Store remote post language information

Signed-off-by: marcin mikołajczak <git@mkljczk.pl>

lib/pleroma/web/activity_pub/object_validators/article_note_page_validator.ex

@@ -108,6 +108,7 @@ defp fix(data) do
     |> fix_attachments()
     |> Transmogrifier.fix_emoji()
     |> Transmogrifier.fix_content_map()
+    |> Transmogrifier.maybe_add_language()
   end
 
   def changeset(struct, data) do

lib/pleroma/web/activity_pub/object_validators/common_fields.ex

@@ -58,6 +58,7 @@ defmacro status_object_fields do
       field(:like_count, :integer, default: 0)
       field(:announcement_count, :integer, default: 0)
       field(:quotes_count, :integer, default: 0)
+      field(:language, :string)
       field(:inReplyTo, ObjectValidators.ObjectID)
       field(:quoteUrl, ObjectValidators.ObjectID)
       field(:url, ObjectValidators.Uri)

lib/pleroma/web/activity_pub/transmogrifier.ex

@@ -44,6 +44,7 @@ def fix_object(object, options \\ []) do
     |> fix_content_map()
     |> fix_addressing()
     |> fix_summary()
+    |> maybe_add_language()
   end
 
   def fix_summary(%{"summary" => nil} = object) do
@@ -1096,4 +1097,40 @@ defp maybe_add_content_map(%{"language" => language, "content" => content} = obj
   end
 
   defp maybe_add_content_map(object), do: object
+
+  def maybe_add_language(object) do
+    language =
+      get_language_from_context(object) |> Pleroma.Web.CommonAPI.Utils.get_valid_language() ||
+        get_language_from_content_map(object) |> Pleroma.Web.CommonAPI.Utils.get_valid_language()
+
+    if language do
+      Map.put(object, "language", language)
+    else
+      object
+    end
+  end
+
+  defp get_language_from_context(%{"@context" => context}) do
+    case context
+         |> Enum.find(fn
+           %{"@language" => language} -> language != "und"
+           _ -> nil
+         end) do
+      %{"@language" => language} -> language
+      _ -> nil
+    end
+  end
+
+  defp get_language_from_context(_), do: nil
+
+  defp get_language_from_content_map(%{"contentMap" => content_map, "content" => source_content}) do
+    content_groups = Map.to_list(content_map)
+
+    case Enum.find(content_groups, fn {_, content} -> content == source_content end) do
+      {language, _} -> language
+      _ -> nil
+    end
+  end
+
+  defp get_language_from_content_map(_), do: nil
 end

lib/pleroma/web/common_api/activity_draft.ex

@@ -14,15 +14,6 @@ defmodule Pleroma.Web.CommonAPI.ActivityDraft do
   import Pleroma.Web.Gettext
   import Pleroma.Web.Utils.Guards, only: [not_empty_string: 1]
 
-  @supported_locales ~w(
-    aa ab ae af ak am an ar as av ay az ba be bg bh bi bm bn bo br bs ca ce ch co cr cs cu cv cy da
-    de dv dz ee el en eo es et eu fa ff fi fj fo fr fy ga gd gl gu gv ha he hi ho hr ht hu hy hz ia
-    id ie ig ii ik io is it iu ja jv ka kg ki kj kk kl km kn ko kr ks ku kv kw ky la lb lg li ln lo
-    lt lu lv mg mh mi mk ml mn mr ms mt my na nb nd ne ng nl nn no nr nv ny oc oj om or os pa pi pl
-    ps pt qu rm rn ro ru rw sa sc sd se sg si sk sl sn so sq sr ss st su sv sw ta te tg th ti tk tl
-    tn to tr ts tt tw ty ug uk ur uz ve vi vo wa wo xh yi yo za zh zu ast ckb kab kmr zgh
-  )
-
   defstruct valid?: true,
             errors: [],
             user: nil,
@@ -236,9 +227,9 @@ defp sensitive(draft) do
   end
 
   defp language(%{params: %{language: language}} = draft) when not_empty_string(language) do
-    case language |> String.split("_") |> Enum.at(0) do
-      locale when locale in @supported_locales ->
-        %__MODULE__{draft | language: locale}
+    case Utils.get_valid_language(language) do
+      language when is_binary(language) ->
+        %__MODULE__{draft | language: language}
 
       _ ->
         draft

lib/pleroma/web/common_api/utils.ex

@@ -23,6 +23,15 @@ defmodule Pleroma.Web.CommonAPI.Utils do
   require Logger
   require Pleroma.Constants
 
+  @supported_locales ~w(
+    aa ab ae af ak am an ar as av ay az ba be bg bh bi bm bn bo br bs ca ce ch co cr cs cu cv cy da
+    de dv dz ee el en eo es et eu fa ff fi fj fo fr fy ga gd gl gu gv ha he hi ho hr ht hu hy hz ia
+    id ie ig ii ik io is it iu ja jv ka kg ki kj kk kl km kn ko kr ks ku kv kw ky la lb lg li ln lo
+    lt lu lv mg mh mi mk ml mn mr ms mt my na nb nd ne ng nl nn no nr nv ny oc oj om or os pa pi pl
+    ps pt qu rm rn ro ru rw sa sc sd se sg si sk sl sn so sq sr ss st su sv sw ta te tg th ti tk tl
+    tn to tr ts tt tw ty ug uk ur uz ve vi vo wa wo xh yi yo za zh zu ast ckb kab kmr zgh
+  )
+
   def attachments_from_ids(%{media_ids: ids, descriptions: desc}) do
     attachments_from_ids_descs(ids, desc)
   end
@@ -482,4 +491,13 @@ def validate_attachments_count(attachments) do
       {:error, dgettext("errors", "Too many attachments")}
     end
   end
+
+  def get_valid_language(language) when is_binary(language) do
+    case language |> String.split("_") |> Enum.at(0) do
+      locale when locale in @supported_locales -> locale
+      _ -> nil
+    end
+  end
+
+  def get_valid_language(_), do: nil
 end