onebox 1.5.5 → 1.5.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: af8a0c496cbfd1be8549197491c181e80dc5423d
-  data.tar.gz: 907eb2132907a74bcd7e54e35e359757c24714ce
+  metadata.gz: ff1798c506e288427056ead18fd48f2988050be3
+  data.tar.gz: ba7f2a9b90eca120f7e02823dd82478efd82b23d
 SHA512:
-  metadata.gz: aa9c7b77f9c7817a2713f625f5c0ae32a5cccdb7db48d2da0ab71d7696f8aa9e610e22975c810d4202937e81dce676a2115ead91a2b904bf6925f8c08244cc7d
-  data.tar.gz: 125ee9336e3a685736ea39b12e5e8dfe20682146ff970afcb3a75596f169e90a0ec9a6e63b900e50207ac67b474551682dffd2e228ad4675bcf3785dce63a59d
+  metadata.gz: 5cefe833b7afd031180985fec397fa7f42704c5c2a8e456260d756805bb4741db9b3a8496556d1a841009b9eda5445c243487f9b30acbe7cff89e2beba06d69b
+  data.tar.gz: d22d9b5ed23f70cde5d8e3bdf8e272c9c5aafb6d4dc989e3db604f8d9b1ed9f010803aa01a00600cd885724056201e8b9f5b517065467960a5e72918dc26ca20

data/.gitignore

@@ -1,6 +1,7 @@
 *.gem
 *.rbc
 .bundle
+/.idea
 .config
 .yardoc
 Gemfile.lock

data/lib/onebox/engine.rb

@@ -13,29 +13,29 @@ module Onebox
     attr_reader :url
     attr_reader :cache
     attr_reader :timeout
-    
+
     DEFUALT = {}
     def options
       @options
     end
-    
+
     def options=(opt)
       return @options if opt.nil? #make sure options provided
       if opt.instance_of? OpenStruct
-        @options = @options.merge(opt.to_h)   
+        @options = @options.merge(opt.to_h)
       else
        @options =  @options.merge(opt)
       end
       @options
     end
-    
+
 
     def initialize(link, cache = nil, timeout = nil)
-      
+
       @options = DEFUALT
       class_name = self.class.name.split("::").last.to_s
       self.options = Onebox.options[class_name] || {} #Set the engine options extracted from global options.
-      
+
       @url = link
       @cache = cache || Onebox.options.cache
       @timeout = timeout || Onebox.options.timeout
@@ -118,6 +118,7 @@ end
 
 require_relative "helpers"
 require_relative "layout_support"
+require_relative "file_type_finder"
 require_relative "engine/standard_embed"
 require_relative "engine/html"
 require_relative "engine/json"
@@ -126,17 +127,17 @@ require_relative "engine/classic_google_maps_onebox"
 require_relative "engine/github_issue_onebox"
 require_relative "engine/github_blob_onebox"
 require_relative "engine/github_commit_onebox"
-# broken
-#require_relative "engine/github_gist_onebox"
+require_relative "engine/github_gist_onebox"
 require_relative "engine/github_pullrequest_onebox"
 require_relative "engine/google_play_app_onebox"
 require_relative "engine/image_onebox"
+require_relative "engine/video_onebox"
+require_relative "engine/audio_onebox"
 require_relative "engine/stack_exchange_onebox"
 require_relative "engine/twitter_status_onebox"
 require_relative "engine/wikipedia_onebox"
 require_relative "engine/youtube_onebox"
+require_relative "engine/youku_onebox"
 require_relative "engine/douban_onebox"
 require_relative "engine/whitelisted_generic_onebox"
 require_relative "engine/pubmed_onebox"
-require_relative "engine/video_onebox"
-require_relative "engine/audio_onebox"

data/lib/onebox/engine/github_blob_onebox.rb

@@ -4,10 +4,10 @@ module Onebox
       include Engine
       include LayoutSupport
 
-      EXPAND_AFTER = 0b001 
+      EXPAND_AFTER = 0b001
       EXPAND_BEFORE = 0b010
       EXPAND_NONE = 0b0
-      
+
       DEFAULTS = {
               :EXPAND_ONE_LINER => EXPAND_AFTER|EXPAND_BEFORE, #set how to expand a one liner. user EXPAND_NONE to disable expand
               :LINES_BEFORE => 10,
@@ -16,7 +16,7 @@ module Onebox
               :MAX_LINES => 20,
               :MAX_CHARS => 5000
       }
-      
+
       matches_regexp(/^https?:\/\/(www\.)?github\.com.*\/blob\//)
 
