Table Name : TBL_CLIENTS
Table Field : XMLDATA
<REPORT xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" DESCRIPTION="TestClient" FILENUM="1234">
<!--<REPORT DESCRIPTION="TestClient" FILENUM="1234">-->
<TRACKING>
<FIRSTNAME>Bobby</FIRSTNAME>
<LASTNAME>Butcher</LASTNAME>
</TRACKING>
</REPORT>
I want to change both the FIRSTNAME and LASTNAME. Is there anyway I can do it in a single query? The only way I can figure it out is using two queries.
UPDATE TBL_CLIENTS
SET [XMLDATA].modify('replace value of (/REPORT/TRACKING/FIRSTNAME/text()) [1] with ("Franny")')
WHERE ORDERID = 5
and
UPDATE TBL_CLIENTS
SET [XMLDATA].modify('replace value of (/REPORT/TRACKING/LASTNAME/text())[1] with ("Farmer")')
WHERE ORDERID = 5
It's not possible - per MSDN, replace has to work on a single instance of an XML node - but you could avoid doing two UPDATEs on the table this way:
DECLARE #doc xml = '<REPORT xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" DESCRIPTION="TestClient" FILENUM="1234">
<!--<REPORT DESCRIPTION="TestClient" FILENUM="1234">-->
<TRACKING>
<FIRSTNAME>Bobby</FIRSTNAME>
<LASTNAME>Butcher</LASTNAME>
</TRACKING>
</REPORT>';
DECLARE #t table (xmldata xml);
insert #t (xmldata) values (#doc);
-- grab the XML data from the table for manipulation...
DECLARE #xmlData xml;
SELECT #xmlData = xmldata FROM #t;
set #xmlData.modify('replace value of (/REPORT/TRACKING/FIRSTNAME/text()) [1] with ("Franny")')
set #xmlData.modify('replace value of (/REPORT/TRACKING/LASTNAME/text()) [1] with ("Farmer")')
-- now we only need to do one update on the table itself.
UPDATE #t
SET [XMLDATA] = #xmlData
SELECT * FROM #t;
I know this isn't exactly what you were asking for, but it should result in less locking time and better performance on the table - if that's something you're aiming for.
Related
Technologies: T-SQL, XML, XQuery
I have an XML #variable in a database table which has a schema section and data section. I would only like to extra only the schema section and create a XML Schema Collection for it. It appears XQuery would be the quickest way. How do I specify the starting tag and ending tag in the following file (I only want to extract everything between <xs:schema xmlns and </xs:schema>?
CREATE FUNCTION [etl].[ufn_GetXmlSchema]
(
#DataLakeBlobId uniqueidentifier
)
RETURNS xml
AS
BEGIN
DECLARE #XmlSchema xml
,#XmlData xml
SET #XmlSchema = ( SELECT [XmlData]
FROM [landing].[v_tbForm] WITH (NOLOCK)
WHERE [DataLakeBlobId] = #DataLakeBlobId
)
--RETURN #XmlSchema.query('</xs:schema>')-- missing matching begin tag
--RETURN #XmlSchema.query('<xs:schema xmlns="" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:msdata="urn:schemas-microsoft-com:xml-msdata" id="NewDataSet">')-- Expected end tag 'xs:schema'
RETURN #XmlSchema.query('<xs:schema xmlns="" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:msdata="urn:schemas-microsoft-com:xml-msdata" id="NewDataSet"></xs:schema>')-- nothing in between was returned
END
GO
SELECT [etl].[ufn_GetXmlSchema]('A257667D-C3AA-471C-9F82-91FA35181833')
Any help is appreciated.
While waiting for a real scenario, here is a good jump start for you. As end result, it creates an XML Schema Collection named dbo.StateAndCities.
SQL
USE tempdb;
GO
-- DDL and sample data population, start
IF EXISTS (SELECT * FROM sys.xml_schema_collections
WHERE name = N'StateAndCities'
AND schema_id = SCHEMA_ID(N'dbo'))
DROP XML SCHEMA COLLECTION dbo.StateAndCities;
DECLARE #tbl TABLE (
ID INT IDENTITY PRIMARY KEY
, state CHAR(2)
, city VARCHAR(30)
);
INSERT INTO #tbl (state, city)
VALUES
('FL', 'Miami')
, ('CA', 'Los Angeles')
, ('TX', 'Austin');
-- DDL and sample data population, end
DECLARE #xml XML
, #XSD XML;
-- Generate XML plus embedded XSD schema
SET #xml = (SELECT NULL,
(
SELECT *
FROM #tbl AS [row]
FOR XML AUTO, ELEMENTS, TYPE, XMLSCHEMA('MyURI'))
FOR XML PATH(''), TYPE, ROOT('root')
);
-- just to see, XML plus embedded XSD schema
SELECT #xml;
-- retrive just XSD
;WITH xmlnamespaces ('http://www.w3.org/2001/XMLSchema' AS xsd)
SELECT #xsd = (SELECT #xml.query('/root/xsd:schema'));
-- just to see, XSD schema
SELECT #xsd AS xsd;
-- create schema collection
CREATE XML SCHEMA COLLECTION dbo.StateAndCities AS #xsd;
My XML is stored as varbinary in a field.
