SQL:在 table 中查找缺失的层次结构文件夹(路径)
SQL: Find missing hierarchy Folders (Paths) in a table
我有一个 table,其中包含文件夹路径。
我需要找到层次结构中这些文件夹之间的所有 "gaps"。
我的意思是,如果 table 包含这 3 个文件夹:
'A'
'A\B\C'
'A\B\C\D\E\F\G'
我需要在层次结构中找到以下丢失的文件夹:
'A\B'
'A\B\C\D'
'A\B\C\D\E'
'A\B\C\D\E\F'
此 table 包含超过 250,000 条记录 的文件夹,因此我们寻求最高效 的方法,否则脚本会卡很久,我们没有时间
评论:我没有所有文件夹的列表。我有 "root" 文件夹和 "leafs" 文件夹,我需要在层次结构中找到它们之间的 "gaps"。
第二条评论:table可以包含[=36=]多个层级,我们需要在所有层级中找到"gaps"层次结构。
就此而言,还有 2 个其他 int 列:"DirID" 和 "BaseDirID"。 "DirID" 列是我们 table 中的 id 列。 "BaseDirID" 包含层次结构中第一个文件夹的 ID。因此,同一层次结构中的所有文件夹(路径)在此列中共享相同的值。样本数据例如:
DirID BaseDirID DisplayPath
1 1 'A'
2 1 'A\B\C'
3 1 'A\B\C\D\E'
4 4 'U'
5 4 'U\V\W'
6 4 'U\V\W\X\Y'
所以我们需要找到以下数据:
BaseDirID DisplayPath
1 'A\B'
1 'A\B\C\D'
4 'U\V'
4 'U\V\W\X'
提前致谢。
这是一种使用 Recursive CTE
和拆分字符串函数
的方法
;WITH existing_hierachies
AS (SELECT DirID,
BaseDirID,
DisplayPath
FROM (VALUES (1,1,'A' ),
(2,1,'A\B\C' ),
(3,1,'A\B\C\D\E' ),
(4,4,'U' ),
(5,4,'U\V\W' ),
(6,4,'U\V\W\X\Y' )) tc (DirID, BaseDirID, DisplayPath) ),
folders_list
AS (SELECT ItemNumber,
item fol,
BaseDirID
FROM (SELECT row_number()over(partition by BaseDirID order by Len(DisplayPath) DESC)rn,*
FROM existing_hierachies) a
CROSS apply dbo.[Delimitedsplit8k](DisplayPath, '\')
Where Rn = 1),
rec_cte
AS (SELECT *,
Cast(fol AS VARCHAR(4000))AS hierar
FROM folders_list
WHERE ItemNumber = 1
UNION ALL
SELECT d.*,
Cast(rc.hierar + '\' + d.fol AS VARCHAR(4000))
FROM rec_cte rc
JOIN folders_list d
ON rc.BaseDirID = d.BaseDirID
AND d.ItemNumber = rc.ItemNumber + 1)
SELECT rc.BaseDirID,
rc.hierar AS Missing_Hierarchies
FROM rec_cte rc
WHERE NOT EXISTS (SELECT 1
FROM existing_hierachies eh
WHERE eh.BaseDirID = rc.BaseDirID
AND eh.DisplayPath = rc.hierar)
Order by rc.BaseDirID
结果:
+-----------+---------------------+
| BaseDirID | Missing_Hierarchies |
+-----------+---------------------+
| 1 | A\B |
| 1 | A\B\C\D |
| 4 | U\V |
| 4 | U\V\W\X |
+-----------+---------------------+
拆分字符串函数代码
CREATE FUNCTION [dbo].[DelimitedSplit8K]
(@pString VARCHAR(8000), @pDelimiter CHAR(1))
RETURNS TABLE WITH SCHEMABINDING AS
RETURN
--===== "Inline" CTE Driven "Tally Table" produces values from 0 up to 10,000...
