将字符串的所有实例提取到串联结果中
Extract All Instances of String into Concatenated Result
使用 SQL Server 2014，我想在一个字段内搜索 return 找到的字符串的所有实例，加上以下单词。例如，列中的文本可能是：
"exec sproc1 and then some more text here and then maybe execute sproc2 exec storedproc3 and maybe exec sproc1"
我想优雅地 return "sproc1, sproc2, storedproc3, sproc1"，因为每个都是 exec 或 execute 之后的词（由空格分隔）。正如您在示例中看到的，前导词可能会有所不同，存储过程名称的长度也可能会有所不同。我已经能够 return 第一次使用 exec/execute；我的问题是有时会有多个（见下文）。
REPLACE(REPLACE(CASE
WHEN [sJSTP].[subsystem]='TSQL' AND CHARINDEX('EXECUTE',[sJSTP].[command],1)>0
THEN SUBSTRING([sJSTP].[command],CHARINDEX('EXECUTE',[sJSTP].[command],1)+8,
IIF(
CHARINDEX(' ',[sJSTP].[command],CHARINDEX('EXECUTE',[sJSTP].[command],1)+8)>0,
CHARINDEX(' ',[sJSTP].[command],CHARINDEX('EXECUTE',[sJSTP].[command],1)+8)-CHARINDEX('EXECUTE',[sJSTP].[command],1)-8,
LEN([sJSTP].[command])))
WHEN [sJSTP].[subsystem]='TSQL' AND CHARINDEX('EXEC',[sJSTP].[command],1)>0 AND CHARINDEX('DCEXEC',[sJSTP].[command],1)<=0
THEN SUBSTRING([sJSTP].[command],CHARINDEX('EXEC',[sJSTP].[command],1)+5,
IIF(
CHARINDEX(' ',[sJSTP].[command],CHARINDEX('EXEC',[sJSTP].[command],1)+5)>0,
CHARINDEX(' ',[sJSTP].[command],CHARINDEX('EXEC',[sJSTP].[command],1)+5)-CHARINDEX('EXEC',[sJSTP].[command],1)-5,
LEN([sJSTP].[command])))
END,'[',''),']','') AS sprocname
它的最终用途是解析来自 msdb..sysjobsteps table 的作业命令，以查看正在使用的存储过程。
编辑： 添加示例数据
示例 1：
执行 quarterly_run 1，'BW'
执行 quarterly_run_2 1, 'QR '
执行 quarterly_run 2，'VAS'
执行 quarterly_run 1，'WR'
执行 quarterly_run 3，'RW'
执行 quarterly_run_2 1, 'ASF'
执行 quarterly_run_3 1, 'ALL'
示例 2：
声明@rundate 日期时间、@rptqtr 日期时间、@qtr int
设置@rundate = getdate()
设置@rptqtr = '06/30/2016'
set @qtr = (select datediff(quarter,@rptqtr,@rundate))
exec quarterly_extract @qtr
示例 3：
执行 Daily_Sync_Process
执行 Daily_Process
因此，如果您想获得紧跟在 exec 之后的内容，那么我会在 space 上拆分，然后使用自连接。这是使用下面函数的代码，它是 Jeff Moden's splitter.
with cte as(
select
job_id
,step_name
,step_id
,s.ItemNumber
,s.Item
from msdb..sysjobsteps
--split on the space
cross apply dbo.DelimitedSplit8K(command,' ') s)
select
c.job_id
,c.step_id
,c.step_name
,c.Item
,c2.Item
from cte c
--self join to get exec myproc in the same row
full join
cte c2 on
c2.ItemNumber = c.ItemNumber + 1
and c.job_id = c2.job_id
and c.step_id = c2.step_id
--we only care where the base table has exec or execute (not executed, etc)
where c.Item = 'exec' or c.Item = 'execute'
order by
c.job_id, c.step_id, c.ItemNumber
重要的是要意识到这会失败，例如，命令是 exec someproc，它有两个 space。您可以使用 replace() 来解决这个问题，但是您必须多次嵌套此替换以考虑尽可能多的 space。您将在拆分器函数
的 command 列中处理它
--here we replace two spaces with 1 for the entire command
cross apply dbo.DelimitedSplit8K(replace(command,' ',' '),' ') s)
分割函数
SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO
CREATE FUNCTION [dbo].[DelimitedSplit8K] (@pString VARCHAR(8000), @pDelimiter CHAR(1))
--WARNING!!! DO NOT USE MAX DATA-TYPES HERE! IT WILL KILL PERFORMANCE!
