递归 SQL 查询以查找所有匹配的标识符
Recursive SQL query to find all matching identifiers
我有一个 table 具有以下结构
CREATE TABLE Source
(
[ID1] INT,
[ID2] INT
);
INSERT INTO Source ([ID1], [ID2])
VALUES (1, 2), (2, 3), (4, 5),
(2, 5), (6, 7)
源和结果示例 tables:
Source table 基本上存储哪个 ID 与另一个 ID 匹配。从图中可以看出,1、2、3、4、5 是相同的。而6、7是相同的。我需要一个 SQL 查询来获得一个结果 table,其中包含 ID 之间的所有匹配项。
我在网站上找到了这个项目 - Recursive query in SQL Server
与我的任务类似,但结果不同。
我试图为我的任务编辑代码,但它不起作用。 "The statement terminated. The maximum recursion 100 has been exhausted before statement completion."
;WITH CTE
AS
(
SELECT DISTINCT
M1.ID1,
M1.ID1 as ID2
FROM Source M1
LEFT JOIN Source M2
ON M1.ID1 = M2.ID2
WHERE M2.ID2 IS NULL
UNION ALL
SELECT
C.ID2,
M.ID1
FROM CTE C
JOIN Source M
ON C.ID1 = M.ID1
)
SELECT * FROM CTE ORDER BY ID1
非常感谢您的帮助!
这是一种通过暴力获取输出的方法,但可能不是 different/larger 数据集的最佳解决方案:
select sub1.rnk as ID1
,sub2.rnk as ID2
from
(
select a.*
,rank() over (partition by 1 order by id1, id2) as RNK
from source a
) sub1
cross join
(
select a.*
,rank() over (partition by 1 order by id1, id2) as RNK
from source a
) sub2
where sub1.rnk <> sub2.rnk
union all
select id1 as ID1
,id2 as ID2
from source
where id1 = 6
union all
select id2 as ID1
,id1 as ID2
from source
where id1 = 6;
这是一个具有挑战性的问题。您正在尝试从两个方向遍历图表。有两个关键思想:
- 添加 "reverse" 条边,因此图形的行为类似于有向图,但在两个方向上都有边。
- 保留已访问过的边的列表。在 SQL 服务器中,字符串是一种方法。
所以:
with s as (
select id1, id2 from source
union -- on purpose
select id2, id1 from source
),
cte as (
select s.id1, s.id2, ',' + cast(s.id1 as varchar(max)) + ',' + cast(s.id2 as varchar(max)) + ',' as ids
from s
union all
select cte.id1, s.id2, ids + cast(s.id2 as varchar(max)) + ','
from cte join
s
on cte.id2 = s.id1
where cte.ids not like '%,' + cast(s.id2 as varchar(max)) + ',%'
)
select *
from cte
order by 1, 2;
这里是db<>fiddle.
- 由于所有节点连接都是双向的 - 将反向关系添加到原始列表
- 从每个节点找到所有可能的路径;几乎是通常的递归,唯一的区别是 - 我们需要保留 root
id1
- 避免循环 - 我们需要注意这一点,因为我们没有方向
来源:
;with src as(
select id1, id2 from source
union
-- reversed connections
select id2, id1 from source
), rec as (
select id1, id2, CAST(CONCAT('/', src.id1, '/', src.id2, '/') as varchar(8000)) path
from src
union all
-- keep the root id1 from the start of each path
select rec.id1, src.id2, CAST(CONCAT(rec.path, src.id2, '/') as varchar(8000))
from rec
-- usual recursion
inner join src on src.id1 = rec.id2
-- avoid cycles
where rec.path not like CONCAT('%/', src.id2, '/%')
)
select id1, id2, path
from rec
order by 1, 2
产出
| id1 | id2 | path |
|-----|-----|-----------|
| 1 | 2 | /1/2/ |
| 1 | 3 | /1/2/3/ |
| 1 | 4 | /1/2/5/4/ |
| 1 | 5 | /1/2/5/ |
| 2 | 1 | /2/1/ |
| 2 | 3 | /2/3/ |
| 2 | 4 | /2/5/4/ |
| 2 | 5 | /2/5/ |
| 3 | 1 | /3/2/1/ |
| 3 | 2 | /3/2/ |
| 3 | 4 | /3/2/5/4/ |
| 3 | 5 | /3/2/5/ |
| 4 | 1 | /4/5/2/1/ |
| 4 | 2 | /4/5/2/ |
| 4 | 3 | /4/5/2/3/ |
| 4 | 5 | /4/5/ |
