課題に少し遅れて、SQLFiddle が ATM を停止しているように見えるので、データ構造を推測する必要があります。それにもかかわらず、それは楽しい挑戦のように思えました (そしてそれは = でした)。
設定：
IF OBJECT_ID('t_link') IS NOT NULL DROP TABLE t_link
IF OBJECT_ID('t_company') IS NOT NULL DROP TABLE t_company
IF OBJECT_ID('t_publisher') IS NOT NULL DROP TABLE t_publisher
IF OBJECT_ID('tempdb..#link_A') IS NOT NULL DROP TABLE #link_A
IF OBJECT_ID('tempdb..#link_B') IS NOT NULL DROP TABLE #link_B
GO
CREATE TABLE t_company ( company_id int IDENTITY(1, 1) NOT NULL PRIMARY KEY,
company_name varchar(100) NOT NULL)
GO
CREATE TABLE t_publisher (publisher_id int IDENTITY(1, 1) NOT NULL PRIMARY KEY,
publisher_name varchar(100) NOT NULL)
CREATE TABLE t_link (company_id int NOT NULL FOREIGN KEY (company_id) REFERENCES t_company (company_id),
publisher_id int NOT NULL FOREIGN KEY (publisher_id) REFERENCES t_publisher (publisher_id),
PRIMARY KEY (company_id, publisher_id),
group_id int NULL
)
GO
-- example content
-- ROW GROUPID Company Publisher
--1 1 A Y
--2 1 A X
--3 1 B Y
--4 1 B Z
--5 2 C W
--6 2 C P
--7 2 D W
INSERT t_company (company_name) VALUES ('A'), ('B'), ('C'), ('D')
INSERT t_publisher (publisher_name) VALUES ('X'), ('Y'), ('Z'), ('W'), ('P')
INSERT t_link (company_id, publisher_id)
SELECT company_id, publisher_id
FROM t_company, t_publisher
WHERE (company_name = 'A' AND publisher_name = 'Y')
OR (company_name = 'A' AND publisher_name = 'X')
OR (company_name = 'B' AND publisher_name = 'Y')
OR (company_name = 'B' AND publisher_name = 'Z')
OR (company_name = 'C' AND publisher_name = 'W')
OR (company_name = 'C' AND publisher_name = 'P')
OR (company_name = 'D' AND publisher_name = 'W')
GO
/*
-- volume testing
TRUNCATE TABLE t_link
DELETE t_company
DELETE t_publisher
DECLARE @company_count int = 1000,
@publisher_count int = 450,
@links_count int = 800
INSERT t_company (company_name)
SELECT company_name = Convert(varchar(100), NewID())
FROM master.dbo.fn_int_list(1, @company_count)
UPDATE STATISTICS t_company
INSERT t_publisher (publisher_name)
SELECT publisher_name = Convert(varchar(100), NewID())
FROM master.dbo.fn_int_list(1, @publisher_count)
UPDATE STATISTICS t_publisher
-- Random links between the companies & publishers
DECLARE @count int
SELECT @count = 0
WHILE @count < @links_count
BEGIN
SELECT TOP 30 PERCENT row_id = IDENTITY(int, 1, 1), company_id = company_id + 0
INTO #link_A
FROM t_company
ORDER BY NewID()
SELECT TOP 30 PERCENT row_id = IDENTITY(int, 1, 1), publisher_id = publisher_id + 0
INTO #link_B
FROM t_publisher
ORDER BY NewID()
INSERT TOP (@links_count - @count) t_link (company_id, publisher_id)
SELECT A.company_id,
B.publisher_id
FROM #link_A A
JOIN #link_B B
ON A.row_id = B.row_id
WHERE NOT EXISTS ( SELECT *
FROM t_link old
WHERE old.company_id = A.company_id
AND old.publisher_id = B.publisher_id)
SELECT @count = @count + @@ROWCOUNT
DROP TABLE #link_A
DROP TABLE #link_B
END
*/
実際のグループ化:
IF OBJECT_ID('tempdb..#links') IS NOT NULL DROP TABLE #links
GO
-- apply grouping
-- init
SELECT row_id = IDENTITY(int, 1, 1),
company_id,
publisher_id,
group_id = 0
INTO #links
FROM t_link
-- don't see an index that would be actually helpful here right-away, using row_id to avoid HEAP
CREATE CLUSTERED INDEX idx0 ON #links (row_id)
--CREATE INDEX idx1 ON #links (company_id)
--CREATE INDEX idx2 ON #links (publisher_id)
UPDATE #links
SET group_id = row_id
-- start grouping
WHILE @@ROWCOUNT > 0
BEGIN
UPDATE #links
SET group_id = new_group_id
FROM #links upd
CROSS APPLY (SELECT new_group_id = Min(group_id)
FROM #links new
WHERE new.company_id = upd.company_id
OR new.publisher_id = upd.publisher_id
) x
WHERE upd.group_id > new_group_id
-- select * from #links
END
-- remove 'holes'
UPDATE #links
SET group_id = (SELECT COUNT(DISTINCT o.group_id)
FROM #links o
WHERE o.group_id <= upd.group_id)
FROM #links upd
GO
UPDATE t_link
SET group_id = new.group_id
FROM t_link upd
LEFT OUTER JOIN #links new
ON new.company_id = upd.company_id
AND new.publisher_id = upd.publisher_id
GO
SELECT row = ROW_NUMBER() OVER (ORDER BY group_id, company_name, publisher_name),
l.group_id,
c.company_name, -- c.company_id,
p.publisher_name -- , p.publisher_id
from t_link l
JOIN t_company c
ON l.company_id = c.company_id
JOIN t_publisher p
ON p.publisher_id = l.publisher_id
ORDER BY 1
一見したところ、このアプローチはまだ誰も試していません。これがさまざまな方法でどのように行われるかを見るのは興味深いです... (パズルを台無しにするので、事前にそれらを読まないことをお勧めします =)
結果は期待どおりに見え (要件と例を理解している限り)、パフォーマンスもそれほど悪くはありませんが、これが機能するレコードの量についての実際の指標はありません。どのようにスケーリングするかはわかりませんが、あまりにも多くの問題を期待しないでください...