I have a use case where my SQL Script is having a variable with comma separated values.
whitelistURL = abc.com,xyz.com
I have to run insert command on all the values of the variable. Something like split with comma and run insert on abc.com and insert on xyz.com
Can someone please suggest the best way to do it. I am new to SQL.
I am using SQL Server 2014.
Try this:
declare #whitelistURL varchar(100) = 'abc.com,xyz.com,xyz.com,'
--set #whitelistURL = #whitelistURL + ','
;with cte as(
select charindex(',', #whitelistURL) [n], SUBSTRING(#whitelistURL, 1,
charindex(',', #whitelistURL) - 1) [url]
union all
select charindex(',', #whitelistURL, n + 1), SUBSTRING(#whitelistURL, n + 1, charindex(',', #whitelistURL, n + 1) - n - 1) from cte
where charindex(',', #whitelistURL, n + 1) > 0
)
select [url] from cte
Only thing to note is that processed string should have delimeter (comma) also at the end, but if it doesn't, just append it, as I did in commented line.
Then insert statement becomes really easy:
insert into MY_TABLE (url) values
select url from cte
You can use a custom split function. There are a lot of implementations of these functions on the web, here is an example:
CREATE FUNCTION [dbo].[fn_Split] (#Text nvarchar(MAX), #Delim char(1))
RETURNS #Values TABLE (Value nvarchar(MAX))
AS
BEGIN
SET #Text = RTRIM(LTRIM(#Text))
DECLARE #chrind int
DECLARE #Piece nvarchar(100)
SELECT #chrind = 1
WHILE #chrind > 0
BEGIN
SELECT #chrind = CHARINDEX(#Delim, #Text)
IF #chrind > 0
SELECT #Piece = RTRIM(LTRIM(LEFT(#Text, #chrind - 1)))
ELSE
SELECT #Piece = RTRIM(LTRIM(#Text))
INSERT #Values(Value) VALUES(CAST(#Piece as varchar(100)))
SELECT #Text = RIGHT(#Text, LEN(#Text) - #chrind)
IF LEN(#Text) = 0 BREAK
END
RETURN
END
This function takes two parameters:
the string to split (in your case 'abc.com,xyz.com,xyz.com,')
the separator (in your case ',')
Now that you have your split function you can use it like this:
select [Value] from [dbo].[fn_Split]('abc.com,xyz.com',',')
This is the output of this command:
You can now combine this with an insert statement:
insert into YOUR_TABLE_NAME(YOUR_COLUMN_NAME)
select [Value] from [dbo].[fn_Split]('abc.com,xyz.com',',')
I have a table on an external site that I need to copy to a local DB, but with some transformations. One of the columns I have to heavily modify is called product_url. The URL is in the form site.com\category\sub-category\brand\model#.
The table in my local db will have 4 columns to hold this data. They will be category, sub-category, brand and model#. So, I will have to first trim the site.com (I did this using truncate), but now I have to parse \category\sub-category\brand\model#
I found a UDF from SO that I think will help out. Here it is:
create function dbo.SplitString
(
#str nvarchar(4000),
#separator char(1)
)
returns table
AS
return (
with tokens(p, a, b) AS (
select
1,
1,
charindex(#separator, #str)
union all
select
p + 1,
b + 1,
charindex(#separator, #str, b + 1)
from tokens
where b > 0
)
select
p-1 zeroBasedOccurance,
substring(
#str,
a,
case when b > 0 then b-a ELSE 4000 end)
AS s
from tokens
)
GO
Now I am having trouble using this function. Probably due to my lack of experience with UDF's.
Here is what I have now:
select s from
dbo.SplitString(select substring(product_url, 8, len(product_url))
from Products, '/')
where zeroBasedOccurance=0 AS Category
This is obviously not even syntactically correct.
I am wondering if I am going about this the best way. I am not yet much of a DBA, so I am having a hard time wrapping my head around this issue. I just need to figure out how to apply this UDF ~4 times for each row in the product_url table.
