mismatched input 'from'. expecting: 'on', 'using' in Athena - sql

Facing this error when using the below code
SELECT AM.MemoryDescription from universal_final_circle_sg_Assets
LEFT JOIN (
SELECT DISTINCT AP2.AssetID,
SUBSTRING(
(
SELECT ', ' + TRIM(STR(CountNo)) + ' x' + Capacity AS char
FROM (
SELECT AssetID, COUNT(*) AS CountNo, Max(CHARACTER_LENGTH(Capacity / 1024 / 1024 / 1024, 5, 2) + ' GB RAM ' + Type) AS Capacity
FROM universal_final_circle_sg_AssetMemoryModules
WHERE SeparatedAsset = 0
GROUP BY AssetID, Capacity, Type
) AP1
WHERE AP1.AssetID = AP2.AssetID
-- FOR XML PATH ('')
), 3, 1000) [MemoryDescription]
FROM (
SELECT AssetID, COUNT(*) AS CountNo, Max(TRIM(Capacity / 1024 / 1024 / 1024),TRIM(5), 2) + ' GB ' + Type)) AS Capacity
FROM universal_final_circle_sg_AssetMemoryModules
WHERE SeparatedAsset = 0
GROUP BY AssetID, Capacity, Type
) AP2
) AM ON universal_final_circle_sg_Assets.ID = AM.AssetID

Related

SQL HIVE Conversion

I'm trying to convert a piece of SQL code to HiveQL, and it's not working as expected.
Please find below the code snippet in SQL that I'm attempting to convert:
SQL Code:
UPDATE
C
SET
C.prod_l = P.prod_l, C.numprod = P.numprod, C.prod_cng = P.prod_cng
FROM
[cnc].dbo.[c_cnc_analysis] C
LEFT JOIN
(
SELECT
X.*,
Len(prod_l) - Len(Replace(prod_l, ' ~ ', ' ')) + 1 AS NumProd,
CASE
WHEN
Len(prod_l) - Len(Replace(prod_l, ' ~ ', ' ')) + 1 = 1
THEN
0
ELSE
1
END
AS PROD_CNG
FROM
(
SELECT DISTINCT
ST2.uitid,
Substring((
SELECT
' ~ ' + ST1.product_id AS [text()]
FROM
(
SELECT
[uitid],
[product_id]
FROM
dbo.[c_cnc_dedup_bse]
GROUP BY
[uitid],
[product_id]
)
ST1
WHERE
ST1.uitid = ST2.uitid
ORDER BY
ST1.uitid FOR xml path ('')), 4, 1000 ) [PROD_L]
FROM
(
SELECT
[uitid],
[product_id]
FROM
dbo.[c_cnc_dedup_bse]
GROUP BY
[uitid],
[product_id]
)
ST2
)
X
)
P
ON C.uitid = P.uitid;
Converted HIVE Query:
create
or replace view prd_temp as
SELECT
`UITID`,
`PRODUCT_ID`
FROM
`C_CNC_DEDUP_BSE`
GROUP BY
`UITID`,
`PRODUCT_ID`;
create
or replace view prd_temp2 as
SELECT
`UITID`,
`PRODUCT_ID`
FROM
`C_CNC_DEDUP_BSE`
GROUP BY
`UITID`,
`PRODUCT_ID`;
create
or replace view prd_temp3 as
SELECT
st1.`uitid`,
concat(' ~ ', st1.`PRODUCT_ID`) AS `text()`
FROM
prd_temp ST1
left join
prd_temp2 st2
on ST1.`UITID` = ST2.`UITID`
where
st1.`UITID` = st2.`UITID`
ORDER BY
ST1.`UITID`;
create
or replace view prd_temp4 as
SELECT
st1.`uitid`,
concat_ws('''', `text()`)
FROM
prd_temp3 ST1
ORDER BY
ST1.`UITID`;
create
or replace view st2 as
SELECT DISTINCT
`UITID`,
SUBSTRING(`_c1` , 4, 1000) as `PROD_L`
FROM
prd_temp4;
create
or replace view x as
SELECT
*,
LENGTH(PROD_L) - LENGTH(REPLACE(PROD_L, ' ~ ', ' ')) + 1 as NumProd,
CASE
WHEN
LENGTH(PROD_L) - LENGTH(REPLACE(PROD_L, ' ~ ', ' ')) + 1 = 1
then
0
ELSE
1
END
as PROD_CNG
from
ST2;
create table C_CNC_ANALYSIS1 as
select
c.*,
P.numprod as numprod,
p.prod_cng as prod_cng,
p.prod_l as prod_l
from
`C_CNC_ANALYSIS` C
LEFT JOIN
X P
ON C.UITID = P.UITID ;
SELECT
*
from
c_cnc_analysis1 limit 100;
Appreciate all the help with this. I think the code converted for the XML path is not working in HIVE, since I'm getting multiple UITIDs (key) and the information in separate rows rather than just one single record per UITID.
Thank You,
Viswanath Sitaraman

