Find a missing values from a table - sql

Is there a way to search in varchar column.
I got table called x with row named par and data in:
150/RXRPR1/18/0020642
150/RXRPR1/18/0020640
150/RXRPR1/18/0020639
151/RXRPR1/18/0020638
151/RXRPR1/18/0020637
151/RXRPR1/18/0020636
151/RXRPR1/18/0020634
The row is missing
150/RXRPR1/18/0020641
151/RXRPR1/18/0020635
How to write a SQL statement to search the table for search the missing data?
The data is of type varchar and I have permissions to select only in database

You can use classical gaps detection in the right 7 chars on your numbers, partitioned by the left 14 chars. Use LEAD function to find the value of the next record and check is the difference between the current value and next value greater than 1. This will detect the gaps and you can calculate the start and the end of the gap by adding 1 to the current value and subtracting one from the next value. Something like this:
declare #t table(col varchar(50))
insert into #t(col) values
('150/RXRPR1/18/0020642'),
('150/RXRPR1/18/0020640'),
('150/RXRPR1/18/0020639'),
('151/RXRPR1/18/0020638'),
('151/RXRPR1/18/0020637'),
('151/RXRPR1/18/0020636'),
('151/RXRPR1/18/0020634')
SELECT
gapStart = left([current], 14) + right('000000' + cast(cast(right([current], 7) as int) + 1 as varchar(10)), 7)
,gapEnd = left([next], 14) + right('000000' + cast(cast(right([next], 7) as int) - 1 as varchar(10)), 7)
FROM
(
SELECT
[current] = col
,[next] = LEAD(col) OVER (partition by left(col, 14) ORDER BY col)
FROM #t
) tmp
WHERE cast(right([next], 7) as int) - cast(Right([current], 7) as int) > 1;

You can try this query:
Please replace #MINVAL,#MAXVAL with respective values.
declare #t table([VALUE] varchar(50))
insert into #t([VALUE]) values
('150/RXRPR1/18/0020642'),
('150/RXRPR1/18/0020640'),
('150/RXRPR1/18/0020639'),
('151/RXRPR1/18/0020638'),
('151/RXRPR1/18/0020637'),
('151/RXRPR1/18/0020636'),
('151/RXRPR1/18/0020634')
DECLARE #MINVAL INT = 20634,
#MAXVAL INT = 20642;
WITH cte
AS (SELECT #MINVAL VAL
UNION ALL
SELECT val + 1 VAL
FROM cte
WHERE val < #MAXVAL)
SELECT missing
FROM (SELECT *,
Replace (Lead([VALUE]) OVER ( ORDER BY val)
, CONVERT (INT, RIGHT (Lead([VALUE]) OVER (ORDER BY val), 7)),
val)
MISSING
FROM cte
LEFT JOIN #t X
ON CONVERT (INT, RIGHT (X.[VALUE], 7)) = cte.val) X
WHERE [VALUE] IS NULL OPTION ( MAXRECURSION 10000)

Related

How to complete and fill in gaps between dates in SQL?

