Related
I am trying to parse out a value from a string that involves getting the last index of a string. Currently, I am doing a horrible hack that involves reversing a string:
SELECT REVERSE(SUBSTRING(REVERSE(DB_NAME()), 1,
CHARINDEX('_', REVERSE(DB_NAME()), 1) - 1))
To me this code is nearly unreadable. I just upgraded to SQL Server 2016 and I hoping there is a better way.
Is there?
If you want everything after the last _, then use:
select right(db_name(), charindex('_', reverse(db_name()) + '_') - 1)
If you want everything before, then use left():
select left(db_name(), len(db_name()) - charindex('_', reverse(db_name()) + '_'))
Wrote 2 functions, 1 to return LastIndexOf for the selected character.
CREATE FUNCTION dbo.LastIndexOf(#source nvarchar(80), #pattern char)
RETURNS int
BEGIN
RETURN (LEN(#source)) - CHARINDEX(#pattern, REVERSE(#source))
END;
GO
and 1 to return a string before this LastIndexOf. Maybe it will be useful to someone.
CREATE FUNCTION dbo.StringBeforeLastIndex(#source nvarchar(80), #pattern char)
RETURNS nvarchar(80)
BEGIN
DECLARE #lastIndex int
SET #lastIndex = (LEN(#source)) - CHARINDEX(#pattern, REVERSE(#source))
RETURN SUBSTRING(#source, 0, #lastindex + 1)
-- +1 because index starts at 0, but length at 1, so to get up to 11th index, we need LENGTH 11+1=12
END;
GO
No, SQL server doesnt have LastIndexOf.
This are the available string functions
But you can always can create your own function
CREATE FUNCTION dbo.LastIndexOf(#source text, #pattern char)
RETURNS
AS
BEGIN
DECLARE #ret text;
SELECT into #ret
REVERSE(SUBSTRING(REVERSE(#source), 1,
CHARINDEX(#pattern, REVERSE(#source), 1) - 1))
RETURN #ret;
END;
GO
Once you have one of the split strings from here,you can do it in a set based way like this..
declare #string varchar(max)
set #string='C:\Program Files\Microsoft SQL Server\MSSQL\DATA\AdventureWorks_Data.mdf'
;with cte
as
(select *,row_number() over (order by (select null)) as rownum
from [dbo].[SplitStrings_Numbers](#string,'\')
)
select top 1 item from cte order by rownum desc
**Output:**
AdventureWorks_Data.mdf
CREATE FUNCTION dbo.LastIndexOf(#text NTEXT, #delimiter NTEXT)
RETURNS INT
AS
BEGIN
IF (#text IS NULL) RETURN NULL;
IF (#delimiter IS NULL) RETURN NULL;
DECLARE #Text2 AS NVARCHAR(MAX) = #text;
DECLARE #Delimiter2 AS NVARCHAR(MAX) = #delimiter;
DECLARE #Index AS INT = CHARINDEX(REVERSE(#Delimiter2), REVERSE(#Text2));
IF (#Index < 1) RETURN 0;
DECLARE #ContentLength AS INT = (LEN('|' + #Text2 + '|') - 2);
DECLARE #DelimiterLength AS INT = (LEN('|' + #Delimiter2 + '|') - 2);
DECLARE #Result AS INT = (#ContentLength - #Index - #DelimiterLength + 2);
RETURN #Result;
END
Allows for multi-character delimiters like ", " (comma space).
Returns 0 if the delimiter is not found.
Takes a NTEXT for comfort reasons as NVARCHAR(MAX)s are implicitely cast into NTEXT but not vice-versa.
Handles delimiters with leading or tailing space correctly!
Try:
select LEN('tran van abc') + 1 - CHARINDEX(' ', REVERSE('tran van abc'))
So, the last index of ' ' is : 9
I came across this thread while searching for a solution to my similar problem which had the exact same requirement but was for a different kind of database that was lacking the REVERSE function.
