I am new to PostgreSQL. I want to converter or add this code to Store Procedure.
WITH RECURSIVE t(i) AS (
SELECT * FROM unnest((select regexp_split_to_array('signature',''))::char[])
), cte AS (
SELECT i AS combo, i, 1 AS ct
FROM t
UNION ALL
SELECT cte.combo || t.i, t.i, ct + 1
FROM cte, t
WHERE ct <= 8
AND position(t.i in cte.combo) = 0
)
SELECT distinct cc.combo,ww.word
FROM cte cc
inner join words ww ON ww.word=cc.combo
WHERE length(combo)>1
AND ww.source_id in(1,2,19,21,24,26,33,34)
ORDER BY cc.combo ASC;
Just put it into a function:
create function generate_anagrams(p_word text)
returns table(combo text, word text)
as
$$
WITH RECURSIVE t(i) AS (
SELECT *
FROM unnest((select regexp_split_to_array(p_word,''))::char[])
), cte AS (
SELECT i AS combo, i, 1 AS ct
FROM t
UNION ALL
SELECT cte.combo || t.i, t.i, ct + 1
FROM cte, t
WHERE ct <= 8
AND position(t.i in cte.combo) = 0
)
SELECT distinct cc.combo,ww.word
FROM cte cc
inner join words ww ON ww.word=cc.combo
WHERE length(combo)>1
AND ww.source_id in(1,2,19,21,24,26,33,34)
ORDER BY cc.combo ASC
$$
language sql;
You can use it like this:
select *
from generate_anagrams('signature');
Related
I have a table like this:
Now I have this code that can get the median value:
SELECT ROUND((t.middle1 + b.middle2) / 2, 2) AS median_item_count
FROM (
SELECT MAX(item_count) AS middle1
FROM (
SELECT item_count,
COUNT(*) OVER() AS row_count,
ROW_NUMBER() OVER (ORDER BY item_count) AS row_number
FROM orders
WHERE item_count <> 0
) top
WHERE (row_number::float / row_count) <= 0.50
) t,
(
SELECT MIN(item_count) AS middle2
FROM (
SELECT item_count,
COUNT(*) OVER() AS row_count,
ROW_NUMBER() OVER (ORDER BY item_count DESC) AS row_number
FROM orders
WHERE item_count <> 0
) bottom
WHERE (row_number::float / row_count) <= 0.50
) b
;
How can I get the median value without using window function OVER()and without using the percentile_disc function???
You can use this function which calculates the median of numeric array elements:
create or replace function median(numeric[])
returns numeric language sql immutable as
$$
select avg(val)
from (
select val
from unnest($1) val
order by 1
limit 2 - mod(array_upper($1, 1), 2)
offset ceil(array_upper($1, 1) / 2.0) - 1
) sub;
$$;
select median(array_agg(item_count))
from orders;
I'm trying to combine range.
WITH a AS (
select '2017-09-16 07:12:57' as begat,'2017-09-16 11:30:22' as endat
union
select '2017-09-18 17:05:21' ,'2017-09-19 13:18:01'
union
select '2017-09-19 15:34:40' ,'2017-09-22 13:29:37'
union
select '2017-09-22 12:24:16' ,'2017-09-22 13:18:29'
union
select '2017-09-28 09:48:54' ,'2017-09-28 13:39:13'
union
select '2017-09-20 13:52:43' ,'2017-09-20 14:14:43'
), b AS (
SELECT *, lag(endat) OVER (ORDER BY begat) < begat OR NULL AS step
FROM a
)
, c AS (
SELECT *, count(step) OVER (ORDER BY begat) AS grp
FROM b
)
SELECT min(begat), coalesce( max(endat), 'infinity' ) AS range