| 5 | 1 | /5/2/1/ |
| 5 | 2 | /5/2/ |
| 5 | 3 | /5/2/3/ |
| 5 | 4 | /5/4/ |
| 6 | 7 | /6/7/ |
| 7 | 6 | /7/6/ |
http://sqlfiddle.com/#!18/76114/13
source table will contain about 100,000 records
没有什么可以帮助您的。任务很不愉快——找到所有可能的联系。差不多CROSS JOIN
。最后连接更多。
看来我想出了与其他发帖人相似的答案。我的方法是插入现有的值对,然后插入每对的反向值。
展开值对列表后,您可以遍历 table 以找到所有对。
CREATE TABLE #Source
([ID1] int, [ID2] int);
INSERT INTO #Source
(
[ID1]
,[ID2]
)
VALUES
(1, 2)
,(2, 3)
,(4, 5)
,(2, 5)
,(6, 7)
INSERT INTO #Source
(
[ID1]
,[ID2]
)
SELECT
[ID2]
,[ID1]
FROM #Source
;WITH expanded AS
(
SELECT DISTINCT
ID1 = s1.ID1
,ID2 = s1.ID2
FROM #Source s1
LEFT JOIN #Source s2 ON s1.ID2 = s2.ID1
UNION
SELECT DISTINCT
ID1 = s1.ID1
,ID2 = s2.ID2
FROM #Source s1
LEFT JOIN #Source s2 ON s1.ID2 = s2.ID1
WHERE s1.ID1 <> s2.ID2
)
,recur AS
(
SELECT DISTINCT
e1.ID1
,e1.ID2
FROM expanded e1
LEFT JOIN expanded e2 ON e1.ID2 = e2.ID1
WHERE e1.ID1 <> e1.ID2
UNION ALL
SELECT DISTINCT
e1.ID1
,e2.ID2
FROM expanded e1
INNER JOIN expanded e2 ON e1.ID2 = e2.ID1
WHERE e1.ID1 <> e2.ID2
)
SELECT DISTINCT
ID1, ID2
FROM recur
ORDER BY ID1, ID2
DROP TABLE #Source
我有一个 table 具有以下结构
CREATE TABLE Source
(
[ID1] INT,
[ID2] INT
);
INSERT INTO Source ([ID1], [ID2])
VALUES (1, 2), (2, 3), (4, 5),
(2, 5), (6, 7)
源和结果示例 tables:
Source table 基本上存储哪个 ID 与另一个 ID 匹配。从图中可以看出,1、2、3、4、5 是相同的。而6、7是相同的。我需要一个 SQL 查询来获得一个结果 table,其中包含 ID 之间的所有匹配项。
我在网站上找到了这个项目 - Recursive query in SQL Server 与我的任务类似,但结果不同。
我试图为我的任务编辑代码,但它不起作用。 "The statement terminated. The maximum recursion 100 has been exhausted before statement completion."
;WITH CTE
AS
(
SELECT DISTINCT
M1.ID1,
M1.ID1 as ID2
FROM Source M1
LEFT JOIN Source M2
ON M1.ID1 = M2.ID2
WHERE M2.ID2 IS NULL
UNION ALL
SELECT
C.ID2,
M.ID1
FROM CTE C
JOIN Source M
ON C.ID1 = M.ID1
)
SELECT * FROM CTE ORDER BY ID1
非常感谢您的帮助!
这是一种通过暴力获取输出的方法,但可能不是 different/larger 数据集的最佳解决方案:
select sub1.rnk as ID1
,sub2.rnk as ID2
from
(
select a.*
,rank() over (partition by 1 order by id1, id2) as RNK
from source a
) sub1
cross join
(
select a.*
,rank() over (partition by 1 order by id1, id2) as RNK
from source a
) sub2
where sub1.rnk <> sub2.rnk
union all
select id1 as ID1
,id2 as ID2
from source
where id1 = 6
union all
select id2 as ID1
,id1 as ID2
from source
where id1 = 6;
这是一个具有挑战性的问题。您正在尝试从两个方向遍历图表。有两个关键思想:
- 添加 "reverse" 条边,因此图形的行为类似于有向图,但在两个方向上都有边。
- 保留已访问过的边的列表。在 SQL 服务器中,字符串是一种方法。
所以:
with s as (
select id1, id2 from source
union -- on purpose
select id2, id1 from source
),
cte as (
select s.id1, s.id2, ',' + cast(s.id1 as varchar(max)) + ',' + cast(s.id2 as varchar(max)) + ',' as ids
from s
union all
select cte.id1, s.id2, ids + cast(s.id2 as varchar(max)) + ','
from cte join
s
on cte.id2 = s.id1
where cte.ids not like '%,' + cast(s.id2 as varchar(max)) + ',%'
)
select *
from cte
order by 1, 2;
这里是db<>fiddle.
