Rich Media: Skip Microformats hashtags

When fixing this problem I incorrectly assumed a.hashtag is
the proper way for detecting hashtags, but it is just something Pleroma and
Mastodon add. Per microformats it should be detected by the presense of rel=tag.

This MR adds a check for rel=tag, but I still left a.hashtag just in case

2 files changed, 17 insertions, 1 deletions

diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex
index 8c226c944..2fae7281c 100644
--- a/lib/pleroma/html.ex
+++ b/lib/pleroma/html.ex
@@ -89,7 +89,7 @@ defmodule Pleroma.HTML do
     Cachex.fetch!(:scrubber_cache, key, fn _key ->
       result =
         content
-        |> Floki.filter_out("a.mention,a.hashtag")
+        |> Floki.filter_out("a.mention,a.hashtag,a[rel~=\"tag\"]")
         |> Floki.attribute("a", "href")
         |> Enum.at(0)
 
diff --git a/test/html_test.exs b/test/html_test.exs
index 64513980b..b8906c46a 100644
--- a/test/html_test.exs
+++ b/test/html_test.exs
@@ -212,5 +212,21 @@ defmodule Pleroma.HTMLTest do
 
       assert url == "https://www.pixiv.net/member_illust.php?mode=medium&illust_id=72255140"
     end
+
+    test "skips microformats hashtags" do
+      user = insert(:user)
+
+      {:ok, activity} =
+        CommonAPI.post(user, %{
+          "status" =>
+            "<a href=\"https://pleroma.gov/tags/cofe\" rel=\"tag\">#cofe</a> https://www.pixiv.net/member_illust.php?mode=medium&illust_id=72255140",
+          "content_type" => "text/html"
+        })
+
+      object = Object.normalize(activity)
+      {:ok, url} = HTML.extract_first_external_url(object, object.data["content"])
+
+      assert url == "https://www.pixiv.net/member_illust.php?mode=medium&illust_id=72255140"
+    end
   end
 end