Related
Let's say I have data:
heloo
cuube
triniity
How to write script that will replace those "doubled" characters with only one? So the result from the above data set would be:
helo
cube
trinity
Usually I post some script where I tried to achieve this, but this time I can't think of any.
This should work:
CREATE PROCEDURE remove_duplicate_characters(#string VARCHAR(100))
AS
DECLARE #result VARCHAR(100)
SET #result=''
SELECT #result=#result+MIN(SUBSTRING(#string ,number,1)) FROM
(
SELECT number FROM master..spt_values WHERE type='p' AND number BETWEEN 1 AND len(#string )) AS t GROUP BY SUBSTRING(#string,number,1) ORDER BY MIN(number)
)
SELECT #result
GO
You then call it like this:
EXEC remove_duplicate_characters 'heloo'
Source
This script does not depend on having access to master functions, and just relies on t-sql string functions.
declare #word varchar(100) = 'aaaacuuuuuubeeeee', #result varchar(100) = ''
declare #letter char, #idx int = 0, #lastletter char = ''
while(#idx <= len(#word))
begin
select #letter = substring(#word,#idx,1)
if (#letter != #lastletter)
begin
select #result = concat(#result,#letter)
end
select #lastletter = #letter,#idx = #idx + 1
end
select #result
I'm having a hard time trying to assign a field name and then place that into a SELECT statement in T SQL. First - I want to get the SELECT statement to work without the convert error popping up, then I want the field value to be assigned to another variable. My code that fails is below.
DECLARE #lid integer
DECLARE #lrid integer
DECLARE #pct integer
DECLARE #rds integer
SET #lid = 4
SET #lrid = 46
SET #pct = 75
SET #rds = 4
DECLARE #c integer --SIMPLE COUNTER
DECLARE #sql nvarchar(999) --RAW SCORE FIELD
DECLARE #cpct float --CALCULATED PERCENT
DECLARE #scrt integer --TOP SCORE
DECLARE #scrf nvarchar(10) --RAW SCORE FIELD
DECLARE #scrr integer --ROUND RAW SCORE
DECLARE #scrs integer --SUMMED RAW SCORE
--SET VARIABLES
SET #cpct = #pct * .01
SET #scrt = (SELECT points FROM league WHERE id = #lid)
--LOOP THROUGH SCORES FROM 1 ON UP
SET #c = 1
SET #scrs = 0
WHILE (#c <= 30)
BEGIN
SET #scrf = 'round' + CAST(#c AS nvarchar(2))
SELECT #scrr =(SELECT #scrf FROM league_lineup WHERE id = #lrid)
SET #scrs = #scrs+#scrr
IF #c > #rds
PRINT 'ROUND ' + CAST(#c AS nvarchar(3)) + ' - SCORE: ' + CAST(#scrs AS nvarchar(5))
SET #c = #c + 1
END
...doesn't work....
Your basic problem is that in TSQL, data is never evaluated as though it weren't data*. That means this is what's happening is similar to that below:
SET #c = 25.48;
SET #scrf = 'round' + CAST(#c AS nvarchar(2));
The value of #scrf is now 'round25.48'. That means that this:
SELECT #scrr = (SELECT #scrf FROM league_lineup WHERE id = #lrid)
Is equivalent to this:
SELECT #scrr =(SELECT 'round25.48' FROM league_lineup WHERE id = #lrid)
Which means you're trying to assign the string (nvarchar) 'round25.48'to #scrr, an integer variable. So you get a conversion error.
You'll want to do something more like:
SELECT #scrr = (SELECT ROUND(#c) FROM league_lineup WHERE id = #lrid);
Finally, be careful with loops in SQL. Chances are you don't actually need it.
*Data can be evaluated as though it were SQL with special functions like EXEC(), but those are exceptions. Any anyways the data must be evaluated as an entire statement and not a fragment.
You should use dynamic query with output parameter in this situation:
Change
SELECT #scrr =(SELECT #scrf FROM league_lineup WHERE id = #lrid)
SET #scrs = #scrs+#scrr
to
DECLARE #sql = 'SELECT #scrr = ' + #scrf + ' FROM league_lineup WHERE id = #lrid'
EXEC sp_executesql #sql, N'#scrr int OUTPUT, #lrid int', #scrr OUTPUT, #lrid
SET #scrs = #scrs+#scrr
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(''))
DECLARE #str VARCHAR (MAX);
SELECT #str = COALESCE(#str + CHAR(10), '') +
'EXECUTE CreateDeno ' + CAST(ID AS VARCHAR)
FROM GL_To_Batch_Details
WHERE TYPE = 'C' AND
Deno_ID IS NULL;
--PRINT #str;--SELECT #str;
**EXEC(#str);**
EDITED
Does EXECUTE statement truncate strings to 8,000 chars like PRINT? How can I execute a dynamic SQL statement having more than 8,000 chars?
