Следующий код демонстрирует один из способов разделения строки на отдельные строки и повторной сборки строк, содержащих двоеточие. Он поддерживает порядок строк ввода и не требует каких-либо недавних функций, например String_Split
.
-- Sample data.
declare @Newline as VarChar(2) = Char(10) + Char(13);
declare @Sample as VarChar(1024) =
'Key:Value' + @Newline +
'Key2:Value2' + @Newline +
'Key3:Value3' + @Newline +
@Newline +
'i have' + @Newline +
'a very ' + @Newline +
'long ' + @Newline +
'uncommom' + @Newline +
'text which i need to drop' + @Newline +
@Newline +
'Key4:Valu4';
-- Display the sample data.
select @Sample as Sample, Replace( @Sample, @Newline, '¶' ) as VisibleSample;
-- Test the splitter.
select ItemNumber, Item, Replace( Item, @Newline, '¶' ) as VisibleItem
from dbo.DelimitedSplit8K( @Sample, @Newline )
where Item like '%:%';
-- Reassemble the items that include a colon.
declare @Result as NVarChar(1024) = Stuff(
( select @Newline + Item
from dbo.DelimitedSplit8K( @Sample, @Newline )
where Item like '%:%'
order by ItemNumber for XML path(''), type).value('.[1]', 'VarChar(max)' ),
1, Len( @NewLine ), '' );
select @Result as Result, Replace( @Result, @Newline, '¶' ) as VisibleResult;
. Сплиттер является модифицированной версией кода Джеффа Модена, который обрабатывает переменнуюограничитель длины:
CREATE FUNCTION [dbo].[DelimitedSplit8K]
--===== Define I/O parameters
(@pString VARCHAR(8000), @pDelimiter VARCHAR(16))
--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+ Len( @pDelimiter ) FROM cteTally t WHERE SUBSTRING(@pString,t.N, Len( @pDelimiter ) ) = @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
;