Delimiter with a condition - sql

I have a column (MarketID) in a table.
I have to derive a value out of it.
I have to check for occurrence of delimiter(.) in the second position and see if there are consecutive three numbers after the delimiter then get that value. If not check for occurrence of delimiter(.) in the fourth position and see if there are consecutive three numbers after the delimiter then get that value
else get 0.
1) In first record: '3.001.1.16', at the second position there is a delimiter(.) and consecutive 3 number exists (001), so my output would be 001..
2)In the second record '3.1.006.4.7',there is a delimiter at second position but we don't have three consecutive numbers so we check for the 4th position and there is a delimiter and consecutive three numbers exist so the output is 006 ..
3) no (.) delimiter so output=0.
create table dbo.SampleList
(
MarketID varchar(100)
)
insert into dbo.SampleList
select '3.001.1.16'
union all
select '3.1.006.4.7'
union all
select 'D16B000000:21109:4'
select * from dbo.SampleList

Assuming SQL Server from dbo, you could use a CASE statement:
SELECT MarketID,
CASE WHEN SUBSTRING(MarketID,2,1) = '.' AND TRY_CONVERT(int,SUBSTRING(MarketID,3,3)) IS NOT NULL THEN SUBSTRING(MarketID,3,3)
WHEN SUBSTRING(MarketID,4,1) = '.' AND TRY_CONVERT(int,SUBSTRING(MarketID,5,3)) IS NOT NULL THEN SUBSTRING(MarketID,5,3)
ELSE '0'
END
FROM #SampleList
TRY_CONVERT to int will verify that the 3 characters are numbers

Here's a solution using a function I've created a few years ago.
It allows you to split a string and get a table as a result.
CREATE FUNCTION [dbo].[splitStringToTable]
(
#List VARCHAR(MAX) ,
#Separator VARCHAR(MAX)
)
RETURNS #Results TABLE
(
ID INT
)
AS
BEGIN
SET #List = #List + ','
DECLARE #POS INT
DECLARE #TEMP VARCHAR(8000)
WHILE (Charindex(#Separator, #List)>0)
BEGIN
SET #POS = Charindex(#Separator, #List)
IF #POS > = 0
BEGIN
SET #TEMP = LEFT(#List, #POS-1)
IF #TEMP <> ''
INSERT INTO #Results (ID) VALUES (#TEMP)
SET #List = Substring(#List, Charindex(#Separator, #List)+len(#Separator), len(#List))
END
END
RETURN
END
GO
Usage:
SELECT *, ISNULL((SELECT TOP 1 ID FROM dbo.[splitStringToStringTable](MarketID, '.') WHERE LEN(ID) = 3), 0) AS Result
FROM SampleList

SELECT MarketID,
(CASE WHEN SUBSTRING(MarketID,2,1) = '.'
THEN
(CASE WHEN SUBSTRING(MarketID,6,1) = '.' THEN SUBSTRING (MarketID,3,3)
WHEN SUBSTRING(MarketID,4,1) = '.' THEN
(CASE WHEN SUBSTRING(MarketID ,8,1)='.' THEN SUBSTRING(MarketID,5,3) ELSE NULL END)ELSE NULL END)
WHEN MarketID NOT LIKE '%.%' THEN '0'
ELSE '0'
END ) AS Output
FROM dbo.SampleList

