Add --keep-non-public option

The prune_objects task already did this by default, but is undocumented.
Now we require an explicit parameter for it.
The parameter also works in combination with --keep-threads

Docs still needs to happen

lib/mix/tasks/pleroma/database.ex

@@ -68,7 +68,8 @@ def run(["prune_objects" | args]) do
         args,
         strict: [
           vacuum: :boolean,
-          keep_threads: :boolean
+          keep_threads: :boolean,
+          keep_non_public: :boolean
         ]
       )
 
@@ -77,41 +78,79 @@ def run(["prune_objects" | args]) do
     deadline = Pleroma.Config.get([:instance, :remote_post_retention_days])
     time_deadline = NaiveDateTime.utc_now() |> NaiveDateTime.add(-(deadline * 86_400))
 
-    if Keyword.get(options, :keep_threads) do
+    log_message = "Pruning objects older than #{deadline} days"
-      Logger.info(
-        "Pruning objects older than #{deadline} days without local interaction, keeping threads intact"
-      )
 
+    log_message =
+      if Keyword.get(options, :keep_non_public) do
+        log_message <> ", keeping non public posts"
+      else
+        log_message
+      end
+
+    log_message =
+      if Keyword.get(options, :keep_threads) do
+        log_message <> ", keeping threads intact"
+      else
+        log_message
+      end
+
+    Logger.info(log_message)
+
+    if Keyword.get(options, :keep_threads) do
       # We want to 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
+      # 4. optionally none of the posts is non-public
       deletable_context =
-        Pleroma.Activity
+        if Keyword.get(options, :keep_non_public) do
-        |> join(:left, [a], b in Pleroma.Bookmark, on: a.id == b.activity_id)
+          Pleroma.Activity
-        |> group_by([a], fragment("? ->> 'context'::text", a.data))
+          |> join(:left, [a], b in Pleroma.Bookmark, on: a.id == b.activity_id)
+          |> group_by([a], fragment("? ->> 'context'::text", a.data))
+          |> having(
+            [a],
+            not fragment(
+              # Posts (checked on Create Activity) is non-public
+              "bool_or((not(?->'to' \\? ? OR ?->'cc' \\? ?)) and ? ->> 'type' = 'Create')",
+              a.data,
+              ^Pleroma.Constants.as_public(),
+              a.data,
+              ^Pleroma.Constants.as_public(),
+              a.data
+            )
+          )
+        else
+          Pleroma.Activity
+          |> join(:left, [a], b in Pleroma.Bookmark, on: a.id == b.activity_id)
+          |> group_by([a], fragment("? ->> 'context'::text", a.data))
+        end
         |> having([a], max(a.updated_at) < ^time_deadline)
         |> having([a], not fragment("bool_or(?)", a.local))
-        |> having([a, b], fragment("max(?::text) is null", b.id))
+        |> having([_, b], fragment("max(?::text) is null", b.id))
         |> select([a], fragment("? ->> 'context'::text", a.data))
 
       Pleroma.Object
       |> where([o], fragment("? ->> 'context'::text", o.data) in subquery(deletable_context))
     else
-      Logger.info("Pruning objects older than #{deadline} days")
+      if Keyword.get(options, :keep_non_public) do
-
+        Pleroma.Object
-      from(o in Object,
+        |> where(
-        where:
+          [o],
           fragment(
             "?->'to' \\? ? OR ?->'cc' \\? ?",
             o.data,
             ^Pleroma.Constants.as_public(),
             o.data,
             ^Pleroma.Constants.as_public()
-          ),
+          )
-        where: o.inserted_at < ^time_deadline,
+        )
-        where:
+      else
-          fragment("split_part(?->>'actor', '/', 3) != ?", o.data, ^Pleroma.Web.Endpoint.host())
+        Pleroma.Object
+      end
+      |> where([o], o.updated_at < ^time_deadline)
+      |> where(
+        [o],
+        fragment("split_part(?->>'actor', '/', 3) != ?", o.data, ^Pleroma.Web.Endpoint.host())
       )
     end
     |> Repo.delete_all(timeout: :infinity)

test/mix/tasks/pleroma/database_test.exs

@@ -46,7 +46,6 @@ test "it replaces objects with references" do
 
   describe "prune_objects" do
     test "it prunes old objects from the database" do
-      insert(:note)
       deadline = Pleroma.Config.get([:instance, :remote_post_retention_days]) + 1
 
       date =
@@ -55,18 +54,134 @@ test "it prunes old objects from the database" do
         |> Timex.to_naive_datetime()
         |> NaiveDateTime.truncate(:second)
 
-      %{id: id} =
+      insert(:note)
+
+      %{id: note_remote_public_id} =
         :note
         |> insert()
-        |> Ecto.Changeset.change(%{inserted_at: date})
+        |> Ecto.Changeset.change(%{updated_at: date})
         |> Repo.update!()
 