 
@@ -25,12 +25,12 @@ module Onebox
         super link, cache , 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 = 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
 
         # Define constant after merging options set in Onebox.options
-        # We can define constant automatically. 
+        # We can define constant automatically.
         options.each_pair {|constant_name,value|
           constant_name_u = constant_name.to_s.upcase
               if constant_name_u == constant_name.to_s
@@ -51,7 +51,7 @@ module Onebox
         range_provided = !(from.nil? && to.nil?) #true if "from" or "to" provided in URL
         from = from.nil? ?  1 : from[0].to_i     #if from not provided default to 1st line
         to   = to.nil?   ? -1 : to[0].to_i       #if to not provided default to undefiend to be handled later in the logic
-        
+
         if to === -1 && range_provided   #case "from" exists but no valid "to". aka ONE_LINER
           one_liner = true
           to = from
@@ -60,7 +60,7 @@ module Onebox
         end
 
         unless range_provided  #case no range provided default to 1..MAX_LINES
-          from = 1 
+          from = 1
           to   = MAX_LINES
           truncated = true if contents_lines_size > MAX_LINES
           #we can technically return here
@@ -69,7 +69,7 @@ module Onebox
         from, to = [from,to].sort                                #enforce valid range.  [from < to]
         from = 1 if from > contents_lines_size                   #if "from" out of TOP bound set to 1st line
         to   = contents_lines_size if to > contents_lines_size   #if "to" is out of TOP bound set to last line.
-        
+
         if one_liner
           @selected_one_liner = from
           if EXPAND_ONE_LINER != EXPAND_NONE
@@ -81,16 +81,16 @@ module Onebox
               to = [to + LINES_AFTER, contents_lines_size].min # make sure expand after does not go out of bound
             end
 
-            from = contents_lines_size if from > contents_lines_size   #if "from" is out of the content top bound 
+            from = contents_lines_size if from > contents_lines_size   #if "from" is out of the content top bound
             # to   = contents_lines_size if to > contents_lines_size   #if "to" is out of  the content top bound
           else
-            #no expand show the one liner solely 
+            #no expand show the one liner solely
           end
         end
-        
+
         if to-from > MAX_LINES && !one_liner  #if exceed the MAX_LINES limit correct unless range was produced by one_liner which it expand setting will allow exceeding the line limit
           truncated = true
-         to = from + MAX_LINES-1  
+         to = from + MAX_LINES-1
         end
 
         {:from               => from,                 #calculated from
@@ -98,30 +98,30 @@ module Onebox
          :to                 => to,                   #calculated to
          :one_liner          => one_liner,            #boolean if a one-liner
          :selected_one_liner => @selected_one_liner,  #if a one liner is provided we create a reference for it.
-         :range_provided     => range_provided,       #boolean if range provided 
+         :range_provided     => range_provided,       #boolean if range provided
          :truncated          => truncated}
       end
 
-      #minimize/compact leading indentation while preserving overall indentation 
+      #minimize/compact leading indentation while preserving overall indentation
       def removeLeadingIndentation  str
         #author Lidlanca 2014
         min_space=100
         a_lines = str.lines
         a_lines.each {|l|
-          l = l.chomp("\n")  # remove new line 
+          l = l.chomp("\n")  # remove new line
           m = l.match /^[ ]*/ # find leading spaces 0 or more
           unless m.nil? || l.size==m[0].size || m[0].size==0 # no match | only spaces in line | empty line
             m_str_length  = m[0].size
             if m_str_length <= 1  # minimum space is 1 or nothing we can break we found our minimum
               min_space = m_str_length
               break #stop iteration
-            end 
+            end
             if m_str_length < min_space
               min_space = m_str_length
-            end 
+            end
           else
             next # SKIP no match or line is only spaces
-          end 
+          end
         }
         a_lines.each {|l|
           re = Regexp.new "^[ ]{#{min_space}}"  #match the minimum spaces of the line
@@ -130,7 +130,7 @@ module Onebox
         a_lines.join
       end
 
-      def line_number_helper(lines,start,selected) 
+      def line_number_helper(lines,start,selected)
         #author Lidlanca  09/15/2014
         lines = removeLeadingIndentation(lines.join).lines # A little ineffeicent we could modify  removeLeadingIndentation to accept array and return array, but for now it is only working with a string
         hash_builder =[]
@@ -155,11 +155,12 @@ module Onebox
           to   = /\d+/.match(m[:to])     #get numeric should only match a positive interger
 