FROM c
GROUP BY grp
ORDER BY 1
Result
1 "2017-09-16 07:12:57";"2017-09-16 11:30:22"
2 "2017-09-18 17:05:21";"2017-09-19 13:18:01"
3 "2017-09-19 15:34:40";"2017-09-22 13:29:37"
4 "2017-09-22 12:24:16";"2017-09-22 13:18:29"
5 "2017-09-28 09:48:54";"2017-09-28 13:39:13"
positions 3,4 intersect (endata> next begat)
How do I make the union of all the intersections into one large interval
I need result
1 "2017-09-16 07:12:57";"2017-09-16 11:30:22"
2 "2017-09-18 17:05:21";"2017-09-19 13:18:01"
3 "2017-09-19 15:34:40";"2017-09-22 13:29:37"
4 "2017-09-28 09:48:54";"2017-09-28 13:39:13"
Hey I would suggest using the following process :
1- Identify when a row is new, so you give a value of 1 to values that do not overlap (CTE b)
2- Sequence together the rows that have overlaps with others. This way you can see have a common identifier that will allow you to MAX and MIN begat and endat (CTE c)
3- For each sequence, give the MIN of begat and the MAX of endat so you will have your final values
WITH a AS (
select '2017-09-16 07:12:57' as begat,'2017-09-16 11:30:22' as endat
union
select '2017-09-18 17:05:21' ,'2017-09-19 13:18:01'
union
select '2017-09-19 15:34:40' ,'2017-09-22 13:29:37'
union
select '2017-09-22 12:24:16' ,'2017-09-22 13:18:29'
union
select '2017-09-28 09:48:54' ,'2017-09-28 13:39:13'
union
select '2017-09-20 13:52:43' ,'2017-09-20 14:14:43'
)
, b AS (
SELECT
begat
, endat
, (begat > MAX(endat) OVER w IS TRUE)::INT is_new
FROM a
WINDOW w AS (ORDER BY begat ROWS BETWEEN UNBOUNDED PRECEDING AND 1 PRECEDING)
)
, c AS (
SELECT
begat
, endat
, SUM((is_new)) OVER (ORDER BY begat) seq
FROM b
)
SELECT
MIN(begat) beg_at
, MAX(endat) end_at
FROM c
GROUP BY seq
EDITED
If you need speed you can use a psql function:
create or replace function append_ranges_in_a() returns setof a
language plpgsql
as
$BODY$
declare
v_current a%rowtype;
v_new a%rowtype;
v_first boolean:=true;
begin
for v_current in select begat, endat from a order by begat, endat
loop
if v_first then
v_first := false;
v_new.begat := v_current.begat;
elsif v_new.endat < v_current.begat then
return next v_new;
v_new.begat := v_current.begat;
end if;
v_new.endat := greatest(v_current.endat,v_new.endat);
end loop;
return next v_new;
return;
end;
$BODY$;
select * from append_ranges_in_a()
I test it with ~ 400000 rows:
delete from a;
insert into a (begat, endat)
select time::text, (time+'1 day'::interval)::text
from (select t+(round(random()*23.0)||' hours')::interval as time
from generate_series('1401-01-01'::timestamp,'2018-08-21'::timestamp,'1 day'::interval) t
) t;
select count(*) from a;
select * from append_ranges_in_a() offset 100000 limit 10
and it is twice fast as O(n^2) pure SQL version.
OLD slow solution:
You can use a recursive WITH query https://www.postgresql.org/docs/current/static/queries-with.html to construct the result row by row.