Any suggestion would be warmly appreciated.
PRINT is limited to 8k in output.
There is also an 8k limit in SSMS results pane.
Go to
tools -> options -> query results
to see the options.
To verify the length of the actual data, check:
SELECT LEN(#str)
When concatenating strings and the result is of type VARCHAR(MAX) and is over 8000 characters, at least one parameter and/or element being used in the concatenation need to be of the VARCHAR(MAX) type otherwise truncation will occur in the resultant string and will not be executable in an EXEC statement.
Example:
DECLARE #sql AS VARCHAR(MAX);
/* DECLARE #someItem AS VARCHAR(100); -- WILL CAUSE TRUNCATION WHEN #sql HAS LEN > 8000 */
DECLARE #someItem AS VARCHAR(MAX); -- All string variables need to be VARCHAR(MAX) when concatenating to another VARCHAR(MAX)
SET #someItem = 'Just assume the resulting #sql variable goes over 8000 characters...';
SET #sql = 'SELECT Something FROM Somewhere WHERE SomeField = ''' + #someItem + '''';
EXEC (#sql);
--PRINT #sql;
More information on MSDN.
"If the result of the concatenation of strings exceeds the limit of
8,000 bytes, the result is truncated. However, if at least one of the
strings concatenated is a large value type, truncation does not
occur."
The default length of a varchar is 30 characters:
CAST (ID AS VARCHAR)
Is it possible that id is longer than 30 characters?
The PRINT command is certainly limited to 8000 chars, irrespective of the length of the output (or whether it is varchar(max)). To work around this you need to output the string in chunks of <8000 chars
Update: In answer to your edit, exec doesn't limit the string length. I've put together the following example to show this:
DECLARE #str VARCHAR (MAX);
;WITH CTE_Count AS
(
select counter = 1
union all
select counter = counter+1
from CTE_Count
Where counter < 2000
)
SELECT
#str=COALESCE(#str + CHAR (10) ,
'' ) + 'select value=' + CAST (counter AS VARCHAR)
from
CTE_Count
Option (MAXRECURSION 0)
PRINT len(#str);--SELECT #str;
exec (#str)
Running this prints the length as 34892 chars, and all 2000 execute statements do run (be warned, it may take a few mins!)
It happens when you concatenate literals if one is not a varchar(max) the result ill be "implicit casted" to varchar(8000).
To generate a literal varchar(max) all parts must be varchar(max).
Note: It happened to me doing updates on varchar(max) columns, never tested with the EXEC command.
Also as noted in previous answers the print command holds a limit but you can try selecting that variable instead of printing it. (also ther's a limit on that select length you can configure on MS-SMS)
I also wanted to see what I was sending to Exec, and was confused by the PRINT limit. Had to write a proc to print in chunks.
CREATE PROCEDURE [dbo].[KFX_PrintVarcharMax]
#strMax varchar(max)
AS
BEGIN
SET NOCOUNT ON;
DECLARE
#index int = 0,
#start int = 1,
#blkSize int = 2000;
WHILE #Start < LEN(#strMax)
BEGIN
IF #start + #blkSize >= LEN(#strMax)
BEGIN
-- If remainder is less than blocksize print the remainder, and exit.
PRINT SUBSTRING(#strMax, #start, #blkSize)
BREAK;
END
-- Else find the next terminator (beyond the blksize)
SET #index = CHARINDEX(CHAR(10), #strMax, #start + #blkSize);
if #index >= #start
BEGIN
PRINT SubString(#strMax, #start, #index - #start + 1)
SET #start = #index + 1;
SET #blkSize = CASE WHEN #start + 2000 < LEN(#strMax) THEN 2000
ELSE LEN(#strMax) - #start + 1 END
END
ELSE
BEGIN
-- No char(10) found. Just print the rest.
PRINT SUBSTRING(#strMax, #start, LEN(#strMax))
BREAK;
END
END
END
Quick check to see if anyone has or knows of a T-SQL function capable of generating slugs from a given nvarchar input. i.e;
"Hello World" > "hello-world"
"This is a test" > "this-is-a-test"
I have a C# function that I normally use for these purposes, but in this case I have a large amount of data to parse and turn into slugs, so it makes more sense to do it on the SQL Server rather than have to transfer data over the wire.