Not sure about your function, but here is mine:
CREATE FUNCTION dbo.FN_PARSENAME(#chunk VARCHAR(4000), #delimiter CHAR(1), #index INT )
RETURNS VARCHAR(1000)
AS
BEGIN
DECLARE
#curIndex INT = 0,
#pos INT = 1,
#prevPos INT = 0,
#result VARCHAR(1000)
WHILE #pos > 0
BEGIN
SET #pos = CHARINDEX(#delimiter, #chunk, #prevPos);
IF(#pos > 0)
BEGIN -- Characters between position and previous position
SET #result = SUBSTRING(#chunk, #prevPos, #pos-#prevPos)
END
ELSE
BEGIN -- Last Delim
SET #result = SUBSTRING(#chunk, #prevPos, LEN(#chunk))
END
IF(#index = #curIndex)
BEGIN
RETURN #result
END
SET #prevPos = #pos + 1
SET #curIndex = #curIndex + 1;
END
RETURN '' -- Else Empty
END
You call it as such:
SELECT Address_Line1 = dbo.fn_Parsename(Merged,'|', 0)
FROM Table
Wherein Merged is the field that is delimited, the '|' is the delimiter, so you would make it '\', and the 0 is which portion of the string you want, 0 being the first, on up.
For your example it would be:
SELECT category = dbo.fn_Parsename(product_url,'\', 1)
, sub-category = dbo.fn_Parsename(product_url,'\', 2)
, brand = dbo.fn_Parsename(product_url,'\', 3)
, model# = dbo.fn_Parsename(product_url,'\', 4)
FROM Table
Or maybe 0-3 depending.
I'm pretty confident I adapted that from something I found, perhaps even on SO, but I can't recall who would deserve credit.
I have data like this:
string 1: 003Preliminary Examination Plan
string 2: Coordination005
string 3: Balance1000sheet
The output I expect is
string 1: 003
string 2: 005
string 3: 1000
And I want to implement it in SQL.
First create this UDF
CREATE FUNCTION dbo.udf_GetNumeric
(
#strAlphaNumeric VARCHAR(256)
)
RETURNS VARCHAR(256)
AS
BEGIN
DECLARE #intAlpha INT
SET #intAlpha = PATINDEX('%[^0-9]%', #strAlphaNumeric)
BEGIN
WHILE #intAlpha > 0
BEGIN
SET #strAlphaNumeric = STUFF(#strAlphaNumeric, #intAlpha, 1, '' )
SET #intAlpha = PATINDEX('%[^0-9]%', #strAlphaNumeric )
END
END
RETURN ISNULL(#strAlphaNumeric,0)
END
GO
Now use the function as
SELECT dbo.udf_GetNumeric(column_name)
from table_name
SQL FIDDLE
I hope this solved your problem.
Reference
Try this one -
Query:
DECLARE #temp TABLE
(
string NVARCHAR(50)
)
INSERT INTO #temp (string)
VALUES
('003Preliminary Examination Plan'),
('Coordination005'),
('Balance1000sheet')
SELECT LEFT(subsrt, PATINDEX('%[^0-9]%', subsrt + 't') - 1)
FROM (
SELECT subsrt = SUBSTRING(string, pos, LEN(string))
FROM (
SELECT string, pos = PATINDEX('%[0-9]%', string)
FROM #temp
) d
) t
Output:
----------
003
005
1000
Query:
DECLARE #temp TABLE
(
string NVARCHAR(50)
)
INSERT INTO #temp (string)
VALUES
('003Preliminary Examination Plan'),
('Coordination005'),
('Balance1000sheet')
SELECT SUBSTRING(string, PATINDEX('%[0-9]%', string), PATINDEX('%[0-9][^0-9]%', string + 't') - PATINDEX('%[0-9]%',
string) + 1) AS Number
FROM #temp
Please try:
declare #var nvarchar(max)='Balance1000sheet'
SELECT LEFT(Val,PATINDEX('%[^0-9]%', Val+'a')-1) from(
SELECT SUBSTRING(#var, PATINDEX('%[0-9]%', #var), LEN(#var)) Val
)x
Getting only numbers from a string can be done in a one-liner.
Try this :
SUBSTRING('your-string-here', PATINDEX('%[0-9]%', 'your-string-here'), LEN('your-string-here'))
NB: Only works for the first int in the string, ex: abc123vfg34 returns 123.
I found this approach works about 3x faster than the top voted answer. Create the following function, dbo.GetNumbers:
CREATE FUNCTION dbo.GetNumbers(#String VARCHAR(8000))
RETURNS VARCHAR(8000)
AS
BEGIN;
WITH
Numbers
AS (
--Step 1.
--Get a column of numbers to represent
--every character position in the #String.
