T-SQL Space Before Capital Letters - tsql

The question is self explanatory. Could you please point out a way to put spaces between each capital letter of a string.
SELECT dbo.SpaceBeforeCap('ThisIsATestString')
would result in
This Is A Test String.

This will add spaces only if the previous and next character is lowercase. That way 'MyABCAnalysis' will be 'My ABC Analysis'.
I added a check for a previous space too. Since some of our strings are prefixed with 'GR_' and some also contain underscores, we can use the replace function as follows:
select dbo.GR_SpaceBeforeCap(replace('GR_ABCAnalysis_Test','_',' '))
Returns 'GR ABC Analysis Test'
CREATE FUNCTION GR_SpaceBeforeCap (
#str nvarchar(max)
)
returns nvarchar(max)
as
begin
declare
#i int, #j int
, #cp nchar, #c0 nchar, #c1 nchar
, #result nvarchar(max)
select
#i = 1
, #j = len(#str)
, #result = ''
while #i <= #j
begin
select
#cp = substring(#str,#i-1,1)
, #c0 = substring(#str,#i+0,1)
, #c1 = substring(#str,#i+1,1)
if #c0 = UPPER(#c0) collate Latin1_General_CS_AS
begin
-- Add space if Current is UPPER
-- and either Previous or Next is lower
-- and Previous or Current is not already a space
if #c0 = UPPER(#c0) collate Latin1_General_CS_AS
and (
#cp <> UPPER(#cp) collate Latin1_General_CS_AS
or #c1 <> UPPER(#c1) collate Latin1_General_CS_AS
)
and #cp <> ' '
and #c0 <> ' '
set #result = #result + ' '
end -- if #co
set #result = #result + #c0
set #i = #i + 1
end -- while
return #result
end

Assuming SQL Server 2005 or later, this modified from code taken here: http://www.kodyaz.com/articles/case-sensitive-sql-split-function.aspx
CREATE FUNCTION SpaceBeforeCap
(
#str nvarchar(max)
)
returns nvarchar(max)
as
begin
declare #i int, #j int
declare #returnval nvarchar(max)
set #returnval = ''
select #i = 1, #j = len(#str)
declare #w nvarchar(max)
while #i <= #j
begin
if substring(#str,#i,1) = UPPER(substring(#str,#i,1)) collate Latin1_General_CS_AS
begin
if #w is not null
set #returnval = #returnval + ' ' + #w
set #w = substring(#str,#i,1)
end
else
set #w = #w + substring(#str,#i,1)
set #i = #i + 1
end
if #w is not null
set #returnval = #returnval + ' ' + #w
return ltrim(#returnval)
end
This can then be called just as you have suggested above.

This function combines previous answers. Selectively choose to preserve adjacent CAPS:
CREATE FUNCTION SpaceBeforeCap (
#InputString NVARCHAR(MAX),
#PreserveAdjacentCaps BIT
)
RETURNS NVARCHAR(MAX)
AS
BEGIN
DECLARE
#i INT, #j INT,
#previous NCHAR, #current NCHAR, #next NCHAR,
#result NVARCHAR(MAX)
SELECT
#i = 1,
#j = LEN(#InputString),
#result = ''
WHILE #i <= #j
BEGIN
SELECT
#previous = SUBSTRING(#InputString,#i-1,1),
#current = SUBSTRING(#InputString,#i+0,1),
#next = SUBSTRING(#InputString,#i+1,1)
IF #current = UPPER(#current) COLLATE Latin1_General_CS_AS
BEGIN
-- Add space if Current is UPPER
-- and either Previous or Next is lower or user chose not to preserve adjacent caps
-- and Previous or Current is not already a space
IF #current = UPPER(#current) COLLATE Latin1_General_CS_AS
AND (
#previous <> UPPER(#previous) COLLATE Latin1_General_CS_AS
OR #next <> UPPER(#next) collate Latin1_General_CS_AS
OR #PreserveAdjacentCaps = 0
)
AND #previous <> ' '
AND #current <> ' '
SET #result = #result + ' '
END
SET #result = #result + #current
SET #i = #i + 1
END
RETURN #result
END
GO
SELECT dbo.SpaceBeforeCap('ThisIsASampleDBString', 1)
GO
SELECT dbo.SpaceBeforeCap('ThisIsASampleDBString', 0)

CLR and regular expressions or 26 replace statements a case sensitive collate clause and a trim.