As an aside, I don't have Remote Desktop access to the box so I can't run code (.net, Powershell etc) against it
Thanks in advance.
EDIT:
As per request, here's the function I generally use to generate slugs:
public static string GenerateSlug(string n, int maxLength)
{
string s = n.ToLower();
s = Regex.Replace(s, #"[^a-z0-9s-]", "");
s = Regex.Replace(s, #"[s-]+", " ").Trim();
s = s.Substring(0, s.Length <= maxLength ? s.Length : maxLength).Trim();
s = Regex.Replace(s, #"s", "-");
return s;
}
You can use LOWER and REPLACE to do this:
SELECT REPLACE(LOWER(origString), ' ', '-')
FROM myTable
For wholesale update of the column (the code sets the slug column according to the value of the origString column:
UPDATE myTable
SET slug = REPLACE(LOWER(origString), ' ', '-')
This is what I've come up with as a solution. Feel free to fix / modify where needed.
I should mention that the database I'm currently developing against is case insensitive hence the LOWER(#str).
CREATE FUNCTION [dbo].[UDF_GenerateSlug]
(
#str VARCHAR(100)
)
RETURNS VARCHAR(100)
AS
BEGIN
DECLARE #IncorrectCharLoc SMALLINT
SET #str = LOWER(#str)
SET #IncorrectCharLoc = PATINDEX('%[^0-9a-z ]%',#str)
WHILE #IncorrectCharLoc > 0
BEGIN
SET #str = STUFF(#str,#incorrectCharLoc,1,'')
SET #IncorrectCharLoc = PATINDEX('%[^0-9a-z ]%',#str)
END
SET #str = REPLACE(#str,' ','-')
RETURN #str
END
Mention to: http://blog.sqlauthority.com/2007/05/13/sql-server-udf-function-to-parse-alphanumeric-characters-from-string/ for the original code.
I know this is an old thread, but for future generation, I found one function that deals even with accents here:
CREATE function [dbo].[slugify](#string varchar(4000))
RETURNS varchar(4000) AS BEGIN
declare #out varchar(4000)
--convert to ASCII
set #out = lower(#string COLLATE SQL_Latin1_General_CP1251_CS_AS)
declare #pi int
--I'm sorry T-SQL have no regex. Thanks for patindex, MS .. :-)
set #pi = patindex('%[^a-z0-9 -]%',#out)
while #pi>0 begin
set #out = replace(#out, substring(#out,#pi,1), '')
--set #out = left(#out,#pi-1) + substring(#out,#pi+1,8000)
set #pi = patindex('%[^a-z0-9 -]%',#out)
end
set #out = ltrim(rtrim(#out))
-- replace space to hyphen
set #out = replace(#out, ' ', '-')
-- remove double hyphen
while CHARINDEX('--', #out) > 0 set #out = replace(#out, '--', '-')
return (#out)
END
Here's a variation of Jeremy's response. This might not technically be slugifying since I'm doing a couple of custom things like replacing "." with "-dot-", and stripping out apostrophes. Main improvement is this one also strips out all consecutive spaces, and doesn't strip out preexisting dashes.
create function dbo.Slugify(#str nvarchar(max)) returns nvarchar(max)
as
begin
declare #IncorrectCharLoc int
set #str = replace(replace(lower(#str),'.',' dot '),'''','')
-- remove non alphanumerics:
set #IncorrectCharLoc = patindex('%[^0-9a-z -]%',#str)
while #IncorrectCharLoc > 0
begin
set #str = stuff(#str,#incorrectCharLoc,1,' ')
set #IncorrectCharLoc = patindex('%[^0-9a-z -]%',#str)
end
-- remove consecutive spaces:
while charindex(' ',#str) > 0
begin
set #str = replace(#str, ' ', ' ')
end
set #str = replace(#str,' ','-')
return #str
end
I took Jeremy's response a couple steps further by removing all consecutive dashes even after spaces are replaced, and removed leading and trailing dashes.