SELECT 1 AS Number
UNION ALL
SELECT Number + 1
FROM Numbers
WHERE Number < LEN(#String)
)
,Characters
AS (
SELECT Character
FROM Numbers
CROSS APPLY (
--Step 2.
--Use the column of numbers generated above
--to tell substring which character to extract.
SELECT SUBSTRING(#String, Number, 1) AS Character
) AS c
)
--Step 3.
--Pattern match to return only numbers from the CTE
--and use STRING_AGG to rebuild it into a single string.
SELECT #String = STRING_AGG(Character,'')
FROM Characters
WHERE Character LIKE '[0-9]'
--allows going past the default maximum of 100 loops in the CTE
OPTION (MAXRECURSION 8000)
RETURN #String
END
GO
Testing
Testing for purpose:
SELECT dbo.GetNumbers(InputString) AS Numbers
FROM ( VALUES
('003Preliminary Examination Plan') --output: 003
,('Coordination005') --output: 005
,('Balance1000sheet') --output: 1000
,('(111) 222-3333') --output: 1112223333
,('1.38hello#f00.b4r#\-6') --output: 1380046
) testData(InputString)
Testing for performance:
Start off setting up the test data...
--Add table to hold test data
CREATE TABLE dbo.NumTest (String VARCHAR(8000))
--Make an 8000 character string with mix of numbers and letters
DECLARE #Num VARCHAR(8000) = REPLICATE('12tf56se',800)
--Add this to the test table 500 times
DECLARE #n INT = 0
WHILE #n < 500
BEGIN
INSERT INTO dbo.NumTest VALUES (#Num)
SET #n = #n +1
END
Now testing the dbo.GetNumbers function:
SELECT dbo.GetNumbers(NumTest.String) AS Numbers
FROM dbo.NumTest -- Time to complete: 1 min 7s
Then testing the UDF from the top voted answer on the same data.
SELECT dbo.udf_GetNumeric(NumTest.String)
FROM dbo.NumTest -- Time to complete: 3 mins 12s
Inspiration for dbo.GetNumbers
Decimals
If you need it to handle decimals, you can use either of the following approaches, I found no noticeable performance differences between them.
change '[0-9]' to '[0-9.]'
change Character LIKE '[0-9]' to ISNUMERIC(Character) = 1 (SQL treats a single decimal point as "numeric")
Bonus
You can easily adapt this to differing requirements by swapping out WHERE Character LIKE '[0-9]' with the following options:
WHERE Letter LIKE '[a-zA-Z]' --Get only letters
WHERE Letter LIKE '[0-9a-zA-Z]' --Remove non-alphanumeric
WHERE Letter LIKE '[^0-9a-zA-Z]' --Get only non-alphanumeric
With the previous queries I get these results:
'AAAA1234BBBB3333' >>>> Output: 1234
'-çã+0!\aº1234' >>>> Output: 0
The code below returns All numeric chars:
1st output: 12343333
2nd output: 01234
declare #StringAlphaNum varchar(255)
declare #Character varchar
declare #SizeStringAlfaNumerica int
declare #CountCharacter int
set #StringAlphaNum = 'AAAA1234BBBB3333'
set #SizeStringAlfaNumerica = len(#StringAlphaNum)
set #CountCharacter = 1
while isnumeric(#StringAlphaNum) = 0
begin
while #CountCharacter < #SizeStringAlfaNumerica
begin
if substring(#StringAlphaNum,#CountCharacter,1) not like '[0-9]%'
begin
set #Character = substring(#StringAlphaNum,#CountCharacter,1)
set #StringAlphaNum = replace(#StringAlphaNum, #Character, '')
end
set #CountCharacter = #CountCharacter + 1
end
set #CountCharacter = 0
end
select #StringAlphaNum
declare #puvodni nvarchar(20)
set #puvodni = N'abc1d8e8ttr987avc'
WHILE PATINDEX('%[^0-9]%', #puvodni) > 0 SET #puvodni = REPLACE(#puvodni, SUBSTRING(#puvodni, PATINDEX('%[^0-9]%', #puvodni), 1), '' )
SELECT #puvodni
A solution for SQL Server 2017 and later, using TRANSLATE:
DECLARE #T table (string varchar(50) NOT NULL);
INSERT #T
(string)
VALUES
('003Preliminary Examination Plan'),
('Coordination005'),
('Balance1000sheet');
SELECT
result =
REPLACE(
TRANSLATE(
T.string COLLATE Latin1_General_CI_AI,
'abcdefghijklmnopqrstuvwxyz',
SPACE(26)),
SPACE(1),
SPACE(0))
FROM #T AS T;
Output:
result
003
005
1000
The code works by:
Replacing characters a-z (ignoring case & accents) with a space
Replacing spaces with an empty string.