SELECT cast (inboxXml as xml) FROM globalDB.Inbox WHERE inboxCId = '207435-N'
I would like to update one attribute (below). However the error is "Cannot call methods on varbinary(max)." I tried different ways to cast it, but I cannot find it.
thank you,
;WITH XMLNAMESPACES(DEFAULT 'http://www.w3.org/2001/XMLSchema')
UPDATE globalDB.Inbox
SET inboxXml.modify('replace value of (//ReceiveDeliveryHeader/DocumentID/ID/#accountingEntity[.="ABC"])[1] with "ZZZ"')
WHERE inboxCId = '207435-N'
The first question is: Why are you storing your XML within a VARBINARY column?
This is slow, clumsy and erronous...
The second thing is: .modify() will work against a real native XML only. Neither inboxXml.modify() nor CAST(inboxXml AS XML).modify() will work...
This is one more reason to change your column's type to XML...
Try this:
DECLARE #tbl TABLE(ID INT IDENTITY,YourXml VARBINARY(MAX));
DECLARE #SomeXML XML='<root><someNode someAttr="test">content</someNode></root>';
INSERT INTO #tbl VALUES(CAST(#SomeXML AS VARBINARY(MAX)));
--this works
SELECT ID
,YourXml
,CAST(YourXml AS XML)
FROM #tbl
WHERE ID=1;
--but this is not allowed
UPDATE #tbl SET CAST(YourXml AS XML).modify('replace value of (/root/someNode/#someAttr)[1] with "blah"')
WHERE ID=1
--What you can do:
DECLARE #intermediateXML XML= (SELECT CAST(YourXml AS XML) FROM #tbl WHERE ID=1);
SET #intermediateXML.modify('replace value of (/root/someNode/#someAttr)[1] with "blah"');
UPDATE #tbl SET YourXml=CAST(#intermediateXML AS VARBINARY(MAX)) WHERE ID=1;
--voila!
SELECT ID
,YourXml
,CAST(YourXml AS XML)
FROM #tbl
WHERE ID=1;
I am using SQL Server (2008/2012) and I know there are similar answers from lots of searching, however I can't seem to find the appropriate example/pointers for my case.
I have an XML column in a SQL Server table holding this data:
<Items>
<Item>
<FormItem>
<Text>FirstName</Text>
<Value>My First Name</Value>
</FormItem>
<FormItem>
<Text>LastName</Text>
<Value>My Last Name</Value>
</FormItem>
<FormItem>
<Text>Age</Text>
<Value>39</Value>
</FormItem>
</Item>
<Item>
<FormItem>
<Text>FirstName</Text>
<Value>My First Name 2</Value>
</FormItem>
<FormItem>
<Text>LastName</Text>
<Value>My Last Name 2</Value>
</FormItem>
<FormItem>
<Text>Age</Text>
<Value>40</Value>
</FormItem>
</Item>
</Items>
So even though the structure of <FormItem> is going to be the same, I can have multiple (most commonly no more than 20-30) sets of form items..
I am essentially trying to return a query from SQL in the format below, i.e. dynamic columns based on /FormItem/Text:
FirstName LastName Age ---> More columns as new `<FormItem>` are returned
My First Name My Last Name 39 Whatever value etc..
My First Name 2 My Last Name 2 40
So, at the moment I had the following:
select
Tab.Col.value('Text[1]','nvarchar(100)') as Question,
Tab.Col.value('Value[1]','nvarchar(100)') as Answer
from
#Questions.nodes('/Items/Item/FormItem') Tab(Col)
Of course that hasn't transposed my XML rows into columns, and obviously is fixed with fields anyway.. I have been trying various "Dynamic SQL" approaches where the SQL performs a distinct selection of (in my case) the <Text> node, and then uses some sort of Pivot? but I couldn't seem to find the magic combination to return the results I need as a dynamic set of columns for each row (<Item> within the collection of <Items>).
I'm sure it can be done having seen so many very similar examples, however again the solution eludes me!
Any help gratefully received!!
Parsing the XML is fairly expensive so instead of parsing once to build a dynamic query and once to get the data you can create a temporary table with a Name-Value list and then use that as the source for a dynamic pivot query.
dense_rank is there to create the ID to pivot around.
To build the column list in the dynamic query it uses the for xml path('') trick.
