Contents

module Boilerpipe
  java_import 'com.kohlschutter.boilerpipe.extractors.ArticleExtractor'
  java_import 'com.kohlschutter.boilerpipe.util.UnicodeTokenizer'
  java_import java.net.URL

  class ArticleExtractor
    def  self.get_text(s)
      url = nil

      begin
        url = Java::JavaNet::URL.new(s)
      rescue Java::JavaNet::MalformedURLException => e
        # not a URL
      end
      input = url ? url : s
      ArticleExtractor::INSTANCE.get_text(input)
    end

    class <<self  
      alias_method :text, :get_text
    end 
  end
end

Version data entries

4 entries across 4 versions & 1 rubygems

Version	Path
jruby-boilerpipe-0.0.6	lib/boilerpipe/extractors/article_extractor.rb
jruby-boilerpipe-0.0.5	lib/boilerpipe/extractors/article_extractor.rb
jruby-boilerpipe-0.0.4	lib/boilerpipe/extractors/article_extractor.rb
jruby-boilerpipe-0.0.3	lib/boilerpipe/extractors/article_extractor.rb