From 0e37fddd5abad5db0378c8186513fbba0fbd6586 Mon Sep 17 00:00:00 2001
From: lain <lain@soykaf.club>
Date: Fri, 3 May 2019 19:15:55 +0200
Subject: [PATCH] Search: Add fts index on objects table.

---
 CHANGELOG.md                                  |  1 +
 lib/mix/tasks/benchmark.ex                    | 25 +++++++++++++++++++
 mix.exs                                       |  3 ++-
 mix.lock                                      |  2 ++
 ...0190501125843_add_fts_index_to_objects.exs |  8 ++++++
 5 files changed, 38 insertions(+), 1 deletion(-)
 create mode 100644 lib/mix/tasks/benchmark.ex
 create mode 100644 priv/repo/migrations/20190501125843_add_fts_index_to_objects.exs

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 67b9649e1..038a001de 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -61,6 +61,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 - Mastodon API: Added support max_id & since_id for bookmark timeline endpoints.
 
 ### Fixed
+- Added an FTS index on objects. Running `vacuum analyze` and setting a larger `work_mem` is recommended.
 - Followers counter not being updated when a follower is blocked
 - Deactivated users being able to request an access token
 - Limit on request body in rich media/relme parsers being ignored resulting in a possible memory leak
diff --git a/lib/mix/tasks/benchmark.ex b/lib/mix/tasks/benchmark.ex
new file mode 100644
index 000000000..0fbb4dbb1
--- /dev/null
+++ b/lib/mix/tasks/benchmark.ex
@@ -0,0 +1,25 @@
+defmodule Mix.Tasks.Pleroma.Benchmark do
+  use Mix.Task
+  alias Mix.Tasks.Pleroma.Common
+
+  def run(["search"]) do
+    Common.start_pleroma()
+
+    Benchee.run(%{
+      "search" => fn ->
+        Pleroma.Web.MastodonAPI.MastodonAPIController.status_search(nil, "cofe")
+      end
+    })
+  end
+
+  def run(["tag"]) do
+    Common.start_pleroma()
+
+    Benchee.run(%{
+      "tag" => fn ->
+        %{"type" => "Create", "tag" => "cofe"}
+        |> Pleroma.Web.ActivityPub.ActivityPub.fetch_public_activities()
+      end
+    })
+  end
+end
diff --git a/mix.exs b/mix.exs
index 9ded9931c..3b368e57e 100644
--- a/mix.exs
+++ b/mix.exs
@@ -111,7 +111,8 @@ defp deps do
       {:prometheus_ecto, "~> 1.4"},
       {:prometheus_process_collector, "~> 1.4"},
       {:recon, github: "ferd/recon", tag: "2.4.0"},
-      {:quack, "~> 0.1.1"}
+      {:quack, "~> 0.1.1"},
+      {:benchee, "~> 1.0", only: :dev}
     ] ++ oauth_deps
   end
 
