onebox 2.2.10 → 2.2.15

data/lib/onebox/engine/twitch_stream_onebox.rb

@@ -3,14 +3,13 @@
 require_relative '../mixins/twitch_onebox'
 
 class Onebox::Engine::TwitchStreamOnebox
-
   def self.twitch_regexp
     /^https?:\/\/(?:www\.|go\.)?twitch\.tv\/(?!directory)([a-zA-Z0-9_]{4,25})$/
   end
+
   include Onebox::Mixins::TwitchOnebox
 
   def query_params
     "channel=#{twitch_id}"
   end
-
 end

data/lib/onebox/engine/twitch_video_onebox.rb

@@ -3,7 +3,6 @@
 require_relative '../mixins/twitch_onebox'
 
 class Onebox::Engine::TwitchVideoOnebox
-
   def self.twitch_regexp
     /^https?:\/\/(?:www\.)?twitch\.tv\/videos\/([0-9]+)/
   end
@@ -13,5 +12,4 @@ class Onebox::Engine::TwitchVideoOnebox
   def query_params
     "video=v#{twitch_id}"
   end
-
 end

data/lib/onebox/engine/typeform_onebox.rb

@@ -13,12 +13,13 @@ module Onebox
         typeform_src = build_typeform_src
 
         <<~HTML
-          <iframe src="#{typeform_src}"
-                  width="100%"
-                  height="600px"
-                  scrolling="no"
-                  frameborder="0">
-          </iframe>
+          <iframe
+            src="#{typeform_src}"
+            width="100%"
+            height="600px"
+            scrolling="no"
+            frameborder="0"
+          ></iframe>
         HTML
       end
 

data/lib/onebox/engine/vimeo_onebox.rb

@@ -25,14 +25,16 @@ module Onebox
         end
         video_src = "https://player.vimeo.com/video/#{video_id}"
         video_src = video_src.gsub('autoplay=1', '').chomp("?")
+
         <<-HTML
-          <iframe width="#{WIDTH}"
-                  height="#{HEIGHT}"
-                  src="#{video_src}"
-                  data-original-href="#{link}"
-                  frameborder="0"
-                  allowfullscreen>
-          </iframe>
+          <iframe
+            width="#{WIDTH}"
+            height="#{HEIGHT}"
+            src="#{video_src}"
+            data-original-href="#{link}"
+            frameborder="0"
+            allowfullscreen
+          ></iframe>
         HTML
       end
 

data/lib/onebox/engine/wikimedia_onebox.rb

@@ -7,7 +7,7 @@ module Onebox
       include LayoutSupport
       include JSON
 
-      matches_regexp /^https?:\/\/commons\.wikimedia\.org\/wiki\/(File:.+)/
+      matches_regexp(/^https?:\/\/commons\.wikimedia\.org\/wiki\/(File:.+)/)
       always_https
 
       def self.priority
@@ -38,7 +38,6 @@ module Onebox
           thumbnail: first_page['imageinfo'].first['thumburl']
         }
       end
-
     end
   end
 end

data/lib/onebox/engine/wikipedia_onebox.rb

@@ -16,10 +16,10 @@ module Onebox
         paras = []
         text = ""
 
-        # Detect section Hash in the url and retrive the related paragraphs.  if no hash provided the first few paragraphs will be used
+        # Detect section Hash in the url and retrive the related paragraphs. if no hash provided the first few paragraphs will be used
         # Author Lidlanca
         # Date 9/8/2014
-        if (m_url_hash = @url.match(/#([^\/?]+)/)) #extract url hash
+        if (m_url_hash = @url.match(/#([^\/?]+)/)) # extract url hash
           m_url_hash_name = m_url_hash[1]
         end
 
@@ -27,17 +27,17 @@ module Onebox
           section_header_title = raw.xpath("//span[@id='#{m_url_hash_name}']")
 
           if section_header_title.empty?
-            paras = raw.search("p") #default get all the paras
+            paras = raw.search("p") # default get all the paras
           else
             section_title_text = section_header_title.inner_text
-            section_header = section_header_title[0].parent #parent element of the section span element should be an <h3> node
+            section_header = section_header_title[0].parent # parent element of the section span element should be an <h3> node
             cur_element = section_header
 
