Menu
I don't know if it has already been answered, but my bad luck or so I can't find it anywhere in stackoverflow with my hunting techniques. Kindly ignore my spamming
We have a requirement where we need to write a API parser that works for any API giving XML output.
We will not know the XML structure before hand.
The solution should convert XML file and save it in a generic tsql table with the XML element/attribute names as first row.
So basically it is XML deserializer for any API.
We cannot use any third party dll for our C# class.
I have no idea about C# so dont know if it is possible or not. But I have been able to write a genric XML->row converter in tsql using OPENXML. The problem with tsql solution is that we are unable to import a huge XML file succesfully into database.
I can supply any details that will be required. Kindly let me know in comments/answers.
I don't wish anyone to write a code for me, any suitable pointers would be enough
Resources: JSON
[
{
"id" : 21953,
"mainReqIdentity" : "xxxx",
"itemName" : "xxxx",
"kanbanPhase" : "xxxx",
"kanbanStatus" : "xxxx",
"backlogItemType" : "xxxx",
"identityDomain" : "xxxx",
"fromDatetime" : "2016-08-05 17:52:34",
"teams" : [],
"releases" : [{
"id" : 1229,
"release_name" : "xxxx",
"release_connection_type" : "xxxx"
}
],
"fpReleases" : [],
"sources" : [{
"sourceName" : "xxxx",
"sourceRecordUrl" : "xxxx",
"sourceRecordIdentity" : "xxxx"
}
],
"productNumbers" : [],
"tags" : [],
"productComponents" : [],
"ranPlatforms" : [],
"subReleases" : [],
"requirementAreaId" : xxxx,
"requirementArea" : "xxxx",
"toBeHandledAtxxxx" : "xxxx"
}, {
"id" : 22014,
"mainReqIdentity" : "xxxx",
"itemName" : "xxxx",
"kanbanPhase" : "xxxx",
"kanbanStatus" : "xxxx",
"backlogItemType" : "xxxx",
"identityDomain" : "xxxx",
"fromDatetime" : "2016-08-05 17:52:34",
"teams" : [],
"releases" : [{
"id" : xxxx,
"release_name" : "xxxx",
"release_connection_type" : "xxxx"
}
],
"fpReleases" : [],
"sources" : [{
"sourceName" : "xxxx",
"sourceRecordUrl" : "xxxx",
"sourceRecordIdentity" : "xxxx"
}
],
"productNumbers" : [],
"tags" : [],
"productComponents" : [],
"ranPlatforms" : [],
"subReleases" : [],
"requirementAreaId" : xxxx,
"requirementArea" : "xxxx",
"f0Date" : "2015-10-01",
"f1Date" : "2015-10-01",
"f2Date" : "2016-02-01",
"f4Date" : "2016-03-31",
"fgDate" : "2016-04-29",
"toBeHandledAtxxxx" : "xxxx"
}
]
XML: 2 samples
Sample 1
<root type="array">
<id type="number">21286</id>
<mainReqIdentity type="string">xxxxxx</mainReqIdentity>
<itemName type="string">xxxxxx</itemName>
<kanbanPhase type="string">xxxxxx</kanbanPhase>
<kanbanStatus type="string">xxxxxx</kanbanStatus>
<kanbanNote type="string">xxxxxx</kanbanNote>
<backlogItemType type="string">xxxxxx</backlogItemType>
<identityDomain type="string">xxxxxx</identityDomain>
<fromDatetime type="string">2016-08-23 17:01:52</fromDatetime>
<teams type="array">
<item type="object">
<team_name type="string">xxxxxx</team_name>
<preliminary type="boolean">xxxxxx</preliminary>
</item>
</teams>
<releases type="array">
<item type="object">
<id type="number">xxxxxx</id>
<release_name type="string">xxxxxx</release_name>
<release_connection_type type="string">xxxxxx</release_connection_type>
</item>
</releases>
