gitlab-org--gitlab-foss/lib/gitlab/email/html_parser.rb

42 lines
993 B
Ruby
Raw Normal View History

module Gitlab
module Email
class HTMLParser
def self.parse_reply(raw_body)
new(raw_body).filtered_text
end
attr_reader :raw_body
def initialize(raw_body)
@raw_body = raw_body
end
def document
@document ||= Nokogiri::HTML.parse(raw_body)
end
def filter_replies!
document.xpath('//blockquote').each(&:remove)
document.xpath('//table').each(&:remove)
2017-02-06 13:22:31 -05:00
# bogus links with no href are sometimes added by outlook,
# and can result in Html2Text adding extra square brackets
# to the text, so we unwrap them here.
document.xpath('//a[not(@href)]').each do |link|
link.replace(link.children)
end
end
def filtered_html
2016-11-10 03:40:53 -05:00
@filtered_html ||= begin
filter_replies!
document.inner_html
end
end
def filtered_text
@filtered_text ||= Html2Text.convert(filtered_html)
end
end
end
end