In my case this was for a OpenEdge (Progress) database, which has a slightly different syntax. This made the INSTR function available to me that most Oracle typed databases offer.
So I came up with the following code:
SELECT
INSTR(foo.filepath, '/',1, LENGTH(foo.filepath) - LENGTH( REPLACE( foo.filepath, '/', ''))) AS IndexOfLastSlash
FROM foo
However, for my specific situation (being the OpenEdge (Progress) database) this did not result into the desired behaviour because replacing the character with an empty char gave the same length as the original string. This doesn't make much sense to me but I was able to bypass the problem with the code below:
SELECT
INSTR(foo.filepath, '/',1, LENGTH( REPLACE( foo.filepath, '/', 'XX')) - LENGTH(foo.filepath)) AS IndexOfLastSlash
FROM foo
Now I understand that this code won't solve the problem for T-SQL because there is no alternative to the INSTR function that offers the Occurence property.
Just to be thorough I'll add the code needed to create this scalar function so it can be used the same way like I did in the above examples. And will do exactly what the OP wanted, serve as a LastIndexOf method for SQL Server.
-- Drop the function if it already exists
IF OBJECT_ID('INSTR', 'FN') IS NOT NULL
DROP FUNCTION INSTR
GO
-- User-defined function to implement Oracle INSTR in SQL Server
CREATE FUNCTION INSTR (#str VARCHAR(8000), #substr VARCHAR(255), #start INT, #occurrence INT)
RETURNS INT
AS
BEGIN
DECLARE #found INT = #occurrence,
#pos INT = #start;
WHILE 1=1
BEGIN
-- Find the next occurrence
SET #pos = CHARINDEX(#substr, #str, #pos);
-- Nothing found
IF #pos IS NULL OR #pos = 0
RETURN #pos;
-- The required occurrence found
IF #found = 1
BREAK;
-- Prepare to find another one occurrence
SET #found = #found - 1;
SET #pos = #pos + 1;
END
RETURN #pos;
END
GO
To avoid the obvious, when the REVERSE function is available you do not need to create this scalar function and you can just get the required result like this:
SELECT
LEN(foo.filepath) - CHARINDEX('\', REVERSE(foo.filepath))+1 AS LastIndexOfSlash
FROM foo
Try this.
drop table #temp
declare #brokername1 nvarchar(max)='indiabullssecurities,canmoney,indianivesh,acumencapitalmarket,sharekhan,edelweisscapital';
Create Table #temp
(
ID int identity(1,1) not null,
value varchar(100) not null
)
INSERT INTO #temp(value) SELECT value from STRING_SPLIT(#brokername1,',')
declare #id int;
set #id=(select max(id) from #temp)
--print #id
declare #results varchar(500)
select #results = coalesce(#results + ',', '') + convert(varchar(12),value)
from #temp where id<#id
order by id
print #results
SELECT REPLACE('<strong>100</strong><b>.00 GB', '%^(^-?\d*\.{0,1}\d+$)%', '');
I want to replace any markup between two parts of the number with above regex, but it does not seem to work. I'm not sure if it is regex syntax that's wrong because I tried simpler one such as '%[^0-9]%' just to test but it didn't work either. Does anyone know how can I achieve this?
You can use PATINDEX
to find the first index of the pattern (string's) occurrence. Then use STUFF to stuff another string into the pattern(string) matched.
Loop through each row. Replace each illegal characters with what you want. In your case replace non numeric with blank. The inner loop is if you have more than one illegal character in a current cell that of the loop.