create function dbo.Slugify(#str nvarchar(max)) returns nvarchar(max) as
begin
declare #IncorrectCharLoc int
set #str = replace(replace(lower(#str),'.','-'),'''','')
-- remove non alphanumerics:
set #IncorrectCharLoc = patindex('%[^0-9a-z -]%',#str)
while #IncorrectCharLoc > 0
begin
set #str = stuff(#str,#incorrectCharLoc,1,' ')
set #IncorrectCharLoc = patindex('%[^0-9a-z -]%',#str)
end
-- replace all spaces with dashes
set #str = replace(#str,' ','-')
-- remove consecutive dashes:
while charindex('--',#str) > 0
begin
set #str = replace(#str, '--', '-')
end
-- remove leading dashes
while charindex('-', #str) = 1
begin
set #str = RIGHT(#str, len(#str) - 1)
end
-- remove trailing dashes
while len(#str) > 0 AND substring(#str, len(#str), 1) = '-'
begin
set #str = LEFT(#str, len(#str) - 1)
end
return #str
end
-- Converts a title such as "This is a Test" to an all lower case string such
-- as "this-is-a-test" for use as the slug in a URL. All runs of separators
-- (whitespace, underscore, or hyphen) are converted to a single hyphen.
-- This is implemented as a state machine having the following four states:
--
-- 0 - initial state
-- 1 - in a sequence consisting of valid characters (a-z, A-Z, or 0-9)
-- 2 - in a sequence of separators (whitespace, underscore, or hyphen)
-- 3 - encountered a character that is neither valid nor a separator
--
-- Once the next state has been determined, the return value string is
-- built based on the transitions from the current state to the next state.
--
-- State 0 skips any initial whitespace. State 1 includes all valid slug
-- characters. State 2 converts multiple separators into a single hyphen
-- and skips trailing whitespace. State 3 skips any punctuation between
-- between characters and, if no additional whitespace is encountered,
-- then the punctuation is not treated as a word separator.
--
CREATE FUNCTION ToSlug(#title AS NVARCHAR(MAX))
RETURNS VARCHAR(MAX)
AS
BEGIN
DECLARE #retval AS VARCHAR(MAX) = ''; -- return value
DECLARE #i AS INT = 1; -- title index
DECLARE #c AS CHAR(1); -- current character
DECLARE #state AS INT = 0; -- current state
DECLARE #nextState AS INT; -- next state
DECLARE #tab AS CHAR(1) = CHAR(9); -- tab
DECLARE #lf AS CHAR(1) = CHAR(10); -- line feed
DECLARE #cr AS CHAR(1) = CHAR(13); -- carriage return
DECLARE #separators AS CHAR(8) = '[' + #tab + #lf + #cr + ' _-]';
DECLARE #validchars AS CHAR(11) = '[a-zA-Z0-9]';
WHILE (#i <= LEN(#title))
BEGIN
SELECT #c = SUBSTRING(#title, #i, 1),
#nextState = CASE
WHEN #c LIKE #validchars THEN 1
WHEN #state = 0 THEN 0
WHEN #state = 1 THEN CASE
WHEN #c LIKE #separators THEN 2
ELSE 3 -- unknown character
END
WHEN #state = 2 THEN 2
WHEN #state = 3 THEN CASE
WHEN #c LIKE #separators THEN 2
ELSE 3 -- stay in state 3
END
END,
#retval = #retval + CASE
WHEN #nextState != 1 THEN ''
WHEN #state = 0 THEN LOWER(#c)
WHEN #state = 1 THEN LOWER(#c)
WHEN #state = 2 THEN '-' + LOWER(#c)
WHEN #state = 3 THEN LOWER(#c)
END,
#state = #nextState,
#i = #i + 1
END
RETURN #retval;
END
To slug with Vietnamese unicode
CREATE function [dbo].[toslug](#string nvarchar(4000))
RETURNS varchar(4000) AS BEGIN
declare #out nvarchar(4000)
declare #from nvarchar(255)
declare #to varchar(255)
--convert to ASCII dbo.slugify
set #string = lower(#string)
set #out = #string
set #from = N'ýỳỷỹỵáàảãạâấầẩẫậăắằẳẵặéèẻẽẹêếềểễệúùủũụưứừửữựíìỉĩịóòỏõọơớờởỡợôốồổỗộđ·/_,:;'
set #to = 'yyyyyaaaaaaaaaaaaaaaaaeeeeeeeeeeeuuuuuuuuuuuiiiiioooooooooooooooood------'
declare #pi int
set #pi = 1
--I'm sorry T-SQL have no regex. Thanks for patindex, MS .. :-)
while #pi<=len(#from) begin
set #out = replace(#out, substring(#from,#pi,1), substring(#to,#pi,1))
set #pi = #pi + 1
end
set #out = ltrim(rtrim(#out))
-- replace space to hyphen
set #out = replace(#out, ' ', '-')
-- remove double hyphen
while CHARINDEX('--', #out) > 0 set #out = replace(#out, '--', '-')
return (#out)
END