<fpReleases type="array">
</fpReleases>
<sources type="array">
<item type="object">
<sourceName type="string">xxxxxx</sourceName>
<sourceRecordUrl type="string">xxxxxx</sourceRecordUrl>
</item>
</sources>
<productNumbers type="array">
</productNumbers>
<tags type="array">
</tags>
<productComponents type="array">
</productComponents>
<ranPlatforms type="array">
</ranPlatforms>
<subReleases type="array">
</subReleases>
<requirementAreaId type="number">xxxxxx</requirementAreaId>
<requirementArea type="string">xxxxxx</requirementArea>
<itemContact type="string">xxxxxx</itemContact>
<toBeHandledAtxxx type="string">xxxxxx</toBeHandledAtLuca>
</item>
<item type="object">
<id type="number">xxxxxx</id>
<mainReqIdentity type="string">xxxxxx</mainReqIdentity>
<itemName type="string">xxxxxx</itemName>
<kanbanPhase type="string">xxxxxx</kanbanPhase>
<kanbanStatus type="string">xxxxxx</kanbanStatus>
<kanbanNote type="string">xxxxxx</kanbanNote>
<backlogItemType type="string">xxxxxx</backlogItemType>
<identityDomain type="string">xxxxxx</identityDomain>
<fromDatetime type="string">2016-08-23 17:01:52</fromDatetime>
<teams type="array">
<item type="object">
<team_name type="string">xxxxxx</team_name>
<preliminary type="boolean">xxxxxx</preliminary>
</item>
</teams>
<releases type="array">
<item type="object">
<id type="number">xxxxxx</id>
<release_name type="string">xxxxxx</release_name>
<release_connection_type type="string">xxxxxx</release_connection_type>
</item>
</releases>
<fpReleases type="array">
</fpReleases>
<sources type="array">
<item type="object">
<sourceName type="string">xxxxxx</sourceName>
<sourceRecordUrl type="string">xxxxxx</sourceRecordUrl>
</item>
</sources>
<productNumbers type="array">
</productNumbers>
<tags type="array">
</tags>
<productComponents type="array">
</productComponents>
<ranPlatforms type="array">
</ranPlatforms>
<subReleases type="array">
</subReleases>
<requirementAreaId type="number">xxxxxx</requirementAreaId>
<requirementArea type="string">xxxxxx</requirementArea>
<oaResultReference type="string">xxxxxx</oaResultReference>
<itemContact type="string">xxxxxx</itemContact>
<f0Date type="string">2014-10-17</f0Date>
<f1Date type="string">2015-01-16</f1Date>
<f2Date type="string">2015-02-13</f2Date>
<f4Date type="string">2015-06-12</f4Date>
<faDate type="string">2015-06-12</faDate>
<fgDate type="string">2015-06-12</fgDate>
<toBeHandledAtxxx type="string">xxxxxx</toBeHandledAtLuca>
</item>
</root>
Sample 2
<ROOT>
<Customer CustomerID="VINET" ContactName="Paul Henriot">
<Order CustomerID="VINET" EmployeeID="5" OrderDate="1996-07-04T00:00:00">
<OrderDetail OrderID="10248" ProductID="11" Quantity="12"/>
<OrderDetail OrderID="10248" ProductID="42" Quantity="10"/>
</Order>
</Customer>
<Customer CustomerID="LILAS" ContactName="Carlos Gonzlez">
<Order CustomerID="LILAS" EmployeeID="3" OrderDate="1996-08-16T00:00:00">
<OrderDetail OrderID="10283" ProductID="72" Quantity="3"/>
</Order>
</Customer>
</ROOT>
SQL
Generic staging Table
create table ZZZZZZZZZ
(
api_id int,
record_type char(1),
record_id INT,
last_run_time datetime,
last_run_by varchar(500),
col1 VARCHAR(500),
col2 VARCHAR(500),
col3 VARCHAR(500),
col4 VARCHAR(500),
col5 VARCHAR(500),