RETURNS TABLE WITH SCHEMABINDING AS
RETURN
/* "Inline" CTE Driven "Tally Table" produces values from 1 up to 10,000... enough to cover VARCHAR(8000)*/
WITH E1(N) AS (
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1
), --10E+1 or 10 rows
E2(N) AS (SELECT 1 FROM E1 a, E1 b), --10E+2 or 100 rows
E4(N) AS (SELECT 1 FROM E2 a, E2 b), --10E+4 or 10,000 rows max
cteTally(N) AS (--==== This provides the "base" CTE and limits the number of rows right up front
-- for both a performance gain and prevention of accidental "overruns"
SELECT TOP (ISNULL(DATALENGTH(@pString),0)) ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) FROM E4
),
cteStart(N1) AS (--==== This returns N+1 (starting position of each "element" just once for each delimiter)
SELECT 1 UNION ALL
SELECT t.N+1 FROM cteTally t WHERE SUBSTRING(@pString,t.N,1) = @pDelimiter
),
cteLen(N1,L1) AS(--==== Return start and length (for use in substring)
SELECT s.N1,
ISNULL(NULLIF(CHARINDEX(@pDelimiter,@pString,s.N1),0)-s.N1,8000)
FROM cteStart s
)
--===== Do the actual split. The ISNULL/NULLIF combo handles the length for the final element when no delimiter is found.
SELECT ItemNumber = ROW_NUMBER() OVER(ORDER BY l.N1),
Item = SUBSTRING(@pString, l.N1, l.L1)
FROM cteLen l
GO
只是另一个内联选项，不限于 8K
例子
Declare @YourTable table (ID int,SomeCol varchar(max))
Insert into @YourTable values
(1,'exec quarterly_run 1, ''BW'' exec quarterly_run_2 1, ''QR '' exec quarterly_run 2, ''VAS'' exec quarterly_run 1, ''WR'' exec quarterly_run 3, ''RW'' exec quarterly_run_2 1, ''ASF'' exec quarterly_run_3 1, ''ALL''')
,(2,'declare @rundate datetime, @rptqtr datetime, @qtr int
set @rundate = getdate() set @rptqtr = ''06/30/2016''
set @qtr = (select datediff(quarter,@rptqtr,@rundate))
exec quarterly_extract @qtr
')
,(3,'exec Daily_Sync_Process exec Daily_Process')
;with cte as (
Select A.ID
,C.*
From @YourTable A
Cross Apply (values (replace(replace(SomeCol,char(13),' '),char(10),' '))) B(CleanString)
Cross Apply (
Select RetSeq,RetVal = case when Lag(RetVal,1) over (Order by RetSeq) in ('Exec','Execute') then RetVal else null end
From (
Select RetSeq = Row_Number() over (Order By (Select null))
,RetVal = LTrim(RTrim(B.i.value('(./text())[1]', 'varchar(max)')))
From (Select x = Cast('<x>' + replace((Select replace(CleanString,' ','§§Split§§') as [*] For XML Path('')),'§§Split§§','</x><x>')+'</x>' as xml).query('.')) as A
Cross Apply x.nodes('x') AS B(i)
) C1
) C
)
Select A.ID
,NewString = Stuff((Select ', ' +RetVal From cte Where ID=A.ID Order By RetSeq For XML Path ('')),1,2,'')
From cte A
Group By A.ID
Returns
ID NewString
1 quarterly_run, quarterly_run_2, quarterly_run, quarterly_run, quarterly_run, quarterly_run_2, quarterly_run_3
2 quarterly_extract
3 Daily_Sync_Process, Daily_Process
