1 files changed, 41 insertions, 39 deletions
diff --git a/app/lib/advanced_text_formatter.rb b/app/lib/advanced_text_formatter.rb
index dcaf34b91..21e81d4d1 100644
--- a/app/lib/advanced_text_formatter.rb
+++ b/app/lib/advanced_text_formatter.rb
@@ -19,6 +19,8 @@ class AdvancedTextFormatter < TextFormatter
     end
   end
 
+  attr_reader :content_type
+
   # @param [String] text
   # @param [Hash] options
   # @option options [Boolean] :multiline
@@ -27,7 +29,7 @@ class AdvancedTextFormatter < TextFormatter
   # @option options [Array<Account>] :preloaded_accounts
   # @option options [String] :content_type
   def initialize(text, options = {})
-    content_type = options.delete(:content_type)
+    @content_type = options.delete(:content_type)
     super(text, options)
 
     @text = format_markdown(text) if content_type == 'text/markdown'
@@ -50,50 +52,50 @@ class AdvancedTextFormatter < TextFormatter
     html.html_safe # rubocop:disable Rails/OutputSafety
   end
 
-  # Differs from `TextFormatter` by skipping HTML tags and entities
-  def entities
-    @entities ||= begin
-      gaps = []
-      total_offset = 0
-
-      escaped = text.gsub(/<[^>]*>|&#[0-9]+;/) do |match|
-        total_offset += match.length - 1
-        end_offset = Regexp.last_match.end(0)
-        gaps << [end_offset - total_offset, total_offset]
-        ' '
-      end
-
-      Extractor.extract_entities_with_indices(escaped, extract_url_without_protocol: false).map do |entity|
-        start_pos, end_pos = entity[:indices]
-        offset_idx = gaps.rindex { |gap| gap.first <= start_pos }
-        offset = offset_idx.nil? ? 0 : gaps[offset_idx].last
-        entity.merge(indices: [start_pos + offset, end_pos + offset])
+  # Differs from TextFormatter by operating on the parsed HTML tree
+  def rewrite
+    if @tree.nil?
+      src = text.gsub(Sanitize::REGEX_UNSUITABLE_CHARS, '')
+      @tree = Nokogiri::HTML5.fragment(src)
+      document = @tree.document
+
+      @tree.xpath('.//text()[not(ancestor::a | ancestor::code)]').each do |text_node|
+        # Iterate over text elements and build up their replacements.
+        content = text_node.content
+        replacement = Nokogiri::XML::NodeSet.new(document)
+        processed_index = 0
+        Extractor.extract_entities_with_indices(
+          content,
+          extract_url_without_protocol: false
+        ) do |entity|
+          # Iterate over entities in this text node.
+          advance = entity[:indices].first - processed_index
+          if advance.positive?
+            # Text node for content which precedes entity.
+            replacement << Nokogiri::XML::Text.new(
+              content[processed_index, advance],
+              document
+            )
+          end
+          replacement << Nokogiri::HTML5.fragment(yield(entity))
+          processed_index = entity[:indices].last
+        end
+        if processed_index < content.size
+          # Text node for remaining content.
+          replacement << Nokogiri::XML::Text.new(
+            content[processed_index, content.size - processed_index],
+            document
+          )
+        end
+        text_node.replace(replacement)
       end
     end
+
+    Sanitize.node!(@tree, Sanitize::Config::MASTODON_OUTGOING).to_html
   end
 
   private
 
-  # Differs from `TextFormatter` in that it keeps HTML; but it sanitizes at the end to remain safe
-  def rewrite
-    entities.sort_by! do |entity|
-      entity[:indices].first
-    end
-
-    result = ''.dup
-
-    last_index = entities.reduce(0) do |index, entity|
-      indices = entity[:indices]
-      result << text[index...indices.first]
-      result << yield(entity)
-      indices.last
-    end
-
-    result << text[last_index..-1]
-
-    Sanitize.fragment(result, Sanitize::Config::MASTODON_OUTGOING)
-  end
-
   def format_markdown(html)
     html = markdown_formatter.render(html)
     html.delete("\r").delete("\n")