col6 VARCHAR(500),
col7 VARCHAR(500),
col8 VARCHAR(500),
col9 VARCHAR(500),
col10 VARCHAR(500),
col11 VARCHAR(500),
col12 VARCHAR(500),
col13 VARCHAR(500),
col14 VARCHAR(500),
col15 VARCHAR(500),
col16 VARCHAR(500),
col17 VARCHAR(500),
col18 VARCHAR(500),
col19 VARCHAR(500),
col20 VARCHAR(500),
col21 VARCHAR(500),
col22 VARCHAR(500),
col23 VARCHAR(500),
col24 VARCHAR(500),
col25 VARCHAR(500),
col26 VARCHAR(500),
col27 VARCHAR(500),
col28 VARCHAR(500),
col29 VARCHAR(500),
col30 VARCHAR(500),
col31 VARCHAR(500),
col32 VARCHAR(500),
col33 VARCHAR(500),
col34 VARCHAR(500),
col35 VARCHAR(500),
col36 VARCHAR(500),
col37 VARCHAR(500),
col38 VARCHAR(500),
col39 VARCHAR(500),
col40 VARCHAR(500),
col41 VARCHAR(500),
col42 VARCHAR(500),
col43 VARCHAR(500),
col44 VARCHAR(500),
col45 VARCHAR(500),
col46 VARCHAR(500),
col47 VARCHAR(500),
col48 VARCHAR(500),
col49 VARCHAR(500),
col50 VARCHAR(500),
col51 VARCHAR(500),
col52 VARCHAR(500),
col53 VARCHAR(500),
col54 VARCHAR(500),
col55 VARCHAR(500),
col56 VARCHAR(500),
col57 VARCHAR(500),
col58 VARCHAR(500),
col59 VARCHAR(500),
col60 VARCHAR(500),
col61 VARCHAR(500),
col62 VARCHAR(500),
col63 VARCHAR(500),
col64 VARCHAR(500),
col65 VARCHAR(500),
col66 VARCHAR(500),
col67 VARCHAR(500),
col68 VARCHAR(500),
col69 VARCHAR(500),
col70 VARCHAR(500),
col71 VARCHAR(500),
col72 VARCHAR(500),
col73 VARCHAR(500),
col74 VARCHAR(500),
col75 VARCHAR(500),
col76 VARCHAR(500),
col77 VARCHAR(500),
col78 VARCHAR(500),
col79 VARCHAR(500),
col80 VARCHAR(500),
col81 VARCHAR(500),
col82 VARCHAR(500),
col83 VARCHAR(500),
col84 VARCHAR(500),
col85 VARCHAR(500),
col86 VARCHAR(500),
col87 VARCHAR(500),
col88 VARCHAR(500),
col89 VARCHAR(500),
col90 VARCHAR(500),
col91 VARCHAR(500),
col92 VARCHAR(500),
col93 VARCHAR(500),
col94 VARCHAR(500),
col95 VARCHAR(500),
col96 VARCHAR(500),
col97 VARCHAR(500),
col98 VARCHAR(500),
col99 VARCHAR(500),
col100 VARCHAR(500),
col101 VARCHAR(500),
col102 VARCHAR(500),
col103 VARCHAR(500),
col104 VARCHAR(500),
col105 VARCHAR(500),
col106 VARCHAR(500),
col107 VARCHAR(500),
col108 VARCHAR(500),
col109 VARCHAR(500),
col110 VARCHAR(500),
col111 VARCHAR(500),
col112 VARCHAR(500),
col113 VARCHAR(500),
col114 VARCHAR(500),
col115 VARCHAR(500),
col116 VARCHAR(500),
col117 VARCHAR(500),
col118 VARCHAR(500),
col119 VARCHAR(500),
col120 VARCHAR(500),
col121 VARCHAR(500),
col122 VARCHAR(500),
col123 VARCHAR(500),
col124 VARCHAR(500),
col125 VARCHAR(500),
col126 VARCHAR(500),
col127 VARCHAR(500),
col128 VARCHAR(500),
col129 VARCHAR(500),
col130 VARCHAR(500),
col131 VARCHAR(500),
col132 VARCHAR(500),
col133 VARCHAR(500),
col134 VARCHAR(500),
col135 VARCHAR(500),
col136 VARCHAR(500),
col137 VARCHAR(500),
col138 VARCHAR(500),
col139 VARCHAR(500),
col140 VARCHAR(500),
col141 VARCHAR(500),
col142 VARCHAR(500),
col143 VARCHAR(500),
col144 VARCHAR(500),
col145 VARCHAR(500),
col146 VARCHAR(500),
col147 VARCHAR(500),
col148 VARCHAR(500),
col149 VARCHAR(500),
col150 VARCHAR(500)
)
Sample Output
Generic XML Parser written in TSQL. There are few hacks in the code and some stray code that need to remove. This works fine. But the trouble is in sending the entire XML document as input parameter from C# code through either direct call or through a file.