- 由于所有节点连接都是双向的 - 将反向关系添加到原始列表
- 从每个节点找到所有可能的路径;几乎是通常的递归,唯一的区别是 - 我们需要保留 root
id1
- 避免循环 - 我们需要注意这一点,因为我们没有方向
来源:
;with src as(
select id1, id2 from source
union
-- reversed connections
select id2, id1 from source
), rec as (
select id1, id2, CAST(CONCAT('/', src.id1, '/', src.id2, '/') as varchar(8000)) path
from src
union all
-- keep the root id1 from the start of each path
select rec.id1, src.id2, CAST(CONCAT(rec.path, src.id2, '/') as varchar(8000))
from rec
-- usual recursion
inner join src on src.id1 = rec.id2
-- avoid cycles
where rec.path not like CONCAT('%/', src.id2, '/%')
)
select id1, id2, path
from rec
order by 1, 2
产出
| id1 | id2 | path |
|-----|-----|-----------|
| 1 | 2 | /1/2/ |
| 1 | 3 | /1/2/3/ |
| 1 | 4 | /1/2/5/4/ |
| 1 | 5 | /1/2/5/ |
| 2 | 1 | /2/1/ |
| 2 | 3 | /2/3/ |
| 2 | 4 | /2/5/4/ |
| 2 | 5 | /2/5/ |
| 3 | 1 | /3/2/1/ |
| 3 | 2 | /3/2/ |
| 3 | 4 | /3/2/5/4/ |
| 3 | 5 | /3/2/5/ |
| 4 | 1 | /4/5/2/1/ |
| 4 | 2 | /4/5/2/ |
| 4 | 3 | /4/5/2/3/ |
| 4 | 5 | /4/5/ |
| 5 | 1 | /5/2/1/ |
| 5 | 2 | /5/2/ |
| 5 | 3 | /5/2/3/ |
| 5 | 4 | /5/4/ |
| 6 | 7 | /6/7/ |
| 7 | 6 | /7/6/ |
http://sqlfiddle.com/#!18/76114/13
source table will contain about 100,000 records
没有什么可以帮助您的。任务很不愉快——找到所有可能的联系。差不多CROSS JOIN
。最后连接更多。
看来我想出了与其他发帖人相似的答案。我的方法是插入现有的值对,然后插入每对的反向值。
展开值对列表后,您可以遍历 table 以找到所有对。
CREATE TABLE #Source
([ID1] int, [ID2] int);
INSERT INTO #Source
(
[ID1]
,[ID2]
)
VALUES
(1, 2)
,(2, 3)
,(4, 5)
,(2, 5)
,(6, 7)
INSERT INTO #Source
(
[ID1]
,[ID2]
)
SELECT
[ID2]
,[ID1]
FROM #Source
;WITH expanded AS
(
SELECT DISTINCT
ID1 = s1.ID1
,ID2 = s1.ID2
FROM #Source s1
LEFT JOIN #Source s2 ON s1.ID2 = s2.ID1
UNION
SELECT DISTINCT
ID1 = s1.ID1
,ID2 = s2.ID2
FROM #Source s1
LEFT JOIN #Source s2 ON s1.ID2 = s2.ID1
WHERE s1.ID1 <> s2.ID2
)
,recur AS
(
SELECT DISTINCT
e1.ID1
,e1.ID2
FROM expanded e1
LEFT JOIN expanded e2 ON e1.ID2 = e2.ID1
WHERE e1.ID1 <> e1.ID2
UNION ALL
SELECT DISTINCT
e1.ID1
,e2.ID2
FROM expanded e1
INNER JOIN expanded e2 ON e1.ID2 = e2.ID1
WHERE e1.ID1 <> e2.ID2
)
SELECT DISTINCT
ID1, ID2
FROM recur
ORDER BY ID1, ID2
DROP TABLE #Source