I create the table
The first row is the candidate first row (ending where ending), but the row is not "ready"
Then I look at the next row (step) and if it is not intersecting I add a ready row,
Also I add a not ready row with the current (last) observed range
When I do not have more rows I calculate the last row
I retain ready rows and the last row
Here is the code
CREATE TABLE a as
select '2017-09-16 07:12:57' as begat,'2017-09-16 11:30:22' as endat
union
select '2017-09-18 17:05:21' ,'2017-09-19 13:18:01'
union
select '2017-09-19 15:34:40' ,'2017-09-22 13:29:37'
union
select '2017-09-22 12:24:16' ,'2017-09-22 13:18:29'
union
select '2017-09-28 09:48:54' ,'2017-09-28 13:39:13'
union
select '2017-09-20 13:52:43' ,'2017-09-20 14:14:43';
WITH RECURSIVE t(begat, endat, ready, step) AS (
select * from (
select *,false,1 from a order by begat, endat limit 1) a
UNION ALL
SELECT new_rows.*
FROM (SELECT * FROM t ORDER BY begat DESC limit 1) t,
lateral (SELECT * FROM a ORDER BY begat, endat OFFSET step LIMIT 1) a,
lateral (
SELECT t.begat, t.endat, true as ready, step WHERE t.endat < a.begat
UNION SELECT CASE WHEN t.endat < a.begat THEN a.begat ELSE t.begat END, greatest(a.endat, t.endat), false, step+1
) new_rows
)
select begat, endat
from (
select begat, endat, ready, row_number() over (order by begat desc, endat desc)=1 is_last
from t
order by begat, endat) t
where ready or is_last;
i using range type
https://www.postgresql.org/docs/9.3/static/rangetypes.html
WITH tmp AS (
-- preparation range type
select begat, coalesce( endat, 'infinity' ) as endAt, tsrange( begat, coalesce( endat, 'infinity' ) ) as rg
from (
select '2017-09-11 17:13:03'::timestamp as begat ,'2017-09-12 12:24:09'::timestamp as endat union
select '2017-09-19 15:34:40','2017-09-20 11:04:45' union
select '2017-09-20 08:32:00','2017-09-22 13:28:37' union
select '2017-09-20 13:52:43','2017-09-20 14:14:43' union
select '2017-09-21 12:24:16','2017-09-21 13:28:29' union
select '2017-09-22 12:24:16','2017-09-22 13:28:29' union
select '2017-09-22 12:34:16','2017-09-23 13:28:29' union
select '2017-09-22 12:25:16','2017-09-24 13:28:29' union
select '2017-09-28 09:48:54','2017-09-28 13:39:13' union
select '2017-09-28 14:22:16','2017-09-28 15:52:15' union
select '2017-10-05 12:17:45','2017-10-06 12:35:38' union
select '2017-10-06 16:20:44','2017-10-07 10:11:09' union
select '2017-10-07 20:38:32','2017-10-09 14:42:29' union
select '2017-10-12 18:22:14','2017-10-12 20:52:45'
) a
),a as (
-- group intersecting range
select l.*
from tmp l left join tmp r on l.begAt > r.begAt and r.rg #> l.rg
where r.begAt is null
),
b AS (
SELECT *, lag(endat) OVER (ORDER BY begat) < begat OR NULL AS step
FROM a
)
, c AS (
SELECT *, count(step) OVER (ORDER BY begat) AS grp
FROM b
)
SELECT min(begat), coalesce( max(endat), 'infinity' ) AS range
FROM c
GROUP BY grp
ORDER BY 1
Input : Keep the column value into next line if word to word space is 3 space and length of the word is >9 .
declare #Table table(CL1 varchar(50))
INSERT INTO #Table
SELECT 'Ohh my GOD'
UNION ALL
SELECT 'hindunewspaer is no1 paper'
select * from #Table
o/p :
CL1
ohh
my god
hindunewpaer
is no1 paper
Used a Split/Parse function. Can be inline if needed.
EDIT - Switch to a Parser which is not limited to 8K because the final
string could easily be larger than 8K
Example
;with cte0 as (
Select Seq=Row_Number() over (Order by (Select null)),RetSeq,RetVal
From #Table A
Cross Apply (
Select RetSeq
,RetVal=case when len(RetVal)>9 then '~~~' else '' end+RetVal+case when len(RetVal)>9 then '~~~' else '' end
From [dbo].[udf-Str-Parse](Replace(CL1,' ','~~~ '),' ')
) B ),
cte1 as ( Select S=Stuff((Select ' '+RetVal From cte0 Order by Seq For XML Path ('')),1,1,'') )
Select CL1 = RetVal
From cte1 A
Cross Apply [dbo].[udf-Str-Parse](A.S,'~~~') B
Order By RetSeq
Returns
CL1
Ohh
my GOD
hindunewspaer
is no1 paper
The Split/Parse Function if Needed
CREATE FUNCTION [dbo].[udf-Str-Parse] (#String varchar(max),#Delimiter varchar(10))
Returns Table
As
Return (
Select RetSeq = Row_Number() over (Order By (Select null))
,RetVal = LTrim(RTrim(B.i.value('(./text())[1]', 'varchar(max)')))
From (Select x = Cast('<x>' + replace((Select replace(#String,#Delimiter,'§§Split§§') as [*] For XML Path('')),'§§Split§§','</x><x>')+'</x>' as xml).query('.')) as A
Cross Apply x.nodes('x') AS B(i)
);
--Thanks Shnugo for making this XML safe
--Select * from [dbo].[udf-Str-Parse]('Dog,Cat,House,Car',',')
--Select * from [dbo].[udf-Str-Parse]('John Cappelletti was here',' ')
--Select * from [dbo].[udf-Str-Parse]('this,is,<test>,for,< & >',',')
Disclaimer: I'm dealing with a rather old legacy system so any comments telling me about poor design are redundant, although I do genuinely appreciate any such sentiment. There is a new version that solves most legacy problems but we still have to maintain the old system, so basically, we have to manage for now.