CREATE PROC ZZZZZZZ
(
@in_api_id int,
@in_xml_doc XML,
@in_xml_root varchar(100),
@in_tot_result_col int = 150,
@in_need_colnm_result CHAR(1) = 'Y',
@in_debug_flg CHAR(1) = 'N'
)
AS
BEGIN
DECLARE
@idoc int,
@sqlstr nvarchar(max) = '',
@param nvarchar(200) = '',
@runtime datetime = getdate(),
@runby varchar(30) = suser_name(),
@cnt int,
@pre_stg_col_nm varchar(max) = '',
@max_lvl int,
@max_node varchar(500)='',
@max_node_wo_slash varchar(500)='',
@xml_col nvarchar(max) = '',
@unq_col nvarchar(max) = '',
@unq_xml_col nvarchar(max)=''
--Create an internal representation of the XML document.
EXEC sp_xml_preparedocument @idoc OUTPUT, @in_xml_doc;
-- Execute a SELECT statement that uses the OPENXML rowset provider.
set @in_xml_root = concat('/',@in_xml_root)
SELECT * into #tmp FROM OPENXML (@idoc, @in_xml_root,2) where id <> 0;
--select * from #tmp_xml_nodes
--select * from #tmp
--select * from #tmp_pre_staging
;with xml_cte(id, parentid, nodetype, localname, prefix, namespaceuri, datatype, prev, text, lvl,node,parent_localname)
AS
(
select id,
parentid,
nodetype,
localname,
prefix,
namespaceuri,
datatype,
prev,
text,
1 as lvl,
cast(CONCAT(@in_xml_root,'/',localname) as varchar(100)) node,
cast('' as varchar(200))
from #tmp
where parentid = 0
UNION all
select t.id,
t.parentid,
t.nodetype,
t.localname,
t.prefix,
t.namespaceuri,
t.datatype,
t.prev,
t.text,
iif(t.nodetype = 1,xc.lvl+1,xc.lvl),
cast(
CONCAT (
xc.node
,iif(t.nodetype = 1,
CONCAT (
'/'
,t.localname
)
,''
)
) AS VARCHAR(100)
),
cast(xc.localname as varchar(200))
from #tmp t
inner join xml_cte xc
on xc.id = t.parentid
)
select * into #xmlcte from xml_cte
--select * from #xmlcte
--v2 change
select @max_lvl = max(lvl)--iif(max(lvl)>=4,1,0) -- the iif condition is just a hack, I dont know why it works
from #xmlcte
select
@max_node = concat(max(node),'/'),
@max_node_wo_slash = max(node)
from #xmlcte
where lvl = @max_lvl
select *,concat(parent_localname,'_',localname,' varchar(500)') fnl_col_nm,
case
when lvl<@max_lvl then concat(replicate('../',@max_lvl-lvl+iif(nodetype=1,nodetype,0)),iif(nodetype=1,'','@'),localname) --v2 change
when lvl>@max_lvl then concat(replace(node,@max_node,''),iif(nodetype=1,'','/@'),localname)--v2 change
else concat('../',iif(nodetype=1,'',concat(parent_localname,'/@')),localname)--v2 change
end col_Struct
,concat(parent_localname,'_',localname) col_unq_nm
,ROW_NUMBER() over (order by(select 100)) sno
,concat('xmlname.value(''/Names[1]/name[',ROW_NUMBER() over (order by(select 100)),']'',''varchar(500)'') AS ',concat(parent_localname,'_',localname)) col_splt_nm
into #xml_col_struct
from #xmlcte
where nodetype <= 2--v2 change
--select * from #xml_col_struct
set @cnt = (select count(distinct col_unq_nm) from #xml_col_struct)
select @pre_stg_col_nm =
(
select concat(',',COLUMN_NAME)
from INFORMATION_SCHEMA.COLUMNS
where table_name = 'ZZZZZZ'
and COLUMN_NAME like 'col%'
and ORDINAL_POSITION <= @cnt+5
order by ORDINAL_POSITION
for xml path('')
)
set @sqlstr = concat(
'insert into ZZZZZ(api_id,record_type,record_id,last_run_time,last_run_by',
@pre_stg_col_nm,
')'
)
select @xml_col =
(
select distinct concat(',',fnl_col_nm,' ''',col_Struct,'''',char(10))
from #xml_col_struct
order by 1
for xml path('')
)
set @xml_col = stuff(@xml_col,1,1,'')
select @unq_col =
(
select distinct concat(',',col_unq_nm )
from #xml_col_struct
order by 1
for xml path('')
)
set @unq_col = stuff(@unq_col,1,1,'')
select @in_tot_result_col = @in_tot_result_col - count(distinct col_unq_nm)
