lib/mix/tasks/pleroma/database.ex

@@ -67,7 +67,8 @@ defmodule Mix.Tasks.Pleroma.Database do
       OptionParser.parse(
         args,
         strict: [
-          vacuum: :boolean
+          vacuum: :boolean,
+          keep_threads: :boolean
         ]
       )
 
@@ -77,24 +78,47 @@ defmodule Mix.Tasks.Pleroma.Database do
 
     Logger.info("Pruning objects older than #{deadline} days")
 
-    time_deadline =
-      NaiveDateTime.utc_now()
-      |> NaiveDateTime.add(-(deadline * 86_400))
+    if Keyword.get(options, :keep_threads) do
+      # We delete objects from threads where
+      # 1. the newest post is still old
+      # 2. none of the activities is local
+      # 3. none of the activities is bookmarked
+      delete_keep_threads_statement = """
+      delete
+      from public.objects o
+      where o.data ->> 'context' in (
+      select
+      a.data ->> 'context'
+      from public.activities a
+      left join public.bookmarks b on a.id = b.activity_id
+      group by (a.data ->> 'context'::text)
+      having max(a.updated_at) < now() - interval '#{deadline} day'
+      and not bool_or(a.local)
+      and max(b.id) is null
+      );
+      """
 
-    from(o in Object,
-      where:
-        fragment(
-          "?->'to' \\? ? OR ?->'cc' \\? ?",
-          o.data,
-          ^Pleroma.Constants.as_public(),
-          o.data,
-          ^Pleroma.Constants.as_public()
-        ),
-      where: o.inserted_at < ^time_deadline,
-      where:
-        fragment("split_part(?->>'actor', '/', 3) != ?", o.data, ^Pleroma.Web.Endpoint.host())
-    )
-    |> Repo.delete_all(timeout: :infinity)
+      Repo.query(delete_keep_threads_statement)
+    else
+      time_deadline =
+        NaiveDateTime.utc_now()
+        |> NaiveDateTime.add(-(deadline * 86_400))
+
+      from(o in Object,
+        where:
+          fragment(
+            "?->'to' \\? ? OR ?->'cc' \\? ?",
+            o.data,
+            ^Pleroma.Constants.as_public(),
+            o.data,
+            ^Pleroma.Constants.as_public()
+          ),
+        where: o.inserted_at < ^time_deadline,
+        where:
+          fragment("split_part(?->>'actor', '/', 3) != ?", o.data, ^Pleroma.Web.Endpoint.host())
+      )
+      |> Repo.delete_all(timeout: :infinity)
+    end
 
