Related
Azure MSSQL Database
I have a column that contains values stored per transaction. The string can contain up to 7 values, separated by a '-'.
I need to be able to extract the value that is stored after the 3rd '-'. The issue is that the length of this column (and the characters that come before the 3rd '-') can vary.
For example:
DIM VALUE
1. NHL--WA-S-MOSG-SER-
2. VDS----HAST-SER-
3. ---D---SER
Row 1 needs to return 'S'
Row 2 needs to return '-'
Row 3 needs to return 'D'
This is by no means an optimal solution, but it works in SQL Server. 😊
TempTable added for testing purposes. Maybe it gives you a hint as of where to start.
Edit: added reference for string_split function (works from SQL Server 2016 up).
CREATE TABLE #tempStrings (
VAL VARCHAR(30)
);
INSERT INTO #tempStrings VALUES ('NHL--WA-S-MOSG-SER-');
INSERT INTO #tempStrings VALUES ('VDS----HAST-SER-');
INSERT INTO #tempStrings VALUES ('---D---SER');
INSERT INTO #tempStrings VALUES ('A-V-D-C--SER');
SELECT
t.VAL,
CASE t.PART WHEN '' THEN '-' ELSE t.PART END AS PART
FROM
(SELECT
t.VAL,
ROW_NUMBER() OVER (PARTITION BY VAL ORDER BY (SELECT NULL)) AS IX,
value AS PART
FROM #tempStrings t
CROSS APPLY string_split(VAL, '-')) t
WHERE t.IX = 4; --DASH COUNT + 1
DROP TABLE #tempStrings;
Output is...
VAL PART
---D---SER D
A-V-D-C--SER C
NHL--WA-S-MOSG-SER- S
VDS----HAST-SER- -
If you always want the fourth element then using CHARINDEX is relatively straightforward:
DROP TABLE IF EXISTS #tmp;
CREATE TABLE #tmp (
rowId INT IDENTITY PRIMARY KEY,
xval VARCHAR(30) NOT NULL
);
INSERT INTO #tmp
VALUES
( 'NHL--WA-S-MOSG-SER-' ),
( 'VDS----HAST-SER-' ),
( '---D---SER' ),
( 'A-V-D-C--SER' );
;WITH cte AS
( -- Work out the position of the 3rd dash
SELECT
rowId,
xval,
CHARINDEX( '-', xval, CHARINDEX( '-', xval, CHARINDEX( '-', xval ) + 1 ) + 1 ) + 1 xstart
FROM #tmp t
), cte2 AS
( -- Work out the length for the substring function
SELECT rowId, xval, xstart, CHARINDEX( '-', xval, xstart) - (xstart) AS xlen
FROM cte
)
SELECT rowId, ISNULL( NULLIF( SUBSTRING( xval, xstart, xlen ), '' ), '-' ) xpart
FROM cte2
I also did a volume test at 1 million rows and this was by far the fastest method compared with STRING_SPLIT, OPENJSON, recursive CTE (the worst at high volume). As a downside this method is less extensible, say you want the second or fifth items for example.
I am trying to get string between second and third instance of ",," using SQL SELECT.
Apparently functions substring and charindex are useful, and I have tried them but the problem is that I need the string between those specific ",,"s and the length of the strings between them can change.
Can't find working example anywhere.
Here is an example:
Table: test
Column: Column1
Row1: cat1,,cat2,,cat3,,cat4,,cat5
Row2: dogger1,,dogger2,,dogger3,,dogger4,,dogger5
Result: cat3dogger3
Here is my closest attempt, it works if the strings are same length every time, but they aren't:
SELECT SUBSTRING(column1,LEN(LEFT(column1,CHARINDEX(',,', column1,12)+2)),LEN(column1) - LEN(LEFT(column1,CHARINDEX(',,', column1,20)+2)) - LEN(RIGHT(column1,CHARINDEX(',,', (REVERSE(column1)))))) AS column1
FROM testi
Just repeat sub-string 3 times, each time moving onto the next ",," e.g.