from #xml_col_struct
select @unq_xml_col =
(
select
concat(',xmlname.value(''/Names[1]/name[',ROW_NUMBER() over (order by(select 100)),']'',''varchar(500)'') AS ',col_unq_nm,char(10))
from (select distinct col_unq_nm from #xml_col_struct) t
for xml path('')
)
set @unq_xml_col = stuff(@unq_xml_col,1,1,'')
set @sqlstr =
concat(
iif(@in_need_colnm_result = 'Y',
concat('
;WITH Split_Names (xmlname)
AS
(
SELECT
CONVERT(XML,''<Names><name>''
+ REPLACE(''',@unq_col,''','','', ''</name><name>'') + ''</name></Names>'') AS xmlname
)
'
--,@sqlstr
,char(10),
' SELECT ',@in_api_id,',''H'',0,''',@runtime,''',''',@runby,''',',char(10)
,@unq_xml_col,replicate(',NULL',@in_tot_result_col)--v2 change
,char(10)
,'FROM Split_Names'
,char(10)
,'union all'
)
,''
)
--,iif(@in_need_colnm_result = 'Y','',@sqlstr)
,'
SELECT ',@in_api_id,',''D'',ROW_NUMBER() over (order by(select 100)),''',@runtime,''',''',@runby,''',*'
,replicate(',NULL',@in_tot_result_col)--v2 change
,char(10)
,'FROM OPENXML (@idoc_inn, ''',@max_node_wo_slash,''',2)'
,char(10)
,'WITH (',@xml_col,')'
)
if @in_debug_flg = 'Y'
begin
select @max_lvl+1,@max_lvl,@max_node_wo_slash,@xml_col,@unq_col,@sqlstr,@unq_xml_col
select * from #xml_col_struct--v2 change
end
else
begin
set @param = '@idoc_inn int'
exec sys.sp_executesql @sqlstr,@param,@idoc_inn = @idoc
end
EXEC sp_xml_removedocument @idoc
END
SQL code to read XML file loaded by C# class. This also works fine, but the trouble is all lines are in separate rows and concatenation truncates after a point
create table #tmp(data_line nvarchar(max))
bulk insert #tmp
FROM '\\Server\\ZZZZ\\Downloads\\Data.xml'
WITH
(
--firstrow = 1
ROWTERMINATOR ='\n'
);
select * from #tmp
C# class
Object httpConn = Dts.Connections["HTTP"].AcquireConnection(null);
HttpClientConnection myConnection = new HttpClientConnection(httpConn);
myConnection.ServerURL = string.Format(("http://xxxx.com/jjjj"),"userid","password");
byte[] webdata = myConnection.DownloadData();
String result_data = Convert.ToBase64String(webdata);
XmlDocument xd = new XmlDocument();
XmlDictionaryReader xr = JsonReaderWriterFactory.CreateJsonReader(webdata, XmlDictionaryReaderQuotas.Max);
xr.Read();
xd.LoadXml(xr.ReadOuterXml());
xd.Save("\\Server\\ZZZZ\\Downloads\\Data.xml");
588
SQL Server lets you retrieve data as XML by supporting the FOR XML clause, which can be included as part of your query. You can use the FOR XML clause in the main (outer) query as well as in subqueries. The clause supports numerous options that let you define the format of the XML data.
We can use SQL Server to return results from a dataset as XML.
If you are getting a properly formatted XML. You can use Dataset. Specifically use Dataset.ReadXml(). This will load your xml in Dataset object independent of xml tags. Then you can use ADO.Net, linq2sql, EF or any other communication method to put it in database.
Since you are saving file on server you can use below code:
DataSet ds = new DataSet();
ds.ReadXml("\\Server\\ZZZZ\\Downloads\\Data.xml");
then you can iterate over each table of dataset using foreach loop. The attributes in the xml will become your columns in the datatable.
So your final code will be something similar to this:
using (DataSet ds = new DataSet())
{
ds.ReadXml("\\Server\\ZZZZ\\Downloads\\Data.xml");
int nTableCounts = ds.Tables.Count;
foreach(DataTable dt in ds.Tables)
{
using (dt)
{
//Put data in SQL table.
}
}
}
Let me know if anything is unclear.