使用 SQL Server 2014，我想在一个字段内搜索 return 找到的字符串的所有实例，加上以下单词。例如，列中的文本可能是：
"exec sproc1 and then some more text here and then maybe execute sproc2 exec storedproc3 and maybe exec sproc1"
我想优雅地 return "sproc1, sproc2, storedproc3, sproc1"，因为每个都是 exec 或 execute 之后的词（由空格分隔）。正如您在示例中看到的，前导词可能会有所不同，存储过程名称的长度也可能会有所不同。我已经能够 return 第一次使用 exec/execute；我的问题是有时会有多个（见下文）。
REPLACE(REPLACE(CASE
WHEN [sJSTP].[subsystem]='TSQL' AND CHARINDEX('EXECUTE',[sJSTP].[command],1)>0
THEN SUBSTRING([sJSTP].[command],CHARINDEX('EXECUTE',[sJSTP].[command],1)+8,
IIF(
CHARINDEX(' ',[sJSTP].[command],CHARINDEX('EXECUTE',[sJSTP].[command],1)+8)>0,
CHARINDEX(' ',[sJSTP].[command],CHARINDEX('EXECUTE',[sJSTP].[command],1)+8)-CHARINDEX('EXECUTE',[sJSTP].[command],1)-8,
LEN([sJSTP].[command])))
WHEN [sJSTP].[subsystem]='TSQL' AND CHARINDEX('EXEC',[sJSTP].[command],1)>0 AND CHARINDEX('DCEXEC',[sJSTP].[command],1)<=0
THEN SUBSTRING([sJSTP].[command],CHARINDEX('EXEC',[sJSTP].[command],1)+5,
IIF(
CHARINDEX(' ',[sJSTP].[command],CHARINDEX('EXEC',[sJSTP].[command],1)+5)>0,
CHARINDEX(' ',[sJSTP].[command],CHARINDEX('EXEC',[sJSTP].[command],1)+5)-CHARINDEX('EXEC',[sJSTP].[command],1)-5,
LEN([sJSTP].[command])))
END,'[',''),']','') AS sprocname
它的最终用途是解析来自 msdb..sysjobsteps table 的作业命令，以查看正在使用的存储过程。
编辑： 添加示例数据
示例 1： 执行 quarterly_run 1，'BW' 执行 quarterly_run_2 1, 'QR ' 执行 quarterly_run 2，'VAS' 执行 quarterly_run 1，'WR' 执行 quarterly_run 3，'RW' 执行 quarterly_run_2 1, 'ASF' 执行 quarterly_run_3 1, 'ALL'
示例 2： 声明@rundate 日期时间、@rptqtr 日期时间、@qtr int
设置@rundate = getdate() 设置@rptqtr = '06/30/2016'
set @qtr = (select datediff(quarter,@rptqtr,@rundate))
exec quarterly_extract @qtr
示例 3： 执行 Daily_Sync_Process 执行 Daily_Process
因此，如果您想获得紧跟在 exec 之后的内容，那么我会在 space 上拆分，然后使用自连接。这是使用下面函数的代码，它是 Jeff Moden's splitter.
with cte as(
select
job_id
,step_name
,step_id
,s.ItemNumber
,s.Item
from msdb..sysjobsteps
--split on the space
cross apply dbo.DelimitedSplit8K(command,' ') s)
select
c.job_id
,c.step_id
,c.step_name
,c.Item
,c2.Item
from cte c
--self join to get exec myproc in the same row
full join
cte c2 on
c2.ItemNumber = c.ItemNumber + 1
and c.job_id = c2.job_id
and c.step_id = c2.step_id
--we only care where the base table has exec or execute (not executed, etc)
where c.Item = 'exec' or c.Item = 'execute'
order by
c.job_id, c.step_id, c.ItemNumber
重要的是要意识到这会失败，例如，命令是 exec someproc，它有两个 space。您可以使用 replace() 来解决这个问题，但是您必须多次嵌套此替换以考虑尽可能多的 space。您将在拆分器函数
command 列中处理它
--here we replace two spaces with 1 for the entire command
cross apply dbo.DelimitedSplit8K(replace(command,' ',' '),' ') s)
分割函数
SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO
CREATE FUNCTION [dbo].[DelimitedSplit8K] (@pString VARCHAR(8000), @pDelimiter CHAR(1))
--WARNING!!! DO NOT USE MAX DATA-TYPES HERE! IT WILL KILL PERFORMANCE!