           @file = m[:file]
+          @lang = Onebox::FileTypeFinder.from_file_name(m[:file])
           contents = open("https://raw.github.com/#{m[:user]}/#{m[:repo]}/#{m[:sha1]}/#{m[:file]}", read_timeout: timeout).read
-          
-          contents_lines = contents.lines           #get contents lines 
+
+          contents_lines = contents.lines           #get contents lines
           contents_lines_size = contents_lines.size #get number of lines
-            
+
           cr = calc_range(m,contents_lines_size)    #calculate the range of lines for output
             selected_one_liner = cr[:selected_one_liner] #if url is a one-liner calc_range will return it
             # puts "SELECTED LINE" + cr[:selected_one_liner].to_s
@@ -173,8 +174,8 @@ module Onebox
             if SHOW_LINE_NUMBER
               lines_result = line_number_helper(contents_lines[from-1..to-1], from, selected_one_liner)  #print code with prefix line numbers in case range provided
               contents = lines_result[:output]
-              @selected_lines_array = lines_result[:array] 
-            else 
+              @selected_lines_array = lines_result[:array]
+            else
               contents = contents_lines[from-1..to-1].join()
             end
 
@@ -194,7 +195,11 @@ module Onebox
       def data
         @data ||= {title: link.sub(/^https?\:\/\/github\.com\//, ''),
                    link: link,
+                   # IMPORTANT NOTE: All of the other class variables are populated
+                   #     as *side effects* of the `raw` method! They must all appear
+                   #     AFTER the call to `raw`! Don't get bitten by this like I did!
                    content: raw,
+                   lang: @lang,
                    lines:  @selected_lines_array ,
                    has_lines: !@selected_lines_array.nil?,
                    selected_one_liner: @selected_one_liner,

data/lib/onebox/engine/github_gist_onebox.rb

@@ -1,9 +1,11 @@
-# This is broken, document.write is only allowed on load
-# See: http://stackoverflow.com/questions/9154026/jquery-dynamically-load-a-gist-embed
 module Onebox
   module Engine
     class GithubGistOnebox
       include Engine
+      include LayoutSupport
+      include JSON
+
+      MAX_FILES = 3
 
       matches_regexp Regexp.new("^http(?:s)?://gist\\.(?:(?:\\w)+\\.)?(github)\\.com(?:/)?")
 
@@ -11,20 +13,67 @@ module Onebox
         "https://api.github.com/gists/#{match[:sha]}"
       end
 
-      def to_html
-        "<script src=\"//gist.github.com/#{match[:sha]}.js\"></script>"
-      end
-
       private
 
       def data
-        { sha: match[:sha], title: match[:sha], link: @url }
+        @data ||= {
+          title: 'gist.github.com',
+          link: link,
+          gist_files: gist_files.take(MAX_FILES),
+          truncated_files?: truncated_files?
+        }
+      end
+
+      def truncated_files?
+        gist_files.size > MAX_FILES
+      end
+
+      def gist_files
+        return [] unless gist_api
+
+        @gist_files ||= gist_api["files"].values.map do |file_json|
+          GistFile.new(file_json)
+        end
+      end
+
+      def gist_api
+        @raw ||= raw.clone
+      rescue OpenURI::HTTPError
+        # The Gist API rate limit of 60 requests per hour was reached.
+        nil
       end
 
       def match
         @match ||= @url.match(%r{gist\.github\.com/([^/]+/)?(?<sha>[0-9a-f]+)})
       end
 
+      class GistFile
+        attr_reader :filename
+        attr_reader :language
+
+        MAX_LINES = 10
+
+        def initialize(json)
+          @json = json
+          @filename = @json["filename"]
+          @language = @json["language"]
+        end
+
+        def content
+          lines.take(MAX_LINES).join("\n")
+        end
+
+        def truncated?
+          lines.size > MAX_LINES
+        end
+
+        private
+
+        def lines
+          @lines ||= @json["content"].split("\n")
+        end
+      end
+
     end
   end
 end

data/lib/onebox/engine/google_play_app_onebox.rb

@@ -5,19 +5,28 @@ module Onebox
       include LayoutSupport
       include HTML
 
+      DEFAULTS = {
+        MAX_DESCRIPTION_CHARS: 500
+      }
+
+
       matches_regexp Regexp.new("^http(?:s)?://play\\.(?:(?:\\w)+\\.)?(google)\\.com(?:/)?/store/apps/")
 
