Sql server 使用联接查询查找重复记录的SQL Server查询

我使用的是SQL Server数据库，其中包含表x、y和映射表xy

表：x

表：XY

我有一个带有X_id、日期、文本的表X，还有一个带有X_id和y_id的映射表xy。 我需要一个查询来找到x的哪些记录是重复的。当x的记录满足以下所有条件时，可以将其视为重复记录

两者的文本相同 日期间隔应为5分钟。 在XY映射表中，两者应具有相同的y_id

---

我能够编写一个查询来满足前两个条件，尽管有重复的数据。但我无法编写满足第三个条件的查询，也无法在执行自联接时显示不同的数据。

我能想到的满足第三个条件的最简单方法是将y_ID聚合到一行进行比较

使用a可以让我更容易阅读，但也可以不用它来编写

测试设置：

查询：

;with cte as (
    select 
        x.*
      , y_ids = stuff((
          select ','+convert(varchar(10),xy.y_id)
          from xy
          where x.x_id = xy.x_id
          order by xy.y_id
          for xml path (''), type).value('.','varchar(max)')
        ,1,1,'')
    from x
)
select * 
from cte
where exists (
    select 1
    from cte as i
    where i.x_id <> cte.x_id
      and abs(datediff(minute,i.date,cte.date))<=5
      and i.text = cte.text
      and i.y_ids = cte.y_ids
)

不聚合y_ID的方法：

---

这是另一个示例，如果x在XY中没有关系数据，是否需要忽略条件3？ 此示例将忽略条件3

    DECLARE @x TABLE(x_id int,[date] datetime, text varchar(10))
    insert into @x values
     ( 1,'2017-02-22 20:40:30.617','txt1')
    ,( 2,'2017-02-22 20:40:06.103','txt1')
    ,( 3,'2017-02-22 20:28:21.393','txt2')
    ,( 4,'2017-02-22 20:28:21.393','txt3')
    ,( 5,'2017-02-22 20:28:21.394','txt3')
     DECLARE @xy TABLE(x_id int, y_id int)
     INSERT INTO @xy VALUES 
     ( 1,3 )
    ,( 1,10) 
    ,( 2,3 )
    ,( 2,10)
    ,( 3,5 );


    SELECT x.*,xy.* FROM @x AS x 
    INNER JOIN @x AS ox ON x.x_id!=ox.x_id AND x.text=ox.text AND ABS(DATEDIFF(MINUTE,x.date,ox.date))<=5
    OUTER APPLY(
       SELECT COUNT(0) AS totaly, SUM(CASE WHEN xy1.y_id+xy2.y_id IS NULL THEN 1 ELSE 0 END) AS NULLROW
       FROM  (SELECT y_id FROM @xy WHERE x_id=x.x_id) AS xy1 FULL JOIN (SELECT y_id FROM @xy WHERE x_id=ox.x_id) AS xy2 ON xy1.y_id=xy2.y_id
    ) AS xy
    WHERE (xy.totaly>0 and xy.NULLROW=0) OR (xy.totaly=0)

---

嘿@Sqlzim，我尝试过你的解决方案。它似乎在显示记录，即使y_id不同。@Raghavendra，那是因为我忘了将I.y_id=cte.y_id添加到where。现在修好了。@Raghavendra很乐意帮忙！

create table x(
    x_id int
  , [date] datetime
  , text varchar(32)
);
insert into x values
 ( 1,'2017-02-22 20:40:30.617','txt1')
,( 2,'2017-02-22 20:40:06.103','txt1')
,( 3,'2017-02-22 20:28:21.393','txt2');

create table xy (
    x_id int
  , y_id int
);
insert into xy values 
 ( 1,3 )
,( 1,10) 
,( 2,3 )
,( 2,10)
,( 3,5 );

;with cte as (
    select 
        x.*
      , y_ids = stuff((
          select ','+convert(varchar(10),xy.y_id)
          from xy
          where x.x_id = xy.x_id
          order by xy.y_id
          for xml path (''), type).value('.','varchar(max)')
        ,1,1,'')
    from x
)
select * 
from cte
where exists (
    select 1
    from cte as i
    where i.x_id <> cte.x_id
      and abs(datediff(minute,i.date,cte.date))<=5
      and i.text = cte.text
      and i.y_ids = cte.y_ids
)

+------+---------------------+------+-------+
| x_id |        date         | text | y_ids |
+------+---------------------+------+-------+
|    1 | 2017-02-22 20:40:30 | txt1 | 3,10  |
|    2 | 2017-02-22 20:40:06 | txt1 | 3,10  |
+------+---------------------+------+-------+

;with cte as (
  select x.*
      , xy.y_id
      , cnt = count(*) over (partition by x.x_id)
    from x inner join xy on x.x_id = xy.x_id
)

select x.x_id, x.date, x.text
from cte as x 
  inner join cte as x2
     on x.x_id <> x2.x_id 
    and x.y_id = x2.y_id
    and x.text = x2.text 
    and x.cnt  = x2.cnt 
    and abs(datediff(minute,x.date,x2.date))<=5
group by x.x_id, x.date, x.text, x.cnt
having count(*) = x.cnt

+------+---------------------+------+
| x_id |        date         | text |
+------+---------------------+------+
|    1 | 2017-02-22 20:40:30 | txt1 |
|    2 | 2017-02-22 20:40:06 | txt1 |
+------+---------------------+------+

    DECLARE @x TABLE(x_id int,[date] datetime, text varchar(10))
    insert into @x values
     ( 1,'2017-02-22 20:40:30.617','txt1')
    ,( 2,'2017-02-22 20:40:06.103','txt1')
    ,( 3,'2017-02-22 20:28:21.393','txt2')
    ,( 4,'2017-02-22 20:28:21.393','txt3')
    ,( 5,'2017-02-22 20:28:21.394','txt3')
     DECLARE @xy TABLE(x_id int, y_id int)
     INSERT INTO @xy VALUES 
     ( 1,3 )
    ,( 1,10) 
    ,( 2,3 )
    ,( 2,10)
    ,( 3,5 );


    SELECT x.*,xy.* FROM @x AS x 
    INNER JOIN @x AS ox ON x.x_id!=ox.x_id AND x.text=ox.text AND ABS(DATEDIFF(MINUTE,x.date,ox.date))<=5
    OUTER APPLY(
       SELECT COUNT(0) AS totaly, SUM(CASE WHEN xy1.y_id+xy2.y_id IS NULL THEN 1 ELSE 0 END) AS NULLROW
       FROM  (SELECT y_id FROM @xy WHERE x_id=x.x_id) AS xy1 FULL JOIN (SELECT y_id FROM @xy WHERE x_id=ox.x_id) AS xy2 ON xy1.y_id=xy2.y_id
    ) AS xy
    WHERE (xy.totaly>0 and xy.NULLROW=0) OR (xy.totaly=0)

x_id date text totaly NULLROW ----------- ----------------------- ---------- ----------- ----------- 1 2017-02-22 20:40:30.617 txt1 2 0 2 2017-02-22 20:40:06.103 txt1 2 0 4 2017-02-22 20:28:21.393 txt3 0 NULL 5 2017-02-22 20:28:21.393 txt3 0 NULL