formatting

[akkoma] / lib / pleroma / html.ex

diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex
index 1c62f2ccc2e9617636c134141d741b1c85147b56..1b920d7fd5cf95781bbaa08d6d5f9107ad810658 100644 (file)
--- a/lib/pleroma/html.ex
+++ b/lib/pleroma/html.ex
@@ -1,13 +1,28 @@
 defmodule Pleroma.HTML do
   alias HtmlSanitizeEx.Scrubber
 
-  @markup Application.get_env(:pleroma, :markup)
+  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
+    Pleroma.Config.get([:markup, :scrub_policy])
+    |> get_scrubbers
+  end
+
+  def filter_tags(html, nil) do
+    get_scrubbers()
+    |> Enum.reduce(html, fn scrubber, html ->
+      filter_tags(html, scrubber)
+    end)
+  end
 
-  def filter_tags(html) do
-    scrubber = Keyword.get(@markup, :scrub_policy)
+  def filter_tags(html, scrubber) do
     html |> Scrubber.scrub(scrubber)
   end
 
+  def filter_tags(html), do: filter_tags(html, nil)
+
   def strip_tags(html) do
     html |> Scrubber.scrub(Scrubber.StripTags)
   end
@@ -19,11 +34,13 @@ 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
 
-  @valid_schemes ["http", "https"]
-
   Meta.remove_cdata_sections_before_scrub()
   Meta.strip_comments()
 
@@ -37,6 +54,23 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do
 
   # microformats
   Meta.allow_tag_with_these_attributes("span", [])
+
+  # allow inline images for custom emoji
+  @allow_inline_images Keyword.get(@markup, :allow_inline_images)
+
+  if @allow_inline_images do
+    # 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",
+      "height",
+      "title",
+      "alt"
+    ])
+  end
+
+  Meta.strip_everything_not_covered()
 end
 
 defmodule Pleroma.HTML.Scrubber.Default do
@@ -45,7 +79,9 @@ defmodule Pleroma.HTML.Scrubber.Default do
   require HtmlSanitizeEx.Scrubber.Meta
   alias HtmlSanitizeEx.Scrubber.Meta
 
-  @valid_schemes ["http", "https"]
+  @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()
@@ -53,6 +89,8 @@ defmodule Pleroma.HTML.Scrubber.Default do
   Meta.allow_tag_with_uri_attributes("a", ["href"], @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", [])
@@ -69,11 +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"], @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",
@@ -112,3 +150,36 @@ defmodule Pleroma.HTML.Scrubber.Default do
 
   Meta.strip_everything_not_covered()
 end
+
+defmodule Pleroma.HTML.Transform.MediaProxy do
+  @moduledoc "Transforms inline image URIs to use MediaProxy."
+
+  alias Pleroma.Web.MediaProxy
+
+  def before_scrub(html), do: html
+
+  def scrub_attribute("img", {"src", "http" <> target}) do
+    media_url =
+      ("http" <> target)
+      |> MediaProxy.url()
+
+    {"src", media_url}
+  end
+
+  def scrub_attribute(tag, attribute), do: attribute
+
+  def scrub({"img", attributes, children}) do
+    attributes =
+      attributes
+      |> Enum.map(fn attr -> scrub_attribute("img", attr) end)
+      |> Enum.reject(&is_nil(&1))
+
+    {"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(text), do: text
+end