RETURNS TABLE WITH SCHEMABINDING AS
RETURN
/* "Inline" CTE Driven "Tally Table" produces values from 1 up to 10,000... enough to cover VARCHAR(8000)*/
WITH E1(N) AS (
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1
), --10E+1 or 10 rows
E2(N) AS (SELECT 1 FROM E1 a, E1 b), --10E+2 or 100 rows
E4(N) AS (SELECT 1 FROM E2 a, E2 b), --10E+4 or 10,000 rows max
cteTally(N) AS (--==== This provides the "base" CTE and limits the number of rows right up front
-- for both a performance gain and prevention of accidental "overruns"
SELECT TOP (ISNULL(DATALENGTH(@pString),0)) ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) FROM E4
),
cteStart(N1) AS (--==== This returns N+1 (starting position of each "element" just once for each delimiter)
SELECT 1 UNION ALL
SELECT t.N+1 FROM cteTally t WHERE SUBSTRING(@pString,t.N,1) = @pDelimiter
),
cteLen(N1,L1) AS(--==== Return start and length (for use in substring)
SELECT s.N1,
ISNULL(NULLIF(CHARINDEX(@pDelimiter,@pString,s.N1),0)-s.N1,8000)
FROM cteStart s
)
--===== Do the actual split. The ISNULL/NULLIF combo handles the length for the final element when no delimiter is found.
SELECT ItemNumber = ROW_NUMBER() OVER(ORDER BY l.N1),
Item = SUBSTRING(@pString, l.N1, l.L1)
FROM cteLen l
GO
只是另一个内联选项，不限于 8K
例子
Declare @YourTable table (ID int,SomeCol varchar(max))
Insert into @YourTable values
(1,'exec quarterly_run 1, ''BW'' exec quarterly_run_2 1, ''QR '' exec quarterly_run 2, ''VAS'' exec quarterly_run 1, ''WR'' exec quarterly_run 3, ''RW'' exec quarterly_run_2 1, ''ASF'' exec quarterly_run_3 1, ''ALL''')
,(2,'declare @rundate datetime, @rptqtr datetime, @qtr int
set @rundate = getdate() set @rptqtr = ''06/30/2016''
set @qtr = (select datediff(quarter,@rptqtr,@rundate))
exec quarterly_extract @qtr
')
,(3,'exec Daily_Sync_Process exec Daily_Process')
;with cte as (
Select A.ID
,C.*
From @YourTable A
Cross Apply (values (replace(replace(SomeCol,char(13),' '),char(10),' '))) B(CleanString)
Cross Apply (
Select RetSeq,RetVal = case when Lag(RetVal,1) over (Order by RetSeq) in ('Exec','Execute') then RetVal else null end
From (
Select RetSeq = Row_Number() over (Order By (Select null))
,RetVal = LTrim(RTrim(B.i.value('(./text())[1]', 'varchar(max)')))
From (Select x = Cast('<x>' + replace((Select replace(CleanString,' ','§§Split§§') as [*] For XML Path('')),'§§Split§§','</x><x>')+'</x>' as xml).query('.')) as A
Cross Apply x.nodes('x') AS B(i)
) C1
) C
)
Select A.ID
,NewString = Stuff((Select ', ' +RetVal From cte Where ID=A.ID Order By RetSeq For XML Path ('')),1,2,'')
From cte A
Group By A.ID
Returns
ID NewString
1 quarterly_run, quarterly_run_2, quarterly_run, quarterly_run, quarterly_run, quarterly_run_2, quarterly_run_3
2 quarterly_extract
3 Daily_Sync_Process, Daily_Process