DECLARE #counter int
SET #counter = 0
WHILE(#counter < (SELECT MAX(ID_COLUMN) FROM Table))
BEGIN
WHILE 1 = 1
BEGIN
DECLARE #RetVal varchar(50)
SET #RetVal = (SELECT Column = STUFF(Column, PATINDEX('%[^0-9.]%', Column),1, '')
FROM Table
WHERE ID_COLUMN = #counter)
IF(#RetVal IS NOT NULL)
UPDATE Table SET
Column = #RetVal
WHERE ID_COLUMN = #counter
ELSE
break
END
SET #counter = #counter + 1
END
Caution: This is slow though! Having a varchar column may impact. So using LTRIM RTRIM may help a bit. Regardless, it is slow.
Credit goes to this StackOverFlow answer.
EDIT
Credit also goes to #srutzky
Edit (by #Tmdean)
Instead of doing one row at a time, this answer can be adapted to a more set-based solution. It still iterates the max of the number of non-numeric characters in a single row, so it's not ideal, but I think it should be acceptable in most situations.
WHILE 1 = 1 BEGIN
WITH q AS
(SELECT ID_Column, PATINDEX('%[^0-9.]%', Column) AS n
FROM Table)
UPDATE Table
SET Column = STUFF(Column, q.n, 1, '')
FROM q
WHERE Table.ID_Column = q.ID_Column AND q.n != 0;
IF ##ROWCOUNT = 0 BREAK;
END;
You can also improve efficiency quite a lot if you maintain a bit column in the table that indicates whether the field has been scrubbed yet. (NULL represents "Unknown" in my example and should be the column default.)
DECLARE #done bit = 0;
WHILE #done = 0 BEGIN
WITH q AS
(SELECT ID_Column, PATINDEX('%[^0-9.]%', Column) AS n
FROM Table
WHERE COALESCE(Scrubbed_Column, 0) = 0)
UPDATE Table
SET Column = STUFF(Column, q.n, 1, ''),
Scrubbed_Column = 0
FROM q
WHERE Table.ID_Column = q.ID_Column AND q.n != 0;
IF ##ROWCOUNT = 0 SET #done = 1;
-- if Scrubbed_Column is still NULL, then the PATINDEX
-- must have given 0
UPDATE table
SET Scrubbed_Column = CASE
WHEN Scrubbed_Column IS NULL THEN 1
ELSE NULLIF(Scrubbed_Column, 0)
END;
END;
If you don't want to change your schema, this is easy to adapt to store intermediate results in a table valued variable which gets applied to the actual table at the end.
Instead of stripping out the found character by its sole position, using Replace(Column, BadFoundCharacter, '') could be substantially faster. Additionally, instead of just replacing the one bad character found next in each column, this replaces all those found.
WHILE 1 = 1 BEGIN
UPDATE dbo.YourTable
SET Column = Replace(Column, Substring(Column, PatIndex('%[^0-9.-]%', Column), 1), '')
WHERE Column LIKE '%[^0-9.-]%'
If ##RowCount = 0 BREAK;
END;
I am convinced this will work better than the accepted answer, if only because it does fewer operations. There are other ways that might also be faster, but I don't have time to explore those right now.
In a general sense, SQL Server does not support regular expressions and you cannot use them in the native T-SQL code.
You could write a CLR function to do that. See here, for example.
For those looking for a performant and easy solution and are willing to enable CLR:
CREATE database TestSQLFunctions
go
use TestSQLFunctions
go
ALTER database TestSQLFunctions set trustworthy on
EXEC sp_configure 'clr enabled', 1
RECONFIGURE WITH OVERRIDE
go
CREATE ASSEMBLY [SQLFunctions]
AUTHORIZATION [dbo]
FROM 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
WITH PERMISSION_SET = SAFE
go
CREATE FUNCTION RegexReplace(
#input nvarchar(max),
#pattern nvarchar(max),
#replacement nvarchar(max)
) RETURNS nvarchar (max)
AS EXTERNAL NAME SQLFunctions.[SQLFunctions.Regex].Replace;
go
-- outputs This is a test
SELECT dbo.RegexReplace('This is a test 12345','[0-9]','')
Content of the DLL:
I stumbled across this post looking for something else but thought I'd mention a solution I use which is far more efficient - and really should be the default implementation of any function when used with a set based query - which is to use a cross applied table function. Seems the topic is still active so hopefully this is useful to someone.