I have a table that looks like this (yes, that is a single column, I know):
And I need a view (for reporting purposes) that will dynamically process the data in said table and return this:
The values are \n-delimited (shudder) and you can assume there will always be the same number of values in each cell (9 in the example, although other databases could have 4 or 12 or any number), although I suppose having NULL-insertion in the event of missing values couldn't hurt. They will also always be in a matching order (as in the example, 'AUD', 'Australian Dollar', and '$' are all the first values in their respective cells, and so on).
I've found various approaches to splitting a single cell out into a view, but nothing that covers merging data in such a way as I require. Sitting at home with a cold has not helped my research capabilities. Help me StackOverflow, you're my only hope!
Bonus points for tidy, relatively readable SQL examples, although I'm anticipating messiness as a natural by-product of the hackish nature of my required solution.
Something like this. I didn't take the time to build out the tables, but it should be fairly obvious where you can replace my variables with your rows. You will also want to do a replace char(10) where I have used commas. You could package it up in a table valued function and then call as a view.
declare #xml1 xml
declare #xml2 xml
declare #xml3 xml
declare #c1 nvarchar(250)
declare #c2 nvarchar(250)
declare #c3 nvarchar(250)
set #c1 = N'AUD,CAD,EUR,GBP,JPY,NZD,USD,KES,CHF';
set #c2 = N'Australian Dollar,Canadian Dollar,Euro,Pound Sterling,Yen,New Zealand Dollar,United States Dollar,Kenyan Shilling, Swiss Franc';
set #c3 = N'$,$,C,L,Y,$,$,K,F';
-- you'd use replace(#c1, char(10), '</r><r>') etc etc for /n delimited code
set #xml1 = N'<root><r>' + replace(#c1,',','</r><r>') + '</r></root>';
set #xml2 = N'<root><r>' + replace(#c2,',','</r><r>') + '</r></root>';
set #xml3 = N'<root><r>' + replace(#c3,',','</r><r>') + '</r></root>';
select code.code, name.name, symbol.symbol
from
(select ROW_NUMBER() over (order by ##rowcount) as ck,
c.value('.','varchar(max)') as [code]
from #xml1.nodes('//root/r') as a(c)) as code
inner join
(select ROW_NUMBER() over (order by ##rowcount) as nk,
n.value('.','varchar(max)') as [name]
from #xml2.nodes('//root/r') as a(n)) as name on code.ck = name.nk
inner join
(select ROW_NUMBER() over (order by ##rowcount) as sk,
s.value('.','varchar(max)') as [symbol]
from #xml3.nodes('//root/r') as a(s)) as symbol on symbol.sk = name.nk
You can run this as a single script in SSMS for verification that it works. No schema necessary.
Using Jeff Moden's Tally Ho! CSV splitter:
CREATE FUNCTION [dbo].[DelimitedSplit8K]
--===== Define I/O parameters
(#pString VARCHAR(8000), #pDelimiter CHAR(1))
--WARNING!!! DO NOT USE MAX DATA-TYPES HERE! IT WILL KILL PERFORMANCE!
RETURNS TABLE WITH SCHEMABINDING AS
RETURN
--===== "Inline" CTE Driven "Tally Table" produces values from 1 up to 10,000...
