Contents

module Boilerpipe
  module SAX
    java_import 'com.kohlschutter.boilerpipe.sax.BoilerpipeHTMLParser'
    java_import 'org.xml.sax.InputSource'
    java_import java.io.StringReader

    class BoilerpipeHTMLParser
      def self.parse(text)
        parser = BoilerpipeHTMLParser.new
        string_reader = StringReader.new(text)
        is = InputSource.new(string_reader)
        parser.parse(is)
        parser.to_text_document
      end
    end
  end
end

Version data entries

7 entries across 7 versions & 1 rubygems

Version	Path
jruby-boilerpipe-0.3.0	lib/boilerpipe/sax/boilerpipe_html_parser.rb
jruby-boilerpipe-0.2.0	lib/boilerpipe/sax/boilerpipe_html_parser.rb
jruby-boilerpipe-0.1.0	lib/boilerpipe/sax/boilerpipe_html_parser.rb
jruby-boilerpipe-0.0.6	lib/boilerpipe/sax/boilerpipe_html_parser.rb
jruby-boilerpipe-0.0.5	lib/boilerpipe/sax/boilerpipe_html_parser.rb
jruby-boilerpipe-0.0.4	lib/boilerpipe/sax/boilerpipe_html_parser.rb
jruby-boilerpipe-0.0.3	lib/boilerpipe/sax/boilerpipe_html_parser.rb