Example runtime on a few of the answers so far based on running recursive set based queries or scalar function, based on 1m rows test set removing the chars from a random newid, ranges from 34s to 2m05s for the WHILE loop examples and from 1m3s to {forever} for the function examples.
Using a table function with cross apply achieves the same goal in 10s. You may need to adjust it to suit your needs such as the max length it handles.
Function:
CREATE FUNCTION [dbo].[RemoveChars](#InputUnit VARCHAR(40))
RETURNS TABLE
AS
RETURN
(
WITH Numbers_prep(Number) AS
(
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1
)
,Numbers(Number) AS
(
SELECT TOP (ISNULL(LEN(#InputUnit),0))
row_number() OVER (ORDER BY (SELECT NULL))
FROM Numbers_prep a
CROSS JOIN Numbers_prep b
)
SELECT
OutputUnit
FROM
(
SELECT
substring(#InputUnit,Number,1)
FROM Numbers
WHERE substring(#InputUnit,Number,1) like '%[0-9]%'
ORDER BY Number
FOR XML PATH('')
) Sub(OutputUnit)
)
Usage:
UPDATE t
SET column = o.OutputUnit
FROM ##t t
CROSS APPLY [dbo].[RemoveChars](t.column) o
Here is a function I wrote to accomplish this based off of the previous answers.
CREATE FUNCTION dbo.RepetitiveReplace
(
#P_String VARCHAR(MAX),
#P_Pattern VARCHAR(MAX),
#P_ReplaceString VARCHAR(MAX),
#P_ReplaceLength INT = 1
)
RETURNS VARCHAR(MAX)
BEGIN
DECLARE #Index INT;
-- Get starting point of pattern
SET #Index = PATINDEX(#P_Pattern, #P_String);
while #Index > 0
begin
--replace matching charactger at index
SET #P_String = STUFF(#P_String, PATINDEX(#P_Pattern, #P_String), #P_ReplaceLength, #P_ReplaceString);
SET #Index = PATINDEX(#P_Pattern, #P_String);
end
RETURN #P_String;
END;
[Gist][1]
[1]: https://gist.github.com/jkdba/ca13fe8f2a9855c4bdbfd0a5d3dfcda2
Edit:
Originally I had a recursive function here which does not play well with sql server as it has a 32 nesting level limit which would result in an error like the below any time you attempt to make 32+ replacements with the function. Instead of trying to make a server level change to allow more nesting (which could be dangerous like allow never ending loops) switching to a while loop makes a lot more sense.
Maximum stored procedure, function, trigger, or view nesting level exceeded (limit 32).
Wrapping the solution inside a SQL function could be useful if you want to reuse it.