I have data in Redshift that I'm aggregating to the Year-Quarter level i.e. number of items by Year-Quarter
I need to show a continuous trend and hence I need to fill-in the gaps in Year-Quarter. The picture below should give a clearer idea of my current data and desired output.
How can I achieve this in Redshift SQL?
A query like this should do the trick:
create table test (yq int, items int);
INSERT INTO test Values (20201,10),(20204, 15),(20213, 25),(20222, 30);
with recursive quarters(q) as (
select min(yq) as q
from test
union all
select decode(right(q::text, 1), 4, q + 7, q + 1) as q
from quarters
where q < (select max(yq) from test)
)
select q as yq, decode(items is null, true,
lag(items ignore nulls) over (order by q), items) as items
from test t
right join quarters q
on t.yq = q.q
order by q;
It uses a recursive CTE to generate the quarters range needed, right joins this with the source data, and then uses a LAG() window function to populate the items if the value is NULL.
This is known as forward filling values:
CREATE TABLE #Temp
(
[YQ] nvarchar(5),
[items] int
)
INSERT INTO #Temp Values ('20201',10),('20204', 15),('20213', 25),('20222', 30)
---------------------------------------------------------------------------------
DECLARE #start int, #end int, #starty int, #endy int
SELECT #start=1, #end=4
SELECT #starty=MIN(Substring(YQ,0,5)), #endy=MIN(Substring(YQ,0,5)) from #Temp
;With cte1(y) as
(
Select #starty as y
union all
Select y + 1
from cte1
where y <= #endy + 1
)
, cte2(n) as
(
Select #start as n
union all
Select n + 1
from cte2
where n < #end
)
SELECT t1.YQ AS 'Year-Quarter',
CASE WHEN t2.items is null then (SELECT TOP 1 MAX(items) from #Temp WHERE items is not null and YQ < t1.YQ) ELSE t2.items END AS '# Items'
FROM
(
SELECT CAST(cte1.y AS nvarchar(4)) + CAST(cte2.n AS nvarchar(1)) AS YQ
FROM cte1, cte2
) t1
LEFT JOIN #Temp t2 ON t2.YQ = t1.YQ
WHERE t1.YQ <= (SELECT MAX(YQ) FROM #Temp)
ORDER BY t1.YQ, t2.items

Add character in front and at the end of each character

In SQL I want to add 0 in front and , at the end of each character.
Example: A30F1 -> 0A,03,00,0F,01
I don't want to use cursor if possible.
Thanks!
EIDT:
I apologize for not asking the most appropriate question at the beginning.
In short, I have a table and for each value in the column name I have to convert it to the desired format. For example, we have a #Temp table:
CREATE TABLE #Temp (id INT, name VARCHAR(25))
INSERT INTO #Temp VALUES (1, 'A30F1'), (2, 'B51R9'), (3, 'L1721')
SELECT * FROM #Temp
One method would be to use a Tally to split the string into it's individual characters, and then use concatenation to add the 0 to the start, and STRING_AGG to comma delimit the results:
DECLARE #YourValue varchar(5) = 'A30F1';
WITH N AS(
SELECT N
FROM (VALUES(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL))N(N)),
Tally AS(
SELECT TOP (LEN(#YourValue))
ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) AS I
FROM N N1, N N2) --Up to 100 characters, add more cross joins for more characters