-- enough to cover VARCHAR(8000)
WITH
E1(N) AS (
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL
SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1 UNION ALL SELECT 1
), --10E+1 or 10 rows
E2(N) AS (SELECT 1 FROM E1 a, E1 b), --10E+2 or 100 rows
E4(N) AS (SELECT 1 FROM E2 a, E2 b), --10E+4 or 10,000 rows max
cteTally(N) AS (--==== This provides the "base" CTE and limits the number of rows right up front
-- for both a performance gain and prevention of accidental "overruns"
SELECT TOP (ISNULL(DATALENGTH(#pString),0)) ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) FROM E4
),
cteStart(N1) AS (--==== This returns N+1 (starting position of each "element" just once for each delimiter)
SELECT 1 UNION ALL
SELECT t.N+1 FROM cteTally t WHERE SUBSTRING(#pString,t.N,1) = #pDelimiter
),
cteLen(N1,L1) AS(--==== Return start and length (for use in substring)
SELECT s.N1,
ISNULL(NULLIF(CHARINDEX(#pDelimiter,#pString,s.N1),0)-s.N1,8000)
FROM cteStart s
)
--===== Do the actual split. The ISNULL/NULLIF combo handles the length for the final element when no delimiter is found.
SELECT ItemNumber = ROW_NUMBER() OVER(ORDER BY l.N1),
Item = SUBSTRING(#pString, l.N1, l.L1)
FROM cteLen l
;
and inline CTE data like this
with
data as (select Num,Currencies from (values
(1,'AUD'+char(10)+'CAD'+char(10)+'USD'+char(10)+'KES')
,(2,'Australian DOllar'+char(10)+'Canadian Dollar'+char(10)+'US Dollar'+char(10)+'Kenyan Shilling')
,(3,'$'+char(10)+'$'+char(10)+'$'+char(10)+'k')
)data(Num,Currencies)
),
The solution is as simple as this:
map as (select * from (values
(1,'Code')
,(2,'Name')
,(3,'Symbol')
)map(Num,Col )
)
select
ItemNumber
,max(Code) as Code
,max(Name) as Name
,max(Symbol) as Symbol
from (
select
map.Num
,map.Col
,c.Item
,c.ItemNumber
from data
join map
on map.Num = data.Num
cross apply dbo.DelimitedSplit8K(data.Currencies,char(10)) c
) t
pivot (max(Item) for Col in (Code,Name,Symbol)) pvt
group by ItemNumber
to give us:
ItemNumber Code Name Symbol
-------------- ---- -------------------- ---------------
1 AUD Australian DOllar $
2 CAD Canadian Dollar $
3 USD US Dollar $
4 KES Kenyan Shilling k
Hope this Helps. Run all together or replace the table variable with a temptable.
Sample Data:
IF OBJECT_ID(N'tempdb..#table') > 0
BEGIN
DROP TABLE #table
END
DECLARE #table TABLE(ATTRIBUTELVAUE VARCHAR(MAX))
INSERT INTO #table
SELECT
'AFN
ALL
DZD
USD
EUR
AOA
XCD
XCD
ARS'
INSERT INTO #table
SELECT
'Afghanistan
Albania
Algeria
American Samoa
Andorra
Angola
Anguilla
Antigua and Barbuda
Argentina'
INSERT INTO #table
SELECT
'AF
AL
DZ
AS
AD
AO
AI
AG
AR'
Query:
IF OBJECT_ID(N'tempdb..#TEMP') > 0
BEGIN
DROP TABLE #TEMP
END
DECLARE #StartLoop INT
DECLARE #EndLoop INT
DECLARE #Code TABLE (ID INT IDENTITY(1, 1),
Code VARCHAR(250))
DECLARE #Name TABLE (ID INT IDENTITY(1, 1),