I'm even doing it at the cell level, that's why I'm putting this as a different answer:
CREATE FUNCTION [dbo].[fnReplaceInvalidChars] (#string VARCHAR(300))
RETURNS VARCHAR(300)
BEGIN
DECLARE #str VARCHAR(300) = #string;
DECLARE #Pattern VARCHAR (20) = '%[^a-zA-Z0-9]%';
DECLARE #Len INT;
SELECT #Len = LEN(#String);
WHILE #Len > 0
BEGIN
SET #Len = #Len - 1;
IF (PATINDEX(#Pattern,#str) > 0)
BEGIN
SELECT #str = STUFF(#str, PATINDEX(#Pattern,#str),1,'');
END
ELSE
BEGIN
BREAK;
END
END
RETURN #str
END
A more speedy approach for large strings would look something like this:
CREATE FUNCTION [dbo].[fnReplaceInvalidChars] (#string VARCHAR(MAX))
RETURNS VARCHAR(MAX)
BEGIN
DECLARE #str VARCHAR(MAX) = #string;
DECLARE #Pattern VARCHAR (MAX) = '%[^a-zA-Z0-9]%';
WHILE PATINDEX(#Pattern,#str) > 0
BEGIN
SELECT #str = STUFF(#str, PATINDEX(#Pattern,#str),1,'');
END
RETURN #str
END
I've created this function to clean up a string that contained non numeric characters in a time field. The time contained question marks when they did not added the minutes, something like this 20:??. Function loops through each character and replaces the ? with a 0 :
CREATE FUNCTION [dbo].[CleanTime]
(
-- Add the parameters for the function here
#intime nvarchar(10)
)
RETURNS nvarchar(5)
AS
BEGIN
-- Declare the return variable here
DECLARE #ResultVar nvarchar(5)
DECLARE #char char(1)
-- Add the T-SQL statements to compute the return value here
DECLARE #i int = 1
WHILE #i <= LEN(#intime)
BEGIN
SELECT #char = CASE WHEN substring(#intime,#i,1) like '%[0-9:]%' THEN substring(#intime,#i,1) ELSE '0' END
SELECT #ResultVar = concat(#ResultVar,#char)
set #i = #i + 1
END;
-- Return the result of the function
RETURN #ResultVar
END
I think this solution is faster and simple. I use always CTE/recursive because WHILE is so slow on SQL Server.
I use it in projects I work with and large databases.
/*
Function: dbo.kSql_ReplaceRegExp
Create Date: 20.02.2021
Author: Karcan Ozbal
Description: The given string value will be replaced according to the given regexp/pattern.
Parameter(s): #Value : Value/Text to REPLACE.
#RegExp : The regexp/pattern to be used for REPLACE operation.
Usage: select dbo.kSql_ReplaceRegExp('2T3EST5','%[0-9]%')
Output: 'TEST'
*/
ALTER FUNCTION [dbo].[kSql_ReplaceRegExp](
#Value nvarchar(max),
#RegExp nvarchar(50)
)
RETURNS nvarchar(max)
AS
BEGIN
DECLARE #Result nvarchar(max)
;WITH CTE AS (
SELECT NUM = 1, VALUE = #Value, IDX = PATINDEX(#RegExp, #Value)
UNION ALL
SELECT NUM + 1, VALUE = REPLACE(VALUE, SUBSTRING(VALUE,IDX,1),''), IDX = PATINDEX(#RegExp, REPLACE(VALUE, SUBSTRING(VALUE,IDX,1),''))
FROM CTE
WHERE IDX > 0
)
SELECT TOP(1) #Result = VALUE
FROM CTE
ORDER BY NUM DESC
OPTION (maxrecursion 0)
RETURN #Result
END
If you are doing this just for a parameter coming into a Stored Procedure, you can use the following:
declare #badIndex int
set #badIndex = PatIndex('%[^0-9]%', #Param)
while #badIndex > 0
set #Param = Replace(#Param, Substring(#Param, #badIndex, 1), '')
set #badIndex = PatIndex('%[^0-9]%', #Param)
I thought this was clearer:
ALTER FUNCTION [dbo].[func_ReplaceChars](
#Value nvarchar(max),
#Chars nvarchar(50)
)
RETURNS nvarchar(max)
AS
BEGIN
DECLARE #cLen int = len(#Chars);
DECLARE #curChar int = 0;
WHILE #curChar<#cLen
BEGIN
set #Value = replace(#Value,substring(#Chars,#curChar,1),'');
set #curChar = #curChar + 1;
END;
RETURN #Value
END
I'm using this code similar to several codes above:
DROP FUNCTION [dbo].[fnCleanString]
GO
CREATE FUNCTION [dbo].[fnCleanString] (#input VARCHAR(max), #Pattern
VARCHAR (20))
RETURNS VARCHAR(max)
BEGIN
DECLARE #str VARCHAR(max) = #input;
DECLARE #Len INT;
DECLARE #INDEX INT;
SELECT #Len = LEN(#input);
WHILE #Len > 0
BEGIN
SET #INDEX = PATINDEX(#Pattern,#str);
IF (#INDEX > 0)
BEGIN
SET #str=REPLACE(#str,SUBSTRING(#str,#INDEX, 1), '');
END
ELSE
BEGIN
BREAK;
END
END
RETURN #str
END
You can use it like this:
SELECT CleanName = dbo.[fnCleanString](Name, '%[0-9]%') from YourTable
I think a simpler and faster approach is iterate by each character of the alphabet:
DECLARE #i int
SET #i = 0
WHILE(#i < 256)
BEGIN
IF char(#i) NOT IN ('0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '.')
