| 2     | Director@Settlor@Shareholder         | 3           | Shareholder                  |     2 | Settlor@Director@Shareholder@ExtraText |           3 | Shareholder                  |
| NULL  | NULL                                 | NULL        | NULL                         |     2 | Settlor@Director@Shareholder@ExtraText |           4 | ExtraText                    |
+-------+--------------------------------------+-------------+------------------------------+-------+----------------------------------------+-------------+------------------------------+

Jeff Moden's string splitting function

SET ANSI_NULLS ON
GO

SET QUOTED_IDENTIFIER ON
GO

CREATE FUNCTION [dbo].[DelimitedSplit8K]
--===== Define I/O parameters
        (@pString VARCHAR(8000), @pDelimiter CHAR(1))
--WARNING!!! DO NOT USE MAX DATA-TYPES HERE!  IT WILL KILL PERFORMANCE!
RETURNS TABLE WITH SCHEMABINDING AS
 RETURN
--===== "Inline" CTE Driven "Tally Table" produces values from 1 up to 10,000...
     -- enough to cover VARCHAR(8000)
  WITH E1(N) AS (
                 SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL
                 SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL
                 SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1
                ),                          --10E+1 or 10 rows
       E2(N) AS (SELECT 1 FROM E1 a, E1 b), --10E+2 or 100 rows
       E4(N) AS (SELECT 1 FROM E2 a, E2 b), --10E+4 or 10,000 rows max
 cteTally(N) AS (--==== This provides the "base" CTE and limits the number of rows right up front
                     -- for both a performance gain and prevention of accidental "overruns"
                 SELECT TOP (ISNULL(DATALENGTH(@pString),0)) ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) FROM E4
                ),
cteStart(N1) AS (--==== This returns N+1 (starting position of each "element" just once for each delimiter)
                 SELECT 1 UNION ALL
                 SELECT t.N+1 FROM cteTally t WHERE SUBSTRING(@pString,t.N,1) = @pDelimiter
                ),
cteLen(N1,L1) AS(--==== Return start and length (for use in substring)
                 SELECT s.N1,
                        ISNULL(NULLIF(CHARINDEX(@pDelimiter,@pString,s.N1),0)-s.N1,8000)
                   FROM cteStart s
                )
--===== Do the actual split. The ISNULL/NULLIF combo handles the length for the final element when no delimiter is found.
 SELECT ItemNumber = ROW_NUMBER() OVER(ORDER BY l.N1),
        Item       = SUBSTRING(@pString, l.N1, l.L1)
   FROM cteLen l

GO