select
-- Substring till the third ',,'
substring(z.col1, 1, patindex('%,,%',z.col1)-1)
from (values ('cat1,,cat2,,cat3,,cat4,,cat5'),('dogger1,,dogger2,,dogger3,,dogger4,,dogger5')) x (col1)
-- Substring from the first ',,'
cross apply (values (substring(x.col1,patindex('%,,%',x.col1)+2,len(x.col1)))) y (col1)
-- Substring from the second ',,'
cross apply (values (substring(y.col1,patindex('%,,%',y.col1)+2,len(y.col1)))) z (col1);
And just to reiterate, this is a terrible way to store data, so the best solution is to store it properly.
Here is an alternative solution using charindex. The base idea is the same as in Dale K's an answer, but instead of cutting the string, we specify the start_location for the search by using the third, optional parameter, of charindex. This way, we get the location of each separator, and could slip each value off from the main string.
declare #vtest table (column1 varchar(200))
insert into #vtest ( column1 ) values('dogger1,,dogger2,,dogger3,,dogger4,,dogger5')
insert into #vtest ( column1 ) values('cat1,,cat2,,cat3,,cat4,,cat5')
declare #separetor char(2) = ',,'
select
t.column1
, FI.FirstInstance
, SI.SecondInstance
, TI.ThirdInstance
, iif(TI.ThirdInstance is not null, substring(t.column1, SI.SecondInstance + 2, TI.ThirdInstance - SI.SecondInstance - 2), null)
from
#vtest t
cross apply (select nullif(charindex(#separetor, t.column1), 0) FirstInstance) FI
cross apply (select nullif(charindex(#separetor, t.column1, FI.FirstInstance + 2), 0) SecondInstance) SI
cross apply (select nullif(charindex(#separetor, t.column1, SI.SecondInstance + 2), 0) ThirdInstance) TI
For transparency, I saved the separator string in a variable.
By default the charindex returns 0 if the search string is not present, so I overwrite it with the value null, by using nullif
IMHO, SQL Server 2016 and its JSON support in the best option here.
SQL
-- DDL and sample data population, start
DECLARE #tbl TABLE (ID INT IDENTITY PRIMARY KEY, Tokens VARCHAR(500));
INSERT INTO #tbl VALUES
('cat1,,cat2,,cat3,,cat4,,cat5'),
('dogger1,,dogger2,,dogger3,,dogger4,,dogger5');
-- DDL and sample data population, end
WITH rs AS
(
SELECT *
, '["' + REPLACE(Tokens
, ',,', '","')
+ '"]' AS jsondata
FROM #tbl
)
SELECT rs.ID, rs.Tokens
, JSON_VALUE(jsondata, '$[2]') AS ThirdToken
FROM rs;
Output
+----+---------------------------------------------+------------+
| ID | Tokens | ThirdToken |
+----+---------------------------------------------+------------+
| 1 | cat1,,cat2,,cat3,,cat4,,cat5 | cat3 |
| 2 | dogger1,,dogger2,,dogger3,,dogger4,,dogger5 | dogger3 |
+----+---------------------------------------------+------------+
It´s the same as #"Yitzhak Khabinsky" but i think it looks clearer
WITH CTE_Data
AS(
SELECT 'cat1,,cat2,,cat3,,cat4,,cat5' AS [String]
UNION
SELECT 'dogger1,,dogger2,,dogger3,,dogger4,,dogger5' AS [String]
)
SELECT
A.[String]
,Value3 = JSON_VALUE('["'+ REPLACE(A.[String], ',,', '","') + '"]', '$[2]')
FROM CTE_Data AS A
I have a field which is a concatenation of single letters. I am trying to order these strings within a view. These values can't be hard coded as there are too many. Is someone able to provide some guidance on the function to use to achieve the desired output below? I am using MSSQL.