UPDATE Table SET Column = replace(Column, char(#i), '')
SET #i = #i + 1
END
I am getting errors with the following stored procedure. I'd like to say that I am new to SQL and currently not up to par yet but anyway, here is the values I'm passing:
USE [AFCache]
GO
DECLARE #return_value int
EXEC #return_value = [dbo].[csp_WellTestValidationResults_GetData]
#ColumnName = N'API14-2',
#ColumnValue = N'60811404740101-60811404740102'
SELECT 'Return Value' = #return_value
GO
and here is the actual stored procedure:
ALTER PROCEDURE [dbo].[csp_WellTestValidationResults_GetData]
-- Declare variables that will get data passed from PIAF to query data
(#ColumnName varchar(max) = 'Blank',
#ColumnValue varchar(max) = 'Blank')
AS
BEGIN
SET NOCOUNT ON;
IF (#ColumnName = 'API14-2')
BEGIN
DECLARE #APIStrip varchar(max);
SET #APIStrip = SUBSTRING(#ColumnName, 0, CHARINDEX('- ', #ColumnName, 0));
DECLARE #LeftNumber varchar(max);
SET #LeftNumber = SUBSTRING(#ColumnValue, 0, CHARINDEX('-', #ColumnValue, 0));
DECLARE #RightNumber varchar(max)
SET #RightNumber = SUBSTRING(#ColumnValue, CHARINDEX('-', #ColumnValue, 0) + 1, LEN(#ColumnValue));
EXEC('Select * from dbo.SSIS_RTRM_WellTestValidationResults where '+#APIStrip+' = '+#LeftNumber+' OR '+#APIStrip+' = '+#RightNumber+' order by TestDate Desc')
END
IF (#ColumnName = 'API14')
BEGIN
EXEC('Select * from dbo.SSIS_RTRM_WellTestValidationResults where '+#ColumnName+' = '''+#ColumnValue+''' order by AssetName, ReservoirName, API14, TestDate Desc')
END
IF (#ColumnName <>'AssetName') or (#ColumnName <>'ReservoirName') or (#ColumnName <>'FieldName')
BEGIN
EXEC('Select wtvv.* from dbo.SSIS_RTRM_WellTestValidationResults wtvv join '+'(select WellId, Max(TestDate) AS TestDate from dbo.SSIS_RTRM_WellTestValidationResults wtv group by WellId)'+' wtvv1 on wtvv1.WellId = wtvv.WellId and wtvv1.TestDate = wtvv.TestDate where '+#ColumnName+' = '''+#ColumnValue+''' order by AssetName, ReservoirName, API14')
END
IF (#ColumnName <>'AssetName') or (#ColumnName <>'ReservoirName') or (#ColumnName<> 'FieldName')or (#ColumnName <>'API14-2')or (#ColumnName <>'API')
BEGIN
SELECT *
FROM dbo.SSIS_RTRM_WellTestValidationResults
WHERE WellId = ''
END
END
When I execute the query I keep getting the following error:
Msg 248, Level 16, State 1, Line 1
The conversion of the varchar value '60811404740101-60811404740102' overflowed an int column.
I have gone through the code and I don’t understand where is my problem and why am I getting this error.