Related

SQL Server Multi Valued Columns Issue

I need multi-valued columns divided into single values
SOS_ID ALLOCATED_PART_NBR ALLOCATED_SALES_ITM ALLOCATED_QTY
523 500~5008~038~5008 2302~~007~5û005 1~1~~~1~2
Note: if no values between ~ delimiter it should insert empty string.
I want the output like this:
SOS_ID ALLOCATED_PART_NBR ALLOCATED_SALES_ITM ALLOCATED_QTY
523 500 2302 1
523 5008 '' 1
523 038 007 ''
523 5008 5û005 ''
523 ''/NULL ''/NULL 1
523 ''/NULL ''/NULL 2
So... here's a method I got to work for what you wanted. First, you need a table-valued function that will split a string into fields based on a delimiter, and which will pad out the number of rows returned to a specified length:
IF EXISTS (SELECT * FROM sys.objects WHERE object_id = OBJECT_ID(N'[dbo].[SplitString]') AND type IN (N'FN', N'IF', N'TF', N'FS', N'FT'))
DROP FUNCTION [dbo].[SplitString]
GO
SET ANSI_NULLS ON
SET QUOTED_IDENTIFIER ON
GO
CREATE FUNCTION [dbo].[SplitString] (
#delimitedString nvarchar(4000),
#delimiter nvarchar(100),
#padRows int
)
/**************************************************************************
DESCRIPTION:
Accepts a delimited string and splits it at the specified
delimiter points. Returns the individual items as a table data
type with the ElementID field as the array index and the Element
field as the data
PARAMETERS:
#delimitedString - The string to be split
#delimiter - String containing the delimiter where
delimited string should be split
#padRows - Any rows less than this value will be padded
with empty rows (NULL means no padding)
RETURNS:
Table data type containing array of strings that were split with
the delimiters removed from the source string
USAGE:
SELECT ElementID, Element
FROM asi_SplitString('11111,22222,3333', ',', NULL)
ORDER BY ElementID
***************************************************************************/
RETURNS #tblArray TABLE
(
ElementID int IDENTITY(1,1),
Element nvarchar(1000)
)
AS
BEGIN
DECLARE #index int
DECLARE #siStart int
DECLARE #siDelSize int
DECLARE #count int
SET #count = 1;
SET #siDelSize = LEN(#delimiter);
--loop through source string and add elements to destination table array
WHILE LEN(#delimitedString) > 0
BEGIN
SET #index = CHARINDEX(#delimiter, #delimitedString);
IF #index = 0
BEGIN
INSERT INTO #tblArray VALUES (#delimitedString);
BREAK;
END
ELSE
BEGIN
INSERT INTO #tblArray VALUES(SUBSTRING(#delimitedString, 1,#index - 1));
SET #siStart = #index + #siDelSize;