       private
 
       def data
-        {
+        result = {
           link: link,
           title: raw.css(".document-title div").inner_text,
           developer: raw.css(".document-subtitle.primary").inner_text,
           image: raw.css(".cover-image").first["src"],
-          description: raw.css(".text-body div").inner_text,
+          description: raw.css(".text-body div").inner_text[0..DEFAULTS[:MAX_DESCRIPTION_CHARS]].chop + "...",
           price: raw.css(".price.buy meta[itemprop=price]").first["content"]
         }
+        if result[:price].to_i <= 0 then
+            result[:price] = "Free"
+        end
+        result
       end
     end
   end

data/lib/onebox/engine/standard_embed.rb

@@ -1,10 +1,9 @@
 module Onebox
   module Engine
     module StandardEmbed
-
       def raw
         return @raw if @raw
-        response = fetch_response(url)
+        response = Onebox::Helpers.fetch_response(url)
         html_doc = Nokogiri::HTML(response.body)
 
         # Determine if we should use OEmbed or OpenGraph
@@ -12,7 +11,7 @@ module Onebox
         if oembed_alternate
           # If the oembed request fails, we can still try the opengraph below.
           begin
-            @raw = Onebox::Helpers.symbolize_keys(::MultiJson.load(fetch_response(oembed_alternate['href']).body))
+            @raw = Onebox::Helpers.symbolize_keys(::MultiJson.load(Onebox::Helpers.fetch_response(oembed_alternate['href']).body))
           rescue Errno::ECONNREFUSED, Net::HTTPError, MultiJson::LoadError
             @raw = nil
           end
@@ -59,38 +58,6 @@ module Onebox
 
         og
       end
-
-      def fetch_response(location, limit = 5, domain = nil,headers=nil)
-        raise Net::HTTPError.new('HTTP redirect too deep', location) if limit == 0
-
-        uri = URI(location)
-        if !uri.host
-          uri = URI("#{domain}#{location}")
-        end
-        http = Net::HTTP.new(uri.host, uri.port)
-        http.open_timeout = Onebox.options.connect_timeout
-        http.read_timeout = Onebox.options.timeout
-        if uri.is_a?(URI::HTTPS)
-          http.use_ssl = true
-          http.verify_mode = OpenSSL::SSL::VERIFY_NONE
-        end
-
-        response = http.request_get(uri.request_uri,headers)
-
-        cookie = response.get_fields('set-cookie')
-        if (cookie)
-          header = {'cookie' => cookie.join("")}
-        end
-        header = nil unless header.is_a? Hash
-
-        case response
-        when Net::HTTPSuccess     then response
-        when Net::HTTPRedirection then fetch_response(response['location'], limit - 1, "#{uri.scheme}://#{uri.host}",header)
-        else
-          response.error!
-        end
-      end
-
     end
   end
 end

data/lib/onebox/engine/youku_onebox.rb

@@ -0,0 +1,49 @@
+module Onebox
+  module Engine
+    class YoukuOnebox
+      include Engine
+      include HTML
+
+      matches_regexp(/^(https?:\/\/)?([\da-z\.-]+)(youku.com\/)(.)+\/?$/)
+
+      # Try to get the video ID. Works for URLs of the form:
+      # * http://v.youku.com/v_show/id_XNjM3MzAxNzc2.html
+      def video_id
+        match = uri.path.match(/\/v_show\/id_([a-zA-Z0-9]*)(\.html)*/)
+        return match[1] if match && match[1]
+
+        nil
+      rescue
+        return nil
+      end
+
+      def to_html
+        "<iframe width='480' height='270' src='http://player.youku.com/embed/#{video_id}' frameborder='0' allowfullscreen></iframe>"
+      end
+
+      def placeholder_html
+        if video_id
+          meta_url = "http://v.youku.com/player/getPlayList/VideoIDS/#{video_id}"
+          response = Onebox::Helpers.fetch_response(meta_url)
+          meta = MultiJson::load(response.body) if response && response.body
+          image_src = if meta && meta['data'] && meta['data'][0] && meta['data'][0]['logo']
+                        meta['data'][0]['logo']
+                      else
+                        nil
+                      end
+          "<img src='#{image_src}' width='480' height='270'>"
+        else
+          to_html
+        end
+      end
+
+      private
+
+      # Note: May throw! Make sure to recue.
+      def uri
+        @_uri ||= URI(@url)
+      end
+
+    end 
+  end 
+end