SQL split string (all possible combination)

I would like to transform this string:
A1+A2+A3.B1+B2.C1
into
A1.B1.C1
A1.B2.C1
A2.B1.C1
A2.B2.C1
A3.B1.C1
A3.B2.C1
How can I do that? (note that each dimension(= a group separate by .), could have x values, I mean it can be A1+A2.B1.C1 or A1+A2.B1+B2+B3+B4+B5.C1+C2)
Thanks
If you have only 3 columns, then just use STRING_SPLIT: number your groups from first split and then do a join 3 times and select each group on corresponding join.
with a as (
select s2.value as v, dense_rank() over(order by s1.value) as rn
from STRING_SPLIT('A1+A2+A3.B1+B2.C1', '.') as s1
cross apply STRING_SPLIT(s1.value, '+') as s2
)
select
a1.v + '.' + a2.v + '.' + a3.v as val
from a as a1
cross join a as a2
cross join a as a3
where a1.rn = 1
and a2.rn = 2
and a3.rn = 3
| val |
----------
|A1.B1.C1|
|A2.B1.C1|
|A3.B1.C1|
|A1.B2.C1|
|A2.B2.C1|
|A3.B2.C1|
If you have indefinite number of groups, then it's better to use recursive CTE instead of dynamic SQL. What you should do:
Start with all the values from the first group.
On recursion step crossjoin all the values of the next group (i.e. step group number is current group number + 1).
Select the last recursion step where you'll have the result.
Code is below:
with a as (
select s2.value as v, dense_rank() over(order by s1.value) as rn
from STRING_SPLIT('A1+A2+A3.B1+B2+B3+B4.C1+C2.D1+D2+D3', '.') as s1
cross apply STRING_SPLIT(s1.value, '+') as s2
)
, b (val, lvl) as (
/*Recursion base*/
select cast(v as nvarchar(1000)) as val, rn as lvl
from a
where rn = 1
union all
/*Increase concatenation on each iteration*/
select cast(concat(b.val, '.', a.v) as nvarchar(1000)) as val, b.lvl + 1 as lvl
from b
join a
on b.lvl + 1 = a.rn /*Recursion step*/
)
select *
from b
where lvl = (select max(rn) from a) /*You need the last step*/
order by val
I won't add a tabular result since it is quite big. But try it by yourself.
Here is SQL server version and fiddle:
with lst(s) as (select * from STRING_SPLIT('A1+A2.B1+B2+B3+B4+B5.C1+C2','.'))
