From f06a0eab50b9ed3e6d4ed4db714d5632225ff9f0 Mon Sep 17 00:00:00 2001
From: Mark Felder <feld@feld.me>
Date: Wed, 25 Mar 2026 14:47:39 -0700
Subject: [PATCH] Move object_to_search_data/1 to Pleroma.Search

This standardizes this functionality within the Search module so
it doesn't need to be imported by other search backends from Meilisearch

Also integrate its filtering rules into Search.indexable?/1 for consistency
---
 changelog.d/search-indexing.skip            |  0
 lib/mix/tasks/pleroma/search/meilisearch.ex |  2 +-
 lib/pleroma/search.ex                       | 39 +++++++++++++++++++-
 lib/pleroma/search/meilisearch.ex           | 40 ++-------------------
 lib/pleroma/search/qdrant_search.ex         |  4 +--
 5 files changed, 43 insertions(+), 42 deletions(-)
 create mode 100644 changelog.d/search-indexing.skip

diff --git a/changelog.d/search-indexing.skip b/changelog.d/search-indexing.skip
new file mode 100644
index 000000000..e69de29bb
diff --git a/lib/mix/tasks/pleroma/search/meilisearch.ex b/lib/mix/tasks/pleroma/search/meilisearch.ex
index edce9e871..facc38815 100644
--- a/lib/mix/tasks/pleroma/search/meilisearch.ex
+++ b/lib/mix/tasks/pleroma/search/meilisearch.ex
@@ -72,7 +72,7 @@ defmodule Mix.Tasks.Pleroma.Search.Meilisearch do
           query,
           timeout: :infinity
         )
-        |> Stream.map(&Pleroma.Search.Meilisearch.object_to_search_data/1)
+        |> Stream.map(&Pleroma.Search.object_to_search_data/1)
         |> Stream.filter(fn o -> not is_nil(o) end)
         |> Stream.chunk_every(chunk_size)
         |> Stream.transform(0, fn objects, acc ->
diff --git a/lib/pleroma/search.ex b/lib/pleroma/search.ex
index f78495c8d..9cd2768c4 100644
--- a/lib/pleroma/search.ex
+++ b/lib/pleroma/search.ex
@@ -38,6 +38,43 @@ defmodule Pleroma.Search do
     search_module.healthcheck_endpoints()
   end
 
-  defp indexable?(%Activity{data: %{"type" => "Create"}}), do: true
+  def object_to_search_data(%Object{} = object) do
+    data = object.data
+
+    content_str =
+      case data["content"] do
+        [nil | rest] -> to_string(rest)
+        str -> str
+      end
+
+    content =
+      with {:ok, scrubbed} <-
+             FastSanitize.Sanitizer.scrub(content_str, Pleroma.HTML.Scrubber.SearchIndexing),
+           trimmed <- String.trim(scrubbed) do
+        trimmed
+      end
+
+    # Make sure we have a non-empty string
+    if content != "" do
+      {:ok, published, _} = DateTime.from_iso8601(data["published"])
+
+      %{
+        id: object.id,
+        content: content,
+        ap: data["id"],
+        published: published |> DateTime.to_unix()
+      }
+    end
+  end
+
+  defp indexable?(%Activity{
+         data: %{"type" => "Create"},
+         object: %Object{
+           data: %{"content" => content, "published" => published, "type" => "Note"}
+         }
+       })
+       when not is_nil(content) and content not in ["", "."] and not is_nil(published),
+       do: true
+
   defp indexable?(_), do: false
 end
diff --git a/lib/pleroma/search/meilisearch.ex b/lib/pleroma/search/meilisearch.ex
index 4541ef14a..dc10076e1 100644
--- a/lib/pleroma/search/meilisearch.ex
+++ b/lib/pleroma/search/meilisearch.ex
@@ -5,6 +5,7 @@ defmodule Pleroma.Search.Meilisearch do
   alias Pleroma.Activity
   alias Pleroma.Config.Getting, as: Config
   alias Pleroma.Object
+  alias Pleroma.Search
 
   import Pleroma.Search.DatabaseSearch
   import Ecto.Query
@@ -119,46 +120,9 @@ defmodule Pleroma.Search.Meilisearch do
     end
   end
 
-  def object_to_search_data(object) do
-    # Only index public or unlisted Notes
-    if not is_nil(object) and object.data["type"] == "Note" and
-         not is_nil(object.data["content"]) and
-         not is_nil(object.data["published"]) and
-         (Pleroma.Constants.as_public() in object.data["to"] or
-            Pleroma.Constants.as_public() in object.data["cc"]) and
-         object.data["content"] not in ["", "."] do
-      data = object.data
-
-      content_str =
-        case data["content"] do
-          [nil | rest] -> to_string(rest)
-          str -> str
-        end
-
-      content =
-        with {:ok, scrubbed} <-
-               FastSanitize.Sanitizer.scrub(content_str, Pleroma.HTML.Scrubber.SearchIndexing),
-             trimmed <- String.trim(scrubbed) do
-          trimmed
-        end
-
-      # Make sure we have a non-empty string
-      if content != "" do
-        {:ok, published, _} = DateTime.from_iso8601(data["published"])
-
-        %{
-          id: object.id,
-          content: content,
-          ap: data["id"],
-          published: published |> DateTime.to_unix()
-        }
-      end
-    end
-  end
-
   @impl true
   def add_to_index(%Activity{object: %Object{} = object} = activity) do
-    search_data = object_to_search_data(object)
+    search_data = Search.object_to_search_data(object)
 
     result =
       meili_put(
diff --git a/lib/pleroma/search/qdrant_search.ex b/lib/pleroma/search/qdrant_search.ex
index 06f5b1983..4d57cfa88 100644
--- a/lib/pleroma/search/qdrant_search.ex
+++ b/lib/pleroma/search/qdrant_search.ex
@@ -5,11 +5,11 @@ defmodule Pleroma.Search.QdrantSearch do
   alias Pleroma.Activity
   alias Pleroma.Config.Getting, as: Config
   alias Pleroma.Object
+  alias Pleroma.Search
 
   alias __MODULE__.OpenAIClient
   alias __MODULE__.QdrantClient
 
-  import Pleroma.Search.Meilisearch, only: [object_to_search_data: 1]
   import Pleroma.Search.DatabaseSearch, only: [maybe_fetch: 3]
 
   @impl true
@@ -84,7 +84,7 @@ defmodule Pleroma.Search.QdrantSearch do
 
   @impl true
   def add_to_index(%Activity{object: %Object{} = object} = activity) do
-    search_data = object_to_search_data(object)
+    search_data = Search.object_to_search_data(object)
 
     with {:ok, embedding} <- get_embedding(search_data.content),
          {:ok, %{status: 200}} <-