SET #delimitedString = SUBSTRING(#delimitedString, #siStart , LEN(#delimitedString) - #siStart + 1);
END
SET #count += 1;
END
IF (#padRows IS NOT NULL)
WHILE (#count < #padRows)
BEGIN
SET #count += 1;
INSERT INTO #tblArray VALUES ('');
END
RETURN;
END
GO
Now you need a sample table with data to test this with (based on your question):
CREATE TABLE TestTable (SOS_ID nvarchar(10),
ALLOCATED_PART_NBR nvarchar(400),
ALLOCATED_SALES_ITM nvarchar(400),
ALLOCATED_QTY nvarchar(400))
INSERT INTO TestTable (SOS_ID, ALLOCATED_PART_NBR, ALLOCATED_SALES_ITM, ALLOCATED_QTY)
VALUES ('523', '500~5008~038~5008', '2302~~007~5û005', '1~1~~~1~2')
Now, some code that will transform the data above into the result you wanted:
DECLARE #fieldCount int;
WITH TildeCounts AS (
SELECT LEN(ALLOCATED_PART_NBR) - LEN(REPLACE(ALLOCATED_PART_NBR, '~', '')) AS TildeCount
FROM TestTable t
UNION ALL
SELECT LEN( ALLOCATED_SALES_ITM) - LEN(REPLACE( ALLOCATED_SALES_ITM, '~', '')) AS TildeCount
FROM TestTable t
UNION ALL
SELECT LEN(ALLOCATED_QTY) - LEN(REPLACE(ALLOCATED_QTY, '~', '')) AS TildeCount
FROM TestTable t
) SELECT #fieldCount = MAX(TildeCount) + 1 FROM TildeCounts;
SELECT t.SOS_ID, a.Element AS [ALLOCATED_PART_NBR], b.Element AS [ALLOCATED_SALES_ITM], c.Element AS [ALLOCATED_QTY]
FROM TestTable t
CROSS APPLY dbo.SplitString(ALLOCATED_PART_NBR, '~', #fieldCount) a
CROSS APPLY dbo.SplitString(ALLOCATED_SALES_ITM, '~', #fieldCount) b
CROSS APPLY dbo.SplitString(ALLOCATED_QTY, '~', #fieldCount) c
WHERE a.ElementID = b.ElementID AND b.ElementID = c.ElementID
What this does is it first gets the maximum number of fields in all the strings (so it can pad out the ones that are shorter). It then selects from the table, CROSS APPYING the function to each column, filtering only for the rows where all the IDs match (line up).
Convert the strings to xml, then select the nth node from each one.
SQL Fiddle Demo
DECLARE #max_field_count int = 6;
SELECT
SOS_ID
,ALLOCATED_PART_NBR = CAST(N'<a>'+REPLACE(ALLOCATED_PART_NBR ,'~','</a><a>')+'</a>' AS XML).query('(a)[sql:column("i")]').value('.','varchar(max)')
,ALLOCATED_SALES_ITM = CAST(N'<a>'+REPLACE(ALLOCATED_SALES_ITM,'~','</a><a>')+'</a>' AS XML).query('(a)[sql:column("i")]').value('.','varchar(max)')
,ALLOCATED_QTY = CAST(N'<a>'+REPLACE(ALLOCATED_QTY ,'~','</a><a>')+'</a>' AS XML).query('(a)[sql:column("i")]').value('.','varchar(max)')
FROM MyTable
CROSS JOIN (SELECT TOP (#max_field_count) ROW_NUMBER() OVER(ORDER BY (SELECT 1)) FROM master.dbo.spt_values) n(i)