Name VARCHAR(250))
DECLARE #Symbol TABLE (ID INT IDENTITY(1, 1),
Symbol VARCHAR(250))
SELECT ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) AS ID,
*
INTO #Temp
FROM #table
SELECT #StartLoop = MIN(ID),
#EndLoop = MAX(ID)
FROM #Temp
WHILE #StartLoop <= #EndLoop
BEGIN
DECLARE #WorkingString VARCHAR(MAX)
SELECT #WorkingString = ATTRIBUTELVAUE + CHAR(10) + ' '
FROM #Temp
WHERE ID = #StartLoop
--print #WorkingString
WHILE CHARINDEX(CHAR(10), #WorkingString) > 0
BEGIN
DECLARE #SearchCharacter INT
DECLARE #WorkingStringLength INT
DECLARE #TempStringLength INT
DECLARE #TempString VARCHAR(MAX)
SET #WorkingStringLength = LEN(#WorkingString)
SET #SearchCharacter = CHARINDEX(CHAR(10), #WorkingString)
SET #TempString = SUBSTRING(#WorkingString, 1, #SearchCharacter - 1)
SET #TempStringLength = LEN(#TempString)
SET #WorkingString = SUBSTRING(#WorkingString, #SearchCharacter + 1, #WorkingStringLength)
SET #TempString = REPLACE(#TempString, CHAR(13), '')
IF #StartLoop = 1
BEGIN
INSERT INTO #Code
SELECT #TempString
END
IF #StartLoop = 2
BEGIN
INSERT INTO #Name
SELECT #TempString
END
IF #StartLoop = 3
BEGIN
INSERT INTO #Symbol
SELECT #TempString
END
END
SET #StartLoop = #StartLoop + 1
END
SELECT Code,
Name,
Symbol
FROM #Code AS c
JOIN #Name AS n
ON c.ID = n.ID
JOIN #Symbol AS s
ON s.ID = n.ID
Cleanup:
IF OBJECT_ID(N'tempdb..#TEMP') > 0
BEGIN
DROP TABLE #TEMP
END
IF OBJECT_ID(N'tempdb..#table') > 0
BEGIN
DROP TABLE #table
END
Because I needed a view, this ended up being my solution:
CREATE FUNCTION [dbo].[CurrencyTableGenerator]()
RETURNS
#CurrencyTable TABLE(
Code NVARCHAR(250)
,Name NVARCHAR(250)
,Symbol NVARCHAR(250)
)
AS
BEGIN
DECLARE #xml1 XML
DECLARE #xml2 XML
DECLARE #xml3 XML
DECLARE #C1 NVARCHAR(250)
DECLARE #C2 NVARCHAR(250)
DECLARE #c3 NVARCHAR(250)
SET #c1 = (SELECT ...)
SET #c2 = (SELECT ...)
SET #c3 = (SELECT ...)
SET #xml1 = N'<root><r>' + REPLACE(#c1, CHAR(10), '</r><r>') + '</r></root>';
SET #xml2 = N'<root><r>' + REPLACE(#c2, CHAR(10), '</r><r>') + '</r></root>';
SET #xml3 = N'<root><r>' + REPLACE(#c3, CHAR(10), '</r><r>') + '</r></root>';
INSERT INTO #CurrencyTable
SELECT Code.Code, Name.Name, Symbol.Symbol
FROM
(SELECT ROW_NUMBER() OVER (ORDER BY ##ROWCOUNT) AS ck,
c.value('.', 'VARCHAR(250)') AS [Code]
FROM #xml1.nodes('//root/r') AS a(c)) AS Code
INNER JOIN
(SELECT ROW_NUMBER() OVER (ORDER BY ##ROWCOUNT) AS nk,
n.value('.', 'VARCHAR(250)') AS [Name]
FROM #xml2.nodes('//root/r') AS a(n)) AS Name ON Code.ck = Name.nk
INNER JOIN
(SELECT ROW_NUMBER() OVER (ORDER BY ##ROWCOUNT) AS sk,
s.value('.', 'VARCHAR(250)') AS [Symbol]
FROM #xml3.nodes('//root/r') AS a(s)) AS Symbol ON Symbol.sk = Name.nk
RETURN
END
GO
CREATE VIEW [dbo].[CurrencyView]
AS
SELECT * FROM [dbo].[CurrencyTableGenerator]()
GO
Thanks to RThomas for the function.
