WITH final AS (
SELECT 'a' AS gname, 'b' AS pname, 'c' AS name, 1 AS gid, 2 AS pid, 3 AS did, 3 AS inp
UNION
SELECT 'a1' AS gname, 'b1' AS pname, 'c1' AS name, 11 AS gid, 21 AS pid, 31 AS did, 3 AS inp
)
Now I want to write a query depending on the inp column value
SELECT
(CASE final.inp
WHEN 1
THEN
(SELECT DISTINCT(final.gid) AS id, final.gname as name FROM
final ORDER BY final.gname)
WHEN 2
THEN
(SELECT DISTINCT(final.pid) AS id, final.pname as name FROM
final WHERE final.gid = $1 ORDER BY final.pname)
WHEN 3
THEN
(SELECT DISTINCT(final.did) AS id, final.name as name FROM
final WHERE final.pid = $1 ORDER BY final.name)
END)
FROM (%s) final;
I know this is not a correct way of writing it.
But this will give you an idea what I am trying to do.
if inp = 1 -> get unique gid's and gname and order by gname
if inp = 2 -> get unique pid's and pname where gid = and order by pname.
I want to write this logic in psql.
I know case When can have only one column so I have to create two cases for a single final.inp=1 for name and id.
I ain't able to write this logic because of this part
(SELECT DISTINCT(final.pid) AS id, final.pname as name FROM
final WHERE final.gid = $1 ORDER BY final.pname)
WHERE ORDER BY <--- and passing the same final value to it.
I am not able to implement it. Can anyone help?
Only assumption
select distinct
case when inp = 1 then gid
when inp = 2 then pid
when inp = 3 then did
end new_id,
case when inp = 1 then gname
when inp = 2 then pname
when inp = 3 then name
end as name
from final
order by 2
DB Fiddle playground
If I input a string as given below, I should be able to convert as mentioned below.
Ex 1: String - 5AB89C should be converted as 0000000005AB0000000089C
Ex 2: String GH1HJ should be converted as GH0000000001HJ
Ex 3: String N99K7H45 should be B0000000099K0000000007H0000000045
Each number should be complimented with 10 leading zeros including the number. In Ex:1, number 5 is complemented with 9 leading zeros making 10 digits, same way 89 is complimented with 8 leading zeros making total of 10 digits. Alphabets and any special characters should be untouched.
Once you get a copy of PatternSplitCM This is easy as pie.
Here's how we do it with one value:
DECLARE #string VARCHAR(8000) = '5AB89C'
SELECT CASE f.[matched] WHEN 1 THEN '00000000'+'' ELSE '' END + f.item
FROM dbo.patternsplitCM(#String,'[0-9]') AS f
ORDER BY f.ItemNumber
FOR XML PATH('');
Returns: 000000005AB0000000089C
Now against a table:
-- sample data
DECLARE #table TABLE (StringId INT IDENTITY, String VARCHAR(8000));
INSERT #table(String)
VALUES('5AB89C'),('GH1HJ'),('N99K7H45');
SELECT t.StringId, oldstring = t.String, newstring = f.padded
FROM #table AS t
CROSS APPLY
(
SELECT CASE f.[matched] WHEN 1 THEN '00000000'+'' ELSE '' END + f.item
FROM dbo.patternsplitCM(t.String,'[0-9]') AS f
ORDER BY f.ItemNumber
FOR XML PATH('')
) AS f(padded);
Returns:
StringId oldstring newstring
----------- ----------------- --------------------------------------
1 5AB89C 000000005AB0000000089C
2 GH1HJ GH000000001HJ
3 N99K7H45 N0000000099K000000007H0000000045
... and that's it. The code to create PatternSplitCM is below.
PatternSplitCM Code:
CREATE FUNCTION dbo.PatternSplitCM
(
#List VARCHAR(8000) = NULL
,#Pattern VARCHAR(50)
) RETURNS TABLE WITH SCHEMABINDING
AS
RETURN
WITH numbers AS (
SELECT TOP(ISNULL(DATALENGTH(#List), 0))
n = ROW_NUMBER() OVER(ORDER BY (SELECT NULL))
FROM
(VALUES (0),(0),(0),(0),(0),(0),(0),(0),(0),(0)) d (n),
(VALUES (0),(0),(0),(0),(0),(0),(0),(0),(0),(0)) e (n),
(VALUES (0),(0),(0),(0),(0),(0),(0),(0),(0),(0)) f (n),
(VALUES (0),(0),(0),(0),(0),(0),(0),(0),(0),(0)) g (n))
SELECT
ItemNumber = ROW_NUMBER() OVER(ORDER BY MIN(n)),
Item = SUBSTRING(#List,MIN(n),1+MAX(n)-MIN(n)),
Matched
FROM (
SELECT n, y.Matched, Grouper = n - ROW_NUMBER() OVER(ORDER BY y.Matched,n)
FROM numbers
CROSS APPLY (
SELECT Matched = CASE WHEN SUBSTRING(#List,n,1) LIKE #Pattern THEN 1 ELSE 0 END
) y
) d
GROUP BY Matched, Grouper
I have a table with unstructured data I am trying to analyze to try to build a relational lookup. I do not have use of word cloud software.