-            # p|text|div covers the general case. We assume presence of atleast 1 P node. if section has no P node we may end up with a P node from the next section.
+            # p|text|div covers the general case. We assume presence of at least 1 P node. if section has no P node we may end up with a P node from the next section.
             # div tag is commonly used as an assets wraper in an article section. often as the first element holding an image.
             # ul support will imporve the output generated for a section with a list as the main content (for example: an Author Bibliography, A musician Discography, etc)
             first_p_found = nil
-            while (((next_sibling = cur_element.next_sibling).name =~ /p|text|div|ul/) || first_p_found.nil?) do  #from section header get the next sibling until it is a breaker tag
+            while (((next_sibling = cur_element.next_sibling).name =~ /p|text|div|ul/) || first_p_found.nil?) do  # from section header get the next sibling until it is a breaker tag
               cur_element = next_sibling
               if (cur_element.name == "p" || cur_element.name == "ul") #we treat a list as we detect a p to avoid showing
                 first_p_found = true
@@ -46,7 +46,7 @@ module Onebox
             end
           end
         else # no hash found in url
-          paras = raw.search("p") #default get all the paras
+          paras = raw.search("p") # default get all the paras
         end
 
         unless paras.empty?
@@ -55,7 +55,7 @@ module Onebox
             break if cnt >= paras.size
             text += " " unless cnt == 0
 
-            if paras[cnt].name == "ul" #Handle UL tag. Generate a textual ordered list (1.item | 2.item | 3.item). Unfourtently no newline allowed in output
+            if paras[cnt].name == "ul" # Handle UL tag. Generate a textual ordered list (1.item | 2.item | 3.item). Unfortunately no newline allowed in output
               li_index = 1
               list_items = []
               paras[cnt].children.css("li").each { |li| list_items.push "#{li_index}." + li.inner_text ; li_index += 1 }
@@ -69,13 +69,17 @@ module Onebox
             cnt += 1
           end
         end
+
         text = "#{text[0..Onebox::LayoutSupport.max_text]}..." if text.length > Onebox::LayoutSupport.max_text
+
         result = {
           link: link,
           title: raw.css("html body h1").inner_text + (section_title_text ? " | " + section_title_text : ""),  #if a section sub title exists add it to the main article title
           description: text
         }
+
         img = raw.css(".image img")
+
         if img && img.size > 0
           img.each do |i|
             src = i["src"]

data/lib/onebox/engine/youku_onebox.rb

@@ -21,21 +21,15 @@ module Onebox
 
       def to_html
         <<~HTML
-          <iframe src="https://player.youku.com/embed/#{video_id}"
-                  width="640"
-                  height="430"
-                  frameborder='0'
-                  allowfullscreen>
-          </iframe>
+          <iframe
+            src="https://player.youku.com/embed/#{video_id}"
+            width="640"
+            height="430"
+            frameborder='0'
+            allowfullscreen
+          ></iframe>
         HTML
       end
-
-      private
-
-      def uri
-        @_uri ||= URI(@url)
-      end
-
     end
   end
 end

data/lib/onebox/engine/youtube_onebox.rb

@@ -13,11 +13,36 @@ module Onebox
       WIDTH  ||= 480
       HEIGHT ||= 360
 
-      def placeholder_html
-        og = get_opengraph.data
+      def parse_embed_response
+        return unless video_id
+        return @parse_embed_response if defined?(@parse_embed_response)
+
+        embed_url = "https://www.youtube.com/embed/#{video_id}"
+        @embed_doc ||= Onebox::Helpers.fetch_html_doc(embed_url)
+
+        begin
+          script_tag = @embed_doc.xpath('//script').find { |tag| tag.to_s.include?('ytcfg.set') }.to_s
+          match = script_tag.to_s.match(/ytcfg\.set\((?<json>.*)\)/)
+
+          yt_json = ::JSON.parse(match[:json])
+          renderer = ::JSON.parse(yt_json['PLAYER_VARS']['embedded_player_response'])['embedPreview']['thumbnailPreviewRenderer']
+
+          title = renderer['title']['runs'].first['text']
+
+          image = "https://img.youtube.com/vi/#{video_id}/hqdefault.jpg"
+        rescue
+          return
+        end
 
