How to shred a XML being passed into a stored procedure? - sql-server

Question

I have an XML being passed into a stored procedure in the following format. I'm struggling with how to shred it in SQL Server 2017:
declare #xml xml = convert(xml, N'<SearchQuery>
<DealTypeDesc>Deal</DealTypeDesc>
<VendorNum>1</VendorNum>
<VendorName>Vendor1</VendorName>
<VendorNum>2</VendorNum>
<VendorName>Vendor2</VendorName>
<VendorNum>3</VendorNum>
<VendorName>Vendor3</VendorName>
<VendorNum>4</VendorNum>
<VendorName>Vendor4</VendorName>
<VendorNum>5</VendorNum>
<VendorName>Vendor5</VendorName>
</SearchQuery>')
-- this is how it is being consumed now. 1 element at a time
SELECT
t.c.value('text()[1]', 'NVARCHAR(MAX)') AS LookupValue
FROM
#xml.nodes('//SearchQuery/VendorNum') AS t(c)
-- I want the results to look like this where I can use the node name as a column and the value as a lookup.
-- I wanted to do this in one pass without having to union all and select from the XML variable every time.
-- I can't change the XML structure since it's coming from a third party, so that option is out.
SELECT
'VendorName' ColumnName,
t.c.value('text()[1]', 'NVARCHAR(MAX)') AS LookupValue
FROM
#xml.nodes('//SearchQuery/VendorName') AS t(c)
UNION ALL
SELECT
'VendorNum' ColumnName,
t.c.value('text()[1]', 'NVARCHAR(MAX)') AS LookupValue
FROM
#xml.nodes('//SearchQuery/VendorNum') AS t(c)

Answer 1

Two options here. The first is a simple query. The second is a helper function which will shred virtually any XML without having to know anything about it. I'll often use this during the Discovery Phase.
First Option
Select ColumnName = a.value('local-name(.)','varchar(100)')
,LookupValue = a.value('.','varchar(max)')
From #XML.nodes('SearchQuery') as C1(n)
Cross Apply C1.n.nodes('*') as C2(a)
Where a.value('local-name(.)','varchar(100)') like 'Vendor%'
Returns
ColumnName LookupValue
VendorNum 1
VendorName Vendor1
VendorNum 2
VendorName Vendor2
VendorNum 3
VendorName Vendor3
VendorNum 4
VendorName Vendor4
VendorNum 5
VendorName Vendor5
The Second Option
Select * from [dbo].[tvf-XML-Hier](#xml) Order by R1
Returns
Perhaps more than you want, but it is easy to trim down
The TVF if Interested
CREATE FUNCTION [dbo].[tvf-XML-Hier](#XML xml)
Returns Table
As Return
with cte0 as (
Select Lvl = 1
,ID = Cast(1 as int)
,Pt = Cast(NULL as int)
,Element = x.value('local-name(.)','varchar(150)')
,Attribute = cast('' as varchar(150))
,Value = x.value('text()[1]','varchar(max)')
,XPath = cast(concat(x.value('local-name(.)','varchar(max)'),'[' ,cast(Row_Number() Over(Order By (Select 1)) as int),']') as varchar(max))
,Seq = cast(1000000+Row_Number() over(Order By (Select 1)) as varchar(max))
,AttData = x.query('.')
,XMLData = x.query('*')
From #XML.nodes('/*') a(x)
Union All
Select Lvl = p.Lvl + 1
,ID = Cast( (Lvl + 1) * 1024 + (Row_Number() Over(Order By (Select 1)) * 2) as int ) * 10
,Pt = p.ID
,Element = c.value('local-name(.)','varchar(150)')
,Attribute = cast('' as varchar(150))
,Value = cast( c.value('text()[1]','varchar(max)') as varchar(max) )
,XPath = cast(concat(p.XPath,'/',c.value('local-name(.)','varchar(max)'),'[',cast(Row_Number() Over(PARTITION BY c.value('local-name(.)','varchar(max)') Order By (Select 1)) as int),']') as varchar(max) )
,Seq = cast(concat(p.Seq,' ',10000000+Cast( (Lvl + 1) * 1024 + (Row_Number() Over(Order By (Select 1)) * 2) as int ) * 10) as varchar(max))
,AttData = c.query('.')
,XMLData = c.query('*')
From cte0 p
Cross Apply p.XMLData.nodes('*') b(c)
)
, cte1 as (
Select R1 = Row_Number() over (Order By Seq),A.*
From (
Select Lvl,ID,Pt,Element,Attribute,Value,XPath,Seq From cte0
Union All
Select Lvl = p.Lvl+1
,ID = p.ID + Row_Number() over (Order By (Select NULL))
,Pt = p.ID
,Element = p.Element
,Attribute = x.value('local-name(.)','varchar(150)')
,Value = x.value('.','varchar(max)')
,XPath = p.XPath + '/#' + x.value('local-name(.)','varchar(max)')
,Seq = cast(concat(p.Seq,' ',10000000+p.ID + Row_Number() over (Order By (Select NULL)) ) as varchar(max))
From cte0 p
Cross Apply AttData.nodes('/*/#*') a(x)
) A
)
Select A.R1
,R2 = IsNull((Select max(R1) From cte1 Where Seq Like A.Seq+'%'),A.R1)
,A.Lvl
,A.ID
,A.Pt
,A.Element
,A.Attribute
,A.XPath
,Title = Replicate('|---',Lvl-1)+Element+IIF(Attribute='','','#'+Attribute)
,A.Value
From cte1 A
/*
Source: http://beyondrelational.com/modules/2/blogs/28/posts/10495/xquery-lab-58-select-from-xml.aspx
Declare #XML xml='<person><firstname preferred="Annie" nickname="BeBe">Annabelle</firstname><lastname>Smith</lastname></person>'
Select * from [dbo].[tvf-XML-Hier](#XML) Order by R1
*/

Answer 2

You could query the two columns separately then join as follows:
select VendorNum, VendorName
from
(
SELECT
n = ROW_NUMBER() OVER (Order by t.vendor.value('text()[1]','NVARCHAR(MAX)')),
VendorNum= t.vendor.value('text()[1]','NVARCHAR(MAX)')
FROM #xml.nodes('SearchQuery/VendorNum') AS t(vendor)
) N
join
(
SELECT
n = ROW_NUMBER() OVER (Order by t.vendor.value('text()[1]','NVARCHAR(MAX)')),
VendorName = t.vendor.value('text()[1]','NVARCHAR(MAX)')
FROM #xml.nodes('SearchQuery/VendorName') AS t(vendor)
) V on V.n =N.n