Implement suggestions from the Meilisearch MR

[akkoma] / lib / mix / tasks / pleroma / search / meilisearch.ex

diff --git a/lib/mix/tasks/pleroma/search/meilisearch.ex b/lib/mix/tasks/pleroma/search/meilisearch.ex
index 2a64385289922cf25645135f5be6b433054d761a..6730a99a90eb0a5da084d9765c90ffcd3281fefd 100644 (file)
--- a/lib/mix/tasks/pleroma/search/meilisearch.ex
+++ b/lib/mix/tasks/pleroma/search/meilisearch.ex
@@ -3,78 +3,128 @@
 # SPDX-License-Identifier: AGPL-3.0-only
 
 defmodule Mix.Tasks.Pleroma.Search.Meilisearch do
-  require Logger
   require Pleroma.Constants
 
   import Mix.Pleroma
   import Ecto.Query
 
+  import Pleroma.Search.Meilisearch,
+    only: [meili_post: 2, meili_put: 2, meili_get: 1, meili_delete!: 1]
+
   def run(["index"]) do
     start_pleroma()
 
-    endpoint = Pleroma.Config.get([Pleroma.Search.Meilisearch, :url])
-
     {:ok, _} =
-      Pleroma.HTTP.post(
-        "#{endpoint}/indexes/objects/settings/ranking-rules",
-        Jason.encode!([
-          "desc(id)",
-          "typo",
+      meili_post(
+        "/indexes/objects/settings/ranking-rules",
+        [
+          "desc(published)",
           "words",
+          "exactness",
           "proximity",
-          "attribute",
           "wordsPosition",
-          "exactness"
-        ])
+          "typo",
+          "attribute"
+        ]
+      )
+
+    {:ok, _} =
+      meili_post(
+        "/indexes/objects/settings/searchable-attributes",
+        [
+          "content"
+        ]
       )
 
-    chunk_size = 100_000
+    IO.puts("Created indices. Starting to insert posts.")
+
+    chunk_size = 10_000
 
     Pleroma.Repo.transaction(
       fn ->
-        Pleroma.Repo.stream(
+        query =
           from(Pleroma.Object,
-            # Only index public posts which are notes and have some text
+            # Only index public and unlisted posts which are notes and have some text
             where:
               fragment("data->>'type' = 'Note'") and
-                fragment("LENGTH(data->>'source') > 0") and
-                fragment("data->'to' \\? ?", ^Pleroma.Constants.as_public()),
-            order_by: fragment("data->'published' DESC")
-          ),
+                (fragment("data->'to' \\? ?", ^Pleroma.Constants.as_public()) or
+                   fragment("data->'cc' \\? ?", ^Pleroma.Constants.as_public())),
+            order_by: [desc: fragment("data->'published'")]
+          )
+
+        count = query |> Pleroma.Repo.aggregate(:count, :data)
+        IO.puts("Entries to index: #{count}")
+
+        Pleroma.Repo.stream(
+          query,
           timeout: :infinity
         )
+        |> Stream.map(&Pleroma.Search.Meilisearch.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 ->
           new_acc = acc + Enum.count(objects)
 
-          IO.puts("Indexed #{new_acc} entries")
+          # Reset to the beginning of the line and rewrite it
+          IO.write("\r")
+          IO.write("Indexed #{new_acc} entries")
 
           {[objects], new_acc}
         end)
-        |> Stream.map(fn objects ->
-          Enum.map(objects, fn object ->
-            data = object.data
-            %{id: object.id, source: data["source"], ap: data["id"]}
-          end)
-        end)
         |> Stream.each(fn objects ->
-          {:ok, _} =
-            Pleroma.HTTP.post(
-              "#{endpoint}/indexes/objects/documents",
-              Jason.encode!(objects)
+          result =
+            meili_put(
+              "/indexes/objects/documents",
+              objects
             )
+
+          with {:ok, res} <- result do
+            if not Map.has_key?(res, "updateId") do
+              IO.puts("\nFailed to index: #{inspect(result)}")
+            end
+          else
+            e -> IO.puts("\nFailed to index due to network error: #{inspect(e)}")
+          end
         end)
         |> Stream.run()
       end,
       timeout: :infinity
     )
+
+    IO.write("\n")
   end
 
   def run(["clear"]) do
     start_pleroma()
 
+    meili_delete!("/indexes/objects/documents")
+  end
+
+  def run(["show-private-key", master_key]) do
+    start_pleroma()
+
     endpoint = Pleroma.Config.get([Pleroma.Search.Meilisearch, :url])
 
-    {:ok, _} = Pleroma.HTTP.request(:delete, "#{endpoint}/indexes/objects/documents", "", [], [])
+    {:ok, result} =
+      Pleroma.HTTP.get(
+        Path.join(endpoint, "/keys"),
+        [{"X-Meili-API-Key", master_key}]
+      )
+
+    decoded = Jason.decode!(result.body)
+
+    if decoded["private"] do
+      IO.puts(decoded["private"])
+    else
+      IO.puts("Error fetching the key, check the master key is correct: #{inspect(decoded)}")
+    end
+  end
+
+  def run(["stats"]) do
+    start_pleroma()
+
+    {:ok, result} = meili_get("/indexes/objects/stats")
+    IO.puts("Number of entries: #{result["numberOfDocuments"]}")
+    IO.puts("Indexing? #{result["isIndexing"]}")
   end
 end