(.+?)}m ) { |placeholder| placeholder = placeholder.gsub(/\n/, '###BR###') } string.gsub!( %r{
(.+?)
}m ) { |placeholder|
placeholder = placeholder.gsub(/\n/, '###BR###')
}
# remove all new lines
string.gsub!(/(\n\r|\r\r\n|\r\n|\n)/, '')
# blockquote handling
string.gsub!( %r{]*)>(.+?)}m ) { "\n" + $2.html2text(true).gsub(/^(.*)$/, '> \1') + "\n" } # pre/code handling 2/2 string.gsub!(/###BR###/, "\n" ) # add counting string.gsub!(/
}im, "\n" )
string.gsub!( %r{<(div|p|pre|br|table|h)(|/| [^>]*)>}i, "\n" )
string.gsub!( %r{(tr|p|br|div)(|\s.+?)>}i, "\n" )
string.gsub!( %r{}i, ' ' )
# strip all other tags
string.gsub!( /\<.+?\>/, '' )
# replace multiple spaces with one
string.gsub!(/ /, ' ')
# strip all & < > "
string.gsub!( '&', '&' )
string.gsub!( '<', '<' )
string.gsub!( '>', '>' )
string.gsub!( '"', '"' )
string.gsub!( ' ', ' ' )
# encode html entities like "–"
string.gsub!( /(&\#(\d+);?)/x ) {
$2.chr
}
# encode html entities like "d;"
string.gsub!( /(&\#[xX]([0-9a-fA-F]+);?)/x ) {
chr_orig = $1
hex = $2.hex
if hex
chr = hex.chr
if chr
chr_orig = chr
else
chr_orig
end
else
chr_orig
end
# check valid encoding
begin
if !chr_orig.encode('UTF-8').valid_encoding?
chr_orig = '?'
end
rescue
chr_orig = '?'
end
chr_orig
}
# remove tailing empty spaces
string.gsub!(/\s+\n$/, "\n")
# remove multiple empty lines
string.gsub!(/\n\n\n/, "\n\n")
string.strip!
# add extracted links
if link_list != ''
string += "\n\n\n" + link_list
end
string.strip
end
=begin
html = text_string.text2html
=end
def text2html
text = CGI.escapeHTML( self )
text.gsub!(/\n/, '
')
text.chomp
end
end