select t1+'.'+t2+'.'+t3 as res from
(select * from STRING_SPLIT((select s from lst where s like 'A%'), '+')) s1(t1) cross join
(select * from STRING_SPLIT((select s from lst where s like 'B%'), '+')) s2(t2) cross join
(select * from STRING_SPLIT((select s from lst where s like 'C%'), '+')) s3(t3);
Of course you can grow it in a regular fashion if the number of dimensions grows.
Here is a Postgresql solution:
with x(s) as (select string_to_array('A1+A2.B1+B2+B3+B4+B5.C1+C2','.'))
select t1||'.'||t2||'.'||t3 as res from
unnest((select string_to_array(s[1],'+') from x)) t1 cross join
unnest((select string_to_array(s[2],'+') from x)) t2 cross join
unnest((select string_to_array(s[3],'+') from x)) t3;
result:
res |
--------|
A1.B1.C1|
A1.B2.C1|
A1.B3.C1|
A1.B4.C1|
A1.B5.C1|
A2.B1.C1|
A2.B2.C1|
A2.B3.C1|
A2.B4.C1|
A2.B5.C1|
A1.B1.C2|
A1.B2.C2|
A1.B3.C2|
A1.B4.C2|
A1.B5.C2|
A2.B1.C2|
A2.B2.C2|
A2.B3.C2|
A2.B4.C2|
A2.B5.C2|
Here my code with your help. I didn't mention, but I can also have more or less than 3 parts, so I'm using a dynamic SQL for this:
declare #FILTER varchar(max)='B+C+D.A+G.T+Y+R.E'
-- Works also with A.B.C
-- Works also with A+B+C.D.E+F
-- Works also with A+B+C.D+E+F+G+H
declare #NB int
declare #SQL varchar(max)=''
select #NB=count(*) from STRING_SPLIT(#FILTER,'.')
set #SQL='
;with T(A,B) as
(select *, row_number() over (order by (select NULL))
from STRING_SPLIT(''' + #FILTER + ''',''.'')
)
select '
;with T(V,N) as (
select *, row_number() over (order by (select NULL))
from STRING_SPLIT(#FILTER,'.')
)
select #SQL=#SQL + 'T' + cast(N as varchar(max)) + ' + ''.'' + ' from T
set #SQL=left(#SQL,len(#SQL)-1) + ' as res from'
;with T(V,N) as (
select *, row_number() over (order by (select NULL))
from STRING_SPLIT(#FILTER,'.')
)
select #SQL=#SQL + '
(select * from STRING_SPLIT((select A from T where B=' + cast(N as varchar(max)) + '), ''+'')) s' + cast(N as varchar(max)) + '(t' + cast(N as varchar(max)) + ') cross join'
from T
set #SQL=left(#SQL,len(#SQL)-len('cross join'))
exec(#SQL)