The string supplied to TRANSLATE can be expanded to include additional characters.
I did not have rights to create functions but had text like
["blahblah012345679"]
And needed to extract the numbers out of the middle
Note this assumes the numbers are grouped together and not at the start and end of the string.
select substring(column_name,patindex('%[0-9]%', column_name),patindex('%[0-9][^0-9]%', column_name)-patindex('%[0-9]%', column_name)+1)
from table name
Although this is an old thread its the first in google search, I came up with a different answer than what came before. This will allow you to pass your criteria for what to keep within a string, whatever that criteria might be. You can put it in a function to call over and over again if you want.
declare #String VARCHAR(MAX) = '-123. a 456-78(90)'
declare #MatchExpression VARCHAR(255) = '%[0-9]%'
declare #return varchar(max)
WHILE PatIndex(#MatchExpression, #String) > 0
begin
set #return = CONCAT(#return, SUBSTRING(#string,patindex(#matchexpression, #string),1))
SET #String = Stuff(#String, PatIndex(#MatchExpression, #String), 1, '')
end
select (#return)
This UDF will work for all types of strings:
CREATE FUNCTION udf_getNumbersFromString (#string varchar(max))
RETURNS varchar(max)
AS
BEGIN
WHILE #String like '%[^0-9]%'
SET #String = REPLACE(#String, SUBSTRING(#String, PATINDEX('%[^0-9]%', #String), 1), '')
RETURN #String
END
Just a little modification to #Epsicron 's answer
SELECT SUBSTRING(string, PATINDEX('%[0-9]%', string), PATINDEX('%[0-9][^0-9]%', string + 't') - PATINDEX('%[0-9]%',
string) + 1) AS Number
FROM (values ('003Preliminary Examination Plan'),
('Coordination005'),
('Balance1000sheet')) as a(string)
no need for a temporary variable
Firstly find out the number's starting length then reverse the string to find out the first position again(which will give you end position of number from the end). Now if you deduct 1 from both number and deduct it from string whole length you'll get only number length. Now get the number using SUBSTRING
declare #fieldName nvarchar(100)='AAAA1221.121BBBB'
declare #lenSt int=(select PATINDEX('%[0-9]%', #fieldName)-1)
declare #lenEnd int=(select PATINDEX('%[0-9]%', REVERSE(#fieldName))-1)
select SUBSTRING(#fieldName, PATINDEX('%[0-9]%', #fieldName), (LEN(#fieldName) - #lenSt -#lenEnd))
T-SQL function to read all the integers from text and return the one at the indicated index, starting from left or right, also using a starting search term (optional):
create or alter function dbo.udf_number_from_text(
#text nvarchar(max),
#search_term nvarchar(1000) = N'',
#number_position tinyint = 1,
#rtl bit = 0
) returns int
as
begin
declare #result int = 0;
declare #search_term_index int = 0;
if #text is null or len(#text) = 0 goto exit_label;
set #text = trim(#text);
if len(#text) = len(#search_term) goto exit_label;
if len(#search_term) > 0
begin
set #search_term_index = charindex(#search_term, #text);
if #search_term_index = 0 goto exit_label;
end;
if #search_term_index > 0
if #rtl = 0
set #text = trim(right(#text, len(#text) - #search_term_index - len(#search_term) + 1));
else
set #text = trim(left(#text, #search_term_index - 1));
if len(#text) = 0 goto exit_label;
declare #patt_number nvarchar(10) = '%[0-9]%';
declare #patt_not_number nvarchar(10) = '%[^0-9]%';
declare #number_start int = 1;
declare #number_end int;
declare #found_numbers table (id int identity(1,1), val int);
while #number_start > 0
begin
set #number_start = patindex(#patt_number, #text);
if #number_start > 0
begin
if #number_start = len(#text)
begin
insert into #found_numbers(val)
select cast(substring(#text, #number_start, 1) as int);
break;
end;
else
begin
set #text = right(#text, len(#text) - #number_start + 1);
set #number_end = patindex(#patt_not_number, #text);
if #number_end = 0
begin
insert into #found_numbers(val)
select cast(#text as int);
break;
end;
else
begin
insert into #found_numbers(val)
select cast(left(#text, #number_end - 1) as int);
if #number_end = len(#text)
break;
else
begin
set #text = trim(right(#text, len(#text) - #number_end));
if len(#text) = 0 break;
end;
end;
end;
end;
end;
if #rtl = 0
select #result = coalesce(a.val, 0)
from (select row_number() over (order by m.id asc) as c_row, m.val
from #found_numbers as m) as a
where a.c_row = #number_position;
else
select #result = coalesce(a.val, 0)
from (select row_number() over (order by m.id desc) as c_row, m.val
from #found_numbers as m) as a
where a.c_row = #number_position;
exit_label:
return #result;
end;
Example:
select dbo.udf_number_from text(N'Text text 10 text, 25 term', N'term',2,1);
returns 10;
This is one of the simplest and easiest one. This will work on the entire String for multiple occurences as well.