+        @parse_embed_response = { image: image, title: title }
+      end
+
+      def placeholder_html
         if video_id || list_id
-          "<img src='#{og[:image]}' width='#{WIDTH}' height='#{HEIGHT}' title='#{og[:title]}'>"
+          result = parse_embed_response
+          result ||= get_opengraph.data
+
+          "<img src='#{result[:image]}' width='#{WIDTH}' height='#{HEIGHT}' title='#{result[:title]}'>"
         else
           to_html
         end
@@ -26,21 +51,23 @@ module Onebox
       def to_html
         if video_id
           <<-HTML
-            <iframe width="#{WIDTH}"
-                    height="#{HEIGHT}"
-                    src="https://www.youtube.com/embed/#{video_id}?#{embed_params}"
-                    frameborder="0"
-                    allowfullscreen>
-            </iframe>
+            <iframe
+              src="https://www.youtube.com/embed/#{video_id}?#{embed_params}"
+              width="#{WIDTH}"
+              height="#{HEIGHT}"
+              frameborder="0"
+              allowfullscreen
+            ></iframe>
           HTML
         elsif list_id
           <<-HTML
-            <iframe width="#{WIDTH}"
-                    height="#{HEIGHT}"
-                    src="https://www.youtube.com/embed/videoseries?list=#{list_id}&wmode=transparent&rel=0&autohide=1&showinfo=1&enablejsapi=1"
-                    frameborder="0"
-                    allowfullscreen>
-            </iframe>
+            <iframe
+              src="https://www.youtube.com/embed/videoseries?list=#{list_id}&wmode=transparent&rel=0&autohide=1&showinfo=1&enablejsapi=1"
+              width="#{WIDTH}"
+              height="#{HEIGHT}"
+              frameborder="0"
+              allowfullscreen
+            ></iframe>
           HTML
         else
           # for channel pages
@@ -52,7 +79,10 @@ module Onebox
       end
 
       def video_title
-        @video_title ||= get_opengraph.data[:title]
+        @video_title ||= begin
+          result = parse_embed_response || get_opengraph.data
+          result[:title]
+        end
       end
 
       private
@@ -138,7 +168,6 @@ module Onebox
       rescue
         {}
       end
-
     end
   end
 end

data/lib/onebox/file_type_finder.rb

@@ -2,7 +2,6 @@
 
 module Onebox
   module FileTypeFinder
-
     # In general, most of file extension names would be recognized
     # by Highlights.js.  However, some need to be checked in other
     # ways, either because they just aren't included, because they

data/lib/onebox/helpers.rb

@@ -7,7 +7,7 @@ module Onebox
 
     class DownloadTooLarge < StandardError; end
 
-    IGNORE_CANONICAL_DOMAINS ||= ['www.instagram.com']
+    IGNORE_CANONICAL_DOMAINS ||= ['www.instagram.com', 'youtube.com']
 
     def self.symbolize_keys(hash)
       return {} if hash.nil?
@@ -90,7 +90,8 @@ module Onebox
 
           code = response.code.to_i
           unless code === 200
-            response.error! unless [301, 302].include?(code)
+            response.error! unless [301, 302, 303, 307, 308].include?(code)
+
             return fetch_response(
               response['location'],
               redirect_limit: redirect_limit - 1,
@@ -127,10 +128,10 @@ module Onebox
 
         http.request_head([uri.path, uri.query].join("?")) do |response|
           code = response.code.to_i
-          unless code === 200 || Onebox::Helpers.blank?(response.header['content-length'])
+          unless code === 200 || Onebox::Helpers.blank?(response.content_length)
             return nil
           end
-          return response.header['content-length']
+          return response.content_length
         end
       end
     end

data/lib/onebox/layout.rb

@@ -32,19 +32,7 @@ module Onebox
     private
 
     def uri
-      @uri = URI(link)
-    end
-
-    def checksum
-      @md5.hexdigest("#{VERSION}:#{link}")
-    end
-
-    def link
-      ::Onebox::Helpers.normalize_url_for_output(record[:link])
-    end
-
-    def domain
-      record[:domain] || URI(link || '').host.to_s.sub(/^www\./, '')
+      @uri ||= URI(::Onebox::Helpers.normalize_url_for_output(record[:link]))
     end
 
     def details
@@ -52,7 +40,7 @@ module Onebox
         link: record[:link],
         title: record[:title],
         favicon: record[:favicon],
-        domain: domain,
+        domain: record[:domain] || uri.host.to_s.sub(/^www\./, ''),
         article_published_time: record[:article_published_time],
         article_published_time_title: record[:article_published_time_title],
         metadata_1_label: record[:metadata_1_label],

data/lib/onebox/matcher.rb

@@ -2,8 +2,12 @@
 
 module Onebox
   class Matcher
-    def initialize(link, options = {})
-      @url = link
+    def initialize(url, options = {})
+      begin
+        @uri = URI(url)
+      rescue URI::InvalidURIError
+      end
+
       @options = options
     end
 