List combination of numbers which have same sum

**N** is a prositive number
Need list of scenarios which have sum equal N
For example if N=4
ScenarioId Value
---------- -----
1 1
1 1
1 1
1 1
2 2
2 1
2 1
3 2
3 2
4 3
4 1
5 4
above list is required. If you sum by ScenarioId all sum must equal to N
UPDATE
Here is my own solution. however, I am not sure about the multiplication of two different number sets would not be equal at any time.
My current question is
Is there any possibilities a + b + c = d + e + f and a * b * c = d * e * f
Test link is here
DECLARE #N int = 4;
SELECT
[Value] = CAST(number + 1 as tinyint)
INTO #Values
FROM master.dbo.spt_values
WHERE number < #N
AND [Type] = 'p'
;WITH COMBINATIONS AS(
SELECT ScenarioKey = CAST(NULL AS nvarchar(MAX)), [Value], Total = 0, Multipication = 1, MemeberCount = 0
FROM #Values
UNION ALL
SELECT ScenarioKey = ISNULL(S.ScenarioKey, '') + IIF(S.ScenarioKey IS NULL, '', N'-') + CAST(P.[Value] AS nvarchar(10)), S.[Value], Total = S.Total + P.[Value], Multipication = S.Multipication * P.[Value], MemeberCount = MemeberCount + 1
FROM #Values P
JOIN COMBINATIONS AS S ON S.Total < S.[Value]
),
SCENARIOS AS(
SELECT
ScenarioKey
,ScenarioId = ROW_NUMBER() OVER(ORDER BY ScenarioKey)
,[Value]
FROM
(
SELECT
ScenarioKey
,[Value]
,Multipication
,MemeberCount
-- this will prevent dublications. because 1 * 2 * 3 = 3 * 2 * 1
-- however, I am not sure about multipication of two different number sets would not be equal any time
,RowNo = ROW_NUMBER() OVER(PARTITION BY [Value],Multipication,MemeberCount ORDER BY [Value],ScenarioKey)
FROM COMBINATIONS
WHERE Total = #N
) X
WHERE RowNo = 1 AND [Value] = #N
)
SELECT
R.ScenarioId
,[Value] = S.[value]
FROM SCENARIOS R
CROSS APPLY (SELECT [value] FROM STRING_SPLIT(R.ScenarioKey, '-')) S
DROP TABLE #Values
It's too long for comment, so I post this as an answer. I want to note, that this is a static example, but I hope it can be easily translated as a dynamic statement.
Steps are written as comments in the statement:
WITH rcte AS
(
-- Recursive query to generate all numbers from 1 to 4
SELECT 0 AS Number
UNION ALL
SELECT Number + 1
FROM rcte
WHERE Number < 4
), permutations AS (
-- All possible permutations with sum equal to 4
-- There is additional column DuplicateMarker.
-- It will be used later, because 0,0,0,4 and 0,4,0,0 are the same
SELECT
t1.Number AS Number1,
t2.Number AS Number2,
t3.Number AS Number3,
t4.Number AS Number4,
CONCAT(LTRIM(STR(t1.Number)), '.', LTRIM(STR(t2.Number)), '.', LTRIM(STR(t3.Number)), '.', LTRIM(STR(t4.Number))) AS DuplicateMarker
FROM rcte t1, rcte t2, rcte t3, rcte t4
WHERE (t1.Number + t2.Number + t3.Number + t4.Number) = 4
), duplicates AS (
-- Get data with splitted DuplicateMarker column
SELECT *
FROM permutations
CROSS APPLY (SELECT [value] FROM STRING_SPLIT(DuplicateMarker, '.')) t
), results AS (
-- Get unique combinations
-- WITHIN GROUP (ORDER BY) will order strings and 0.0.0.4 and 0.4.0.0 will be the same
SELECT DISTINCT STRING_AGG([value], '.') WITHIN GROUP (ORDER BY [value]) AS ScenarioValue
FROM duplicates
GROUP BY Number1, Number2, Number3, Number4
)
SELECT
DENSE_RANK() OVER (ORDER BY r.ScenarioValue) AS ScenarioID,
s.[value]
FROM results r
CROSS APPLY (SELECT [value] FROM STRING_SPLIT(r.ScenarioValue, '.')) s
WHERE [value] <> '0'
Output:
ScenarioID value
1 4
2 1
2 3
3 2
3 2
4 1
4 1
4 2
5 1
5 1
5 1
5 1
Update:
Thanks to #AndriyM's comment, I've made some changes and now you can eliminate string manipulations:
WITH rcte AS
(
-- Recursive query to generate all numbers from 0 to 4
SELECT 0 AS Number
UNION ALL
SELECT Number + 1
FROM rcte
WHERE Number < 4
), combinations AS (
-- All different combinations with sum equal to 4
SELECT
t1.Number AS Number1,
t2.Number AS Number2,
t3.Number AS Number3,
t4.Number AS Number4,
ROW_NUMBER() OVER (ORDER BY t1.Number, t2.Number, t3.Number, t4.NUmber) AS ScenarioID
FROM rcte t1, rcte t2, rcte t3, rcte t4
WHERE
((t1.Number + t2.Number + t3.Number + t4.Number) = 4) AND
(t1.Number <= t2.Number) AND
(t2.Number <= t3.Number) AND
(t3.Number <= t4.Number)
)
SELECT c.ScenarioID, v.[value]
FROM combinations c
CROSS APPLY (VALUES (c.NUmber1), (c.Number2), (c.Number3), (c.Number4)) AS v ([value])
WHERE v.[value] > 0
Update 2:
Approach using dynamic statement - probably not the best approach, but is based on statement from first update:
-- Set your #n value
DECLARE #n int
SET #n = 4
-- Declarations
DECLARE #combinationsSelect nvarchar(max)
DECLARE #combinationsRowNumber nvarchar(max)
DECLARE #combinationsFrom nvarchar(max)
DECLARE #combinationsWhere1 nvarchar(max)
DECLARE #combinationsWhere2 nvarchar(max)
DECLARE #combinationsValues nvarchar(max)
SET #combinationsSelect = N''
SET #combinationsRowNumber = N''
SET #combinationsFrom = N''
SET #combinationsValues = N''
SET #combinationsWhere1 = N''
SET #combinationsWhere2 = N''
-- Generate dynamic parts of the statement
;WITH numbers AS
(
SELECT 1 AS Number
UNION ALL
SELECT Number + 1
FROM Numbers
WHERE Number < #n
)
SELECT
#combinationsSelect = #combinationsSelect + N', t' + LTRIM(STR(Number)) + N'.Number AS Number' + LTRIM(STR(Number)),
#combinationsRowNumber = #combinationsRowNumber + N', t' + LTRIM(STR(Number)) + N'.Number',
#combinationsValues = #combinationsValues + N', (c.Number' + LTRIM(STR(Number)) + N')',
#combinationsFrom = #combinationsFrom + N', rcte t' + LTRIM(STR(Number)),
#combinationsWhere1 = #combinationsWhere1 + N'+ t' + LTRIM(STR(Number)) + N'.Number ',
#combinationsWhere2 = #combinationsWhere2 +
CASE
WHEN Number = 1 THEN N''
ELSE N'AND (t' + LTRIM(STR(Number-1)) + N'.Number <= t' + + LTRIM(STR(Number)) + N'.Number) '
END
FROM
numbers
SET #combinationsSelect = STUFF(#combinationsSelect, 1, 2, N'')
SET #combinationsRowNumber = STUFF(#combinationsRowNumber, 1, 2, N'')
SET #combinationsValues = STUFF(#combinationsValues, 1, 2, N'')
SET #combinationsFrom = STUFF(#combinationsFrom, 1, 2, N'')
SET #combinationsWhere1 = STUFF(#combinationsWhere1, 1, 2, N'')
SET #combinationsWhere2 = STUFF(#combinationsWhere2, 1, 4, N'')
-- Dynamic statement
DECLARE #stm nvarchar(max)
SET #stm =
N'WITH rcte AS (
SELECT 0 AS Number
UNION ALL
SELECT Number + 1
FROM rcte
WHERE Number < ' + LTRIM(STR(#n)) +
N'), combinations AS (
SELECT ' +
#combinationsSelect +
N', ROW_NUMBER() OVER (ORDER BY ' + #combinationsRowNumber + N') AS ScenarioID
FROM ' + #combinationsFrom +
N' WHERE ((' + #combinationsWhere1 + N') = ' + LTRIM(STR(#n)) + ') AND ' + #combinationsWhere2 +
N')
SELECT c.ScenarioID, v.[value]
FROM combinations c
CROSS APPLY (VALUES ' + #combinationsValues + N') AS v ([value])
WHERE v.[value] > 0'
-- Execute dynamic statement
EXEC (#stm)
If you have sample data like below
You can write query like below
Declare #N int =4
Select T.*
From #T T
cross apply (
select S, SUM(V) Total
From #T
Group By S) Totals
Where Totals.Total=#N and T.S = Totals.S