CREATE FUNCTION dbo.fn_GetNumbers(#strInput NVARCHAR(500))
RETURNS NVARCHAR(500)
AS
BEGIN
DECLARE #strOut NVARCHAR(500) = '', #intCounter INT = 1
WHILE #intCounter <= LEN(#strInput)
BEGIN
SELECT #strOut = #strOut + CASE WHEN SUBSTRING(#strInput, #intCounter, 1) LIKE '[0-9]' THEN SUBSTRING(#strInput, #intCounter, 1) ELSE '' END
SET #intCounter = #intCounter + 1
END
RETURN #strOut
END
Following a solution using a single common table expression (CTE).
DECLARE #s AS TABLE (id int PRIMARY KEY, value nvarchar(max));
INSERT INTO #s
VALUES
(1, N'003Preliminary Examination Plan'),
(2, N'Coordination005'),
(3, N'Balance1000sheet');
SELECT * FROM #s ORDER BY id;
WITH t AS (
SELECT
id,
1 AS i,
SUBSTRING(value, 1, 1) AS c
FROM
#s
WHERE
LEN(value) > 0
UNION ALL
SELECT
t.id,
t.i + 1 AS i,
SUBSTRING(s.value, t.i + 1, 1) AS c
FROM
t
JOIN #s AS s ON t.id = s.id
WHERE
t.i < LEN(s.value)
)
SELECT
id,
STRING_AGG(c, N'') WITHIN GROUP (ORDER BY i ASC) AS value
FROM
t
WHERE
c LIKE '[0-9]'
GROUP BY
id
ORDER BY
id;
DECLARE #index NVARCHAR(20);
SET #index = 'abd565klaf12';
WHILE PATINDEX('%[0-9]%', #index) != 0
BEGIN
SET #index = REPLACE(#index, SUBSTRING(#index, PATINDEX('%[0-9]%', #index), 1), '');
END
SELECT #index;
One can replace [0-9] with [a-z] if numbers only are wanted with desired castings using the CAST function.
If we use the User Define Function, the query speed will be greatly reduced. This code extracts the number from the string....
SELECT
Reverse(substring(Reverse(rtrim(ltrim( substring([FieldName] , patindex('%[0-9]%', [FieldName] ) , len([FieldName]) )))) , patindex('%[0-9]%', Reverse(rtrim(ltrim( substring([FieldName] , patindex('%[0-9]%', [FieldName] ) , len([FieldName]) )))) ), len(Reverse(rtrim(ltrim( substring([FieldName] , patindex('%[0-9]%', [FieldName] ) , len([FieldName]) ))))) )) NumberValue
FROM dbo.TableName
CREATE OR REPLACE FUNCTION count_letters_and_numbers(input_string TEXT)
RETURNS TABLE (letters INT, numbers INT) AS $$
BEGIN
RETURN QUERY SELECT
sum(CASE WHEN input_string ~ '[A-Za-z]' THEN 1 ELSE 0 END) as letters,
sum(CASE WHEN input_string ~ '[0-9]' THEN 1 ELSE 0 END) as numbers
FROM unnest(string_to_array(input_string, '')) as input_string;
END;
$$ LANGUAGE plpgsql;
For the hell of it...
This solution is different to all earlier solutions, viz:
There is no need to create a function
There is no need to use pattern matching
There is no need for a temporary table
This solution uses a recursive common table expression (CTE)
But first - note the question does not specify where such strings are stored. In my solution below, I create a CTE as a quick and dirty way to put these strings into some kind of "source table".