Current output
CustID | Code
123 | BCA
Desired output
CustID | Code
123 | ABC
I have tried using a UDF
CREATE FUNCTION [dbo].[Alphaorder] (#str VARCHAR(50))
returns VARCHAR(50)
BEGIN
DECLARE #len INT,
#cnt INT =1,
#str1 VARCHAR(50)='',
#output VARCHAR(50)=''
SELECT #len = Len(#str)
WHILE #cnt <= #len
BEGIN
SELECT #str1 += Substring(#str, #cnt, 1) + ','
SET #cnt+=1
END
SELECT #str1 = LEFT(#str1, Len(#str1) - 1)
SELECT #output += Sp_data
FROM (SELECT Split.a.value('.', 'VARCHAR(100)') Sp_data
FROM (SELECT Cast ('<M>' + Replace(#str1, ',', '</M><M>') + '</M>' AS XML) AS Data) AS A
CROSS APPLY Data.nodes ('/M') AS Split(a)) A
ORDER BY Sp_data
RETURN #output
END
This works when calling one field
ie.
Select CustID, dbo.alphaorder(Code)
from dbo.source
where custid = 123
however when i try to apply this to top(10) i receive the error
"Invalid length parameter passed to the LEFT or SUBSTRING function."
Keeping in mind my source has ~4million records, is this still the best solution?
Unfortunately i am not able to normalize the data into a separate table with records for each Code.
This doesn't rely on a id column to join with itself, performance is almost as fast
as the answer by #Shnugo:
SELECT
CustID,
(
SELECT
chr
FROM
(SELECT TOP(LEN(Code))
SUBSTRING(Code,ROW_NUMBER() OVER(ORDER BY (SELECT NULL)),1)
FROM sys.messages) A(Chr)
ORDER by chr
FOR XML PATH(''), type).value('.', 'varchar(max)'
) As CODE
FROM
source t
First of all: Avoid loops...
You can try this:
DECLARE #tbl TABLE(ID INT IDENTITY, YourString VARCHAR(100));
INSERT INTO #tbl VALUES ('ABC')
,('JSKEzXO')
,('QKEvYUJMKRC');
--the cte will create a list of all your strings separated in single characters.
--You can check the output with a simple SELECT * FROM SeparatedCharacters instead of the actual SELECT
WITH SeparatedCharacters AS
(
SELECT *
FROM #tbl
CROSS APPLY
(SELECT TOP(LEN(YourString)) ROW_NUMBER() OVER(ORDER BY (SELECT NULL)) FROM master..spt_values) A(Nmbr)
CROSS APPLY
(SELECT SUBSTRING(YourString,Nmbr,1))B(Chr)
)
SELECT ID,YourString
,(
SELECT Chr As [*]
FROM SeparatedCharacters sc1
WHERE sc1.ID=t.ID
ORDER BY sc1.Chr
FOR XML PATH(''),TYPE
).value('.','nvarchar(max)') AS Sorted
FROM #tbl t;
The result
ID YourString Sorted
1 ABC ABC
2 JSKEzXO EJKOSXz
3 QKEvYUJMKRC CEJKKMQRUvY
The idea in short
The trick is the first CROSS APPLY. This will create a tally on-the-fly. You will get a resultset with numbers from 1 to n where n is the length of the current string.
The second apply uses this number to get each character one-by-one using SUBSTRING().
The outer SELECT calls from the orginal table, which means one-row-per-ID and use a correalted sub-query to fetch all related characters. They will be sorted and re-concatenated using FOR XML. You might add DISTINCT in order to avoid repeating characters.