Looks like the SSIS_RTRM_WellTestValidationResults table has an int column for API14-2. It would help if you posted your table schema as well.
Without seeing your table schema I can only presume your using a standard int data type for API14 column. Looking at your code your splitting the large number on the dash (-). This is leaving you with the number 60,811,404,740,101 and 60,811,404,740,102 for the left and right sides. This far exceeds the max int value of 2,147,483,647. You will need to update your column data type to be bigint which has a max value of 9,223,372,036,854,775,807
Try replacing this line:
DECLARE #return_value int
With this:
DECLARE #return_value [numeric](18, 0)
i have a code like this
create function factfind(#num integer)
returns integer
as
begin
if (#num=1) then
return 1;
else
return(#num*factfind(#num-1));
end if;
end
errors was that,
Msg 156, Level 15, State 1, Procedure factfind, Line 5
Incorrect syntax near the keyword 'then'.
Msg 156, Level 15, State 1, Procedure factfind, Line 7
Incorrect syntax near the keyword 'else'.
Msg 195, Level 15, State 10, Procedure factfind, Line 8
'factfind' is not a recognized built-in function name.
please help me friends.
...
begin
return ( CASE
WHEN #num=1 THEN 1
ELSE #num * dbo.factfind(#num-1)
END
);
end
Edit: needs to be dbo.factfind because scalar udfs must be schema qualified
Execute this:
CREATE FUNCTION dbo.fakultät(#n DECIMAL(38,0))
RETURNS DECIMAL(38,0)
AS
BEGIN
DECLARE #tmp DECIMAL(38,0)
IF (#n <= 1)
SELECT #tmp = 1
ELSE
SELECT #tmp = #n * dbo.fakultät(#n - 1)
RETURN #tmp
END
or:
CREATE FUNCTION dbo.Factorial ( #iNumber int )
RETURNS INT
AS
BEGIN
DECLARE #i int
IF #iNumber <= 1
SET #i = 1
ELSE
SET #i = #iNumber * dbo.Factorial( #iNumber - 1 )
RETURN (#i)
END
The problem you have is in part the syntax of the if statement in TSQL, the right thing to do is:
create function factfind(#num integer)
returns integer
as
begin
declare #Result int
set #Result = 1
if (#num>1)
set #Result = #num * dbo.factfind(#num-1);
return #Result
end
Say that the raw text of CSV exports and an associated timestamps are stored in a database, where one record is equivalent to one export.
Does anyone have a way to execute a query on the CSV file stored in that field without creating a second connection to the database or exporting the data to a file and then reopening it using the csv text driver?
Assume that:
1) you can't write out a physical file onto the server in the solution
2) you can't a second connection to the server w/ OPENROWSET (servers, usernames & passwords change)
3) that it must be a 100% SQL solution - must be able to be run as an SP
4) that you only need to work with one record at time - the solution doesn't need to account for selecting from multiple csv files stored in the DB.
My solution would be to create a UDF that will parse the CSV data into a table variable. Then, in the SP, retrieve the CSV, pass it to the UDF, then run the query against the table variable.