Note also - this solution uses a recursive common table expression (CTE) - so don't get confused by the usage of two CTEs here. The first is simply to make the data avaliable to the solution - but it is only the second CTE that is required in order to solve this problem. You can adapt the code to make this second CTE query your existing table, view, etc.
Lastly - my coding is verbose, trying to use column and CTE names that explain what is going on and you might be able to simplify this solution a little. I've added in a few pseudo phone numbers with some (expected and atypical, as the case may be) formatting for the fun of it.
with SOURCE_TABLE as (
select '003Preliminary Examination Plan' as numberString
union all select 'Coordination005' as numberString
union all select 'Balance1000sheet' as numberString
union all select '1300 456 678' as numberString
union all select '(012) 995 8322 ' as numberString
union all select '073263 6122,' as numberString
),
FIRST_CHAR_PROCESSED as (
select
len(numberString) as currentStringLength,
isNull(cast(try_cast(replace(left(numberString, 1),' ','z') as tinyint) as nvarchar),'') as firstCharAsNumeric,
cast(isNull(cast(try_cast(nullIf(left(numberString, 1),'') as tinyint) as nvarchar),'') as nvarchar(4000)) as newString,
cast(substring(numberString,2,len(numberString)) as nvarchar) as remainingString
from SOURCE_TABLE
union all
select
len(remainingString) as currentStringLength,
cast(try_cast(replace(left(remainingString, 1),' ','z') as tinyint) as nvarchar) as firstCharAsNumeric,
cast(isNull(newString,'') as nvarchar(3999)) + isNull(cast(try_cast(nullIf(left(remainingString, 1),'') as tinyint) as nvarchar(1)),'') as newString,
substring(remainingString,2,len(remainingString)) as remainingString
from FIRST_CHAR_PROCESSED fcp2
where fcp2.currentStringLength > 1
)
select
newString
,* -- comment this out when required
from FIRST_CHAR_PROCESSED
where currentStringLength = 1
So what's going on here?
Basically in our CTE we are selecting the first character and using try_cast (see docs) to cast it to a tinyint (which is a large enough data type for a single-digit numeral). Note that the type-casting rules in SQL Server say that an empty string (or a space, for that matter) will resolve to zero, so the nullif is added to force spaces and empty strings to resolve to null (see discussion) (otherwise our result would include a zero character any time a space is encountered in the source data).
The CTE also returns everything after the first character - and that becomes the input to our recursive call on the CTE; in other words: now let's process the next character.
Lastly, the field newString in the CTE is generated (in the second SELECT) via concatenation. With recursive CTEs the data type must match between the two SELECT statements for any given column - including the column size. Because we know we are adding (at most) a single character, we are casting that character to nvarchar(1) and we are casting the newString (so far) as nvarchar(3999). Concatenated, the result will be nvarchar(4000) - which matches the type casting we carry out in the first SELECT.
If you run this query and exclude the WHERE clause, you'll get a sense of what's going on - but the rows may be in a strange order. (You won't necessarily see all rows relating to a single input value grouped together - but you should still be able to follow).
Hope it's an interesting option that may help a few people wanting a strictly expression-based solution.
In Oracle
You can get what you want using this:
SUBSTR('ABCD1234EFGH',REGEXP_INSTR ('ABCD1234EFGH', '[[:digit:]]'),REGEXP_COUNT ('ABCD1234EFGH', '[[:digit:]]'))
Sample Query:
SELECT SUBSTR('003Preliminary Examination Plan ',REGEXP_INSTR ('003Preliminary Examination Plan ', '[[:digit:]]'),REGEXP_COUNT ('003Preliminary Examination Plan ', '[[:digit:]]')) SAMPLE1,
SUBSTR('Coordination005',REGEXP_INSTR ('Coordination005', '[[:digit:]]'),REGEXP_COUNT ('Coordination005', '[[:digit:]]')) SAMPLE2,
SUBSTR('Balance1000sheet',REGEXP_INSTR ('Balance1000sheet', '[[:digit:]]'),REGEXP_COUNT ('Balance1000sheet', '[[:digit:]]')) SAMPLE3 FROM DUAL
If you are using Postgres and you have data like '2000 - some sample text' then try substring and position combination, otherwise if in your scenario there is no delimiter, you need to write regex:
SUBSTRING(Column_name from 0 for POSITION('-' in column_name) - 1) as
number_column_name
I have 2 string in input for example '1,5,6' and '2,89,9' with same number of element (3 or plus).
