How to use Substring to pull multiple items from a field - sql-server

Question

First post - I am trying to pull ten different pieces of information from a single field. Let me start with this is not my table, just what I was given to work with. This is a varchar max field.
'3350|#|1234567|~|3351|#|8/1/2017|~|3352|#|Acme|~|3353|~|10000.00|~|3354|#||~|3355|#||~3356|#|Yes|~|3357|#|Doe,John|~|3358|#|CA|~|3359|#|5551212'
I know that the numbers that start with 33 are keys telling me what information is in that section. 3350 has the invoice #1234567. 3351 has the invoice date of 8/1/17. etc. 3354 and 3355 were left null. The keys are unchanging and will be the same for every record in the table.
I need to pull the data from between 3350|#| and |~|3351 to get my invoice# and between 3351|#| and |~|3352 to get my date, etc, but I am struggling with how to word this. Any help would be appreciated and any critiques on my first post will be taken constructively.

Answer 1

The #YourTable is just a table variable used for demonstration / illustration
For Rows - Example
Declare #YourTable table (ID int,SomeCol varchar(max))
Insert Into #YourTable values
(1,'3350|#|1234567|~|3351|#|8/1/2017|~|3352|#|Acme|~|3353|#|10000.00|~|3354|#||~|3355|#||~|3356|#|Yes|~|3357|#|Doe,John|~|3358|#|CA|~|3359|#|5551212')
Select A.ID
,Item = left(RetVal,charindex('|#|',RetVal+'|#|')-1)
,Value = right(RetVal,len(RetVal)-charindex('|#|',RetVal+'|#|')-2)
From #YourTable A
Cross Apply [dbo].[udf-Str-Parse](A.SomeCol,'|~|') B
Returns
For Columns - Example
Declare #YourTable table (ID int,SomeCol varchar(max))
Insert Into #YourTable values
(1,'3350|#|1234567|~|3351|#|8/1/2017|~|3352|#|Acme|~|3353|#|10000.00|~|3354|#||~|3355|#||~|3356|#|Yes|~|3357|#|Doe,John|~|3358|#|CA|~|3359|#|5551212')
Select *
From (
Select A.ID
,Item = left(RetVal,charindex('|#|',RetVal+'|#|')-1)
,Value = right(RetVal,len(RetVal)-charindex('|#|',RetVal+'|#|')-2)
From #YourTable A
Cross Apply [dbo].[udf-Str-Parse](A.SomeCol,'|~|') B
) A
Pivot (max([Value]) For [Item] in ([3350],[3351],[3352],[3353],[3354],[3355],[3356],[3357],[3358],[3359]) ) p
Returns
The UDF if Interested
CREATE FUNCTION [dbo].[udf-Str-Parse] (#String varchar(max),#Delimiter varchar(10))
Returns Table
As
Return (
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(#String,#Delimiter,'§§Split§§') as [*] For XML Path('')),'§§Split§§','</x><x>')+'</x>' as xml).query('.')) as A
Cross Apply x.nodes('x') AS B(i)
);
--Thanks Shnugo for making this XML safe
--Select * from [dbo].[udf-Str-Parse]('Dog,Cat,House,Car',',')
--Select * from [dbo].[udf-Str-Parse]('John Cappelletti was here',' ')

Answer 2

You can try a tally based splitter like below
declare #t table ( id int, col nvarchar(max));
insert into #t values
(1, '3350|#|1234567|~|3351|#|8/1/2017|~|3352|#|Acme|~|3353|~|10000.00|~|3354|#||~|3355|#||~3356|#|Yes|~|3357|#|Doe,John|~|3358|#|CA|~|3359|#|5551212')
,(2, '3350|#|123334567|~|3351|#|8/2/2017|~|3352|#|Acme|~|3353|~|10000.00|~|3354|#||~|3355|#||~3356|#|Yes|~|3357|#|Doe,John|~|3358|#|CA|~|3359|#|5551212');
select
id,
case
when split_values like '3350|#|%' then 'id'
when split_values like '3351|#|%' then 'date'
end as fieldname,
SUBSTRING(split_values,8,LEN(split_values)-7) as value
from
(
select
--t.col as col,
row_number() over (partition by t.col order by t1.N asc) as row_num,
t.id,
SUBSTRING( t.col, t1.N, ISNULL(NULLIF(CHARINDEX('|~|',t.col,t1.N),0)-t1.N,8000)) as split_values
from #t t
join
(
select
t.col,
1 as N
from #t t
UNION ALL
select
t.col,
t1.N + 3 as N
from #t t
join
(
select
top 8000
row_number() over(order by (select NULL)) as N
from
sys.objects s1
cross join
sys.objects s2
) t1
on SUBSTRING(t.col,t1.N,3) = '|~|'
) t1
on t1.col=t.col
)a
where
split_values like '3350|#|%' or
split_values like '3351|#|%'
Live demo