100
Thank you for placing so many details. Now - together with the bounty - people rush in for help.
This is not really an answer, at least it's not a solution for your actual issue! Rather some thoughts / hints:
This should be done completely differently!
Your current approach is awfull...
FROM OPENXML
Your sample 1 is not even valid XML.
<item>
<toBeHandledAtxxx type="string">xxxxxx</toBeHandledAtLuca>
ISO8601... The given format will be working, but is a sign, that this XML is not created the best way...If this is your actual response, any XML based approach will never work. I hope this happened in order to reduce the lines...
In sample 1 there can be any number of items below <root>. There are 9 !!! areas of potential 1:n data (more than one team, more than one release...).
in relational concepts you'd have to spread this over several related tables
Your sample 2 is quite plain, but has got a 3-level-hierarchy too.
How do you want to put this in your multi-hundred-columns-table? Side-by-side??? Tons of rows due to a cartesian product???
Your sample 2 might be fairly easy to read into a plain structure. You can use local-name() to know which is a Customer and which is an OrderDetail.
But in your sample 2 all of them are called <item>...
Your sample 2 is plain attribute centered XML while your sample 1 mixes attributes and element centered data.
One day there comes the moment, where you want to shuffle the data from your staging table into the fitting structures. Reading from your crude multi-hundred-column-table means, that you have to know everything about the original XML. You must work with complex mapping tables in order to know, what the value of col107 is (semantic, type, format...). For this process you will need a very specific routine for each single kind of XML
At the bottom you show how you are reading the XML file from SQL Server
You follow a line-wise approach, which let you state: but the trouble is all lines are in separate rows. Better try it like this, it will read the whole XML in one single go:
DECLARE @x XML=
(
SELECT x
FROM OPENROWSET(BULK 'C:\YourPath\YourXMLFile.xml', SINGLE_BLOB) AS YourFile(x)
);
select @x;
Especially the last point (very specific routine for each single kind of XML) cries for an import of your XML as-is. There is - at least in my eyes - absolutely no value in your attempts to get any XML into one huge plain table. Better use a slim staging table with some meta columns and one single column for the full XML (might be as NVARCHAR(MAX) to keep it more tolerant against invalid XMLs). There you fill in the XML exactly as you've read it.
Anyway you will need a specific reading process for each kind of XML. Create this directly for the XML.
Do not use FROM OPENXML This is outdated... In your case this still might be a possible way, but - if performance does not matter - you should better use the function you find in John Capelettis answer. This will recursively traverse down litterally any XML and provide the information in a table - without the need to dive into XPath and XQuery.
Best was to define a specific reading process for each kind of XML based on the modern XML methods .nodes(),.query() and .value(). This will be clean, fast and maintainable.
Come back with new question(s) if you need help with this!
Just imagine, your XML sender adds one element somewhere in the middle. In your table the same content moves from col108 to col109. Do you really want to go into versioning of your reading process? If you read the data directly from XML the added element would be just added to the reading process. Older XML without this value can be read with the same engine without troubles...
42
Consider the following
I use a helper function (shamelessly lifted from http://beyondrelational.com/modules/2/blogs/28/posts/10495/xquery-lab-58-select-from-xml.aspx ... with a couple of tweaks i.e. range keys) to convert virtually any XML into a hierarchy.
I should note that I opted for Temp Tables rather than a series of CTEs just for performance and convenience. I'm sure if you want, you could easily migrate into a CTE approach.
Regarding performance, we're looking at 90 - 110ms for the sample files provided. I can't speak to how well this would perform with a LARGE XML source.