Split column value to match yes or no

I have two tables named Retail and Activity and the data is as shown below:
Retail Table
Activity Table
My main concern is about Ok and Fault column of the table Retail, as you can see it contains comma separated value of ActivityId.
What i want is, if the Ok column has ActivityId the corresponding column will have Yes, if the Fault column has ActivityId then it should be marked as No
Note I have only four columns that is fixed, it means i have to check that either four of the columns has its value in Ok or Fault, if yes then only i have to print yes or no, otherwise null.
Desired result should be like :
If the value is in Ok then yes other wise No.
I guessing you want to store 'yes' or 'No' in some column. Below is the query to update that column :
UPDATE RetailTable
SET <Result_Column>=
CASE
WHEN Ok IS NOT NULL THEN 'Yes'
WHEN Fault IS NOT NULL THEN 'No'
END
You can use below code as staring point:
DECLARE #Retail TABLE
(
PhoneAuditID INT,
HandsetQuoteID INT,
Ok VARCHAR(50)
)
INSERT INTO #Retail VALUES (1, 1009228, '4,22,5')
INSERT INTO #Retail VALUES (2, 1009229, '1')
DECLARE #Activity TABLE
(
ID INT,
Activity VARCHAR(50)
)
INSERT INTO #Activity VALUES (1, 'BatteryOK?'), (4, 'PhonePowersUp?'), (22,'SomeOtherQuestion?'), (5,'LCD works OK?')
SELECT R.[PhoneAuditID], R.[HandsetQuoteID], A.[Activity], [Ok] = CASE WHEN A.[ID] IS NOT NULL THEN 'Yes' END
FROM #Retail R
CROSS APPLY dbo.Split(R.Ok, ',') S
LEFT JOIN #Activity A ON S.[items] = A.[ID]
I have used Split function provided here:
separate comma separated values and store in table in sql server
Try following query. i have used pivot to show row as columns. I have also used split function to split id values which you can find easily on net:
CREATE TABLE PhoneAudit
(
PhoneAuditRetailID INT,
HandsetQuoteID INT,
Ok VARCHAR(50),
Fault VARCHAR(50)
)
INSERT INTO PhoneAudit VALUES (1,10090,'1,2','3')
CREATE TABLE ActivityT
(
ID INT,
Activity VARCHAR(100)
)
INSERT INTO ActivityT VALUES (1,'Battery')
INSERT INTO ActivityT VALUES (2,'HasCharger')
INSERT INTO ActivityT VALUES (3,'HasMemoryCard')
INSERT INTO ActivityT VALUES (4,'Test')
DECLARE #SQL AS NVARCHAR(MAX)
DECLARE #ColumnName AS NVARCHAR(MAX)
SELECT #ColumnName= ISNULL(#ColumnName + ',','') + QUOTENAME(Activity) FROM (SELECT DISTINCT Activity FROM ActivityT) AS Activities
SET #SQL = 'SELECT PhoneAuditRetailID, HandsetQuoteID,
' + #ColumnName + '
FROM
(SELECT
t1.PhoneAuditRetailID,
t1.HandsetQuoteID,
TEMPOK.*
FROM
PhoneAudit t1
CROSS APPLY
(
SELECT
Activity,
(CASE WHEN ID IN (SELECT * FROM dbo.SplitIDs(t1.Ok,'',''))
THEN ''YES''
ELSE ''NO''
END) AS VALUE
FROM
ActivityT t2
) AS TEMPOK) AS t3
PIVOT
(
MIN(VALUE)
FOR Activity IN ('+ #ColumnName + ')
) AS PivotTable;'
EXEC sp_executesql #SQL
DROP TABLE PhoneAudit
DROP TABLE ActivityT
There are several ways to do this. If you are looking for a purely declarative approach, you could use a recursive CTE. The following example of this is presented as a generic solution with test data which should be adaptable to your needs:
Declare #Delimiter As Varchar(2)
Set #Delimiter = ','
Declare #Strings As Table
(
String Varchar(50)
)
Insert Into #Strings
Values
('12,345,6,78,9'),
(Null),
(''),
('123')
;With String_Columns As
(
Select
String,
Case
When String Is Null Then ''
When CharIndex(#Delimiter,String,0) = 0 Then ''
When Len(String) = 0 Then ''
Else Left(String,CharIndex(#Delimiter,String,0)-1)
End As String_Column,
Case
When String Is Null Then ''
When CharIndex(#Delimiter,String,0) = 0 Then ''
When Len(String) = 0 Then ''
When Len(Left(String,CharIndex(#Delimiter,String,0)-1)) = 0 Then ''
Else Right(String,Len(String)-Len(Left(String,CharIndex(#Delimiter,String,0)-1))-1)
End As Remainder,
1 As String_Column_Number
From
#Strings
Union All
Select
String,
Case
When CharIndex(#Delimiter,Remainder,0) = 0 Then Remainder
Else Left(Remainder,CharIndex(#Delimiter,Remainder,0)-1)
End As Remainder,
Case
When CharIndex(#Delimiter,Remainder,0) = 0 Then ''
When Len(Left(Remainder,CharIndex(#Delimiter,Remainder,0)-1)) = 0 Then ''
Else Right(Remainder,Len(Remainder)-Len(Left(Remainder,CharIndex(#Delimiter,Remainder,0)-1))-1)
End As Remainder,
String_Column_Number + 1
From
String_Columns
Where
(Remainder Is Not Null And Len(Remainder) > 1)
)
Select
String,
String_Column,
String_Column_Number
From
String_Columns