I really have no idea how to solve this problem. Searching for solutions has lead me to tools that might do this for me that cost money, not coded solutions.
Basically my data looks like this:
CK1 CK2 Comment
--------------------------------------------------------------
1 A This is a comment.
2 A Another comment here.
And this is what I need to create:
CK1 CK2 Words
--------------------------------------------------------------
1 A This
1 A is
1 A a
1 A comment.
2 A Another
2 A comment
2 A here.
What you are trying to do is tokenize a string using a space as a Delimiter. In the SQL world people often refer to functions that do this as a "Splitter". The potential pitfall of using a splitter for this type of thing is how words can be separated by multiple spaces, tabs, CHAR(10)'s, CHAR(13)'s, CHAR()'s, etc. Poor grammar, such as not adding a space after a period results in this:
" End of sentence.Next sentence"
sentence.Next is returned as a word.
The way I like to tokenize human text is to:
Replace any text that isn't a character with a space
Replace duplicate spaces
Trim the string
Split the newly transformed string using a space as the delimiter.
Below is my solution followed by the DDL to create the functions used.
-- Sample Data
DECLARE #yourtable TABLE (CK1 INT, CK2 CHAR(1), Comment VARCHAR(8000));
INSERT #yourtable (CK1, CK2, Comment)
VALUES
(1,'A','This is a typical comment...Follewed by another...'),
(2,'A','This comment has double spaces and tabs and even carriage
returns!');
-- Solution
SELECT t.CK1, t.CK2, split.itemNumber, split.itemIndex, split.itemLength, split.item
FROM #yourtable AS t
CROSS APPLY samd.patReplace(t.Comment,'[^a-zA-Z ]',' ') AS c1
CROSS APPLY samd.removeDupChar8K(c1.newString,' ') AS c2
CROSS APPLY samd.delimitedSplitAB8K(LTRIM(RTRIM(c2.NewString)),' ') AS split;
Results (truncated for brevity):
CK1 CK2 itemNumber itemIndex itemLength item
----------- ---- -------------------- ----------- ----------- --------------
1 A 1 1 4 This
1 A 2 6 2 is
1 A 3 9 1 a
1 A 4 11 7 typical
1 A 5 19 7 comment
...
2 A 1 1 4 This
2 A 2 6 7 comment
2 A 3 14 3 has
2 A 4 18 6 double
...
Note that the splitter I'm using is based of Jeff Moden's Delimited Split8K with a couple tweeks.