First, create a UDF to return a table from the CSV value (uses CHAR(13) to determine new lines, may need to be altered to work with your data):
CREATE FUNCTION [dbo].[fnParseCSV] (#InputString NVARCHAR(MAX), #Delimiter NCHAR(1) = ',')
RETURNS #tbl TABLE (ID int, Val NVARCHAR(64)) AS
BEGIN
declare #singleLine nvarchar(max)
declare #id int
declare #val varchar(64)
WHILE LEN(#InputString) > 0 BEGIN
IF CHARINDEX(char(13), #InputString) > 0 BEGIN
SELECT #singleLine = SUBSTRING(#InputString, 1, CHARINDEX(char(13), #InputString) - 1)
IF CHARINDEX(#Delimiter, #singleline) > 0 BEGIN
SELECT #id = convert(int, SUBSTRING(#singleline, 1, CHARINDEX(#Delimiter, #singleline) - 1))
SELECT #val = RIGHT(#singleline, LEN(#singleline) - CHARINDEX(#Delimiter, #singleline) )
INSERT INTO #tbl (id, val) values (#id, #val)
END
SELECT #InputString = RIGHT(#InputString, LEN(#InputString) - CHARINDEX(char(13), #InputString) )
END
ELSE
BEGIN
IF CHARINDEX(#Delimiter, #inputString) > 0
BEGIN
SELECT #id = convert(int, SUBSTRING(#inputString, 1, CHARINDEX(#Delimiter, #inputString) - 1))
SELECT #val = RIGHT(#inputString, LEN(#inputString) - CHARINDEX(#Delimiter, #inputString) )
INSERT INTO #tbl (id, val) values (#id, #val)
END
set #inputString = ''
END
END
RETURN
END
Then run the query against that output:
select * from dbo.fnParseCsv('123,val1' + char(13) + '456,val2' + CHAR(13) + '789,val3', ',')
You could set up a series of user-defined functions which could parse through the column. It would likely be slow and wouldn't be robust at all.
As an example though (with no real error checking, etc. and only minimally tested):
IF OBJECT_ID('dbo.Test_CSV_Search') IS NOT NULL
DROP TABLE dbo.Test_CSV_Search
GO
CREATE TABLE dbo.Test_CSV_Search
(
my_id INT IDENTITY NOT NULL,
txt VARCHAR(MAX) NOT NULL,
CONSTRAINT PK_Test_CSV_Search PRIMARY KEY CLUSTERED (my_id)
)
GO
INSERT INTO dbo.Test_CSV_Search (txt) VALUES ('11, 12, 13, 14,15,16
21,22, 23,24, 25,26
31,22,33,34,35,36')
GO
IF OBJECT_ID('dbo.Get_CSV_Row') IS NOT NULL
DROP FUNCTION dbo.Get_CSV_Row
GO
CREATE FUNCTION dbo.Get_CSV_Row
(#my_id INT, #col_num SMALLINT, #search_value VARCHAR(100))
RETURNS #results TABLE (row_num INT, row_txt VARCHAR(MAX))
AS
BEGIN
DECLARE
#csv_txt VARCHAR(MAX),
#full_row VARCHAR(MAX),
#start_pos INT,
#end_pos INT,
#col_txt VARCHAR(100),
#cur_col SMALLINT,
#line_start INT,
#line_end INT,
#row_num INT
SELECT #csv_txt = txt + CHAR(10) FROM dbo.Test_CSV_Search WHERE my_id = #my_id
SELECT
#line_start = 1,
#cur_col = 1,
#start_pos = 1,
#row_num = 1
WHILE (CHARINDEX(CHAR(10), #csv_txt, #line_start) > 0)
BEGIN
SELECT
#line_end = CHARINDEX(CHAR(10), #csv_txt, #line_start),
#end_pos = CHARINDEX(',', #csv_txt, #start_pos)
WHILE (#cur_col < #col_num)
BEGIN
SET #start_pos = #end_pos + 1
SET #end_pos = CHARINDEX(',', #csv_txt, #start_pos)
SET #cur_col = #cur_col + 1
END
IF (RTRIM(LTRIM(SUBSTRING(#csv_txt, #start_pos, #end_pos - #start_pos))) = #search_value)
BEGIN
INSERT INTO #results (row_num, row_txt) VALUES (#row_num, RTRIM(LTRIM(SUBSTRING(#csv_txt, #line_start, #line_end - #line_start))))
END
SELECT
#line_start = #line_end + 1,
#start_pos = #line_end + 1,
#cur_col = 1,
#row_num = #row_num + 1
END
RETURN
END
GO
SELECT * FROM dbo.Get_CSV_Row(1, 1, '11')