Another strategy would be to check the ascii value of each character:
create function SpaceBeforeCap
(#str nvarchar(max))
returns nvarchar(max)
as
begin
declare #result nvarchar(max)= left(#str, 1),
#i int = 2
while #i <= len(#str)
begin
if ascii(substring(#str, #i, 1)) between 65 and 90
select #result += ' '
select #result += substring(#str, #i, 1)
select #i += 1
end
return #result
end
/***
SELECT dbo.SpaceBeforeCap('ThisIsATestString')
**/

To avoid loops altogether, use of a tally table can help here. If you are running on SQL 2022, then the generate_series function can remove even this dependency. This method will be significantly faster than iterating through a loop.
create function core.ufnAddSpaceBeforeCapital
(
#inputString nvarchar(max)
)
returns nvarchar(max)
as
begin
declare #outputString nvarchar(max)
select
#outputString = string_agg(iif(t.value = 1, upper(substring(#inputString,t.value,1)),iif(ascii(substring(#inputString,t.value,1)) between 65 and 90, ' ','') + substring(#inputString,t.value,1)),'')
from
generate_series(1,cast(len(#inputString) as int)) t
return #outputString
end
The scalar function is not inlineable, so I've provided an alternative inline table-valued function if that's what you need.
create function core.ufnAddSpaceBeforeCapitalITVF
(
#inputString nvarchar(max)
)
returns table
as
return
(
select
string_agg(iif(t.value = 1, upper(substring(#inputString,t.value,1)),iif(ascii(substring(#inputString,t.value,1)) between 65 and 90, ' ','') + substring(#inputString,t.value,1)),'') as outputString
from
generate_series(1,cast(len(#inputString) as int)) t
)
end

While I really like the char looping answers I was not thrilled with the performance. I have found this performs in a fraction of the time for my use case.
CREATE function SpaceBeforeCap
(#examine nvarchar(max))
returns nvarchar(max)
as
begin
DECLARE #index as INT
SET #index = PatIndex( '%[^ ][A-Z]%', #examine COLLATE Latin1_General_BIN)
WHILE #index > 0 BEGIN
SET #examine = SUBSTRING(#examine, 1, #index) + ' ' + SUBSTRING(#examine, #index + 1, LEN(#examine))
SET #index = PatIndex( '%[^ ][A-Z]%', #examine COLLATE Latin1_General_BIN)
END
RETURN LTRIM(#examine)
end
This makes use of the fact that
case sensitive pattern search only works in some collations. The character class [^ ] means anything except space, so as we add the missing spaces we match farther into the string until it is complete.

