Kelompokkan Semua Catatan Terkait dalam Hubungan Banyak ke Banyak, komponen terhubung grafik SQL

Saya berpikir untuk menggunakan CTE rekursif , tetapi, sejauh yang saya tahu, di SQL Server tidak mungkin menggunakan UNION untuk menghubungkan anggota jangkar dan anggota rekursif dari CTE rekursif (saya pikir itu mungkin dilakukan di PostgreSQL), jadi tidak mungkin untuk menghilangkan duplikat.

declare @i int

with cte as (
     select
         GroupID,
         row_number() over(order by Company) as rn
     from Table1
)
update cte set GroupID = rn

select @i = @@rowcount

-- while some rows updated
while @i > 0
begin
    update T1 set
        GroupID = T2.GroupID
    from Table1 as T1
        inner join (
            select T2.Company, min(T2.GroupID) as GroupID
            from Table1 as T2
            group by T2.Company
        ) as T2 on T2.Company = T1.Company
    where T1.GroupID > T2.GroupID

    select @i = @@rowcount

    update T1 set
        GroupID = T2.GroupID
    from Table1 as T1
        inner join (
            select T2.Publisher, min(T2.GroupID) as GroupID
            from Table1 as T2
            group by T2.Publisher
        ) as T2 on T2.Publisher = T1.Publisher
    where T1.GroupID > T2.GroupID

    -- will be > 0 if any rows updated
    select @i = @i + @@rowcount
end

;with cte as (
     select
         GroupID,
         dense_rank() over(order by GroupID) as rn
     from Table1
)
update cte set GroupID = rn

demo biola sql

Saya juga sudah mencoba algoritma pencarian pertama yang luas. Saya pikir itu bisa lebih cepat (lebih baik dalam hal kompleksitas), jadi saya akan memberikan solusi di sini. Saya telah menemukan bahwa itu tidak lebih cepat dari pendekatan SQL, meskipun:

declare @Company nvarchar(2), @Publisher nvarchar(2), @GroupID int

declare @Queue table (
    Company nvarchar(2), Publisher nvarchar(2), ID int identity(1, 1),
    primary key(Company, Publisher)
)

select @GroupID = 0

while 1 = 1
begin
    select top 1 @Company = Company, @Publisher = Publisher
    from Table1
    where GroupID is null

    if @@rowcount = 0 break

    select @GroupID = @GroupID + 1

    insert into @Queue(Company, Publisher)
    select @Company, @Publisher

    while 1 = 1
    begin
        select top 1 @Company = Company, @Publisher = Publisher
        from @Queue
        order by ID asc

        if @@rowcount = 0 break

        update Table1 set
            GroupID = @GroupID
        where Company = @Company and Publisher = @Publisher

        delete from @Queue where Company = @Company and Publisher = @Publisher

        ;with cte as (
            select Company, Publisher from Table1 where Company = @Company and GroupID is null
            union all
            select Company, Publisher from Table1 where Publisher = @Publisher and GroupID is null
        )
        insert into @Queue(Company, Publisher)
        select distinct c.Company, c.Publisher
        from cte as c
        where not exists (select * from @Queue as q where q.Company = c.Company and q.Publisher = c.Publisher)
   end
end

demo biola sql

Saya telah menguji versi saya dan versi Gordon Linoff untuk memeriksa kinerjanya. Sepertinya CTE jauh lebih buruk, saya tidak sabar menunggu saat CTE selesai di lebih dari 1000 baris.

Berikut demo sql fiddle dengan data acak. Hasil saya adalah:
128 baris :
solusi RBAR saya:190 md
solusi SQL saya:27ms
Solusi Gordon Linoff:958ms
256 baris :
solusi RBAR saya:560 md
solusi SQL saya:1226ms
Solusi Gordon Linoff:45371 md

Ini data acak, jadi hasilnya mungkin tidak terlalu konsisten. Saya pikir waktu dapat diubah oleh indeks, tetapi saya tidak berpikir itu dapat mengubah keseluruhan gambar.

lama versi - menggunakan tabel sementara, hanya menghitung GroupID tanpa menyentuh tabel awal:

declare @i int

-- creating table to gather all possible GroupID for each row
create table #Temp
(
    Company varchar(1), Publisher varchar(1), GroupID varchar(1),
    primary key (Company, Publisher, GroupID)
)

-- initializing it with data
insert into #Temp (Company, Publisher, GroupID)
select Company, Publisher, Company
from Table1

select @i = @@rowcount

-- while some rows inserted into #Temp
while @i > 0
begin
    -- expand #Temp in both directions
    ;with cte as (
        select
            T2.Company, T1.Publisher,
            T1.GroupID as GroupID1, T2.GroupID as GroupID2
        from #Temp as T1
            inner join #Temp as T2 on T2.Company = T1.Company
        union
        select
            T1.Company, T2.Publisher,
            T1.GroupID as GroupID1, T2.GroupID as GroupID2
        from #Temp as T1
            inner join #Temp as T2 on T2.Publisher = T1.Publisher        
    ), cte2 as (
        select
            Company, Publisher,
            case when GroupID1 < GroupID2 then GroupID1 else GroupID2 end as GroupID
        from cte
    )
    insert into #Temp
    select Company, Publisher, GroupID
    from cte2
    -- don't insert duplicates
    except
    select Company, Publisher, GroupID
    from #Temp

    -- will be > 0 if any row inserted
    select @i = @@rowcount
end

select
    Company, Publisher,
    dense_rank() over(order by min(GroupID)) as GroupID
from #Temp
group by Company, Publisher

=> contoh sql fiddle