debian-mirror-gitlab/lib/gitlab/email/html_parser.rb
2019-02-13 22:33:31 +05:30

43 lines
1 KiB
Ruby

# frozen_string_literal: true
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)
# 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
@filtered_html ||= begin
filter_replies!
document.inner_html
end
end
def filtered_text
@filtered_text ||= Html2Text.convert(filtered_html)
end
end
end
end