SELECT STRING_AGG(CONCAT('0',SS.C),',') WITHIN GROUP (ORDER BY T.I) AS NewString
FROM (VALUES(#YourValue))V(YourValue)
CROSS JOIN Tally T
CROSS APPLY (VALUES(SUBSTRING(V.YourValue,T.I,1)))SS(C);
It appears this is meant to be against a table, not a single value. This needs, however, very few changes to work against a table:
WITH N AS(
SELECT N
FROM (VALUES(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL))N(N)),
Tally AS(
SELECT TOP (SELECT MAX(LEN(YourColumn)) FROM dbo.YourTable)
ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) AS I
FROM N N1, N N2) --Up to 100 characters, add more cross joins for more characters
SELECT STRING_AGG(CONCAT('0',SS.C),',') WITHIN GROUP (ORDER BY T.I) AS NewString
FROM dbo.YourTable YT
JOIN Tally T ON LEN(YT.YourColumn) >= T.I
CROSS APPLY (VALUES(SUBSTRING(YT.YourColumn,T.I,1)))SS(C)
GROUP BY YT.YourColumn;
db<>fiddle
I solved the simplest possible with a few variables, WHILE and SUBSTRING
DECLARE #var VARCHAR(20) = 'A30F1', #i INT = 1, #res NVARCHAR(20)
WHILE (#i <= LEN(#var))
BEGIN
SET #res = #res + '0' + SUBSTRING(#var, #i, 1) + ','
SET #i = #i + 1
END
SELECT LEFT(#res, LEN(#res) - 1) output
Check demo on DB<>FIDDLE.
Original answer:
A recursive CTE and a STRING_AGG() call is also an option (SQL Server 2017+ is needed):
DECLARE #text varchar(max) = 'A30F1';
WITH rCTE AS
(
SELECT 1 AS CharacterPosition, SUBSTRING(#text, 1, 1) AS Character
UNION ALL
SELECT CharacterPosition + 1, SUBSTRING(#text, CharacterPosition + 1, 1)
FROM rCTE
WHERE CharacterPosition < LEN(#text)
)
SELECT STRING_AGG('0' + Character, ',') WITHIN GROUP (ORDER BY CharacterPosition)
FROM rCTE
OPTION (MAXRECURSION 0);
Update:
You need a different statement, if the names are stored in a table, again using recursion and STRING_AGG():
Table:
CREATE TABLE #Temp (id INT, name VARCHAR(25))
INSERT INTO #Temp VALUES (1, 'A30F1'), (2, 'B51R9'), (3, 'L1721')
Statement:
; WITH rCTE AS (
SELECT
t.id AS id,
LEFT(t.name, 1) AS Character,
STUFF(t.name, 1, 1, '') AS CharactersRemaining,
1 AS CharacterPosition
FROM #Temp t
UNION ALL
SELECT
r.id,
LEFT(r.CharactersRemaining, 1),
STUFF(r.CharactersRemaining, 1, 1, ''),
CharacterPosition + 1
FROM rCTE r
WHERE LEN(r.CharactersRemaining) > 0
)
SELECT
id,
STRING_AGG('0' + Character, ',') WITHIN GROUP (ORDER BY CharacterPosition) AS name
FROM rCTE
GROUP BY id
OPTION (MAXRECURSION 0);
Result:
id name
1 0A,03,00,0F,01
2 0B,05,01,0R,09
3 0L,01,07,02,01
If you are only applying this to English alphabet characters and digits as in your example you could do this.
CREATE TABLE #Temp (id INT, name VARCHAR(25))
INSERT INTO #Temp VALUES (1, 'A30F1'), (2, 'B51R9'), (3, 'L1721'), (4, 'A')
SELECT SUBSTRING(REPLACE(
0x00 + CAST(CAST(name AS NVARCHAR(25)) AS BINARY(50)), CHAR(0), '0,')
, 3
, LEN(name) * 3 - 1)
FROM #Temp
returns
0A,03,00,0F,01
0B,05,01,0R,09
0L,01,07,02,01
0A
This takes advantage of the fact that the binary representation of the nvarchar and varchar is the same for this limited character set except for padding out with 0x00
'A30F1' -> 0x4133304631
N'A30F1' -> 0x41003300300046003100