That's it :-)
Hint: SQL-Server 2017+
With version v2017 there's the new function STRING_AGG(). This would make the re-concatenation very easy:
WITH SeparatedCharacters AS
(
SELECT *
FROM #tbl
CROSS APPLY
(SELECT TOP(LEN(YourString)) ROW_NUMBER() OVER(ORDER BY (SELECT NULL)) FROM master..spt_values) A(Nmbr)
CROSS APPLY
(SELECT SUBSTRING(YourString,Nmbr,1))B(Chr)
)
SELECT ID,YourString
,STRING_AGG(sc.Chr,'') WITHIN GROUP(ORDER BY sc.Chr) AS Sorted
FROM SeparatedCharacters sc
GROUP BY ID,YourString;
Considering your table having good amount of rows (~4 Million), I would suggest you to create a persisted calculated field in the table, to store these values. As calculating these values at run time in a view, will lead to performance problems.
If you are not able to normalize, add this as a denormalized column to the existing table.
I think the error you are getting could be due to empty codes.
If LEN(#str) = 0
BEGIN
SET #output = ''
END
ELSE
BEGIN
... EXISTING CODE BLOCK ...
END
I can suggest to split string into its characters using referred SQL function.
Then you can concatenate string back, this time ordered alphabetically.
Are you using SQL Server 2017? Because with SQL Server 2017, you can use SQL String_Agg string aggregation function to concatenate characters splitted in an ordered way as follows
select
t.CustId, string_agg(strval, '') within GROUP (order by strval)
from CharacterTable t
cross apply dbo.SPLIT(t.code) s
where strval is not null
group by CustId
order by CustId
If you are not working on SQL2017, then you can follow below structure using SQL XML PATH for concatenation in SQL
select
CustId,
STUFF(
(
SELECT
'' + strval
from CharacterTable ct
cross apply dbo.SPLIT(t.code) s
where strval is not null
and t.CustId = ct.CustId
order by strval
FOR XML PATH('')
), 1, 0, ''
) As concatenated_string
from CharacterTable t
order by CustId
I have a column u_manualdoc which contains the values are like this CGY DR# 7405. I want to remove the CGY DR#.
Here's the code:
select u_manualdoc, cardcode, cardname from ODLN
I want only the 7405 number. Thanks!
Try this:
--sample data you provided in comments
declare #tbl table(codes varchar(20))
insert into #tbl values
('CGY PST - 58277') , ('CGY RMC PST # 58083'), ('CGY DR # 7443'), ('CSI # 1304'), ('PO# 0568 , 0570'), ('CGY DR# 7446')
--actual query that you can apply to your table
select SUBSTRING(codes, PATINDEX('%[0-9]%', codes), len(codes)) from #tbl
The key point here is to use patindex, which searches for a pattern and returns index where such pattern occur. I specified %[0-9]% which means that we search for any digit - it will return first occurrence of a digit. Now- since this would be our starting point to substring, we pass it to such function. Third parameter of substring is length. Since we want the rest of a string, len function makes sure that we get that :)
Applying to your naming:
select SUBSTRING(u_manualdoc, PATINDEX('%[0-9]%', u_manualdoc), len(u_manualdoc)),
cardcode,
cardname
from ODLN
You should use string functions charindex,len and substring to get it.
See the code below.
select SUBSTRING(u_manualdoc,CHARINDEX('#',u_manualdoc)+1,LEN(u_manualdoc)- CHARINDEX('#',u_manualdoc))
EDIT
In addition to the other answers, you can use this simple method:
select
substring(
u_manualdoc,
len(u_manualdoc) - patindex('%[^0-9]%', reverse(u_manualdoc)) + 2,
len(u_manualdoc)
),
cardcode, cardname
from ODLN
In this example, patindex finds the first non-digit (as specified by ^[0-9]) from the right side of the string, and then uses that as the starting point of the substring.
This will work on all of your sample strings (including 'PO# 0568 , 0570 CGY DR# 7446').
Or use SQL Server Regex, which lets you use more powerful regular expressions within your queries.