-- enough to cover NVARCHAR(4000)
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
引用自http://www.sqlservercentral.com/articles/Tally+Table/72993/
我有一个 table,其中包含文件夹路径。 我需要找到层次结构中这些文件夹之间的所有 "gaps"。 我的意思是,如果 table 包含这 3 个文件夹:
'A'
'A\B\C'
'A\B\C\D\E\F\G'
我需要在层次结构中找到以下丢失的文件夹:
'A\B'
'A\B\C\D'
'A\B\C\D\E'
'A\B\C\D\E\F'
此 table 包含超过 250,000 条记录 的文件夹,因此我们寻求最高效 的方法,否则脚本会卡很久,我们没有时间
评论:我没有所有文件夹的列表。我有 "root" 文件夹和 "leafs" 文件夹,我需要在层次结构中找到它们之间的 "gaps"。
第二条评论:table可以包含[=36=]多个层级,我们需要在所有层级中找到"gaps"层次结构。 就此而言,还有 2 个其他 int 列:"DirID" 和 "BaseDirID"。 "DirID" 列是我们 table 中的 id 列。 "BaseDirID" 包含层次结构中第一个文件夹的 ID。因此,同一层次结构中的所有文件夹(路径)在此列中共享相同的值。样本数据例如:
DirID BaseDirID DisplayPath
1 1 'A'
2 1 'A\B\C'
3 1 'A\B\C\D\E'
4 4 'U'
5 4 'U\V\W'
6 4 'U\V\W\X\Y'
所以我们需要找到以下数据:
BaseDirID DisplayPath
1 'A\B'
1 'A\B\C\D'
4 'U\V'
4 'U\V\W\X'
提前致谢。
这是一种使用 Recursive CTE
和拆分字符串函数
;WITH existing_hierachies
AS (SELECT DirID,
BaseDirID,
DisplayPath
FROM (VALUES (1,1,'A' ),
(2,1,'A\B\C' ),
(3,1,'A\B\C\D\E' ),
(4,4,'U' ),
(5,4,'U\V\W' ),
(6,4,'U\V\W\X\Y' )) tc (DirID, BaseDirID, DisplayPath) ),
folders_list
AS (SELECT ItemNumber,
item fol,
BaseDirID
FROM (SELECT row_number()over(partition by BaseDirID order by Len(DisplayPath) DESC)rn,*
FROM existing_hierachies) a
CROSS apply dbo.[Delimitedsplit8k](DisplayPath, '\')
Where Rn = 1),
rec_cte
AS (SELECT *,
Cast(fol AS VARCHAR(4000))AS hierar
FROM folders_list
WHERE ItemNumber = 1
UNION ALL
SELECT d.*,
Cast(rc.hierar + '\' + d.fol AS VARCHAR(4000))
FROM rec_cte rc
JOIN folders_list d
ON rc.BaseDirID = d.BaseDirID
AND d.ItemNumber = rc.ItemNumber + 1)
SELECT rc.BaseDirID,
rc.hierar AS Missing_Hierarchies
FROM rec_cte rc
WHERE NOT EXISTS (SELECT 1
FROM existing_hierachies eh
WHERE eh.BaseDirID = rc.BaseDirID
AND eh.DisplayPath = rc.hierar)
Order by rc.BaseDirID
结果:
+-----------+---------------------+
| BaseDirID | Missing_Hierarchies |
+-----------+---------------------+
| 1 | A\B |
| 1 | A\B\C\D |
| 4 | U\V |
| 4 | U\V\W\X |
+-----------+---------------------+
拆分字符串函数代码
CREATE FUNCTION [dbo].[DelimitedSplit8K]
(@pString VARCHAR(8000), @pDelimiter CHAR(1))
RETURNS TABLE WITH SCHEMABINDING AS
RETURN
--===== "Inline" CTE Driven "Tally Table" produces values from 0 up to 10,000...
-- enough to cover NVARCHAR(4000)
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
引用自http://www.sqlservercentral.com/articles/Tally+Table/72993/