I am using SSMS 2008 and trying to concatenate one of the rows together based on a different field's grouping. I have two columns, people_id and address_desc. They look like this:
address_desc people_id
---------- ------------
Murfreesboro, TN 37130 F15D1135-9947-4F66-B778-00E43EC44B9E
11 Mohawk Rd., Burlington, MA 01803 C561918F-C2E9-4507-BD7C-00FB688D2D6E
Unknown, UN 00000 C561918F-C2E9-4507-BD7C-00FB688D2D6E Jacksonville, NC 28546 FC7C78CD-8AEA-4C8E-B93D-010BF8E4176D
Memphis, TN 38133 8ED8C601-5D35-4EB7-9217-012905D6E9F1
44 Maverick St., Fitchburg, MA 8ED8C601-5D35-4EB7-9217-012905D6E9F1
Now I want to concatenate the address_desc field / people_id. So the first one here should just display "Murfreesboro, TN 37130" for address_desc. But second person should have just one line instead of two which says "11 Mohawk Rd., Burlington, MA 01803;Unknown, UN 00000" for address_desc.
How do I do this? I tried using CTE, but this was giving me ambiguity error:
WITH CTE ( people_id, address_list, address_desc, length )
AS ( SELECT people_id, CAST( '' AS VARCHAR(8000) ), CAST( '' AS VARCHAR(8000) ), 0
FROM dbo.address_view
GROUP BY people_id
UNION ALL
SELECT p.people_id, CAST( address_list +
CASE WHEN length = 0 THEN '' ELSE ', ' END + c.address_desc AS VARCHAR(8000) ),
CAST( c.address_desc AS VARCHAR(8000)), length + 1
FROM CTE c
INNER JOIN dbo.address_view p
ON c.people_id = p.people_id
WHERE p.address_desc > c.address_desc )
SELECT people_id, address_list
FROM ( SELECT people_id, address_list,
RANK() OVER ( PARTITION BY people_id ORDER BY length DESC )
FROM CTE ) D ( people_id, address_list, rank )
WHERE rank = 1 ;
Here was my initial SQL query:
SELECT a.address_desc, a.people_id
FROM dbo.address_view a
INNER JOIN (SELECT people_id
FROM dbo.address_view
GROUP BY people_id
HAVING COUNT(*) > 1) t
ON a.people_id = t.people_id
order by a.people_id
You can use FOR XML PATH('') like this:
DECLARE #TestData TABLE
(
address_desc NVARCHAR(100) NOT NULL
,people_id UNIQUEIDENTIFIER NOT NULL
);
INSERT #TestData
SELECT 'Murfreesboro, TN 37130', 'F15D1135-9947-4F66-B778-00E43EC44B9E'
UNION ALL
SELECT '11 Mohawk Rd., Burlington, MA 01803', 'C561918F-C2E9-4507-BD7C-00FB688D2D6E'
UNION ALL
SELECT 'Unknown, UN 00000', 'C561918F-C2E9-4507-BD7C-00FB688D2D6E'
UNION ALL
SELECT 'Memphis, TN 38133', '8ED8C601-5D35-4EB7-9217-012905D6E9F1'
UNION ALL
SELECT '44 Maverick St., Fitchburg, MA', '8ED8C601-5D35-4EB7-9217-012905D6E9F1';
SELECT a.people_id,
(SELECT SUBSTRING(
(SELECT ';'+b.address_desc
FROM #TestData b
WHERE a.people_id = b.people_id
FOR XML PATH(''), TYPE).value('.', 'NVARCHAR(MAX)')
,2
,4000)
) GROUP_CONCATENATE
FROM #TestData a
GROUP BY a.people_id
Results:
people_id GROUP_CONCATENATE
------------------------------------ ------------------------------------------------------
F15D1135-9947-4F66-B778-00E43EC44B9E Murfreesboro, TN 37130
C561918F-C2E9-4507-BD7C-00FB688D2D6E 11 Mohawk Rd., Burlington, MA 01803;Unknown, UN 00000
8ED8C601-5D35-4EB7-9217-012905D6E9F1 Memphis, TN 38133;44 Maverick St., Fitchburg, MA