MSSQL Bulk String to XML Insert Into - sql-server

Question

Currently we import a table Import_File which has an Options column which has delimited values.
We need to load those delimited values to a different table.
Currently we do that one row at a time which tends to be slower as the number of rows can be 100k+
Is there a way to speed up the code below?
Declare #InvId uniqueidentifier
Declare #xml xml
Declare CurrFeatureList Cursor For
Select
import.InventoryId,
N'<root><r><![CDATA[' + replace( import.OPTIONS ,',',']]></r><r><![CDATA[') + ']]></r></root>'
From Import_File import with (nolock)
Where
import.options IS NOT NULL
And ISNULL(import.IsFeatureProcessed,0) = 0
And LEN(ISNULL(import.OPTIONS,''))>10
And import.InventoryId Is Not Null
OPEN CurrFeatureList
FETCH NEXT FROM CurrFeatureList
INTO #InvId, #xml
Print 'Inventory Import #10000'
Print GetDate()
WHILE ##FETCH_STATUS = 0
BEGIN
BEGIN TRY
Insert Into Import_File_Feature
(
FeatureId,
InventoryId,
FeatureText,
FeatureGroup,
FeatureCategory,
FeatureIsAvailable,
FeatureIsStandard
)
Select
NEWID(),
#InvId,
t.value('.','varchar(250)'),
'',
'',
1,
1
From #xml.nodes('//root/r') as a(t)
FETCH NEXT FROM CurrFeatureList
INTO #InvId, #xml
END TRY
BEGIN CATCH
Print 'Error '
Print #InvId
Print ERROR_NUMBER()
Print ERROR_SEVERITY()
Print ERROR_STATE()
Print ERROR_PROCEDURE()
Print ERROR_LINE()
Print ERROR_MESSAGE()
FETCH NEXT FROM CurrFeatureList
INTO #InvId, #xml
END CATCH
END
Close CurrFeatureList
Deallocate CurrFeatureList
GO

Answer 1

The only reason I have ever seen a cursor & TRY/CATCH block used for this kind of thing is for identifying and analyzing bad records while developing a new ETL process. If that's not what you're doing then the cursor is not required and will slow you down.
Let's review what you're doing:
You're pulling data into your cursor (CurrFeatureList) and turning Import_File.Options into an XML field so you can later use the XML NODES method to "split" your string.
Kick off the cursor
For each InventoryId you're:
a. splitting the Import_File.Options into multiple rows
b. inserting that InventoryId and associated rows into Import_File_Feature
c. If there's an error you print it and move on to the next record
What you should be doing
Note how I split this string using XML nodes:
DECLARE #x varchar(100) = 'abc,cde,fff';
SELECT item = xxx.value('(text())[1]', 'varchar(100)')
FROM (VALUES (CAST(('<r>'+REPLACE(#x,',','</r><r>') +'</r>') AS xml))) x(xx)
CROSS APPLY xx.nodes('r') xxx(xxx);
Results
item
-----
abc
cde
fff
OPTION 1
Combine your initial join and subsequent XML/XML nodes splitter logic into one statement and do the insert:
WITH
yourData AS
(
Select
import.InventoryId,
x = N'<r><![CDATA[' + replace( import.OPTIONS ,',',']]></r><r><![CDATA[') + ']]></r>'
From Import_File import with (nolock)
Where
import.options IS NOT NULL
And ISNULL(import.IsFeatureProcessed,0) = 0
And LEN(ISNULL(import.OPTIONS,''))>10
And import.InventoryId Is Not Null
),
split AS
(
SELECT InventoryId, item = i.value('.', 'varchar(8000)')
FROM yourData
CROSS APPLY x.nodes('r') s(i)
)
Insert Into Import_File_Feature
(
FeatureId,
InventoryId,
FeatureText,
FeatureGroup,
FeatureCategory,
FeatureIsAvailable,
FeatureIsStandard
)
Select
newid(),
import.InventoryId,
item, -- this is the split out item from import.Options
'',
'',
1,
1
FROM split;
OPTION 2
Get a copy of DelimitedSplit8K and use it to do your splitting.
WITH split AS
(
Select
import.InventoryId,
import.OPTIONS
From Import_File import with (nolock)
CROSS APPLY dbo.DelimitedSplit8K(import.OPTIONS, ',')
Where
import.options IS NOT NULL
And ISNULL(import.IsFeatureProcessed,0) = 0
And LEN(ISNULL(import.OPTIONS,''))>10
And import.InventoryId Is Not Null
)
Insert Into Import_File_Feature
(
FeatureId,
InventoryId,
FeatureText,
FeatureGroup,
FeatureCategory,
FeatureIsAvailable,
FeatureIsStandard
)
Select
newid(),
import.InventoryId,
item,
'',
'',
1,
1
FROM split
Note that, because I don't have any table definitions or sample data there was no way for me to test the code above.