-      assert length(Repo.all(Object)) == 2
+      note_remote_non_public =
+        %{id: note_remote_non_public_id, data: note_remote_non_public_data} =
+        :note
+        |> insert()
+
+      note_remote_non_public
+      |> Ecto.Changeset.change(%{
+        updated_at: date,
+        data: note_remote_non_public_data |> update_in(["to"], fn _ -> [] end)
+      })
+      |> Repo.update!()
+
+      assert length(Repo.all(Object)) == 3
 
       Mix.Tasks.Pleroma.Database.run(["prune_objects"])
 
       assert length(Repo.all(Object)) == 1
-      refute Object.get_by_id(id)
+      refute Object.get_by_id(note_remote_public_id)
+      refute Object.get_by_id(note_remote_non_public_id)
+    end
+
+    test "with the --keep-non-public option it still keeps non-public posts even if they are not local" do
+      deadline = Pleroma.Config.get([:instance, :remote_post_retention_days]) + 1
+
+      date =
+        Timex.now()
+        |> Timex.shift(days: -deadline)
+        |> Timex.to_naive_datetime()
+        |> NaiveDateTime.truncate(:second)
+
+      insert(:note)
+
+      %{id: note_remote_id} =
+        :note
+        |> insert()
+        |> Ecto.Changeset.change(%{updated_at: date})
+        |> Repo.update!()
+
+      note_remote_non_public =
+        %{data: note_remote_non_public_data} =
+        :note
+        |> insert()
+
+      note_remote_non_public
+      |> Ecto.Changeset.change(%{
+        updated_at: date,
+        data: note_remote_non_public_data |> update_in(["to"], fn _ -> [] end)
+      })
+      |> Repo.update!()
+
+      assert length(Repo.all(Object)) == 3
+
+      Mix.Tasks.Pleroma.Database.run(["prune_objects", "--keep-non-public"])
+
+      assert length(Repo.all(Object)) == 2
+      refute Object.get_by_id(note_remote_id)
+    end
+
+    test "with the --keep-threads and --keep-non-public option it keeps old threads with non-public replies even if the interaction is not local" do
+      # For non-public we only check Create Activities because only these are relevant for threads
+      # Flags are always non-public, Announces from relays can be non-public...
+      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_user1 = insert(:user, local: false)
+      remote_user2 = insert(:user, local: false)
+
+      # Old remote non-public reply (should be kept)
+      {:ok, old_remote_post1_activity} =
+        CommonAPI.post(remote_user1, %{status: "some thing", local: false})
+
+      old_remote_post1_activity
+      |> Ecto.Changeset.change(%{local: false, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      {:ok, old_remote_non_public_reply_activity} =
+        CommonAPI.post(remote_user2, %{
+          status: "some reply",
+          in_reply_to_status_id: old_remote_post1_activity.id
+        })
+
+      old_remote_non_public_reply_activity
+      |> Ecto.Changeset.change(%{
+        local: false,
+        updated_at: old_insert_date,
+        data: old_remote_non_public_reply_activity.data |> update_in(["to"], fn _ -> [] end)
+      })
+      |> Repo.update!()
+
+      # Old remote non-public Announce (should be removed)
+      {:ok, old_remote_post2_activity = %{data: %{"object" => old_remote_post2_id}}} =
+        CommonAPI.post(remote_user1, %{status: "some thing", local: false})
+
+      old_remote_post2_activity
+      |> Ecto.Changeset.change(%{local: false, updated_at: old_insert_date})
+      |> Repo.update!()
+
+      {:ok, old_remote_non_public_repeat_activity} =
+        CommonAPI.repeat(old_remote_post2_activity.id, remote_user2)
+
+      old_remote_non_public_repeat_activity
+      |> Ecto.Changeset.change(%{
+        local: false,
+        updated_at: old_insert_date,
+        data: old_remote_non_public_repeat_activity.data |> update_in(["to"], fn _ -> [] end)
+      })
+      |> Repo.update!()
+
+      assert length(Repo.all(Object)) == 3
+
+      Mix.Tasks.Pleroma.Database.run(["prune_objects", "--keep-threads", "--keep-non-public"])
+
+      Repo.all(Pleroma.Activity)
+      assert length(Repo.all(Object)) == 2
+      refute Object.get_by_ap_id(old_remote_post2_id)
     end
 
     test "with the --keep-threads option it still keeps non-old threads even with no local interactions" do
@@ -143,7 +258,7 @@ test "with the --keep-threads option it deletes old threads with no local intera
 
       Mix.Tasks.Pleroma.Database.run(["prune_objects", "--keep-threads"])
 
-      assert Repo.all(Object) == []
+      assert length(Repo.all(Object)) == 0
     end
 
     test "with the --keep-threads option it keeps old threads with local interaction" do