The SQL
--Drop Table #TempBase;Drop Table #TempCols;Drop Table #TempHier;Drop Table #TempPivot
-- Declare @Vars
Declare @in_api_id int = 1
Declare @runby varchar(30)='Some User'
Declare @XML xml ='<Root><Customer CustomerID="VINET" ContactName="Paul Henriot"><Order CustomerID="VINET" EmployeeID="5" OrderDate="1996-07-04T00:00:00"><OrderDetail OrderID="10248" ProductID="11" Quantity="12"/><OrderDetail OrderID="10248" ProductID="42" Quantity="10"/></Order></Customer><Customer CustomerID="LILAS" ContactName="Carlos Gonzlez"><Order CustomerID="LILAS" EmployeeID="3" OrderDate="1996-08-16T00:00:00"><OrderDetail OrderID="10283" ProductID="72" Quantity="3"/></Order></Customer></Root>'
--Declare @XML xml='<catalog><product description="Cardigan Sweater" product_image="cardigan.jpg"><catalog_item gender="Men''s"><item_number>QWZ5671</item_number><price>39.95</price><size description="Medium"><color_swatch image="red_cardigan.jpg">Red</color_swatch><color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch></size><size description="Large"><color_swatch image="red_cardigan.jpg">Red</color_swatch><color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch></size></catalog_item><catalog_item gender="Women''s"><item_number>RRX9856</item_number><price>42.50</price><size description="Small"><color_swatch image="red_cardigan.jpg">Red</color_swatch><color_swatch image="navy_cardigan.jpg">Navy</color_swatch><color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch></size><size description="Medium"><color_swatch image="red_cardigan.jpg">Red</color_swatch><color_swatch image="navy_cardigan.jpg">Navy</color_swatch><color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch><color_swatch image="black_cardigan.jpg">Black</color_swatch></size><size description="Large"><color_swatch image="navy_cardigan.jpg">Navy</color_swatch><color_swatch image="black_cardigan.jpg">Black</color_swatch></size><size description="Extra Large"><color_swatch image="burgundy_cardigan.jpg">Burgundy</color_swatch><color_swatch image="black_cardigan.jpg">Black</color_swatch></size></catalog_item></product></catalog>'
--Select * From [dbo].[udf-XML-Hier](@XML) Order by R1
-- Generate Base Hier Data from XML
Select * Into #TempBase From [dbo].[udf-XML-Hier](@XML) Order by R1
-- Generate Required Columns with Sequence
Select *,ColSeq = Row_Number() over (Order by MinR1),ColName = concat('col',Row_Number() over (Order by MinR1) ),ColTitle = IIF(Attribute='','_','')+Element+IIF(Attribute='','','_'+Attribute)
Into #TempCols
From (
Select Element,Attribute,MinR1 = Min(R1)
From #TempBase
Where R1>1
Group By Element,Attribute
) A
-- Extend Base Data with Col Seq
Select A.*,C.ColSeq,RowSeq = 1+Sum(RowFlg) over (Order By R1)
Into #TempHier
From (Select *,RowFlg =IIF(Lag(Lvl,1) over (Order By R1)>Lvl,1,0) From #TempBase) A
Join #TempCols C on (A.Element=C.Element and A.Attribute=C.Attribute)
-- Generate Data to be Pivoted and Augment for Inheritance
Select RowSeq=0,ColSeq,ColName,Value = cast(ColTitle as varchar(max))
Into #TempPivot
From #TempCols
Union All
Select A.RowSeq,A.ColSeq,A.ColName,Value = IsNull(B.Value,'')
From (
Select A.*,R1 = case when B.R1 is not null then B.R1 else (Select Max(R1) from #TempHier Where ColSeq=A.ColSeq and RowSeq<=A.RowSeq) end
From (
Select A.*,B.*
From (Select Distinct RowSeq From #TempHier) A
Join (Select * From #TempCols) B on (1=1)
) A
Left Join #TempHier B on (A.RowSeq=B.RowSeq and A.ColSeq=B.ColSeq )
) A
Join #TempHier B on (A.R1=B.R1)
-- Build and Execute the Final Select
Declare @SQL varchar(max) = ''
Select @SQL = @SQL+concat(',',ColName,'=max(case when ColSeq=',ColSeq,' then Value else null end)') from #TempCols Order by ColSeq
Select @SQL = '
Select api_id = '+cast(@in_api_id as varchar(25))+'
,record_type = max(case when RowSeq=0 then ''H'' else ''D'' end)
,record_id = RowSeq
,last_run_time = GetDate()
,last_run_by ='''+@runby+''''
+@SQL+'
From #TempPivot
Group By RowSeq
Order By RowSeq
'
Exec(@SQL)
Returns
Performance
I know this is a small sample, but the results are returned between 80 and 160ms.
The Table-Valued Function (if needed)
CREATE FUNCTION [dbo].[udf-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(10000001 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].[udf-XML-Hier](@XML) Order by R1
*/
Edit - Just for fun, I grabbed an XML file from http://www.service-architecture.com/articles/object-oriented-databases/xml_file_for_complex_data.html , and the results are as follows:
38
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