TRY THIS
DECLARE #table TABLE(DirtyCol VARCHAR(100));
INSERT INTO #table
VALUES('AB ABCDE # 123'), ('ABCDE# 123'), ('AB: ABC# 123 AB: ABC# 123'), ('AB#'), ('AB # 1 000 000'), ('AB # 1`234`567'), ('AB # (9)(876)(543)');
WITH tally
AS (
SELECT TOP (100) N = ROW_NUMBER() OVER(ORDER BY ##spid)
FROM sys.all_columns),
data
AS (
SELECT DirtyCol,
Col
FROM #table
CROSS APPLY
(
SELECT
(
SELECT C+''
FROM
(
SELECT N,
SUBSTRING(DirtyCol, N, 1) C
FROM tally
WHERE N <= DATALENGTH(DirtyCol)
) [1]
WHERE C BETWEEN '0' AND '9'
ORDER BY N FOR XML PATH('')
)
) p(Col)
WHERE p.Col IS NOT NULL)
SELECT DirtyCol,
CAST(Col AS INT) IntCol
FROM data;
I’m fairly used to using MySQL, but not particularly familiar with SQL Server. Tough luck, the database I’m dealing with here is on SQL Server 2014.
I have a table with a column whose values are all integers with leading, separating, and trailing semicolons, like these three fictitious rows:
;905;1493;384;13387;29;933;467;28732;
;905;138;3084;1387;290;9353;4767;2732;
;9085;14493;3864;130387;289;933;4767;28732;
What I am trying to do now is to select all rows where more than one number taken from a list of numbers appears in this column. So for example, given the three rows above, if I have the group 905,467,4767, the statement I’m trying to figure out how to construct should return the first two rows: the first row contains 905 and 467; the second row contains 905 and 4767. The third row contains only 4767, so that row should not be returned.
As far as I can tell, SQL Server does not actually support regex directly (and I don’t even know what managed code is), which doesn’t help. Even with regex, I wouldn’t know where to begin. Oracle seems to have a function that would be very useful, but that’s Oracle.
Most similar questions on here deal with finding multiple instances of the same character (usually singular) and solve the problem by replacing the string to match with nothing and counting the difference in length. I suppose that would technically work here, too, but given a ‘filter’ group of 15 numbers, the SELECT statement would become ridiculously long and convoluted and utterly unreadable. Additionally, I only want to match entire numbers (so if one of the numbers to match is 29, the value 29 would match in the first row, but the value 290 in the second row should not match), which means I’d have to include the semicolons in the REPLACE clause and then discount them when calculating the length. A complete mess.
What I would ideally like to do is something like this:
SELECT * FROM table WHERE REGEXP_COUNT(column, ';(905|467|4767);') > 1
– but that will obviously not work, for all kinds of reasons (the most obvious one being the nonexistence of REGEXP_COUNT outside Oracle).
Is there some sane, manageable way of doing this?
You can do
SELECT *
FROM Mess
CROSS APPLY (SELECT COUNT(*)
FROM (VALUES (905),
(467),
(4767)) V(Num)
WHERE Col LIKE CONCAT('%;', Num, ';%')) ca(count)
WHERE count > 1
SQL Fiddle
Or alternatively
WITH Nums
AS (SELECT Num
FROM (VALUES (905),
(467),
(4767)) V(Num))
SELECT Mess.*
FROM Mess
CROSS APPLY (VALUES(CAST(CONCAT('<x>', REPLACE(Col, ';', '</x><x>'), '</x>') AS XML))) x(x)
CROSS APPLY (SELECT COUNT(*)
FROM (SELECT n.value('.', 'int')
FROM x.x.nodes('/x') n(n)
WHERE n.value('.', 'varchar') <> ''
INTERSECT
SELECT Num
FROM Nums) T(count)
HAVING COUNT(*) > 1) ca2(count)
Could you put your arguments into a table (perhaps using a table-valued function accepting a string (of comma-separated integers) as a parameter) and use something like this?
