Merge branch 'develop' into 'fix/mix-task-uploads-moduledoc'

[akkoma] / lib / pleroma / html.ex

diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex
index 8a5ede614247f90a8d56efb4552c0d6e1a0a11f4..8a0333461557a1000108e8b3d802d77be1d310ff 100644 (file)
--- a/lib/pleroma/html.ex
+++ b/lib/pleroma/html.ex
@@ -1,33 +1,12 @@
 defmodule Pleroma.HTML do
   alias HtmlSanitizeEx.Scrubber
 
-  @markup Application.get_env(:pleroma, :markup)
-
-  def valid_schemes() do
-    [
-      "https://",
-      "http://",
-      "dat://",
-      "dweb://",
-      "gopher://",
-      "ipfs://",
-      "ipns://",
-      "irc:",
-      "ircs:",
-      "magnet:",
-      "mailto:",
-      "mumble:",
-      "ssb://",
-      "xmpp:"
-    ]
-  end
-
   defp get_scrubbers(scrubber) when is_atom(scrubber), do: [scrubber]
   defp get_scrubbers(scrubbers) when is_list(scrubbers), do: scrubbers
   defp get_scrubbers(_), do: [Pleroma.HTML.Scrubber.Default]
 
   def get_scrubbers() do
-    Keyword.get(@markup, :scrub_policy)
+    Pleroma.Config.get([:markup, :scrub_policy])
     |> get_scrubbers
   end
 
@@ -55,16 +34,18 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do
   paragraphs, breaks and links are allowed through the filter.
   """
 
+  @markup Application.get_env(:pleroma, :markup)
+  @uri_schemes Application.get_env(:pleroma, :uri_schemes, [])
+  @valid_schemes Keyword.get(@uri_schemes, :valid_schemes, [])
+
   require HtmlSanitizeEx.Scrubber.Meta
   alias HtmlSanitizeEx.Scrubber.Meta
 
-  alias Pleroma.HTML
-
   Meta.remove_cdata_sections_before_scrub()
   Meta.strip_comments()
 
   # links
-  Meta.allow_tag_with_uri_attributes("a", ["href"], HTML.valid_schemes())
+  Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes)
   Meta.allow_tag_with_these_attributes("a", ["name", "title"])
 
   # paragraphs and linebreaks
@@ -75,11 +56,11 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do
   Meta.allow_tag_with_these_attributes("span", [])
 
   # allow inline images for custom emoji
-  @markup Application.get_env(:pleroma, :markup)
   @allow_inline_images Keyword.get(@markup, :allow_inline_images)
 
   if @allow_inline_images do
-    Meta.allow_tag_with_uri_attributes("img", ["src"], HTML.valid_schemes())
+    # restrict img tags to http/https only, because of MediaProxy.
+    Meta.allow_tag_with_uri_attributes("img", ["src"], ["http", "https"])
 
     Meta.allow_tag_with_these_attributes("img", [
       "width",
@@ -98,14 +79,18 @@ defmodule Pleroma.HTML.Scrubber.Default do
   require HtmlSanitizeEx.Scrubber.Meta
   alias HtmlSanitizeEx.Scrubber.Meta
 
-  alias Pleroma.HTML
+  @markup Application.get_env(:pleroma, :markup)
+  @uri_schemes Application.get_env(:pleroma, :uri_schemes, [])
+  @valid_schemes Keyword.get(@uri_schemes, :valid_schemes, [])
 
   Meta.remove_cdata_sections_before_scrub()
   Meta.strip_comments()
 
-  Meta.allow_tag_with_uri_attributes("a", ["href"], HTML.valid_schemes())
+  Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes)
   Meta.allow_tag_with_these_attributes("a", ["name", "title"])
 
+  Meta.allow_tag_with_these_attributes("abbr", ["title"])
+
   Meta.allow_tag_with_these_attributes("b", [])
   Meta.allow_tag_with_these_attributes("blockquote", [])
   Meta.allow_tag_with_these_attributes("br", [])
@@ -122,11 +107,11 @@ defmodule Pleroma.HTML.Scrubber.Default do
   Meta.allow_tag_with_these_attributes("u", [])
   Meta.allow_tag_with_these_attributes("ul", [])
 
-  @markup Application.get_env(:pleroma, :markup)
   @allow_inline_images Keyword.get(@markup, :allow_inline_images)
 
   if @allow_inline_images do
-    Meta.allow_tag_with_uri_attributes("img", ["src"], HTML.valid_schemes())
+    # restrict img tags to http/https only, because of MediaProxy.
+    Meta.allow_tag_with_uri_attributes("img", ["src"], ["http", "https"])
 
     Meta.allow_tag_with_these_attributes("img", [
       "width",
@@ -181,7 +166,7 @@ defmodule Pleroma.HTML.Transform.MediaProxy do
     {"src", media_url}
   end
 
-  def scrub_attribute(tag, attribute), do: attribute
+  def scrub_attribute(_tag, attribute), do: attribute
 
   def scrub({"img", attributes, children}) do
     attributes =
@@ -192,7 +177,9 @@ defmodule Pleroma.HTML.Transform.MediaProxy do
     {"img", attributes, children}
   end
 
+  def scrub({:comment, _children}), do: ""
+
   def scrub({tag, attributes, children}), do: {tag, attributes, children}
-  def scrub({tag, children}), do: children
+  def scrub({_tag, children}), do: children
   def scrub(text), do: text
 end