     prune_hashtags_query = """
     DELETE FROM hashtags AS ht

test/mix/tasks/pleroma/database_test.exs

@@ -68,6 +68,176 @@ defmodule Mix.Tasks.Pleroma.DatabaseTest do
       assert length(Repo.all(Object)) == 1
       refute Object.get_by_id(id)
     end
+
+    test "with the --keep-threads option it still keeps non-old threads even with no local interactions" do
+      remote_user = insert(:user, local: false)
+      remote_user2 = insert(:user, local: false)
+
+      {:ok, remote_post_activity} =
+        CommonAPI.post(remote_user, %{status: "some thing", local: false})
+
+      {:ok, remote_post_reply_activity} =
+        CommonAPI.post(remote_user2, %{
+          status: "some reply",
+          in_reply_to_status_id: remote_post_activity.id
+        })
+
+      remote_post_activity
+      |> Ecto.Changeset.change(%{local: false})
+      |> Repo.update!()
+
+      remote_post_reply_activity
+      |> Ecto.Changeset.change(%{local: false})
+      |> Repo.update!()
+
+      assert length(Repo.all(Object)) == 2
+
+      Mix.Tasks.Pleroma.Database.run(["prune_objects", "--keep-threads"])
+
+      assert length(Repo.all(Object)) == 2
+    end
+
+    test "with the --keep-threads option it deletes old threads with no local interaction" do
+      deadline = Pleroma.Config.get([:instance, :remote_post_retention_days]) + 1
+
+      old_insert_date =
+        Timex.now()
+        |> Timex.shift(days: -deadline)
+        |> Timex.to_naive_datetime()
+        |> NaiveDateTime.truncate(:second)
+
+      remote_user = insert(:user, local: false)
+      remote_user2 = insert(:user, local: false)
+
+      {:ok, old_remote_post_activity} =
+        CommonAPI.post(remote_user, %{status: "some thing", local: false})
+
+      old_remote_post_activity
+      |> Ecto.Changeset.change(%{local: false, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      {:ok, old_remote_post_reply_activity} =
+        CommonAPI.post(remote_user2, %{
+          status: "some reply",
+          in_reply_to_status_id: old_remote_post_activity.id
+        })
+
+      old_remote_post_reply_activity
+      |> Ecto.Changeset.change(%{local: false, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      {:ok, old_favourite_activity} =
+        CommonAPI.favorite(remote_user2, old_remote_post_activity.id)
+
+      old_favourite_activity
+      |> Ecto.Changeset.change(%{local: false, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      {:ok, old_repeat_activity} = CommonAPI.repeat(old_remote_post_activity.id, remote_user2)
+
+      old_repeat_activity
+      |> Ecto.Changeset.change(%{local: false, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      assert length(Repo.all(Object)) == 2
+
+      Mix.Tasks.Pleroma.Database.run(["prune_objects", "--keep-threads"])
+
+      assert Repo.all(Object) == []
+    end
+
+    test "with the --keep-threads option it keeps old threads with local interaction" do
+      deadline = Pleroma.Config.get([:instance, :remote_post_retention_days]) + 1
+
+      old_insert_date =
+        Timex.now()
+        |> Timex.shift(days: -deadline)
+        |> Timex.to_naive_datetime()
+        |> NaiveDateTime.truncate(:second)
+
+      remote_user = insert(:user, local: false)
+      local_user = insert(:user, local: true)
+
+      # local reply
+      {:ok, old_remote_post1_activity} =
+        CommonAPI.post(remote_user, %{status: "some thing", local: false})
+
+      old_remote_post1_activity
+      |> Ecto.Changeset.change(%{local: false, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      {:ok, old_local_post2_reply_activity} =
+        CommonAPI.post(local_user, %{
+          status: "some reply",
+          in_reply_to_status_id: old_remote_post1_activity.id
+        })
+
+      old_local_post2_reply_activity
+      |> Ecto.Changeset.change(%{local: true, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      # local Like
+      {:ok, old_remote_post3_activity} =
+        CommonAPI.post(remote_user, %{status: "some thing", local: false})
+
+      old_remote_post3_activity
+      |> Ecto.Changeset.change(%{local: false, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      {:ok, old_favourite_activity} = CommonAPI.favorite(local_user, old_remote_post3_activity.id)
+
+      old_favourite_activity
+      |> Ecto.Changeset.change(%{local: true, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      # local Announce
+      {:ok, old_remote_post4_activity} =
+        CommonAPI.post(remote_user, %{status: "some thing", local: false})
+
+      old_remote_post4_activity
+      |> Ecto.Changeset.change(%{local: false, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      {:ok, old_repeat_activity} = CommonAPI.repeat(old_remote_post4_activity.id, local_user)
+
+      old_repeat_activity
+      |> Ecto.Changeset.change(%{local: true, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      assert length(Repo.all(Object)) == 4
+
+      Mix.Tasks.Pleroma.Database.run(["prune_objects", "--keep-threads"])
+
+      assert length(Repo.all(Object)) == 4
+    end
+
+    test "with the --keep-threads option it keeps old threads with bookmarked posts" do
+      deadline = Pleroma.Config.get([:instance, :remote_post_retention_days]) + 1
+
+      old_insert_date =
+        Timex.now()
+        |> Timex.shift(days: -deadline)
+        |> Timex.to_naive_datetime()
+        |> NaiveDateTime.truncate(:second)
+
+      remote_user = insert(:user, local: false)
+      local_user = insert(:user, local: true)
+
+      {:ok, old_remote_post_activity} =
+        CommonAPI.post(remote_user, %{status: "some thing", local: false})
+
+      old_remote_post_activity
+      |> Ecto.Changeset.change(%{local: false, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      Pleroma.Bookmark.create(local_user.id, old_remote_post_activity.id)
+
+      assert length(Repo.all(Object)) == 1
+
+      Mix.Tasks.Pleroma.Database.run(["prune_objects", "--keep-threads"])
+
+      assert length(Repo.all(Object)) == 1
+    end
   end
 
   describe "running update_users_following_followers_counts" do