当组在 MS SQL 服务器（连续）中重复时，按组删除除第一个和最后一个值以外的所有值

Question

我们有一个聊天系统，有时每秒为聊天期间的每个事件生成多个事件日志。问题是这些消耗了大量的数据存储（这在该平台上非常昂贵），我们希望简化我们实际存储的内容并删除真正不需要的东西。

为此，有一个事件类型表示聊天在队列中的位置。我们不关心每个位置，只要它们不干预该聊天的事件即可。因此，我们只想保留每个不同组中的第一个和最后一个，在该组中没有其他事件类型可以在那个时期获得 "total time in queue"。

更复杂的是，客户可以在按部门转移时进出队列，因此同一个聊天可以有多个队列位置记录块。我试过使用 FIRST_VALUE 和 LAST_VALUE 并且它让我大部分时间都在那里，但是当我们遇到这些事件的两个不同块的情况时失败了。

这是生成测试数据的脚本：

<!-- language: lang-sql -->
    CREATE TABLE #testdata (
    id varchar(18),
    name varchar(8),
    [type] varchar(20),
    livechattranscriptid varchar(18),
    groupid varchar(40)) 

INSERT INTO #testdata (id,name,[type],livechattranscriptid,groupid) VALUES 
('0DZ14000003I2pOGAS','34128314','ChatRequest','57014000000ltfIAAQ','57014000000ltfIAAQChatRequest'),
('0DZ14000003IGmQGAW','34181980','Enqueue','57014000000ltfIAAQ','57014000000ltfIAAQEnqueue'),
('0DZ14000003IHbqGAG','34185171','Enqueue','57014000000ltfIAAQ','57014000000ltfIAAQEnqueue'),
('0DZ14000003ILuHGAW','34201743','Enqueue','57014000000ltfIAAQ','57014000000ltfIAAQEnqueue'),
('0DZ14000003IQ6cGAG','34217778','Enqueue','57014000000ltfIAAQ','57014000000ltfIAAQEnqueue'),
('0DZ14000003IR7JGAW','34221794','PushAssignment','57014000000ltfIAAQ','57014000000ltfIAAQPushAssignment'),
('0DZ14000003IiDnGAK','34287448','Enqueue','57014000000ltfIAAQ','57014000000ltfIAAQEnqueue'),
('0DZ14000003IiDoGAK','34287545','PushAssignment','57014000000ltfIAAQ','57014000000ltfIAAQPushAssignment'),
('0DZ14000003Iut5GAC','34336044','Enqueue','57014000000ltfIAAQ','57014000000ltfIAAQEnqueue'),
('0DZ14000003Iv7HGAS','34336906','Accept','57014000000ltfIAAQ','57014000000ltfIAAQAccept')

这里尝试识别任何按名称字段排序并按转录 ID 分组的组的第一个和最后一个 ID：

select *,FIRST_VALUE(id) OVER(Partition BY groupid order by livechattranscriptid,name asc) as firstinstancegroup,
    LAST_VALUE(id) OVER(Partition BY groupid order by livechattranscriptid,name asc RANGE BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING) as lastinstancegroup from #testdata order by livechattranscriptid,name

问题是，它为整个组的所有记录提供了相同的第一个和最后一个 ID，而不是将每组 Enqueue 记录视为一个不同的组。我如何将 Enqueue 的每个不同的分组实例视为一个唯一的组？

Answer 1

这是一个类似的解决方案Grouping contiguous table data

不漂亮，但您会发现基于 OP 的逻辑。同一列上的连续数据

declare @mytable table (
    id varchar(18),
    name varchar(8),
    [type] varchar(20),
    livechattranscriptid varchar(18),
    groupid varchar(100)) 

INSERT INTO @mytable (id,name,[type],livechattranscriptid,groupid) VALUES 
('0DZ14000003I2pOGAS','34128314','ChatRequest','57014000000ltfIAAQ','57014000000ltfIAAQChatRequest'),
('0DZ14000003IGmQGAW','34181980','Enqueue','57014000000ltfIAAQ','57014000000ltfIAAQEnqueue'),
('0DZ14000003IHbqGAG','34185171','Enqueue','57014000000ltfIAAQ','57014000000ltfIAAQEnqueue'),
('0DZ14000003ILuHGAW','34201743','Enqueue','57014000000ltfIAAQ','57014000000ltfIAAQEnqueue'),
('0DZ14000003IQ6cGAG','34217778','Enqueue','57014000000ltfIAAQ','57014000000ltfIAAQEnqueue'),
('0DZ14000003IR7JGAW','34221794','PushAssignment','57014000000ltfIAAQ','57014000000ltfIAAQPushAssignment'),
('0DZ14000003IiDnGAK','34287448','Enqueue','57014000000ltfIAAQ','57014000000ltfIAAQEnqueue'),
('0DZ14000003IiDoGAK','34287545','PushAssignment','57014000000ltfIAAQ','57014000000ltfIAAQPushAssignment'),
('0DZ14000003Iut5GAC','34336044','Enqueue','57014000000ltfIAAQ','57014000000ltfIAAQEnqueue'),
('0DZ14000003Iv7HGAS','34336906','Accept','57014000000ltfIAAQ','57014000000ltfIAAQAccept')


;with myend as (   --- get all ends
 select 
 *
  from 
 (select 
   iif(groupid <> lead(groupid,1,groupid) over (order by name),
     id,
     'x') [newid],name
 from @mytable
 )x 
 where newid <> 'x'
 )
 , mystart as   -- get all starts
 (
 select 
  *
    from 
 (select 
   iif(groupid <> lag(groupid,1,groupid) over (order by name),
     id,
     'x') [newid], name,type,livechattranscriptid
 from @mytable
 )x 
 where newid <> 'x'
 )  ,
 finalstart as (   --- get all starts including the first row

  select id, 
    name,type,livechattranscriptid,
    row_number() over (order by name) rn
    from (
    select id,name,type,livechattranscriptid 
    from (
    select top 1 id, name,type,livechattranscriptid
    from @mytable
    order by name) x
    union all
    select newid,name,type,livechattranscriptid from mystart
    ) y

 ),
 finalend as   -- get all ends and add the last row
   (

  select id, 
    row_number() over (order by name) rn
    from (
    select id,name from (
    select top 1 id,name
    from @mytable
    order by name desc) x
    union all
    select newid,name from myend
    ) y
  )
select 
  s.id [startid]
  ,s.name
  ,s.type
  ,s.livechattranscriptid
  ,e.id [lastid]
   from    
  finalend e
  inner join finalstart s 
     on   e.rn = s.rn    --- bind the two results over the positions or row number

当组在 MS SQL 服务器（连续）中重复时，按组删除除第一个和最后一个值以外的所有值

Removing All but the first and last values by group when the group is repeated in MS SQL Server (contiguous)

sql

sql-server

contiguous