Hello, I have some data imported into a database that has html tags. I have the code below which replaces certain tags, and the last set of code removes all other between < > tags. This is working well. The issue is that if the tag has a carriage return after the tag I also need to remove those. Here is two examples. In the first example the code I have will work fine.
Eg 1.
<html><body>enter new academic year, change data and save.</body></html>
Desired Result = enter new academic year, change data and save.
In this second example. I also need to remove the carriage return after the <html>, <body>, </div> and >
. Note sometimes a tag may have a carriage return after it and in other cases it will not.
Eg 2.
<html>
<body>
<div align="left"><font face="Arial"><span style="font-size:8pt">Navigate to Setup SACR > Foundation
Tables >
Academic Structure > Program Planner<br />
Search for Program/Plan combination and check
highest Academic Year still this year</span></font></div>
</body>
</html>
Desired Result = Navigate to Setup SACR > Foundation
Tables > Academic Structure > Program Planner
Search for Program/Plan combination and check
highest Academic Year still this year
Usage: dbo.udf_StripHTML(TS_Description) TS_Description
USE [UofA]
GO
/****** Object: UserDefinedFunction [dbo].[udf_StripHTML] Script Date: 18/08/2015 8:43:19 AM ******/
SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO
ALTER FUNCTION [dbo].[udf_StripHTML]
(
@HTMLText varchar(MAX)
)
RETURNS varchar(MAX)
AS
BEGIN
DECLARE @Start int
DECLARE @End int
DECLARE @Length int
-- Replace the HTML entity & with the '&' character (this needs to be done first, as
-- '&' might be double encoded as '&amp;')
SET @Start = CHARINDEX('&', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1
WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '&')
SET @Start = CHARINDEX('&', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1
END
-- Replace the HTML entity < with the '<' character
SET @Start = CHARINDEX('<', @HTMLText)
SET @End = @Start + 3
SET @Length = (@End - @Start) + 1
WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '<')
SET @Start = CHARINDEX('<', @HTMLText)
SET @End = @Start + 3
SET @Length = (@End - @Start) + 1
END
-- Replace the HTML entity > with the '>' character
SET @Start = CHARINDEX('>', @HTMLText)
SET @End = @Start + 3
SET @Length = (@End - @Start) + 1
WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '>')
SET @Start = CHARINDEX('>', @HTMLText)
SET @End = @Start + 3
SET @Length = (@End - @Start) + 1
END
-- Replace the HTML entity & with the '&' character
SET @Start = CHARINDEX('&amp;', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1
WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '&')
SET @Start = CHARINDEX('&amp;', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1
END
-- Replace the HTML entity with the ' ' character
SET @Start = CHARINDEX(' ', @HTMLText)
SET @End = @Start + 5
SET @Length = (@End - @Start) + 1
WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, ' ')
SET @Start = CHARINDEX(' ', @HTMLText)
SET @End = @Start + 5
SET @Length = (@End - @Start) + 1
END
-- Replace the HTML entity " with the '"' character
SET @Start = CHARINDEX('"', @HTMLText)
SET @End = @Start + 5
SET @Length = (@End - @Start) + 1
WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '"')
SET @Start = CHARINDEX('"', @HTMLText)
SET @End = @Start + 5
SET @Length = (@End - @Start) + 1
END
-- Replace any <br> tags with a newline
SET @Start = CHARINDEX('<br>', @HTMLText)
SET @End = @Start + 3
SET @Length = (@End - @Start) + 1
WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, CHAR(13) + CHAR(10))
--CHAR(13) + CHAR(10)
SET @Start = CHARINDEX('<br>', @HTMLText)
SET @End = @Start + 3
SET @Length = (@End - @Start) + 1
END
-- Replace any <br/> tags with a newline
SET @Start = CHARINDEX('<br/>', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1
WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, CHAR(13) + CHAR(10))
--CHAR(13) + CHAR(10)
SET @Start = CHARINDEX('<br/>', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1
END
-- Replace any <br /> tags with a newline
SET @Start = CHARINDEX('<br />', @HTMLText)
SET @End = @Start + 5
SET @Length = (@End - @Start) + 1
WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, CHAR(13) + CHAR(10))
--CHAR(13) + CHAR(10)
SET @Start = CHARINDEX('<br />', @HTMLText)
SET @End = @Start + 5
SET @Length = (@End - @Start) + 1
END
-- Remove anything between <whatever> tags
SET @Start = CHARINDEX('<', @HTMLText)
SET @End = CHARINDEX('>', @HTMLText, CHARINDEX('<', @HTMLText))
SET @Length = (@End - @Start) + 1
WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '')
SET @Start = CHARINDEX('<', @HTMLText)
SET @End = CHARINDEX('>', @HTMLText, CHARINDEX('<', @HTMLText))
SET @Length = (@End - @Start) + 1
END
RETURN LTRIM(RTRIM(@HTMLText))
END