How to include string text in a STUFF function (XML Path)?

Code:
ISNULL(LTRIM(STUFF( (SELECT ', ' + PL.Pipe_Product
FROM Reporting.PipelineInformation PL
WHERE PL.Project_ID = TI.Project_ID
FOR XML PATH('')), 1, 1, '')),'___________') AS Pipe_Product
How can I do this?
Another approach can be to add a ROW_NUMBER into the sub-query to decide whether a comma or and should be inserted. This should be faster since you don't have separate queries against the same PipelineInformation table both of which are correlated sub-queries.
DECLARE #PL TABLE (Pipe_Product VARCHAR(50), Project_ID INT)
INSERT #PL VALUES ('gas', 1),('oil', 1),('orange juice', 1), ('milk', 2), ('honey', 2)
SELECT
TI.Project_ID,
SUBSTRING((
SELECT
CASE WHEN RowNum = 1 THEN ' and ' ELSE ', ' END + T.Pipe_Product AS [text()]
FROM (
SELECT
Pipe_Product,
Project_ID,
ROW_NUMBER() OVER (ORDER BY Pipe_Product DESC) AS RowNum
FROM #PL
WHERE Project_ID = TI.Project_ID
) T
ORDER BY RowNum DESC
FOR XML PATH('')
), 3, 4000) AS [Pipe_Product]
FROM (SELECT 1 UNION ALL SELECT 2) AS TI (Project_ID)
The sample data above outputs:
Project_ID Pipe_Product
----------- -----------------------------
1 gas, oil and orange juice
2 honey and milk
Try this edited result instead:
reverse(stuff(reverse(ISNULL(LTRIM(STUFF((
SELECT ', ' + PL.Pipe_Product
FROM Reporting.PipelineInformation PL
WHERE PL.Project_ID = TI.Project_ID
FOR XML PATH('')
), 1, 1, '')), '___________')), charindex(' ,', reverse(ISNULL(LTRIM(STUFF((
SELECT ', ' + PL.Pipe_Product
FROM Reporting.PipelineInformation PL
WHERE PL.Project_ID = TI.Project_ID
FOR XML PATH('')
), 1, 1, '')), '___________'))), 2, ' dna '))

Remove Leading Zeros On Ip Address in SQL

I have a column called IP with data such as 10.001.99.108
I want to run a script to change it to look like 10.1.99.108
I have used this before:
update TABLE set IP = substring(IP, patindex('%[^0]%',IP), 10)
but that removes leading zeros at the begging.
Im not sure how I could change it to do the second segment.
You can do this with parsename() and a method to remove the leading zeros. The following removes the leading zeros by casting to an integer and then back to string:
select (cast(cast(parsename(ip, 4) as int) as varchar(255)) +
cast(cast(parsename(ip, 3) as int) as varchar(255)) +
cast(cast(parsename(ip, 2) as int) as varchar(255)) +
cast(cast(parsename(ip, 1) as int) as varchar(255))
)
try this solution
DECLARE #IpAdress AS TABLE ( IP VARCHAR(100) )
INSERT #IpAdress
( IP )
VALUES ( '10.001.99.108' ),
( '010.001.099.008' ),
( '080.081.999.008' );
WITH Tally
AS ( SELECT n = 1
UNION ALL
SELECT n + 1
FROM Tally
WHERE n <= 100
),
split
AS ( SELECT i.IP ,
CONVERT(INT, ( CASE WHEN CHARINDEX('.', S.string) > 0
THEN LEFT(S.string,
CHARINDEX('.', S.string)
- 1)
ELSE string
END )) AS part
FROM #IpAdress AS i
INNER JOIN Tally AS T ON SUBSTRING('.' + IP, T.N, 1) = '.'
AND T.N <= LEN(i.IP)
CROSS APPLY ( SELECT String = ( CASE
WHEN T.N = 1
THEN LEFT(i.IP,
CHARINDEX('.',
i.IP) - 1)
ELSE SUBSTRING(i.IP,
T.N, 1000)
END )
) S
)
SELECT DISTINCT
o.ip ,
SUBSTRING(( SELECT '.' + CONVERT(VARCHAR, i.part)
FROM split AS i
WHERE i.ip = o.ip
FOR
XML PATH('')
), 2, 1000) AS newIP
FROM split AS o
output result
ip newIP
010.001.099.008 10.1.99.8
080.081.999.008 80.81.999.8
10.001.99.108 10.1.99.108