DECLARE #T table (String varchar(255))
INSERT INTO #T
VALUES
(';905;1493;384;13387;29;933;467;28732;')
, (';905;138;3084;1387;290;9353;4767;2732;')
, (';9085;14493;3864;130387;289;933;4767;28732;')
DECLARE #Arguments table (Arg int)
INSERT INTO #Arguments
VALUES
(905)
, (467)
, (4767)
SELECT String
FROM
#T
CROSS JOIN #Arguments
GROUP BY String
HAVING SUM(CASE WHEN PATINDEX('%;' + CAST(Arg AS varchar) + ';%', String) > 0 THEN 1 ELSE 0 END) > 1
And example of using this with a function to generate the arguments:
CREATE FUNCTION GenerateArguments (#Integers varchar(255))
RETURNS #Arguments table (Arg int)
AS
BEGIN
WITH cte
AS
(
SELECT
PATINDEX('%,%', #Integers) p
, LEFT(#Integers, PATINDEX('%,%', #Integers) - 1) n
UNION ALL
SELECT
CASE WHEN PATINDEX('%,%', SUBSTRING(#Integers, p + 1, LEN(#Integers))) + p = p THEN 0 ELSE PATINDEX('%,%', SUBSTRING(#Integers, p + 1, LEN(#Integers))) + p END
, CASE WHEN PATINDEX('%,%', SUBSTRING(#Integers, p + 1, LEN(#Integers))) = 0 THEN RIGHT(#Integers, PATINDEX('%,%', REVERSE(#Integers)) - 1) ELSE LEFT(SUBSTRING(#Integers, p + 1, LEN(#Integers)), PATINDEX('%,%', SUBSTRING(#Integers, p + 1, LEN(#Integers))) - 1) END
FROM cte
WHERE p <> 0
)
INSERT INTO #Arguments (Arg)
SELECT n
FROM cte
RETURN
END
GO
DECLARE #T table (String varchar(255))
INSERT INTO #T
VALUES
(';905;1493;384;13387;29;933;467;28732;')
, (';905;138;3084;1387;290;9353;4767;2732;')
, (';9085;14493;3864;130387;289;933;4767;28732;')
;
SELECT String
FROM
#T
CROSS JOIN GenerateArguments('905,467,4767')
GROUP BY String
HAVING SUM(CASE WHEN PATINDEX('%;' + CAST(Arg AS varchar) + ';%', String) > 0 THEN 1 ELSE 0 END) > 1
You can achieve this using the like function for the regex and row_number to determine the number of matches.
Here we declare the column values for testing:
DECLARE #tbl TABLE (
string NVARCHAR(MAX)
)
INSERT #tbl VALUES
(';905;1493;384;13387;29;933;467;28732;'),
(';905;138;3084;1387;290;9353;4767;2732;'),
(';9085;14493;3864;130387;289;933;4767;28732;')
Then we pass your search parameters into a table variable to be joined on:
DECLARE #search_tbl TABLE (
search_value INT
)
INSERT #search_tbl VALUES
(905),
(467),
(4767)
Finally we join the table with the column to search for onto the search table. We apply the row_number function to determine the number of times it matches. We select from this subquery where the row_number = 2 meaning that it joined at least twice.
SELECT
string
FROM (
SELECT
tbl.string,
ROW_NUMBER() OVER (PARTITION BY tbl.string ORDER BY tbl.string) AS rn
FROM #tbl tbl
JOIN #search_tbl search_tbl ON
tbl.string LIKE '%;' + CAST(search_tbl.search_value AS NVARCHAR(MAX)) + ';%'
) tbl
WHERE rn = 2
You could build a where clause like this :
WHERE
case when column like '%;905;%' then 1 else 0 end +
case when column like '%;467;%' then 1 else 0 end +
case when column like '%;4767;%' then 1 else 0 end >= 2
The advantage is that you do not need a helper table. I don't know how you build the query, but the following also works, and is useful if the numbers are in a tsql variable.
case when column like ('%;' + #n + ';%') then 1 else 0 end