Generate a comma-separated list of numbers in a single string

Is there a way to generate a comma-separated string of a series of numbers where the "begin" and "end" numbers are provided?
For example, provide the numbers 1 and 10 and the output would be a single value of: 1,2,3,4,5,6,7,8,9,10
10/10/2019 edit explaining why I'm interested in this:
My workplace writes queries with several columns in the SELECT statement plus aggregate functions. Then a GROUP BY clause using the column numbers. I figured using a macro that creates a comma-separated list to copy/paste in would save some time.
SELECT t.colA
, t.colB
, t.colC
, t.colD
, t.colE
, t.colF
, t.colG
, t.colH
, t.colI
, t.colJ
, sum(t.colK) as sumK
, sum(t.colL) as sumL
, sum(t.colM) as sumM
FROM t
GROUP BY 1, 2, 3, 4, 5, 6, 7, 8, 9, 10
;
You can use a recursive CTE to generate your numbers, and xml_agg to generate your string:
with recursive nums (counter) as
( select * from (select cast(1 as bigint) as counter) t
union all
select
counter + 1
from nums
where counter between 1 and 9
)
select
trim(trailing ',' from cast(xmlagg(cast(counter as varchar(2)) || ',' order by counter) as varchar(100)))
from nums
Check these methods in SQL Server-
IF OBJECT_ID('TEMPDB..#Sample') IS NOT NULL
DROP TABLE #Sample
Create table #Sample
(
NUM int
)
declare #n int
select #n=10
insert into #Sample(NUM)
SELECT NUM FROM (select row_number() over (order by (select null)) AS NUM from sys.columns) A WHERE NUM<=#N
--Method 1 (For SQL SERVER -NEW VERSION Support)
SELECT STRING_AGG(NUM,',') AS EXPECTED_RESULT FROM #Sample
--Method 1 (For SQL SERVER -OLD VERSION Support)
select DISTINCT STUFF(CAST((
SELECT ' ,' +CAST(c.num AS VARCHAR(MAX))
FROM (
SELECT num
FROM #Sample
) c
FOR XML PATH(''), TYPE) AS VARCHAR(MAX)), 1, 2, '') AS EXPECTED_RESULT
from #Sample t
While loop seems appropriate
declare #begin int=1
declare #end int=11
declare #list varchar(500)
if #begin > #end
begin
select 'error, beginning number ' + convert(varchar(500),#begin)
+ ' must not be greater than ending number '
+ convert(varchar(500),#end) + '.' err
return
end
else
set #list = convert(varchar(500),#begin)
;
while #begin < #end
begin
set #begin += 1
set #list = #list + ',' + convert(varchar(500),#begin)
end
select #list
You might want to use varchar(5000) or something depending on how big you want it to get.
disclaimer -- I don't know if this works with teradata
I'm not sure there is a good direct way to generate a series in Teradata. You can fake it a few different ways though. Here's a comma separated list of numbers from 5 to 15, for example:
SELECT TRIM(TRAILING ',' FROM (XMLAGG(TRIM(rn)|| ',' ) (VARCHAR(10000))))
FROM (SELECT 4 + ROW_NUMBER() OVER (ORDER BY Sys_Calendar."CALENDAR".day_of_calendar) as rn FROM Sys_Calendar."CALENDAR" QUALIFY rn <= 15) t
I've only used sys_calendar.calendar here because it's a big table. Any big table would do here though.
Here's one way to do it in Teradata:
SELECT ARRAY_AGG(src.RowNum)
FROM (
SELECT ROW_NUMBER() OVER() AS RowNum
FROM sys_calendar.calendar
QUALIFY RowNum BETWEEN <begin_num> AND <end_num>
) src
This will give you the output as an ARRAY data type, which you can probably cast as a VARCHAR. It also assumes begin_num > 0 and <end_num> is less than the number of rows in the sys_calendar.calendar view. You can always fiddle with this to fit your required range of values.
There are also DelimitedBuild UDFs out there (if you can find one) that can be used to convert row values into delimited strings.
The cheapest way to achieve your goal is this one (no functions, or joins to tables required):
WITH RECURSIVE NumberRanges(TheNumber,TheString) AS
(
SELECT 1 AS TheNumber,casT(1 as VARCHAR(500)) as TheString
FROM
(
SELECT * FROM (SELECT NULL AS X) X
) DUMMYTABLE
UNION ALL
SELECT
TheNumber + 1 AS TheNumber,
TheString ||',' || TRIM(TheNumber+1)
FROM NumberRanges
WHERE
TheNumber < 10
)
SELECT TheString
FROM NumberRanges
QUALIFY ROW_NUMBER() OVER ( ORDER BY TheNumber DESC) = 1;
Result String: 1,2,3,4,5,6,7,8,9,10