Related

How to remove duplicate words from a string comparing to other string in SQL

I need to check string2 if there are words that I already have in string1 and remove those.
declare #Text1 nvarchar(500) = 'apple, orange, pear'
declare #Text2 nvarchar(500) = 'banana, apple'
The output should be 'banana'
Edit: I just realized I made the question not properly.
So, this is right:
DECLARE #Tab TABLE (Ingredients nvarchar(500))
insert #Tab select 'apple, orange, pear'
insert #Tab select 'banana, apple'
insert #Tab select 'pear, mango'
declare #Ingredients nvarchar(4000) = ''
select #Ingredients = #Ingredients + value + ',' from #Tab cross apply STRING_SPLIT(Ingredients, ',')
SELECT #Ingredients
current result:
apple,orange,pear,banana,apple,pear,mango,
expected result:
apple,orange,pear,banana,mango,
So if that is the case I would like to suggest you to create a function:
SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO
CREATE FUNCTION GetUniqueValues
(
#LIST AS NVARCHAR(MAX)
)
RETURNS NVARCHAR(MAX)
AS
BEGIN
DECLARE #POS INT
DECLARE #LEN INT
DECLARE #VALUE NVARCHAR(MAX)
SET #POS = 0
SET #LEN = 0
DECLARE #RESULT NVARCHAR(MAX) = ''
WHILE CHARINDEX(',', #LIST, #POS + 1) > 0
BEGIN
SET #LEN = CHARINDEX(',', #LIST, #POS + 1) - #POS
SET #VALUE = RTRIM(LTRIM(SUBSTRING(#LIST, #POS, #LEN)))
IF (CHARINDEX(#VALUE, #RESULT) = 0)
BEGIN
IF (LEN(RTRIM(LTRIM(#RESULT))) = 0)
BEGIN
SET #RESULT = #VALUE
END
ELSE
BEGIN
SET #RESULT = #RESULT + ', ' + #VALUE
END
END
SET #POS = CHARINDEX(',', #LIST, #POS + #LEN) +1
END
RETURN #RESULT
END
GO
You can use this function like this based on you example:
SELECT dbo.GetUniqueValues(#Ingredients)
Expected result
apple, orange, pear, banana, mango
you can use something like this:
DECLARE #Text1 NVARCHAR(500)= 'apple, orange, pear';
DECLARE #Text2 NVARCHAR(500)= 'banana, apple, cucumber, pear';
--convert to xml for further split using nodes
declare #xmlText1 as xml = convert(xml, Concat('<a>',replace(#Text1,',','</a><a>'),'</a>'))
declare #xmlText2 as xml = convert(xml, Concat('<a>',replace(#Text2,',','</a><a>'),'</a>'))
--remove duplicates from #text2 that exist in #text1
;with cte (val) as (
select ', ' + value
from (
select ltrim(n.value('.', 'VARCHAR(10)')) AS value
from #xmlText2.nodes('a') as t(n)
except
select ltrim(n.value('.', 'VARCHAR(10)')) AS value
from #xmlText1.nodes('a') as t(n)
) as t
for xml path ('')
)
-- reassign #text2
select #Text2 = stuff(val,1,1,'') from cte
--output
select #Text2 as newText2
result
You can try this:
DECLARE #Text1 NVARCHAR(500)= 'apple, orange, pear';
DECLARE #Text2 NVARCHAR(500)= 'banana, apple';
SELECT *
INTO #temp
FROM
(
SELECT *
FROM fn_split(#Text1, ',')
) a;
SELECT *
INTO #temp1
FROM
(
SELECT *
FROM fn_split(#Text2, ',')
) b;
SELECT item
FROM #temp1 a
WHERE NOT EXISTS
(
SELECT item
FROM #temp b
WHERE a.item = b.item
);

Random Number Generator - Create a matrix of random numbers where the values in each row sum to X in T-SQL?