Functions used:
CREATE FUNCTION dbo.rangeAB
(
#low bigint,
#high bigint,
#gap bigint,
#row1 bit
)
RETURNS TABLE WITH SCHEMABINDING AS RETURN
WITH L1(N) AS
(
SELECT 1
FROM (VALUES
(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),
(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),
(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),
(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),(0),
(0),(0)) T(N) -- 90 values
),
L2(N) AS (SELECT 1 FROM L1 a CROSS JOIN L1 b CROSS JOIN L1 c),
iTally AS (SELECT rn = ROW_NUMBER() OVER (ORDER BY (SELECT 1)) FROM L2 a CROSS JOIN L2 b)
SELECT r.RN, r.OP, r.N1, r.N2
FROM
(
SELECT
RN = 0,
OP = (#high-#low)/#gap,
N1 = #low,
N2 = #gap+#low
WHERE #row1 = 0
UNION ALL -- COALESCE required in the TOP statement below for error handling purposes
SELECT TOP (ABS((COALESCE(#high,0)-COALESCE(#low,0))/COALESCE(#gap,0)+COALESCE(#row1,1)))
RN = i.rn,
OP = (#high-#low)/#gap+(2*#row1)-i.rn,
N1 = (i.rn-#row1)*#gap+#low,
N2 = (i.rn-(#row1-1))*#gap+#low
FROM iTally AS i
ORDER BY i.rn
) AS r
WHERE #high&#low&#gap&#row1 IS NOT NULL AND #high >= #low AND #gap > 0;
GO
CREATE FUNCTION samd.NGrams8k
(
#string VARCHAR(8000), -- Input string
#N INT -- requested token size
)
RETURNS TABLE WITH SCHEMABINDING AS RETURN
SELECT
position = r.RN,
token = SUBSTRING(#string, CHECKSUM(r.RN), #N)
FROM dbo.rangeAB(1, LEN(#string)+1-#N,1,1) AS r
WHERE #N > 0 AND #N <= LEN(#string);
GO
CREATE FUNCTION samd.patReplace8K
(
#string VARCHAR(8000),
#pattern VARCHAR(50),
#replace VARCHAR(20)
)
RETURNS TABLE WITH SCHEMABINDING AS RETURN
SELECT newString =
(
SELECT CASE WHEN #string = CAST('' AS VARCHAR(8000)) THEN CAST('' AS VARCHAR(8000))
WHEN #pattern+#replace+#string IS NOT NULL THEN
CASE WHEN PATINDEX(#pattern,token COLLATE Latin1_General_BIN)=0
THEN ng.token ELSE #replace END END
FROM samd.NGrams8K(#string, 1) AS ng
ORDER BY ng.position
FOR XML PATH(''),TYPE
).value('text()[1]', 'VARCHAR(8000)');
GO
CREATE FUNCTION samd.delimitedSplitAB8K
(
#string VARCHAR(8000), -- input string
#delimiter CHAR(1) -- delimiter
)
RETURNS TABLE WITH SCHEMABINDING AS RETURN
SELECT
itemNumber = ROW_NUMBER() OVER (ORDER BY d.p),
itemIndex = CHECKSUM(ISNULL(NULLIF(d.p+1, 0),1)),
itemLength = CHECKSUM(item.ln),
item = SUBSTRING(#string, d.p+1, item.ln)
FROM (VALUES (DATALENGTH(#string))) AS l(s) -- length of the string
CROSS APPLY
(
SELECT 0 UNION ALL -- for handling leading delimiters
SELECT ng.position
FROM samd.NGrams8K(#string, 1) AS ng
WHERE token = #delimiter
) AS d(p) -- delimiter.position
CROSS APPLY (VALUES( --LEAD(d.p, 1, l.s+l.d) OVER (ORDER BY d.p) - (d.p+l.d)
ISNULL(NULLIF(CHARINDEX(#delimiter,#string,d.p+1),0)-(d.p+1), l.s-d.p))) AS item(ln);
GO
CREATE FUNCTION dbo.RemoveDupChar8K(#string varchar(8000), #char char(1))
RETURNS TABLE WITH SCHEMABINDING AS RETURN
SELECT NewString =
replace(replace(replace(replace(replace(replace(replace(
#string COLLATE LATIN1_GENERAL_BIN,
replicate(#char,33), #char), --33
replicate(#char,17), #char), --17
replicate(#char,9 ), #char), -- 9
replicate(#char,5 ), #char), -- 5
replicate(#char,3 ), #char), -- 3
replicate(#char,2 ), #char), -- 2
replicate(#char,2 ), #char); -- 2
GO
1) If we are using SQL Server 2016 and above then we should probably
use the built-in function STRING_SPLIT
-- SQL 2016and above
DECLARE #txt NVARCHAR(100) = N'This is a comment.'
select [value] from STRING_SPLIT(#txt, ' ')
2) Only if 1 does not fit, then if the number of separation (the space in our case) is less then 3 which fit your sample data, then we should probably use PARSENAME
-- BEFORE SQL 2016 if we have less than 4 parts
DECLARE #txt NVARCHAR(100) = N'This is a comment.'
DECLARE #Temp NVARCHAR(200) = REPLACE (#txt,'.','#')
SELECT t FROM (VALUES(1),(2),(3),(4))T1(n)
CROSS APPLY (SELECT REPLACE(PARSENAME(REPLACE(#Temp,' ','.'),T1.n), '#','.'))T2(t)
3) Only if the 1 and 2 does not fit, then we should use SQLCLR function
http://dataeducation.com/sqlclr-string-splitting-part-2-even-faster-even-more-scalable/
4) Only if we cannot use 1,2 and we cannot use SQLCLR (which implies a real problematic administration and has nothing with security since you can have all the SQLCLR function in a read-only database for the use of all users, as I explain in my lectures), then you can use T-SQL and create UDF.
https://sqlperformance.com/2012/07/t-sql-queries/split-strings
I want to update more than 10 columns at the same time , and my problem is I want to put where clause for all these columns.
