Redo indexing mechanism (#16)

* Bumped up the line length because I fear no man

* Refactored indexing

Previously, indexing worked by collecting the video IDs of only videos
that matched indexing criteria. This new model instead stores ALL videos
for a given source, but will only _download_ videos that meet that criteria.
This lets us backfill without indexing, makes it easier to add in other
backends, lets us download one-off videos for a source that don't quite
meet criteria, you name it.

* Updated media finders to respect format filters; Added credo file

test/pinchflat/tasks/source_tasks_test.exs

@@ -1,6 +1,7 @@
 defmodule Pinchflat.Tasks.SourceTasksTest do
   use Pinchflat.DataCase
 
+  import Mox
   import Pinchflat.TasksFixtures
   import Pinchflat.MediaFixtures
   import Pinchflat.MediaSourceFixtures
@@ -8,9 +9,12 @@ defmodule Pinchflat.Tasks.SourceTasksTest do
   alias Pinchflat.Tasks
   alias Pinchflat.Tasks.Task
   alias Pinchflat.Tasks.SourceTasks
+  alias Pinchflat.Media.MediaItem
   alias Pinchflat.Workers.MediaIndexingWorker
   alias Pinchflat.Workers.VideoDownloadWorker
 
+  setup :verify_on_exit!
+
   describe "kickoff_indexing_task/1" do
     test "it does not schedule a job if the interval is <= 0" do
       source = source_fixture(index_frequency_minutes: -1)
@@ -46,6 +50,61 @@ defmodule Pinchflat.Tasks.SourceTasksTest do
     end
   end
 
+  describe "index_media_items/1" do
+    setup do
+      stub(YtDlpRunnerMock, :run, fn _url, _opts, _ot -> {:ok, source_attributes_return_fixture()} end)
+
+      {:ok, [source: source_fixture()]}
+    end
+
+    test "it creates a media_item record for each media ID returned", %{source: source} do
+      assert media_items = SourceTasks.index_media_items(source)
+
+      assert Enum.count(media_items) == 3
+      assert ["video1", "video2", "video3"] == Enum.map(media_items, & &1.media_id)
+      assert ["Video 1", "Video 2", "Video 3"] == Enum.map(media_items, & &1.title)
+      assert Enum.all?(media_items, fn mi -> mi.original_url end)
+      assert Enum.all?(media_items, fn %MediaItem{} -> true end)
+    end
+
+    test "it attaches all media_items to the given source", %{source: source} do
+      source_id = source.id
+      assert media_items = SourceTasks.index_media_items(source)
+
+      assert Enum.count(media_items) == 3
+      assert Enum.all?(media_items, fn %MediaItem{source_id: ^source_id} -> true end)
+    end
+
+    test "it won't duplicate media_items based on media_id and source", %{source: source} do
+      _first_run = SourceTasks.index_media_items(source)
+      _duplicate_run = SourceTasks.index_media_items(source)
+
+      media_items = Repo.preload(source, :media_items).media_items
+      assert Enum.count(media_items) == 3
+    end
+
+    test "it can duplicate media_ids for different sources", %{source: source} do
+      other_source = source_fixture()
+
+      media_items = SourceTasks.index_media_items(source)
+      media_items_other_source = SourceTasks.index_media_items(other_source)
+
+      assert Enum.count(media_items) == 3
+      assert Enum.count(media_items_other_source) == 3
+
+      assert Enum.map(media_items, & &1.media_id) ==
+               Enum.map(media_items_other_source, & &1.media_id)
+    end
+
+    test "it returns a list of media_items or changesets", %{source: source} do
+      first_run = SourceTasks.index_media_items(source)
+      duplicate_run = SourceTasks.index_media_items(source)
+
+      assert Enum.all?(first_run, fn %MediaItem{} -> true end)
+      assert Enum.all?(duplicate_run, fn %Ecto.Changeset{} -> true end)
+    end
+  end
+
   describe "enqueue_pending_media_downloads/1" do
     test "it enqueues a job for each pending media item" do
       source = source_fixture()