How to generate a matrix of random numbers where the values in each row add up to X in T-SQL?
The solution matrix should be dynamic:
User can specify number of columns to be returned in the result
User can specify number of rows to be returned in the result
Each row must sum to X (eg. 1)
create proc RandomNumberGenerator
(
#rows int
, #cols int
, #rowsumtotal float
)
as
....
First create a UDF...
CREATE FUNCTION [dbo].[_ex_fn_SplitToTable] (#str varchar(5000), #sep varchar(1) = null)
RETURNS #ReturnVal table (n int, s varchar(5000))
AS
/*
Alpha Test
-----------
select * from [dbo].[_ex_fn_SplitToTable_t2]('a b c d e',' ')
*/
BEGIN
if #sep = ' '
begin
set #sep = CHAR(167)
set #str = REPLACE(#str,' ',CHAR(167))
end
declare #str2 varchar(5000)
declare #sep2 varchar(1)
if LEN(ISNULL(#sep,'')) = 0
begin
declare #i int
set #i = 0
set #str2 = ''
declare #char varchar(1)
startloop:
set #i += 1
--print #i
set #char = substring(#str,#i,1)
set #str2 = #str2 + #char + ','
if LEN(#str) <= #i
goto exitloop
goto startloop
exitloop:
set #str2 = left(#str2,LEN(#str2) - 1)
set #sep2 = ','
--print #str2
end
else
begin
set #str2 = #str
set #sep2 = #sep
end
;WITH Pieces(n, start, stop) AS (
SELECT 1, 1, CHARINDEX(#sep2, #str2)
UNION ALL
SELECT n + 1, stop + 1, CHARINDEX(#sep2, #str2, stop + 1)
FROM Pieces
WHERE stop > 0
)
insert into #ReturnVal(n,s)
SELECT n,
SUBSTRING(#str2, start, CASE WHEN stop > 0 THEN stop-start ELSE 5000 END) AS s
FROM Pieces option (maxrecursion 32767)
RETURN
END
GO
Then, create this stored proc...
CREATE PROC [dbo].[RandomNumberGenerator]
(
#Pockets int = 6,
#SumTo float = 100,
#i_iterations int = 100
)
/*
ALPHA TEST
----------
exec RandomNumberGenerator 10, 100, 500
*/
AS
if object_id('tempdb..#_Random_00') is not null drop table #_Random_00
declare #columnstring varchar(max) = (SELECT REPLICATE('c ',#Pockets) as Underline)
print #columnstring
if object_id('tempdb..#_Random_columns') is not null drop table #_Random_columns
select s+CONVERT(varchar,dbo.PadLeft(convert(varchar,n),'0',3)) cols
into #_Random_columns
from [dbo].[_ex_fn_SplitToTable](#columnstring,' ') where LEN(s) > 0
-- ===========================
--select * from #_Random_columns
-- ===========================
declare #columns_sql varchar(max)
set #columns_sql =
(
select distinct
stuff((SELECT distinct + cast(cols as varchar(50)) + ' float, '
FROM (
select cols
from #_Random_columns
) t2
--where t2.n = t1.n
FOR XML PATH('')),3,0,'')
from (
select cols
from #_Random_columns
) t1
)
set #columns_sql = LEFT(#columns_sql,LEN(#columns_sql) - 1)
print #columns_sql
declare #sql varchar(max)
set #sql = 'if object_id(''tempdb..##_proctable_Random_01'') is not null drop table ##_proctable_Random_01 '
print #sql
execute(#sql)
set #sql = 'create table ##_proctable_Random_01 (rowid int,' + #columns_sql + ')'
print #sql
execute(#sql)
declare #TotalOfRand float
declare #i_inner int
declare #i_outer int
set #i_outer = 0
start_outer:
set #i_outer = #i_outer + 1
set #i_inner = 0
declare #sumstring varchar(max)
set #sumstring = ''
start_inner:
set #i_inner = #i_inner+1
set #sumstring = #sumstring + CONVERT(varchar, rand()) + ','
if #i_inner >= #Pockets
goto exit_inner
goto start_inner
exit_inner:
set #TotalOfRand = ( select sum(convert(float,s)) from dbo._ex_fn_SplitToTable(#sumstring,',') )
declare #sumstring_quotient varchar(max)
set #sumstring_quotient = replace(#sumstring,',', '/' + Convert(varchar,#TotalOfRand) + '*' + convert(varchar,#SumTo) + ',')
set #sumstring_quotient = LEFT(#sumstring_quotient,len(#sumstring_quotient) - 1)
print #sumstring_quotient
set #sql = '
insert into ##_proctable_Random_01
select
( select count(*) + 1 from ##_proctable_Random_01 ) rowid,' + #sumstring_quotient
execute(#sql)
if #i_outer >= #i_iterations
goto exit_outer
goto start_outer
exit_outer:
select * from ##_proctable_Random_01
drop table ##_proctable_Random_01
GO

