1 files changed, 99 insertions, 11 deletions

diff --git a/app/lib/formatter.rb b/app/lib/formatter.rb
index 1610f3689..f2c4beed5 100644
--- a/app/lib/formatter.rb
+++ b/app/lib/formatter.rb
@@ -2,6 +2,29 @@
 
 require 'singleton'
 
+class HTMLRenderer < Redcarpet::Render::HTML
+  def block_code(code, language)
+    "<pre><code>#{encode(code).gsub("\n", "<br/>")}</code></pre>"
+  end
+
+  def autolink(link, link_type)
+    return link if link_type == :email
+    Formatter.instance.link_url(link)
+  rescue Addressable::URI::InvalidURIError, IDN::Idna::IdnaError
+    encode(link)
+  end
+
+  private
+
+  def html_entities
+    @html_entities ||= HTMLEntities.new
+  end
+
+  def encode(html)
+    html_entities.encode(html)
+  end
+end
+
 class Formatter
   include Singleton
   include RoutingHelper
@@ -35,16 +58,26 @@ class Formatter
 
     html = raw_content
     html = "RT @#{prepend_reblog} #{html}" if prepend_reblog
-    html = encode_and_link_urls(html, linkable_accounts)
+    html = format_markdown(html) if status.content_type == 'text/markdown'
+    html = encode_and_link_urls(html, linkable_accounts, keep_html: %w(text/markdown text/html).include?(status.content_type))
+    html = reformat(html, true) if %w(text/markdown text/html).include?(status.content_type)
     html = encode_custom_emojis(html, status.emojis, options[:autoplay]) if options[:custom_emojify]
-    html = simple_format(html, {}, sanitize: false)
-    html = html.delete("\n")
+
+    unless %w(text/markdown text/html).include?(status.content_type)
+      html = simple_format(html, {}, sanitize: false)
+      html = html.delete("\n")
+    end
 
     html.html_safe # rubocop:disable Rails/OutputSafety
   end
 
-  def reformat(html)
-    sanitize(html, Sanitize::Config::MASTODON_STRICT)
+  def format_markdown(html)
+    html = markdown_formatter.render(html)
+    html.delete("\r").delete("\n")
+  end
+
+  def reformat(html, outgoing = false)
+    sanitize(html, Sanitize::Config::MASTODON_STRICT.merge(outgoing: outgoing))
   rescue ArgumentError
     ''
   end
@@ -98,8 +131,40 @@ class Formatter
     html.html_safe # rubocop:disable Rails/OutputSafety
   end
 
+  def link_url(url)
+    "<a href=\"#{encode(url)}\" target=\"blank\" rel=\"nofollow noopener noreferrer\">#{link_html(url)}</a>"
+  end
+
   private
 
+  def markdown_formatter
+    extensions = {
+      autolink: true,
+      no_intra_emphasis: true,
+      fenced_code_blocks: true,
+      disable_indented_code_blocks: true,
+      strikethrough: true,
+      lax_spacing: true,
+      space_after_headers: true,
+      superscript: true,
+      underline: true,
+      highlight: true,
+      footnotes: false,
+    }
+
+    renderer = HTMLRenderer.new({
+      filter_html: false,
+      escape_html: false,
+      no_images: true,
+      no_styles: true,
+      safe_links_only: true,
+      hard_wrap: true,
+      link_attributes: { target: '_blank', rel: 'nofollow noopener' },
+    })
+
+    Redcarpet::Markdown.new(renderer, extensions)
+  end
+
   def html_entities
     @html_entities ||= HTMLEntities.new
   end
@@ -109,14 +174,14 @@ class Formatter
   end
 
   def encode_and_link_urls(html, accounts = nil, options = {})
-    entities = utf8_friendly_extractor(html, extract_url_without_protocol: false)
-
     if accounts.is_a?(Hash)
       options  = accounts
       accounts = nil
     end
 
-    rewrite(html.dup, entities) do |entity|
+    entities = options[:keep_html] ? html_friendly_extractor(html) : utf8_friendly_extractor(html, extract_url_without_protocol: false)
+
+    rewrite(html.dup, entities, options[:keep_html]) do |entity|
       if entity[:url]
         link_to_url(entity, options)
       elsif entity[:hashtag]
@@ -191,7 +256,7 @@ class Formatter
   end
   # rubocop:enable Metrics/BlockNesting
 
-  def rewrite(text, entities)
+  def rewrite(text, entities, keep_html = false)
     text = text.to_s
 
     # Sort by start index
@@ -204,12 +269,12 @@ class Formatter
 
     last_index = entities.reduce(0) do |index, entity|
       indices = entity.respond_to?(:indices) ? entity.indices : entity[:indices]
-      result << encode(text[index...indices.first])
+      result << (keep_html ? text[index...indices.first] : encode(text[index...indices.first]))
       result << yield(entity)
       indices.last
     end
 
-    result << encode(text[last_index..-1])
+    result << (keep_html ? text[last_index..-1] : encode(text[last_index..-1]))
 
     result.flatten.join
   end
@@ -224,6 +289,29 @@ class Formatter
     Extractor.remove_overlapping_entities(special + standard + extra)
   end
 
+  def html_friendly_extractor(html, options = {})
+    gaps = []
+    total_offset = 0
+
+    escaped = html.gsub(/<[^>]*>|&#[0-9]+;/) do |match|
+      total_offset += match.length - 1
+      end_offset = Regexp.last_match.end(0)
+      gaps << [end_offset - total_offset, total_offset]
+      "\u200b"
+    end
+
+    entities = Extractor.extract_hashtags_with_indices(escaped, :check_url_overlap => false) +
+               Extractor.extract_mentions_or_lists_with_indices(escaped)
+    Extractor.remove_overlapping_entities(entities).map do |extract|
+      pos = extract[:indices].first
+      offset_idx = gaps.rindex { |gap| gap.first <= pos }
+      offset = offset_idx.nil? ? 0 : gaps[offset_idx].last
+      next extract.merge(
+        :indices => [extract[:indices].first + offset, extract[:indices].last + offset]
+      )
+    end
+  end
+
   def link_to_url(entity, options = {})
     url        = Addressable::URI.parse(entity[:url])
     html_attrs = { target: '_blank', rel: 'nofollow noopener noreferrer' }