diff --git a/mix.lock b/mix.lock
index 08221eadc..e97f4ec38 100644
--- a/mix.lock
+++ b/mix.lock
@@ -3,6 +3,7 @@
   "auto_linker": {:git, "https://git.pleroma.social/pleroma/auto_linker.git", "c00c4e75b35367fa42c95ffd9b8c455bf9995829", [ref: "c00c4e75b35367fa42c95ffd9b8c455bf9995829"]},
   "base64url": {:hex, :base64url, "0.0.1", "36a90125f5948e3afd7be97662a1504b934dd5dac78451ca6e9abf85a10286be", [:rebar], [], "hexpm"},
   "bbcode": {:hex, :bbcode, "0.1.0", "400e618b640b635261611d7fb7f79d104917fc5b084aae371ab6b08477cb035b", [:mix], [{:nimble_parsec, "~> 0.5", [hex: :nimble_parsec, repo: "hexpm", optional: false]}], "hexpm"},
+  "benchee": {:hex, :benchee, "1.0.1", "66b211f9bfd84bd97e6d1beaddf8fc2312aaabe192f776e8931cb0c16f53a521", [:mix], [{:deep_merge, "~> 1.0", [hex: :deep_merge, repo: "hexpm", optional: false]}], "hexpm"},
   "bunt": {:hex, :bunt, "0.2.0", "951c6e801e8b1d2cbe58ebbd3e616a869061ddadcc4863d0a2182541acae9a38", [:mix], [], "hexpm"},
   "cachex": {:hex, :cachex, "3.0.2", "1351caa4e26e29f7d7ec1d29b53d6013f0447630bbf382b4fb5d5bad0209f203", [:mix], [{:eternal, "~> 1.2", [hex: :eternal, repo: "hexpm", optional: false]}, {:unsafe, "~> 1.0", [hex: :unsafe, repo: "hexpm", optional: false]}], "hexpm"},
   "calendar": {:hex, :calendar, "0.17.4", "22c5e8d98a4db9494396e5727108dffb820ee0d18fed4b0aa8ab76e4f5bc32f1", [:mix], [{:tzdata, "~> 0.5.8 or ~> 0.1.201603", [hex: :tzdata, repo: "hexpm", optional: false]}], "hexpm"},
@@ -17,6 +18,7 @@
   "crypt": {:git, "https://github.com/msantos/crypt", "1f2b58927ab57e72910191a7ebaeff984382a1d3", [ref: "1f2b58927ab57e72910191a7ebaeff984382a1d3"]},
   "db_connection": {:hex, :db_connection, "2.0.5", "ddb2ba6761a08b2bb9ca0e7d260e8f4dd39067426d835c24491a321b7f92a4da", [:mix], [{:connection, "~> 1.0.2", [hex: :connection, repo: "hexpm", optional: false]}], "hexpm"},
   "decimal": {:hex, :decimal, "1.7.0", "30d6b52c88541f9a66637359ddf85016df9eb266170d53105f02e4a67e00c5aa", [:mix], [], "hexpm"},
+  "deep_merge": {:hex, :deep_merge, "1.0.0", "b4aa1a0d1acac393bdf38b2291af38cb1d4a52806cf7a4906f718e1feb5ee961", [:mix], [], "hexpm"},
   "earmark": {:hex, :earmark, "1.3.2", "b840562ea3d67795ffbb5bd88940b1bed0ed9fa32834915125ea7d02e35888a5", [:mix], [], "hexpm"},
   "ecto": {:hex, :ecto, "3.0.7", "44dda84ac6b17bbbdeb8ac5dfef08b7da253b37a453c34ab1a98de7f7e5fec7f", [:mix], [{:decimal, "~> 1.6", [hex: :decimal, repo: "hexpm", optional: false]}, {:jason, "~> 1.0", [hex: :jason, repo: "hexpm", optional: true]}, {:poison, "~> 2.2 or ~> 3.0", [hex: :poison, repo: "hexpm", optional: true]}], "hexpm"},
   "ecto_sql": {:hex, :ecto_sql, "3.0.5", "7e44172b4f7aca4469f38d7f6a3da394dbf43a1bcf0ca975e958cb957becd74e", [:mix], [{:db_connection, "~> 2.0", [hex: :db_connection, repo: "hexpm", optional: false]}, {:ecto, "~> 3.0.6", [hex: :ecto, repo: "hexpm", optional: false]}, {:mariaex, "~> 0.9.1", [hex: :mariaex, repo: "hexpm", optional: true]}, {:postgrex, "~> 0.14.0", [hex: :postgrex, repo: "hexpm", optional: true]}, {:telemetry, "~> 0.3.0", [hex: :telemetry, repo: "hexpm", optional: false]}], "hexpm"},
diff --git a/priv/repo/migrations/20190501125843_add_fts_index_to_objects.exs b/priv/repo/migrations/20190501125843_add_fts_index_to_objects.exs
new file mode 100644
index 000000000..9b274695e
--- /dev/null
+++ b/priv/repo/migrations/20190501125843_add_fts_index_to_objects.exs
@@ -0,0 +1,8 @@
+defmodule Pleroma.Repo.Migrations.AddFTSIndexToObjects do
+  use Ecto.Migration
+
+  def change do
+    drop_if_exists index(:activities, ["(to_tsvector('english', data->'object'->>'content'))"], using: :gin, name: :activities_fts)
+    create index(:objects, ["(to_tsvector('english', data->>'content'))"], using: :gin, name: :objects_fts)
+  end
+end