@@ -14,12 +18,10 @@ module Onebox
     end
 
     def oneboxed
-      uri = URI(@url)
-      return unless uri.port.nil? || Onebox.options.allowed_ports.include?(uri.port)
-      return unless uri.scheme.nil? || Onebox.options.allowed_schemes.include?(uri.scheme)
-      ordered_engines.find { |engine| engine === uri && has_allowed_iframe_origins?(engine) }
-    rescue URI::InvalidURIError
-      nil
+      return if @uri.nil?
+      return if @uri.port && !Onebox.options.allowed_ports.include?(@uri.port)
+      return if @uri.scheme && !Onebox.options.allowed_schemes.include?(@uri.scheme)
+      ordered_engines.find { |engine| engine === @uri && has_allowed_iframe_origins?(engine) }
     end
 
     def has_allowed_iframe_origins?(engine)

data/lib/onebox/mixins/git_blob_onebox.rb

@@ -25,14 +25,18 @@ module Onebox
       }
 
       module InstanceMethods
-        def initialize(link, timeout = nil)
-          super link, timeout
+        def initialize(url, timeout = nil)
+          super url, timeout
           # merge engine options from global Onebox.options interface
           # self.options = Onebox.options["GithubBlobOnebox"] #  self.class.name.split("::").last.to_s
           # self.options = Onebox.options[self.class.name.split("::").last.to_s] #We can use this a more generic approach. extract the engine class name automatically
 
           self.options = DEFAULTS
 
+          @selected_lines_array = nil
+          @selected_one_liner = 0
+          @model_file = nil
+
           # Define constant after merging options set in Onebox.options
           # We can define constant automatically.
           options.each_pair do |constant_name, value|
@@ -47,8 +51,6 @@ module Onebox
         end
 
         private
-        @selected_lines_array = nil
-        @selected_one_liner = 0
 
         def calc_range(m, contents_lines_size)
           truncated = false
@@ -150,7 +152,7 @@ module Onebox
         end
 
         def raw
-          return @raw if @raw
+          return @raw if defined?(@raw)
 
           m = @url.match(self.raw_regexp)
 
@@ -161,11 +163,9 @@ module Onebox
             @file = m[:file]
             @lang = Onebox::FileTypeFinder.from_file_name(m[:file])
 
-            if @lang == "stl" && link.match(/^https?:\/\/(www\.)?github\.com.*\/blob\//)
-
+            if @lang == "stl" && link.match?(/^https?:\/\/(www\.)?github\.com.*\/blob\//)
               @model_file = @lang.dup
               @raw = "https://render.githubusercontent.com/view/solid?url=" + self.raw_template(m)
-
             else
               contents = URI.open(self.raw_template(m), read_timeout: timeout).read
 

data/lib/onebox/mixins/github_body.rb

@@ -0,0 +1,30 @@
+# frozen_string_literal: true
+
+module Onebox
+  module Mixins
+    module GithubBody
+      def self.included(klass)
+        klass.include(Onebox::Engine)
+        klass.include(InstanceMethods)
+      end
+
+      module InstanceMethods
+        GITHUB_COMMENT_REGEX = /(<!--.*?-->\r\n)/
+        MAX_BODY_LENGTH = 80
+        def compute_body(body)
+          body = body.dup
+          excerpt = nil
+
+          body = (body || '').gsub(GITHUB_COMMENT_REGEX, '')
+          body = body.length > 0 ? body : nil
+          if body && body.length > MAX_BODY_LENGTH
+            excerpt = body[MAX_BODY_LENGTH..body.length].rstrip
+            body = body[0..MAX_BODY_LENGTH - 1]
+          end
+
+          [body, excerpt]
+        end
+      end
+    end
+  end
+end