Class: Jekyll::Embed

Inherits:

Object

• Object
• Jekyll::Embed

Defined in:

lib/jekyll/embed.rb,
lib/jekyll/embed/cache.rb,
lib/jekyll/embed/filter.rb,
lib/jekyll/embed/content.rb

Overview

The idea with this class is to find the best safe representation of a link. For a YouTube video it could be the sandboxed iframe. This loads the video and allows you to reproduce it while preventing YT to call home and send data about your users. But other social networks will try to take control of their containers by modifying the page. They resist sandboxing and don't work correctly. For them, we cleanup unwanted HTML tags such as

Returns:

• (Jekyll::Embed::Cache)

# File 'lib/jekyll/embed.rb', line 277

def cache
  @cache ||= Jekyll::Embed::Cache.new('Jekyll::Embed')
end

.cleanup(html_fragment, url) ⇒ String

Returns:

• (String)

# File 'lib/jekyll/embed.rb', line 296

def cleanup(html_fragment, url)
  html = Loofah.fragment(html_fragment).scrub!(:prune)

  # Add our own attributes
  html.css('iframe').each do |iframe|
    IFRAME_ATTRIBUTES.each do |attr|
      set_value_for_attr(iframe, attr)
    end

    # Embedding itself require allow-same-origin
    iframe['sandbox'] += allow_same_origin(url)
  end

  html.css('audio, video').each do |media|
    MEDIA_ATTRIBUTES.each do |attr|
      set_value_for_attr(media, attr)
    end

    media['src'] = UrlPrivacy.clean media['src']
  end

  html.css('img').each do |img|
    IMAGE_ATTRIBUTES.each do |attr|
      set_value_for_attr(img, attr)
    end
  end

  html.css('a').each do |a|
    A_ATTRIBUTES.each do |attr|
      set_value_for_attr(a, attr)
    end
  end

  html.css('[src]').each do |element|
    element['src'] = UrlPrivacy.clean(element['src'])
  end

  html.css('[href]').each do |element|
    element['href'] = UrlPrivacy.clean(element['href'])
  end

  # Return the cleaned up HTML as a String
  html.to_s
end

.config ⇒ Hash

Returns:

• (Hash)

# File 'lib/jekyll/embed.rb', line 179

def config
  @config ||= Jekyll::Utils.deep_merge_hashes(DEFAULT_CONFIG, (site.config['embed'] || {})).tap do |c|
    c['attributes']['allow'].concat (DIRECTIVES - c.dig('attributes', 'allow').join.split(';').map do |s|
                                                    s.split(' ').first
                                                  end).join(" 'none';|").split('|')
  end
end

.embed(url) ⇒ String

Render the URL as HTML

1. Try oembed for video and image
2. If rich oembed, cleanup
3. If OGP, render templates
4. Else, render fallback template

Parameters:

• URL (String)

Returns:

• (String) —

  HTML

# File 'lib/jekyll/embed.rb', line 159

def embed(url)
  raise URI::Error unless url.is_a? String

  url = url.strip

  # Quick check
  raise URI::Error unless url.start_with? 'http'

  # Just to verify the URL is valid
  # TODO: Use Addressable
  URI.parse url

  oembed(url) || ogp(url) || fallback(url) || url
rescue URI::Error
  Jekyll.logger.warn "#{url.inspect} is not a valid URL"

  url
end

.fallback(url) ⇒ Object

Try something

# File 'lib/jekyll/embed.rb', line 241

def fallback(url)
  cache.getset("fallback+#{url}") do
    html        = ::Nokogiri::HTML.fragment get(url).body
    element     = html.css('article').first
    element   ||= html.css('section').first
    element   ||= html.css('main').first
    element   ||= html.css('body').first
    title       = html.css('title').first
    description = html.css('meta[name="description"]').first

    context = info.dup
    context[:registers][:page] = payload['page'] = {
      'title' => text(title),
      'description' => text(description),
      'url' => url,
      'image' => element&.css('img')&.first&.public_send(:[], 'src'),
      'locale' => html.css('html')&.first&.public_send(:[], 'lang')
    }

    cleanup fallback_template.render!(payload, context), url
  end
rescue ArgumentError
  Jekyll.logger.warn 'Invalid contents (fallback):', url
  nil
rescue Faraday::Error, ::Nokogiri::SyntaxError
  nil
end

.get(url) ⇒ Faraday::Response

Parameters:

• URL (String)

Returns:

• (Faraday::Response)

# File 'lib/jekyll/embed.rb', line 271

def get(url)
  @get_cache ||= {}
  @get_cache[url] ||= http_client.get url
end

.http_client ⇒ Faraday::Connection

Returns:

• (Faraday::Connection)

# File 'lib/jekyll/embed.rb', line 282

def http_client
  @http_client ||= Faraday.new do |builder|
    builder.options.timeout = 4
    builder.options.open_timeout = 1
    builder.options.read_timeout = 1
    builder.options.write_timeout = 1
    builder.use FaradayMiddleware::FollowRedirects
    builder.use :http_cache, shared_cache: false, store: cache, serializer: Marshal
  end
end

.oembed(url) ⇒ String, NilClass

Try for OEmbed

Parameters:

• URL (String)

Returns:

• (String, NilClass) —

  Sanitized HTML or nil

# File 'lib/jekyll/embed.rb', line 191

def oembed(url)
  cache.getset("oembed+#{url}") do
    oembed = OEmbed::Providers.get url

    # Prevent caching of nil?
    raise OEmbed::Error unless oembed.respond_to? :html

    context = info.dup
    context[:registers][:page] = payload['page'] = cleanup(oembed.html, url)

    embed_template.render!(payload, context)
  end
rescue OEmbed::Error
  nil
end

.ogp(url) ⇒ String, NilClass

Try for OGP.

Parameters:

• URL (String)

Returns:

• (String, NilClass)

# File 'lib/jekyll/embed.rb', line 210

def ogp(url)
  cache.getset("ogp+#{url}") do
    ogp = OGP::OpenGraph.new get(url).body
    page = {
      locale: ogp.locales.first,
      title: ogp.title,
      url: ogp.url,
      description: ogp.description,
      type: ogp.type,
      data: ogp.data
    }.transform_keys(&:to_s)

    %w[image video audio].each do |attr|
      page[attr] = ogp.public_send(:"#{attr}s").find do |a|
        a && a.url && http?(a.url)
      end&.url
    end

    context = info.dup
    context[:registers][:page] = payload['page'] = page

    cleanup ogp_template.render!(payload, context), url
  end
rescue ArgumentError
  Jekyll.logger.warn 'Invalid contents (OGP):', url
  nil
rescue LL::ParserError, OGP::MalformedSourceError, OGP::MissingAttributeError, Faraday::Error
  nil
end

.reset ⇒ nil

Reset variables

Returns:

• (nil)

# File 'lib/jekyll/embed.rb', line 135

def reset
  @allow_same_origin =
    @cache =
      @config =
        @embed_template =
          @fallback_template =
            @get_cache =
              @http_client =
                @info =
                  @ogp_template =
                    @payload =
                      @value_for_attr =
                      nil
end

.site ⇒ Object

# File 'lib/jekyll/embed.rb', line 95

def site
  unless @site
    raise Jekyll::Errors::InvalidConfigurationError,
          'Site is missing, configure with `Jekyll::Embed.site = site`'
  end

  @site
end

.site=(site) ⇒ Jekyll::Site

This is an initializer of sorts

Parameters:

• (Jekyll::Site)

Returns:

• (Jekyll::Site)

Raises:

• (ArgumentError)

# File 'lib/jekyll/embed.rb', line 108

def site=(site)
  raise ArgumentError, 'Site must be a Jekyll::Site' unless site.is_a? Jekyll::Site

  @site = site

  # Add the _includes dir so we can provide default templates that
  # can be overriden locally or by the theme.
  includes_dir = File.expand_path(File.join(__dir__, '..', '..', '_includes'))
  site.includes_load_paths << includes_dir unless site.includes_load_paths.include? includes_dir
  # Since we're embedding, we're allowing iframes
  Loofah::HTML5::SafeList::ALLOWED_ELEMENTS_WITH_LIBXML2 << 'iframe'

  reset

  # Other elements that are disallowed
  config['scrub']&.each do |scrub|
    Loofah::HTML5::SafeList::ALLOWED_ELEMENTS_WITH_LIBXML2.delete(scrub)
  end

  payload['embed'] = config['attributes']

  site
end

.text(node) ⇒ Object

# File 'lib/jekyll/embed.rb', line 341

def text(node)
  node&.text&.tr("\n", '')&.tr("\r", '')&.strip&.squeeze(' ')
end