My code is:
UPDATE Customer AS c
SET
name = a.name,
address= a.address,
telephone = a.telephone,
--
--
--
FROM Customer a
INNER JOIN
( SELECT casenumber
, max(currentDate) AS md
FROM Customer
GROUP BY casenumber
) AS z
ON z.casenumber = a.casenumber
AND z.md = a.currentDate
WHERE (a.casenumber = c.casenumber)
In the above statement I want to add condition as to update columns only when they are not 0.
for exmple,
UPDATE Customer AS C
SET name = a.name,
address= a.address,
...
..
WHERE a.name <> 0,
a.address <> 0,
a.telephone <> 0
....
...
Is it possible to put where condition to check each column?
Any suggestions are appreciated..
Something like this (assuming name <> 0 is a typo and your names are really character columns)
UPDATE customer AS c
SET name = CASE WHEN name <> '' THEN a.name ELSE name END,
address = CASE WHEN address <> '' THEN a.address ELSE address END
This essentially updates the column to it's current value if it's empty.
Note that this does not deal with NULL values! If you need to treat NULL and '' identically you need to use coalesce(name, '') instead.
I have tables with following structure
create table Doc(
id int identity(1, 1) primary key,
DocumentStartValue varchar(100)
)
create Metadata (
DocumentValue varchar(100),
StartDesignation char(1),
PageNumber int
)
GO
Doc contains
id DocumentStartValue
1000 ID-1
1100 ID-5
2000 ID-8
3000 ID-9
Metadata contains
Documentvalue StartDesignation PageNumber
ID-1 D 0
ID-2 NULL 1
ID-3 NULL 2
ID-4 NULL 3
ID-5 D 0
ID-6 NULL 1
ID-7 NULL 2
ID-8 D 0
ID-9 D 0
What I need to is to map Metadata.DocumentValues to Doc.id
So the result I need is something like
id DocumentValue PageNumber
1000 ID-1 0
1000 ID-2 1
1000 ID-3 2
1000 ID-4 3
1100 ID-5 0
1100 ID-6 1
1100 ID-7 2
2000 ID-8 0
3000 ID-9 0
Can it be achieved without the use of cursor?
Something like, sorry can't test
;WITH RowList AS
( --assign RowNums to each row...
SELECT
ROW_NUMBER() OVER (ORDER BY id) AS RowNum,
id, DocumentStartValue
FROM
doc
), RowPairs AS
( --this allows us to pair a row with the previous rows to create ranges
SELECT
R.DocumentStartValue AS Start, R.id,
R1.DocumentStartValue AS End
FROM
RowList R JOIN RowList R1 ON R.RowNum + 1 = R1.RowNum
)
--use ranges to join back and get the data
SELECT
RP.id, M.DocumentValue, M.PageNumber
FROM
RowPairs RP
JOIN
Metadata M ON RP.Start <= M.DocumentValue AND M.DocumentValue < RP.End
Edit: This assumes that you can rely on the ID-x values matching and being ascending. If so, StartDesignation is superfluous/redundant and may conflict with the Doc table DocumentStartValue
with rm as
(
select DocumentValue
,PageNumber
,case when StartDesignation = 'D' then 1 else 0 end as IsStart
,row_number() over (order by DocumentValue) as RowNumber
from Metadata
)
,gm as
(
select
DocumentValue as DocumentGroup
,DocumentValue
,PageNumber
,RowNumber
from rm
where RowNumber = 1
union all
select
case when rm.IsStart = 1 then rm.DocumentValue else gm.DocumentGroup end
,rm.DocumentValue
,rm.PageNumber
,rm.RowNumber
from gm
inner join rm on rm.RowNumber = (gm.RowNumber + 1)
)
select d.id, gm.DocumentValue, gm.PageNumber
from Doc d
inner join gm on d.DocumentStartValue = gm.DocumentGroup
Try to use query above (maybe you will need to add option (maxrecursion ...) also) and add index on DocumentValue for Metadata table. Also, it it's possible - it will be better to save appropriate group on Metadat rows inserting.
UPD: I've tested it and fixed errors in my query, not it works and give result as in initial question.
UPD2: And recommended indexes:
create clustered index IX_Metadata on Metadata (DocumentValue)
create nonclustered index IX_Doc_StartValue on Doc (DocumentStartValue)