I have a column in sql server 2005 table which stores the xhtml data. I
want to convert and store this data as plain text in another table.
Answer:
Create FUNCTION [dbo].[funConvertHTMLtoPlainText](@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 '&')
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('&', @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 + 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
tags with a newline
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, CHAR(13) + CHAR(10))
SET @Start = CHARINDEX('
', @HTMLText)
SET @End = @Start + 3SET @Length = (@End - @Start) + 1
END
-- Replace any
tags with a newline
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, 'CHAR(13) + CHAR(10)')
SET @Start = CHARINDEX('
', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1
END
------ -- Replace any
tags with a newline
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, 'CHAR(13) + CHAR(10)')
SET @Start = CHARINDEX('
', @HTMLText)
SET @End = @Start + 5
SET @Length = (@End - @Start) + 1
END
-- Remove anything between
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
I got it in a another bolog.
No comments:
Post a Comment