Those 2 string i want made a "ordinate join" as
1 2
5 89
6 9
i have think to assign a rownumber and made a join between 2 result set as
SELECT a.item, b.item FROM
(
SELECT
ROW_NUMBER() OVER (ORDER BY (SELECT 0)) AS rownumber,
* FROM dbo.Split('1,5,6',',')
) AS a
INNER JOIN
(
SELECT
ROW_NUMBER() OVER (ORDER BY (SELECT 0)) AS rownumber,
* FROM dbo.Split('2,89,9',',')
) AS b ON a.rownumber = b.rownumber
is that a best practice ever?
When dbo.Split() returns the data-set, nothing you do can assign the row_number you want (based on their order in the string) with absolute certainty. SQL never guarantees an ordering without an ORDER BY that actually relates to the data.
With you trick of using (SELECT 0) to order by you may often get the right values. Probably very often. But this is never guaranteed. Once in a while you will get the wrong order.
Your best option is to recode dbo.Split() to assign a row_number as the string is parsed. Only then can you know with 100% certainty that the row_number really does correspond to the item's position in the list.
Then you join them as you suggest, and get the results you want.
Other than that, the idea does seem fine to me. Though you may wish to consider a FULL OUTER JOIN if one list can be longer than the other.
You can do it like this as well
Consider your split function like this:
CREATE FUNCTION Split
(
#delimited nvarchar(max),
#delimiter nvarchar(100)
) RETURNS #t TABLE
(
id int identity(1,1),
val nvarchar(max)
)
AS
BEGIN
declare #xml xml
set #xml = N'<root><r>' + replace(#delimited,#delimiter,'</r><r>') + '</r></root>'
insert into #t(val)
select
r.value('.','varchar(5)') as item
from #xml.nodes('//root/r') as records(r)
RETURN
END
GO
The it will be a simple task to JOIN them together. Like this:
SELECT
*
FROM
dbo.Split('1,5,6',',') AS a
JOIN dbo.Split('2,89,9',',') AS b
ON a.id=b.id
The upside of this is that you do not need any ROW_NUMBER() OVER(ORDER BY SELECT 0)
Edit
As in the comment the performance is better with a recursive split function. So maybe something like this:
CREATE FUNCTION dbo.Split (#s varchar(512),#sep char(1))
RETURNS table
AS
RETURN (
WITH Pieces(pn, start, stop) AS (
SELECT 1, 1, CHARINDEX(#sep, #s)
UNION ALL
SELECT pn + 1, stop + 1, CHARINDEX(#sep, #s, stop + 1)
FROM Pieces
WHERE stop > 0
)
SELECT pn,
SUBSTRING(#s, start, CASE WHEN stop > 0 THEN stop-start ELSE 512 END) AS s
FROM Pieces
)
GO
And then the select is like this:
SELECT
*
FROM
dbo.Split('1,5,6',',') AS a
JOIN dbo.Split('2,89,9',',') AS b
ON a.pn=b.pn
Thanks to Arion's suggestion. It's very useful for me. I modified the function a little bit to support varchar(max) type of input string, and max length of 1000 for the delimiter string. Also, added a parameter to indicate if you need the empty string in the final return.
For MatBailie's question, because this is an inline function, you can include the pn column in you outer query which is calling this function.