This solution requires that your table has a primary key (ID). If you have the XML in a variable it can be somewhat simplified.
select dense_rank() over(order by ID, I.N) as ID,
F.N.value('(Text/text())[1]', 'varchar(max)') as Name,
F.N.value('(Value/text())[1]', 'varchar(max)') as Value
into #T
from YourTable as T
cross apply T.XMLCol.nodes('/Items/Item') as I(N)
cross apply I.N.nodes('FormItem') as F(N)
declare #SQL nvarchar(max)
declare #Col nvarchar(max)
select #Col =
(
select distinct ','+quotename(Name)
from #T
for xml path(''), type
).value('substring(text()[1], 2)', 'nvarchar(max)')
set #SQL = 'select '+#Col+'
from #T
pivot (max(Value) for Name in ('+#Col+')) as P'
exec (#SQL)
drop table #T
SQL Fiddle
select Tab.Col.value('(FormItem[Text = "FirstName"]/Value)[1]', 'varchar(32)') as FirstName,
Tab.Col.value('(FormItem[Text = "LastName"]/Value)[1]', 'varchar(32)') as LastName,
Tab.Col.value('(FormItem[Text = "Age"]/Value)[1]', 'int') as Age
from #Questions.nodes('/Items/Item') Tab(Col)
I wanted to add my "own answer" really just for completeness to possibly help others.. however it is most definitely based on the great help from #Mikael above!! so again, this is really for completeness only - all kudos to #Mikael.
Basically I ended up with the following proc. I needed to select some data/filter, and get some joined data too and allow some boolean filtering on some of the input params. Then drop into the next section which was create a temp table of my relational data and the required xml nodes via the cross apply. The final step was to then pivot the results/dynamically create the columns from the selected XML node..
CREATE PROCEDURE [dbo].[usp_RPT_ExtractFlattenentries]
#CompanyID int,
#MainSelector nvarchar(50) = null,
#SecondarySelector nvarchar(255) = null,
#DateFrom datetime = '01-jan-2012',
#DateTo datetime = '31-dec-2100',
#SysReference nvarchar(20) = null
AS
BEGIN
SET NOCOUNT ON;
-- Create the table var to hold the XML form data from the entries
declare #FeedbackXml table (
ID int identity primary key,
XMLCol xml,
CompanyName nvarchar(20),
SysReference nvarchar(20),
RecordDate datetime,
EntryName nvarchar(255),
MainSelector nvarchar(50)
)
-- STEP 1: Get the raw submission data based on the params passed in
-- *Note: The double casting is necessary as the "form" field is nvarchar (not varchar) and we need xml in UTF-8 format
begin
insert into #FeedbackXml
(XMLCol, CompanyName, SysReference, RecordDate, EntryName, MainSelector)
select cast(cast(e.form as nvarchar(max)) as xml), c.name, e.SysReference, e.RecordDate, e.name, e.wizard
from
entries s
left join
companies o on e.companies = c.ID
where
(#CompanyID = -1 or #CompanyID = e.companies)
and
(#MainSelector is null or #MainSelector = e.wizard)
and
(#SecondarySelector is null or #SecondarySelector = e.name)
and
(#SysReference is null or #SysReference = e.SysReference)
and
(e.RecordDate >= #DateFrom and e.RecordDate <= #DateTo)
end
-- STEP 2: Flatten the required XML structure to provide a base for the pivot, and include other fields we wish to output
select dense_rank() over(order by ID) as ID,
T.RecordDate, T.CompanyName, T.SysReference, T.EntryName, T.MainSelector,
F.N.value('(FieldNameNode/text())[1]', 'nvarchar(max)') as FieldName,
F.N.value('(FieldNameValue/text())[1]', 'nvarchar(max)') as FieldValue
into #TempData
from #FeedbackXml as T
cross apply T.XMLCol.nodes('/root/companies/') as I(N) -- Xpath to the desired node start point
cross apply I.N.nodes('company') as F(N) -- The actual node collection that forms the "field name" and "field value" data
-- STEP 3: Pivot the #TempData table creating a dynamic column structure based on the selected XML nodes in step 2
declare #SQL nvarchar(max)
declare #Col nvarchar(max)
select #Col =
(
select distinct ','+quotename(FieldName)
from #TempData
for xml path(''), type
).value('substring(text()[1], 2)', 'nvarchar(max)')
set #SQL = 'select CompanyName, SysReference, EntryName, MainSelector, RecordDate, '+#Col+'
from #TempData
pivot (max(FieldValue) for FieldName in ('+#Col+')) as P'
exec (#SQL)
drop table #TempData
END
Again, really only added this answer to provide a complete picture from my perspective, and may help others.
Table is named as MasterTable
Columns
ID type BIGINT,
Name type VARCHAR(200) (stores xml type data for some reasons)
Name contains data structured as
<en-US>SomeEnglishText</en-US><it-IT>SomeItalicText</it-IT>
When I need to Update the Master Table then at that time I Need to cast the Varchar to xml then conditionally update / replace the value part of particular tag i.e either en-US / it-IT.