To find a substring matching separated by commas

I have a table say "user"which is having a col "access" having multi values separated by comma.
and i have another table " codes" which has a column "SCRCODES" having some user codes as single valued.
so i need to check whether the multi values in the col "access" of the table "user" is having any of the values present in the "SCRCODES" col of the table "codes"
someone please advise on this.
Thanks
i think this will help you:
ALTER FUNCTION [dbo].[Split]
(
#RowData NVARCHAR(MAX) ,
#SplitOn NVARCHAR(5)
)
RETURNS #ReturnValue TABLE ( Data NVARCHAR(MAX) )
AS
BEGIN
DECLARE #Counter INT
SET #Counter = 1
WHILE ( CHARINDEX(#SplitOn, #RowData) > 0 )
BEGIN
INSERT INTO #ReturnValue
( data
)
SELECT Data = LTRIM(RTRIM(SUBSTRING(#RowData, 1,
CHARINDEX(#SplitOn,
#RowData) - 1)))
SET #RowData = SUBSTRING(#RowData,
CHARINDEX(#SplitOn, #RowData) + 1,
LEN(#RowData))
SET #Counter = #Counter + 1
END
INSERT INTO #ReturnValue
( data )
SELECT Data = LTRIM(RTRIM(#RowData))
RETURN
END;
GO
DECLARE #str VARCHAR(MAX)
SET #str = select access from users where oid = "1"
SELECT *
FROM codes c, users u where c.SCRCODES in dbo.Split(#str, ',')
I assume that your sercodes does not contain comma.
You can do something like this:
select sercodes from codes
inner join users
on user.codeid = codes.codeid
where charindex(sercodes + ',', access) > 0 or charindex(',' + sercodes , access) > 0
The idea is that access will be stored like this way "read, write, execute". So, it will be either end with comma or start with comma and part of the string..
Please let me know whether it is working. You can give actual table data and design to get more accurate query.

Query to get only numbers from a string

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

How to parse String field in SQL Server 2008 if that String is in csv format

I have a string field in which csv row is inserted
'6 33','318011385','3183300153','Z','21.11.2011 13:33:22','51','51','2','0','032425','','','','','8 50318011100 318069332','','21.11.2011','21.11.2011','','0','','','GOT','0','0','0','0','0','0','0','0','0','0','0','21.11.2011','4','','','','','','','','','','','','',''
I need to extract several fields from this csv format using t-sql.
My main approach was to count colons (,) and based on the colon num to parse the data between two colons:
select min(SUBSTRING(field,charindex(''',''',recorddata,charindex(''',''',recorddata)+1)+3,CHARINDEX(''',''',field,charindex(''',''',field,charindex(''',''',field)+1)+3) - (charindex(''',''',field,charindex(''',''',field)+1)+3))) as fld from TBLSYNCEXPORT where SUBSTRING(field,2,CHARINDEX(''',''',field,0)-2) = #type and substring(field,CHARINDEX(''',''',field)+3,3) = #person and SUBSTRING(field,charindex(''',''',field,charindex(''',''',field)+1)+3,CHARINDEX(''',''',field,charindex(''',''',field,charindex(''',''',field)+1)+3) - (charindex(''',''',field,charindex(''',''',field)+1)+3)) > #prev_type
is there a better method that this one?
If you prefer a more clear way, at least for me, you can do something like this:
CREATE TABLE #destination_table(
value varchar(10)
)
DECLARE #position INT
DECLARE #source_string VARCHAR( 1000 )
SELECT #source_string = "'6 33','318011385','3183300153','Z','21.11.2011 13:33:22','51','51','2','0','032425','','','','','8 50318011100 318069332','','21.11.2011','21.11.2011','','0','','','GOT','0','0','0','0','0','0','0','0','0','0','0','21.11.2011','4','','','','','','','','','','','','',''"
SELECT #position = CHARINDEX(',', #source_string )
WHILE #position <> 0
BEGIN
INSERT INTO #destination_table VALUES( LEFT( #source_string, #position-1 ) )
SELECT #source_string = STUFF( #source_string, 1, #position, NULL )
SELECT #position = CHARINDEX(',', #source_string )
END
INSERT INTO #destination_table VALUES( #source_string)
SELECT * FROM #destination_table
-- or select what you need
select value from #destination_table where id = 2
drop table #destination_table
It'll insert the different values in a table and then you can choose the needed values.