X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fhtml.ex;h=4b42d8c9b93a178de7d8f120a8a3a8f044672230;hb=83589ca6a56ed4ff6d7e9a116fbbf1797ba50e39;hp=5e1f5bf96f469c002ca866ba087baaf97440f957;hpb=dec23500d8988c22a99f049ef1d1e49328ba075a;p=akkoma

diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex
index 5e1f5bf96..4b42d8c9b 100644
--- a/lib/pleroma/html.ex
+++ b/lib/pleroma/html.ex
@@ -1,5 +1,5 @@
 # Pleroma: A lightweight social networking server
-# Copyright © 2017-2018 Pleroma Authors <https://pleroma.social/>
+# Copyright © 2017-2019 Pleroma Authors <https://pleroma.social/>
 # SPDX-License-Identifier: AGPL-3.0-only
 
 defmodule Pleroma.HTML do
@@ -9,7 +9,7 @@ defmodule Pleroma.HTML do
   defp get_scrubbers(scrubbers) when is_list(scrubbers), do: scrubbers
   defp get_scrubbers(_), do: [Pleroma.HTML.Scrubber.Default]
 
-  def get_scrubbers() do
+  def get_scrubbers do
     Pleroma.Config.get([:markup, :scrub_policy])
     |> get_scrubbers
   end
@@ -27,6 +27,66 @@ defmodule Pleroma.HTML do
   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_activity(content, scrubbers, activity, key \\ "") do
+    key = "#{key}#{generate_scrubber_signature(scrubbers)}|#{activity.id}"
+
+    Cachex.fetch!(:scrubber_cache, key, fn _key ->
+      object = Pleroma.Object.normalize(activity)
+      ensure_scrubbed_html(content, scrubbers, object.data["fake"] || false)
+    end)
+  end
+
+  def get_cached_stripped_html_for_activity(content, activity, key) do
+    get_cached_scrubbed_html_for_activity(
+      content,
+      HtmlSanitizeEx.Scrubber.StripTags,
+      activity,
+      key
+    )
+  end
+
+  def ensure_scrubbed_html(
+        content,
+        scrubbers,
+        false = _fake
+      ) do
+    {:commit, filter_tags(content, scrubbers)}
+  end
+
+  def ensure_scrubbed_html(
+        content,
+        scrubbers,
+        true = _fake
+      ) do
+    {:ignore, 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}"
+
+    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
 
 defmodule Pleroma.HTML.Scrubber.TwitterText do
@@ -36,29 +96,31 @@ 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
 
-  def version do
-    0
-  end
-
   Meta.remove_cdata_sections_before_scrub()
   Meta.strip_comments()
 
   # links
   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("a", ["name", "title", "class"])
+
+  Meta.allow_tag_with_this_attribute_values("a", "rel", [
+    "tag",
+    "nofollow",
+    "noopener",
+    "noreferrer"
+  ])
 
   # 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)
@@ -83,20 +145,24 @@ defmodule Pleroma.HTML.Scrubber.Default do
 
   require HtmlSanitizeEx.Scrubber.Meta
   alias HtmlSanitizeEx.Scrubber.Meta
-
-  def version do
-    0
-  end
+  # credo:disable-for-previous-line
+  # No idea how to fix this one…
 
   @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", "data-user", "data-tag"], @valid_schemes)
-  Meta.allow_tag_with_these_attributes("a", ["name", "title"])
+  Meta.allow_tag_with_these_attributes("a", ["name", "title", "class"])
+
+  Meta.allow_tag_with_this_attribute_values("a", "rel", [
+    "tag",
+    "nofollow",
+    "noopener",
+    "noreferrer"
+  ])
 
   Meta.allow_tag_with_these_attributes("abbr", ["title"])
 
@@ -111,7 +177,7 @@ 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", [])
@@ -165,10 +231,6 @@ defmodule Pleroma.HTML.Transform.MediaProxy do
 
   alias Pleroma.Web.MediaProxy
 
-  def version do
-    0
-  end
-
   def before_scrub(html), do: html
 
   def scrub_attribute("img", {"src", "http" <> target}) do