Increasing a number in a string

There are some objects encoded as key:value strings and stored in a table, I'd like to increase sequence number of all objects, which is one field in the object.
For example:
ID Value
--------------------------
504 s:0;d:n;e:test;
506 s:1;d:y;e:branch;
507 s:2;d:y;e:;
I'd like to change them to:
ID Value
--------------------------
504 s:1;d:n;e:test;
506 s:2;d:y;e:branch;
507 s:3;d:y;e:;
Is there a simple way to do this?
Is there a simple way to do this?
No not really.
You can find the positions of s: and d: and then use that to extract the number inbetween, increase it by one and stuff it back into where it belongs.
declare #T table
(
ID int,
Value varchar(50)
);
insert into #T values
(504, 's:0;d:n;e:test;'),
(506, 's:1;d:y;e:branch;'),
(507, 's:2;d:y;e:;');
select T.ID,
stuff(T.Value, P.S, P.D - P.S - 1, S.Value) as NewValue
from #T as T
cross apply (values(charindex('s:', T.Value) + 2,
charindex('d:', T.Value))) as P(S, D)
cross apply (values(substring(T.Value, P.S, P.D - P.S - 1) + 1)) as S(Value)
A version where you find the ; after s: instead of d: as suggested by Eric in a comment.
select T.ID,
stuff(T.Value, S.Pos, SEnd.Pos - S.Pos, V.NewValue) as NewValue
from #T as T
cross apply (values(charindex('s:', T.Value) + 2)) as S(Pos)
cross apply (values(charindex(';', T.Value, S.Pos))) as SEnd(Pos)
cross apply (values(substring(T.Value, S.Pos, SEnd.Pos - S.Pos) + 1)) as V(NewValue)
DECLARE #val nvarchar(200)
SET #val = 's:1;d:y;e:branch;'
SELECT 's:' + CONVERT(nvarchar(100), CONVERT(INT, SUBSTRING(#val, charindex(':', #val) + 1, charindex(';', #val) - charindex(':', #val) -1)) + 1) + SUBSTRING(#val, charindex(':', #val),1000)
You can use what's in the SELECT's query in an UPDATE statement to change the table values
Using the split string functions from here:Split strings the right way – or the next best way
declare #string varchar(max)
set #string='504 s:0;d:n;e:test;'
;with cte as(select * from
[dbo].[SplitStrings_Numbers]
(#string,':'))
select b.item+1 from cte c
cross apply
(select * from [dbo].[SplitStrings_Numbers](c.item,';')) b
where isnumeric(b.item)=1
This accounts for empty or non-integer values; it will ignore them in the event they can't be incremented by one.
-- Build Test Data
IF OBJECT_ID('tempdb..#test') IS NOT NULL DROP TABLE #test
CREATE TABLE #test (ID INT, Value VARCHAR(100))
INSERT #test
VALUES
(504,'s:0;d:n;e:test;'),
(506,'s:1;d:y;e:branch;'),
(507,'s:2;d:y;e:;'),
(508,'s:;d:y;e:;'),
(509,'s:xyz;d:y;e:;');
-- Update S: values
WITH sVals AS
(
SELECT ID, Value, TRY_PARSE(SUBSTRING(Value,CHARINDEX('s:',Value)+2,CHARINDEX(';',Value,CHARINDEX('s:',Value))-(CHARINDEX('s:',Value)+2)) AS INT) AS sVal
FROM #test AS t
)
UPDATE s
SET Value = IIF(sVal IS NOT NULL, STUFF(Value,CHARINDEX('s:',Value)+2,CHARINDEX(';',Value,CHARINDEX('s:',Value))-(CHARINDEX('s:',Value)+2),sVal+1), Value)
FROM sVals AS s
-- Check the results
SELECT *
FROM #test
You can as the below:
DECLARE #val VARCHAR(100) = 's:12;d:n;e:test;'
SELECT REPLACE(#val, ':' + SUBSTRING(#val, 3, PATINDEX('%;d:%', #val) - 3) + ';', ':' + CAST(SUBSTRING(#val, 3, PATINDEX('%;d:%', #val) - 3)+ 1 AS VARCHAR(MAX)) + ';')
Result: s:13;d:n;e:test;