Also there are chances that No data/tags are there in Name column so I think at the time of Inserting data it would Insert empty tag elements in the table like <en-US></en-US><it-IT></it-IT>, so the update query must handle empty value in tag elements namely en-US/it-IT.
I am trying to do it like following update query.
DECLARE #Str VARCHAR(200)
SET #Str = 'Test Text'
UPDATE [MasterTable]
SET [Name] = cast([MasterTable].[Name] as xml).modify('replace value of (en-US/text())[1] with sql:variable("#Str")')
WHERE [ID]=18
I getting following error when running the query
Illegal use of xml data type method 'modify'. A non-mutator method is expected in this context.
You can not assign from a xml.modify. Modify works on the variable/column directly. You can also not use modify on a cast.
You can extract the name to a xml variable, modify the xml and then put it back to the table.
declare #str varchar(200) = 'Test'
declare #xml xml
select #xml = cast(Name as xml)
from MasterTable
where ID = 18
set #xml.modify('replace value of (en-US/text())[1] with sql:variable("#Str")')
update MasterTable
set Name = cast(#xml as varchar(200))
where ID = 18
If you need this to work over more than one row at a time you can use a table variable with columns id and name where data type for name is xml instead of the #xml variable.
declare #str varchar(200) = 'Test Text'
declare #T table (ID int, Name xml)
insert into #T
select ID, cast(Name as xml)
from MasterTable
where Name is not null
update #T
set Name.modify('replace value of (en-US/text())[1] with sql:variable("#Str")')
update MasterTable
set Name = cast(T.Name as varchar(200))
from #T as T
where MasterTable.ID = T.ID
I am using a table with an XML data field to store the audit trails of all other tables in the database.
That means the same XML field has various XML information. For example my table has two records with XML data like this:
1st record:
<client>
<name>xyz</name>
<ssn>432-54-4231</ssn>
</client>
2nd record:
<emp>
<name>abc</name>
<sal>5000</sal>
</emp>
These are the two sample formats and just two records. The table actually has many more XML formats in the same field and many records in each format.
Now my problem is that upon query I need these XML formats to be converted into tabular result sets.
What are the options for me? It would be a regular task to query this table and generate reports from it. I want to create a stored procedure to which I can pass that I need to query "<emp>" or "<client>", then my stored procedure should return tabular data.
does this help?
INSERT INTO #t (data) SELECT '
<client>
<name>xyz</name>
<ssn>432-54-4231</ssn>
</client>'
INSERT INTO #t (data) SELECT '
<emp>
<name>abc</name>
<sal>5000</sal>
</emp>'
DECLARE #el VARCHAR(20)
SELECT #el = 'client'
SELECT
x.value('local-name(.)', 'VARCHAR(20)') AS ColumnName,
x.value('.','VARCHAR(20)') AS ColumnValue
FROM #t
CROSS APPLY data.nodes('/*[local-name(.)=sql:variable("#el")]') a (x)
/*
ColumnName ColumnValue
-------------------- --------------------
client xyz432-54-4231
*/
SELECT #el = 'emp'
SELECT
x.value('local-name(.)', 'VARCHAR(20)') AS ColumnName,
x.value('.','VARCHAR(20)') AS ColumnValue
FROM #t
CROSS APPLY data.nodes('/*[local-name(.)=sql:variable("#el")]') a (x)
/*
ColumnName ColumnValue
-------------------- --------------------
emp abc5000
*/
Neither xyz432-54-4231 nor abc5000 is valid XML.
You can try to select only one particular format with a like statement, f.e.:
select *
from YourTable
where YourColumn like '[a-z][a-z][a-z][0-9][0-9][0-9][0-9]'
This would match 3 letters followed by 4 numbers.
A better option is probably to add an extra column to the table, where you save the type of the logging. Then you can use that column to select all "emp" or "client" rows.
An option would be to create a series of views that present the aduit table, per type in the relations that you're execpting
for example
select
c.value('name','nvarchar(50)') as name,
c.value('ssn', 'nvarchar(20)') as ssn
from yourtable
cross apply yourxmlcolumn.nodes('/client') as t(c)
you could then follow the same pattern for the emp
you could also create a view (or computed column) to identify each xml type like this:
select yourxmlcolumn.value('local-name(/*[1])', 'varchar(100)') as objectType
from yourtable
Use open xml method
DECLARE #idoc int
EXEC sp_xml_preparedocument #idoc OUTPUT, #xmldoc
SELECT * into #test
FROM OPENXML (#idoc, 'xmlfilepath',2)
WITH (Name varchar(50),ssn varchar(20)
)
EXEC sp_xml_removedocument #idoc
after you get the data in the #test
and you can manipulate this.
you may be put the diff data in diff xml file.