Getting upper into lower case

In my SELECT statement, I have:
,UserName
When this comes through in the query, it appears as: JOHN.SMITH
Is it possible to use CAST or CONVERT to change this to John Smith?
Any advice gratefully appreciated.
Thanks.
First replace the period with a space:
SELECT REPLACE(SELECT UserName FROM YourTable, '.', ' ')
Save this in a variable, or put this select directly to the function below.
Unfortunately, I don't have t-sql at my disposal right now, so I can't check the syntax to be 100% correct.
Then to set only first chars to uppercase. If you were using oracle, I would tell you to use initcap, but this doesn't exist in t-sql.
Taken from link: http://www.devx.com/tips/Tip/17608
create function initcap (#text varchar(4000))
returns varchar(4000)
as
begin
declare #counter int,
#length int,
#char char(1),
#textnew varchar(4000)
set #text = rtrim(#text)
set #text = lower(#text)
set #length = len(#text)
set #counter = 1
set #text = upper(left(#text, 1) ) + right(#text, #length - 1)
while #counter <> #length --+ 1
begin
select #char = substring(#text, #counter, 1)
IF #char = space(1) or #char = '_' or #char = ',' or #char = '.' or #char = '\'
or #char = '/' or #char = '(' or #char = ')'
begin
set #textnew = left(#text, #counter) + upper(substring(#text,
#counter+1, 1)) + right(#text, (#length - #counter) - 1)
set #text = #textnew
end
set #counter = #counter + 1
end
return #text
end
So use this function to convert the uppercase string. Hope this helps.
You could go about it like so:
DECLARE #UserName AS varchar(50) = 'JOHN.SMITH'
SELECT LEFT(UPPER(LEFT(#UserName, CHARINDEX('.', #UserName)-1)),1) + SUBSTRING(LOWER(LEFT(#UserName, CHARINDEX('.', #UserName)-1)),2,LEN(LEFT(#UserName, CHARINDEX('.', #UserName)-1))-1) + ' ' + LEFT(UPPER(RIGHT(#UserName, LEN(#UserName) - CHARINDEX('.', #UserName))),1) + SUBSTRING(LOWER(RIGHT(#UserName, LEN(#UserName) - CHARINDEX('.', #UserName))),2,LEN(RIGHT(#UserName, LEN(#UserName) - CHARINDEX('.', #UserName)))-1)
It gets everything before the . and then uppers the first letter whilst lowering the rest and then does the same for everything after the ..
However, it would be much better if you handled this in your code as when you come back to reading this query you may not know what it's doing.

How do i can resolve this promblem?

I have an table include 1 column ID and 12 columns month (Month01 to Month12). If i have an parameter #month=9, how can i compare to get column Month01 to Month09 without Month10, Month11, Month12. Please help me!
Simo's answer is more elegant, but below is an alternative "basic" way to do this:
DECLARE #month INT
SET #month = 9
IF #Month = 1
BEGIN
SELECT Id, Month01
FROM MonthlyData
END
IF #Month = 2
BEGIN
SELECT Id, Month01, Month02
FROM MonthlyData
END
-- Repeat for months 3-9
IF #Month = 9
BEGIN
SELECT Id, Month01, Month02, Month03, Month04,
Month05, Month06, Month07, Month08, Month09
FROM MonthlyData
END
-- Repeat for months 10-12
See my SQL Fiddle.
declare #str varchar(1000)
SELECT #str= coalesce(#str + ', ', '') + a.name
FROM (
Select name from sys.columns
where object_id = OBJECT_ID('table_months')
and isnumeric(right(name,2))= 1 and name like 'month%'
and cast(right(name,2) as int) < '03') a
-- Instead of '03' you use a variable and assign required moths number
declare #sql nvarchar(100)
set #sql = 'select ID, '+ #str+' from table_months'
exec sp_executesql #sql
you may try this out also :)
DECLARE #month int = 9
DECLARE #Sql nvarchar(100) =''
DECLARE #pos int = 1
WHILE(#pos <= #month)
BEGIN
SET #Sql = #Sql + (',month' + right('00'+ rtrim(#pos), 2))
SET #pos = #pos + 1
END
SET #Sql= 'SELECT ID ' +#Sql + ' FROM table'
EXEC sp_executesql #Sql
DECLARE #month int
DECLARE #tableName nvarchar(128)
SET #month = 9;
SET #tableName = 'months' -- YOUR TABLE's NAME
DECLARE #query nvarchar(2048)
SET #query =
'SELECT id, ' + STUFF((SELECT DISTINCT ', ' + name
FROM sys.columns WHERE name LIKE'Month%'
AND object_id = OBJECT_ID(#tableName)
AND CONVERT(INT, RIGHT(name, 2)) <= #month
FOR XML PATH(''), TYPE).value('.', 'NVARCHAR(MAX)'),1,1,'')
+ ' FROM ' + #tableName;
EXEC(#query)

