All geek questions in one place

SQL Server - remove all non-printable ASCII characters

We recently switched from SQL Server 2012 to SQL Server 2014, and all of our code FOR XMLstarted throwing errors on non-printable ASCII characters. I wrote this terrible function to remove non-printable ASCII characters as a quick fix. I want to replace it with something cleaner. Is there any way to do this?

ALTER FUNCTION [dbo].[remove_non_printable_chars]
(@input_string nvarchar(max))
RETURNS nvarchar(max)
BEGIN
    RETURN
    REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(
    REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(
    REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(REPLACE(
    REPLACE(REPLACE(@input_string,
        CHAR(1), ''),CHAR(2), ''),CHAR(3), ''),CHAR(4), ''),CHAR(5), ''),CHAR(6), ''),CHAR(7), ''),CHAR(8), ''),CHAR(9), ''),CHAR(10), ''),
        CHAR(11), ''),CHAR(12), ''),CHAR(13), ''),CHAR(14), ''),CHAR(15), ''),CHAR(16), ''),CHAR(17), ''),CHAR(18), ''),CHAR(19), ''),CHAR(20), ''),
        CHAR(21), ''),CHAR(22), ''),CHAR(23), ''),CHAR(24), ''),CHAR(25), ''),CHAR(26), ''),CHAR(27), ''),CHAR(28), ''),CHAR(29), ''),CHAR(30), ''),
        CHAR(31), ''), NCHAR(0) COLLATE Latin1_General_100_BIN2, '')
END

Here is the code FOR XMLthat broke. (I did not write this. He was already in the code base).

SELECT @HTMLTableData =
(
    SELECT  HTMLRows 
    FROM (
        SELECT N'<tr>' + HTMLRow + N'</tr>' AS HTMLRows 
        FROM @HTMLRowData
    ) mi            
    FOR XML PATH(''), TYPE
).value('/', 'NVARCHAR(MAX)')
+4
source share
2 answers

Another variant.

This function will replace control characters and correct any residual repeated spaces. For example, Jane Smith{13}was herewill not return as Jane Smithwas here, but ratherJane Smith was here

CREATE FUNCTION [dbo].[udf-Str-Strip-Control](@S varchar(max))
Returns varchar(max)
Begin
    ;with  cte1(N) As (Select 1 From (Values(1),(1),(1),(1),(1),(1),(1),(1),(1),(1)) N(N)),
           cte2(C) As (Select Top (32) Char(Row_Number() over (Order By (Select NULL))-1) From cte1 a,cte1 b)
    Select @S = Replace(@S,C,' ')
     From  cte2

    Return LTrim(RTrim(Replace(Replace(Replace(@S,' ','><'),'<>',''),'><',' ')))
End
--Select [dbo].[udf-Str-Strip-Control]('Michael        '+char(13)+char(10)+'LastName')  --Returns: Michael LastName
+3

:

create function [dbo].[remove_non_printable_chars] (@input_string nvarchar(max))
returns table with schemabinding as return (
  select 
    replace(replace(replace(replace(replace(replace(replace(replace(replace(replace(
    replace(replace(replace(replace(replace(replace(replace(replace(replace(replace(
    replace(replace(replace(replace(replace(replace(replace(replace(replace(replace(
    replace(replace(@input_string collate latin1_general_100_bin2,
        char(1), ''),char(2), ''),char(3), ''),char(4), ''),char(5), ''),char(6), ''),char(7), ''),char(8), ''),char(9), ''),char(10), ''),
        char(11), ''),char(12), ''),char(13), ''),char(14), ''),char(15), ''),char(16), ''),char(17), ''),char(18), ''),char(19), ''),char(20), ''),
        char(21), ''),char(22), ''),char(23), ''),char(24), ''),char(25), ''),char(26), ''),char(27), ''),char(28), ''),char(29), ''),char(30), ''),
        char(31), ''), char(0) , '') 
     as clean_string
);
go

:

select c.clean_string
from dbo.remove_non_printable_chars(@dirtystring) c


select ...
  , c.clean_string
from t
  cross apply dbo.remove_non_printable_chars(t.dirty_string) c

:

+3

Source: https://habr.com/ru/post/1673743/

More articles:


All Articles