X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fhtml.ex;h=b4a4742ee30c39699e0ecaf079a8226415ead5f3;hb=040ab352a543bdaa7ac4c078db0fc24f0db37d5a;hp=eb31f131eadfa6ba56ecac7f5573c6bed1e5e7ca;hpb=33e3a7ba7dab750f2a5f85e22b0e44251ec308d2;p=akkoma

diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex
index eb31f131e..b4a4742ee 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
@@ -28,13 +28,18 @@ defmodule Pleroma.HTML do
   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) do
-    key = "#{generate_scrubber_signature(scrubbers)}|#{object.id}"
+  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 get_cached_stripped_html_for_object(content, object) do
-    get_cached_scrubbed_html_for_object(content, HtmlSanitizeEx.Scrubber.StripTags, object)
+  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(
@@ -50,15 +55,23 @@ defmodule Pleroma.HTML do
 
   defp generate_scrubber_signature(scrubbers) do
     Enum.reduce(scrubbers, "", fn scrubber, signature ->
-      # If a scrubber does not have a version(e.g HtmlSanitizeEx.Scrubber.StripTags) it is assumed it is always 0)
-      version =
-        if Kernel.function_exported?(scrubber, :version, 0) do
-          scrubber.version
-        else
-          0
-        end
-
-      "#{signature}#{to_string(scrubber)}#{version}"
+      "#{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
@@ -76,23 +89,19 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do
   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"])
 
   # 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)
@@ -118,10 +127,6 @@ defmodule Pleroma.HTML.Scrubber.Default do
   require HtmlSanitizeEx.Scrubber.Meta
   alias HtmlSanitizeEx.Scrubber.Meta
 
-  def version do
-    0
-  end
-
   @markup Application.get_env(:pleroma, :markup)
   @uri_schemes Application.get_env(:pleroma, :uri_schemes, [])
   @valid_schemes Keyword.get(@uri_schemes, :valid_schemes, [])
@@ -130,7 +135,7 @@ defmodule Pleroma.HTML.Scrubber.Default do
   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_these_attributes("abbr", ["title"])
 
@@ -145,7 +150,7 @@ 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", [])
@@ -199,10 +204,6 @@ 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