CREATE FUNCTION dbo.Split (#s nvarchar(max),#sep nvarchar(1000), #IncludeEmpty bit)
RETURNS table
AS
RETURN (
WITH Pieces(pn, start, stop) AS (
SELECT convert(bigint, 1) , convert(bigint, 1), convert(bigint,CHARINDEX(#sep, #s))
UNION ALL
SELECT pn + 1, stop + LEN(#sep), CHARINDEX(#sep, #s, stop + LEN(#sep))
FROM Pieces
WHERE stop > 0
)
SELECT pn,
SUBSTRING(#s, start, CASE WHEN stop > 0 THEN stop-start ELSE LEN(#s) END) AS s
FROM Pieces
where start< CASE WHEN stop > 0 THEN stop ELSE LEN(#s) END + #IncludeEmpty
)
But I ran into a bit issue with this function when the list intended to return had more than 100 records. So, I created another function purely using string parsing functions:
Create function [dbo].[udf_split] (
#ListString nvarchar(max),
#Delimiter nvarchar(1000),
#IncludeEmpty bit)
Returns #ListTable TABLE (ID int, ListValue varchar(max))
AS
BEGIN
Declare #CurrentPosition int, #NextPosition int, #Item nvarchar(max), #ID int
Select #ID = 1,
#ListString = #Delimiter+ #ListString + #Delimiter,
#CurrentPosition = 1+LEN(#Delimiter)
Select #NextPosition = Charindex(#Delimiter, #ListString, #CurrentPosition)
While #NextPosition > 0 Begin
Select #Item = Substring(#ListString, #CurrentPosition, #NextPosition-#CurrentPosition)
If #IncludeEmpty=1 or Len(LTrim(RTrim(#Item)))>0 Begin
Insert Into #ListTable (ID, ListValue) Values (#ID, LTrim(RTrim(#Item)))
Set #ID = #ID+1
End
Select #CurrentPosition = #NextPosition+LEN(#Delimiter),
#NextPosition = Charindex(#Delimiter, #ListString, #CurrentPosition)
End
RETURN
END
Hope this could help.
I'm working on a report in reporting services that has the user select a number of items from a multivalue list. The query for the report uses the resulting list in a simple
SELECT foo FROM bar WHERE foobar IN (#SelectedItemsFromMultiValueList)
I'm now altering the report and need to iterate over the items in #SelectedItemsFromMultiValueList using a cursor. I've looked around but can't figure out how to do this - made even more difficult by the fact that I'm not sure what to call a list of values used in an IN or even declare one manually (eg. DECLARE #SelectedItemsFromMultiValueList ???)
Does anybody know how to cursor over a multivalue list parameter or how to call something like that in SQL so I can search more effectively for a solution?
Your multi-value list is going to come in to sql as a list of comma separated values (i.e. "31,26,17")
To iterate through these values you need a way to split the values into a table. This is a function I have used, that I believe was originally coded by Jens Suessmeyer:
CREATE FUNCTION [dbo].[ufn_split]
( #Delimiter varchar(5),
#List nvarchar(max)
)
RETURNS #TableOfValues table
( RowID smallint IDENTITY(1,1),
[Value] NVARCHAR(max)
)
AS
BEGIN
DECLARE #LenString int
WHILE len( #List ) > 0
BEGIN
SELECT #LenString =
(CASE charindex( #Delimiter, #List )
WHEN 0 THEN len( #List )
ELSE ( charindex( #Delimiter, #List ) -1 )
END
)
INSERT INTO #TableOfValues
SELECT substring( #List, 1, #LenString )
SELECT #List =
(CASE ( len( #List ) - #LenString )
WHEN 0 THEN ''
ELSE right( #List, len( #List ) - #LenString - 1 )
END
)
END
RETURN
END
So you call this function, passing it #SelectedItemsFromMultiValueList and it will return to you a table of values that you can then do with what you want.
For example:
SELECT * FROM Foo WHERE X IN (SELECT [value] FROM dbo.ufn_split(',', #SelectedItemsFromMultiValueList)
i prefer my set-based solution using a recursive cte
declare #delim varchar(max),
#string varchar(max)
set #delim=','
set #string='1,2,3,4,5,6,7,8,9,10'
;with c as
(
select
CHARINDEX(#delim,#string,1) as Pos,
case when CHARINDEX(#delim,#string,1)>0 then SUBSTRING(#string,1,CHARINDEX(#delim,#string,1)-1) else #string end as Value,
case when CHARINDEX(#delim,#string,1)>0 then SUBSTRING(#string,CHARINDEX(#delim,#string,1)+1,LEN(#string)-CHARINDEX(#delim,#string,1)) else '' end as String
union all
select
CHARINDEX(#delim,String,1) as Pos,
case when CHARINDEX(#delim,String,1)>0 then SUBSTRING(String,1,CHARINDEX(#delim,String,1)-1) else String end as Value,
case when CHARINDEX(#delim,String,1)>0 then SUBSTRING(String,CHARINDEX(#delim,String,1)+1,LEN(String)-CHARINDEX(#delim,String,1)) else '' end as String
from c
where LEN(String)>0
)
select
Value
from c
option (maxrecursion 10000)
you then take whatever your query is and do an inner join with c.