Stash

[akkoma] / lib / pleroma / html.ex

diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex
index 00b26963da070e4685be1ce6dbb128c7e7ff621e..291b0e612c032fa2755341efa6e81cf6424abce8 100644 (file)
--- a/lib/pleroma/html.ex
+++ b/lib/pleroma/html.ex
@@ -1,32 +1,78 @@
+# Pleroma: A lightweight social networking server
+# Copyright © 2017-2019 Pleroma Authors <https://pleroma.social/>
+# SPDX-License-Identifier: AGPL-3.0-only
+
 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
-    Keyword.get(@markup, :scrub_policy)
+    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, get_scrubbers())
+  end
+
+  def filter_tags(html, scrubbers) when is_list(scrubbers) do
+    Enum.reduce(scrubbers, html, fn scrubber, html ->
       filter_tags(html, scrubber)
     end)
   end
 
-  def filter_tags(html, scrubber) do
-    html |> Scrubber.scrub(scrubber)
+  def filter_tags(html, scrubber), do: Scrubber.scrub(html, scrubber)
+  def filter_tags(html), do: filter_tags(html, nil)
+  def strip_tags(html), do: Scrubber.scrub(html, Scrubber.StripTags)
+
+  def get_cached_scrubbed_html_for_object(content, scrubbers, object, module) do
+    key = "#{module}#{generate_scrubber_signature(scrubbers)}|#{object.id}"
+    Cachex.fetch!(:scrubber_cache, key, fn _key -> ensure_scrubbed_html(content, scrubbers) end)
   end
 
-  def filter_tags(html), do: filter_tags(html, nil)
+  def get_cached_stripped_html_for_object(content, object, module) do
+    get_cached_scrubbed_html_for_object(
+      content,
+      HtmlSanitizeEx.Scrubber.StripTags,
+      object,
+      module
+    )
+  end
+
+  def ensure_scrubbed_html(
+        content,
+        scrubbers
+      ) do
+    {:commit, filter_tags(content, scrubbers)}
+  end
+
+  defp generate_scrubber_signature(scrubber) when is_atom(scrubber) do
+    generate_scrubber_signature([scrubber])
+  end
+
+  defp generate_scrubber_signature(scrubbers) do
+    Enum.reduce(scrubbers, "", fn scrubber, signature ->
+      "#{signature}#{to_string(scrubber)}"
+    end)
+  end
+
+  def extract_first_external_url(_, nil), do: {:error, "No content"}
+
+  def extract_first_external_url(object, content) do
+    key = "URL|#{object.id}"
 
-  def strip_tags(html) do
-    html |> Scrubber.scrub(Scrubber.StripTags)
+    Cachex.fetch!(:scrubber_cache, key, fn _key ->
+      result =
+        content
+        |> Floki.filter_out("a.mention")
+        |> Floki.attribute("a", "href")
+        |> Enum.at(0)
+
+      {:commit, {:ok, result}}
+    end)
   end
 end
 
@@ -37,8 +83,7 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do
   """
 
   @markup Application.get_env(:pleroma, :markup)
-  @uri_schemes Application.get_env(:pleroma, :uri_schemes, [])
-  @valid_schemes Keyword.get(@uri_schemes, :valid_schemes, [])
+  @valid_schemes Pleroma.Config.get([:uri_schemes, :valid_schemes], [])
 
   require HtmlSanitizeEx.Scrubber.Meta
   alias HtmlSanitizeEx.Scrubber.Meta
@@ -47,15 +92,15 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do
   Meta.strip_comments()
 
   # links
-  Meta.allow_tag_with_uri_attributes("a", ["href"], @valid_schemes)
-  Meta.allow_tag_with_these_attributes("a", ["name", "title"])
+  Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes)
+  Meta.allow_tag_with_these_attributes("a", ["name", "title", "class"])
 
   # paragraphs and linebreaks
   Meta.allow_tag_with_these_attributes("br", [])
   Meta.allow_tag_with_these_attributes("p", [])
 
   # microformats
-  Meta.allow_tag_with_these_attributes("span", [])
+  Meta.allow_tag_with_these_attributes("span", ["class"])
 
   # allow inline images for custom emoji
   @allow_inline_images Keyword.get(@markup, :allow_inline_images)
@@ -82,14 +127,13 @@ defmodule Pleroma.HTML.Scrubber.Default do
   alias HtmlSanitizeEx.Scrubber.Meta
 
   @markup Application.get_env(:pleroma, :markup)
-  @uri_schemes Application.get_env(:pleroma, :uri_schemes, [])
-  @valid_schemes Keyword.get(@uri_schemes, :valid_schemes, [])
+  @valid_schemes Pleroma.Config.get([:uri_schemes, :valid_schemes], [])
 
   Meta.remove_cdata_sections_before_scrub()
   Meta.strip_comments()
 
-  Meta.allow_tag_with_uri_attributes("a", ["href"], @valid_schemes)
-  Meta.allow_tag_with_these_attributes("a", ["name", "title"])
+  Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes)
+  Meta.allow_tag_with_these_attributes("a", ["name", "title", "class"])
 
   Meta.allow_tag_with_these_attributes("abbr", ["title"])
 
@@ -104,7 +148,7 @@ defmodule Pleroma.HTML.Scrubber.Default do
   Meta.allow_tag_with_these_attributes("ol", [])
   Meta.allow_tag_with_these_attributes("p", [])
   Meta.allow_tag_with_these_attributes("pre", [])
-  Meta.allow_tag_with_these_attributes("span", [])
+  Meta.allow_tag_with_these_attributes("span", ["class"])
   Meta.allow_tag_with_these_attributes("strong", [])
   Meta.allow_tag_with_these_attributes("u", [])
   Meta.allow_tag_with_these_attributes("ul", [])
@@ -168,7 +212,7 @@ 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 =
@@ -179,9 +223,9 @@ defmodule Pleroma.HTML.Transform.MediaProxy do
     {"img", attributes, children}
   end
 
-  def scrub({:comment, children}), do: ""
+  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