Compare 2 or more column values in arbitrary order

I need a quick way to compare 2 or more values from different tables where the orders are arbitrarily stored in sql server. The data comes from a 3rd party who will not change.
Example data below shows the same item described in two ways. the remaining columns contain other data that i am joining.
table1
i j other columns...
1 2 ...
table2
i j other columns
2 1 ...
1 2 ...
right now for 2, i do a union query to cover both directions (i=i, j=j / i=j, j=i) . but if you expand to 3, that is 9 possible orders.
SELECT * FROM Table1 INNER JOIN Table2 ON Table1.i = Table2.i AND Table1.j = Table2.j
UNION
SELECT * FROM Table1 INNER JOIN Table2 ON Table1.i = Table2.j AND Table1.j = Table2.i
is there a way to order data returned from the first two columns before doing the comparison so i don't have to create all the unions?
Edit: New xml approach
I wonder how this approach performs:
select *, cast( '<c>' + cast(i as varchar) + '</c>' +
'<c>' + cast(j as varchar) + '</c>' +
'<c>' + cast(k as varchar) + '</c>'
as xml).query('for $a in /c order by $a return concat($a, "/")').value('.', 'varchar(100)')
from #Table1 o
This can be wrapped in a function and referenced in a persisted column... which should scale very well for you:
create table dbo.Table1 (pk int identity(1,1) primary key, i int, j int, k int);
insert into dbo.Table1
values(1, 2, 3), (3, 1, 2), (4, 5, 6), (9,9,9);
go
create function dbo.fn_GenerateCompare(#i int, #j int, #k int)
returns varchar(100)
with schemabinding
as
begin
return
(
select cast('<c>' + cast(#i as varchar) + '</c>' +
'<c>' + cast(#j as varchar) + '</c>' +
'<c>' + cast(#k as varchar) + '</c>'
as xml).query('for $a in /c order by $a return concat($a, "/")').value('.', 'varchar(100)')
);
end
alter table dbo.Table1
add Compare as dbo.fn_GenerateCompare(i, j, k) persisted;
select * from dbo.Table1
Returns:
pk i j k Compare
-- - - - -------
1 1 2 3 1/2/3
2 3 1 2 1/2/3
3 4 5 6 4/5/6
4 9 9 9 9/9/9
Your query should now be really simple. Slap an index on the new Compare column and it should fly.
Original Post:
I like the sorted list idea proposed by Thorsten. Heres a rough idea of how it might be done. Performance would be greatly improved by persisting this compare column on the table (trigger or persisted computed column?)
declare #Table1 table (pk int identity(1,1) primary key, i int, j int, k int)
declare #Table2 table (pk int identity(1,1) primary key, i int, j int, k int)
insert into #Table1
values(1, 2, 3), (3, 1, 2), (4, 5, 6), (9,9,9)
insert into #Table2
values (2, 1, 3), (6, 4, 5)
--since the order is unimportant, concatenate the columns into a sorted array
--note how 1,2,3 and 3,1,2 both result in the same compare value:
select *
from #Table1 o
cross
apply ( select cast(value as varchar) + '/'
from #Table1
unpivot (value for c in (i,j,k)) as u
where pk = o.pk
order
by value
for xml path('')
)d(compare)
--now, bring in the 2nd table
select [src] = 1, pk, compare
from #Table1 o
cross
apply ( select cast(value as varchar) + '/'
from #Table1
unpivot (value for c in (i,j,k)) as u
where pk = o.pk
order
by value
for xml path('')
)d(compare)
union all
select [src] = 2, pk, compare
from #Table2 o
cross
apply ( select cast(value as varchar) + '/'
from #Table2
unpivot (value for c in (i,j,k)) as u
where pk = o.pk
order
by value
for xml path('')
)d(compare)
--now just group them to find the matching rows
select min(src), min(pk), compare
from (
select [src] = 1, pk, compare
from #Table1 o
cross
apply ( select cast(value as varchar) + '/'
from #Table1
unpivot (value for c in (i,j,k)) as u
where pk = o.pk
order
by value
for xml path('')
)d(compare)
union all
select [src] = 2, pk, compare
from #Table2 o
cross
apply ( select cast(value as varchar) + '/'
from #Table2
unpivot (value for c in (i,j,k)) as u
where pk = o.pk
order
by value
for xml path('')
)d(compare)
)grouped
group
by compare
having count(*) > 1;