Add comma every nth character in value

my problem is pretty simple. I get a value from a sql select which looks like this:
ARAMAUBEBABRBGCNDKDEEEFOFIFRGEGRIEISITJPYUCAKZKG
and I need it like this:
AR,AM,AU,BE,BA,BR,BG,CN,DK,DE,EE,FO,FI,FR,GE,GR,IE,IS,IT,JP,YU,CA,KZ,KG
The length is different in each dataset.
I tried it with format(), stuff() and so on but nothing brought me the result I need.
Thanks in advance
With a little help of a numbers table and for xml path.
-- Sample table
declare #T table
(
Value nvarchar(100)
)
-- Sample data
insert into #T values
('ARAMAU'),
('ARAMAUBEBABRBGCNDKDEEEFOFIFRGEGRIEISITJPYUCAKZKG')
declare #Len int
set #Len = 2;
select stuff(T2.X.value('.', 'nvarchar(max)'), 1, 1, '')
from #T as T1
cross apply (select ','+substring(T1.Value, 1+Number*#Len, #Len)
from Numbers
where Number >= 0 and
Number < len(T1.Value) / #Len
order by Number
for xml path(''), type) as T2(X)
Try on SE-Data
Time to update your resume.
create function DontDoThis (
#string varchar(max),
#count int
)
returns varchar(max)
as
begin
declare #result varchar(max) = ''
declare #token varchar(max) = ''
while DATALENGTH(#string) > 0
begin
select #token = left(#string, #count)
select #string = REPLACE(#string, #token, '')
select #result += #token + case when DATALENGTH(#string) = 0 then '' else ',' end
end
return #result
end
Call:
declare #test varchar(max) = 'ARAMAUBEBABRBGCNDKDEEEFOFIFRGEGRIEISITJPYUCAKZKG'
select dbo.DontDoThis(#test, 2)
gbn's comment is exactly right, if not very diplomatic :) TSQL is a poor language for string manipulation, but if you write a CLR function to do this then you will have the best of both worlds: .NET string functions called from pure TSQL.
I believe this is what QQping is looking for.
-- select .dbo.DelineateEachNth('ARAMAUBEBABRBGCNDKDEEEFOFIFRGEGRIEISITJPYUCAKZKG',2,',')
create function DelineateEachNth
(
#str varchar(max), -- Incoming String to parse
#length int, -- Length of desired segment
#delimiter varchar(100) -- Segment delimiter (comma, tab, line-feed, etc)
)
returns varchar(max)
AS
begin
declare #resultString varchar(max) = ''
-- only set delimiter(s) when lenght of string is longer than desired segment
if LEN(#str) > #length
begin
-- continue as long as there is a remaining string to parse
while len(#str) > 0
begin
-- as long as know we still need to create a segment...
if LEN(#str) > #length
begin
-- build result string from leftmost segment length
set #resultString = #resultString + left(#str, #length) + #delimiter
-- continually shorten result string by current segment
set #str = right(#str, len(#str) - #length)
end
-- as soon as the remaining string is segment length or less,
-- just use the remainder and empty the string to close the loop
else
begin
set #resultString = #resultString + #str
set #str = ''
end
end
end
-- if string is less than segment length, just pass it through
else
begin
set #resultString = #str
end
return #resultString
end
With a little help from Regex
select Wow=
(select case when MatchIndex %2 = 0 and MatchIndex!=0 then ',' + match else match end
from dbo.RegExMatches('[^\n]','ARAMAUBEBABRBGCNDKDEEEFOFIFRGEGRIEISITJPYUCAKZKG',1)
for xml path(''))