[feature] Clean up/uncache remote media (#407)

* Add whereNotEmptyAndNotNull

* Add GetRemoteOlderThanDays

* Add GetRemoteOlderThanDays

* Add PruneRemote to Manager interface

* Start implementing PruneRemote

* add new attachment + status to tests

* fix up and test GetRemoteOlderThan

* fix bad import

* PruneRemote: return number pruned

* add Cached column to mediaattachment

* update + test pruneRemote

* update mediaTest

* use Cached column

* upstep bun to latest version

* embed structs in mediaAttachment

* migrate mediaAttachment to new format

* don't default cached to true

* select only remote media

* update db dependencies

* step bun back to last working version

* update pruneRemote to use Cached field

* fix storage path of test attachments

* add recache logic to manager

* fix trimmed aspect ratio

* test prune and recache

* return errwithcode

* tidy up different paths for emoji vs attachment

* fix incorrect thumbnail type being stored

* expose TransportController to media processor

* implement tee-ing recached content

* add thoughts of dog to test fedi attachments

* test get remote files

* add comment on PruneRemote

* add postData cleanup to recache

* test thumbnail fetching

* add incredible diagram

* go mod tidy

* buffer pipes for recache streaming

* test for client stops reading after 1kb

* add media-remote-cache-days to config

* add cron package

* wrap logrus so it's available to cron

* start and stop cron jobs gracefully

1 files changed, 111 insertions, 0 deletions

diff --git a/internal/media/pruneremote_test.go b/internal/media/pruneremote_test.go
new file mode 100644
index 000000000..f9d71cae2
--- /dev/null
+++ b/internal/media/pruneremote_test.go
@@ -0,0 +1,111 @@
+/*
+   GoToSocial
+   Copyright (C) 2021-2022 GoToSocial Authors admin@gotosocial.org
+
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU Affero General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU Affero General Public License for more details.
+
+   You should have received a copy of the GNU Affero General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+package media_test
+
+import (
+	"bytes"
+	"context"
+	"io"
+	"os"
+	"testing"
+
+	"codeberg.org/gruf/go-store/storage"
+	"github.com/stretchr/testify/suite"
+)
+
+type PruneRemoteTestSuite struct {
+	MediaStandardTestSuite
+}
+
+func (suite *PruneRemoteTestSuite) TestPruneRemote() {
+	testAttachment := suite.testAttachments["remote_account_1_status_1_attachment_1"]
+	suite.True(testAttachment.Cached)
+
+	totalPruned, err := suite.manager.PruneRemote(context.Background(), 1)
+	suite.NoError(err)
+	suite.Equal(1, totalPruned)
+
+	prunedAttachment, err := suite.db.GetAttachmentByID(context.Background(), testAttachment.ID)
+	suite.NoError(err)
+
+	// the media should no longer be cached
+	suite.False(prunedAttachment.Cached)
+}
+
+func (suite *PruneRemoteTestSuite) TestPruneRemoteTwice() {
+	totalPruned, err := suite.manager.PruneRemote(context.Background(), 1)
+	suite.NoError(err)
+	suite.Equal(1, totalPruned)
+
+	// final prune should prune nothing, since the first prune already happened
+	totalPrunedAgain, err := suite.manager.PruneRemote(context.Background(), 1)
+	suite.NoError(err)
+	suite.Equal(0, totalPrunedAgain)
+}
+
+func (suite *PruneRemoteTestSuite) TestPruneAndRecache() {
+	ctx := context.Background()
+	testAttachment := suite.testAttachments["remote_account_1_status_1_attachment_1"]
+
+	totalPruned, err := suite.manager.PruneRemote(ctx, 1)
+	suite.NoError(err)
+	suite.Equal(1, totalPruned)
+
+	// media should no longer be stored
+	_, err = suite.storage.Get(testAttachment.File.Path)
+	suite.Error(err)
+	suite.ErrorIs(err, storage.ErrNotFound)
+	_, err = suite.storage.Get(testAttachment.Thumbnail.Path)
+	suite.Error(err)
+	suite.ErrorIs(err, storage.ErrNotFound)
+
+	// now recache the image....
+	data := func(_ context.Context) (io.Reader, int, error) {
+		// load bytes from a test image
+		b, err := os.ReadFile("../../testrig/media/thoughtsofdog-original.jpeg")
+		if err != nil {
+			panic(err)
+		}
+		return bytes.NewBuffer(b), len(b), nil
+	}
+	processingRecache, err := suite.manager.RecacheMedia(ctx, data, nil, testAttachment.ID)
+	suite.NoError(err)
+
+	// synchronously load the recached attachment
+	recachedAttachment, err := processingRecache.LoadAttachment(ctx)
+	suite.NoError(err)
+	suite.NotNil(recachedAttachment)
+
+	// recachedAttachment should be basically the same as the old attachment
+	suite.True(recachedAttachment.Cached)
+	suite.Equal(testAttachment.ID, recachedAttachment.ID)
+	suite.Equal(testAttachment.File.Path, recachedAttachment.File.Path)           // file should be stored in the same place
+	suite.Equal(testAttachment.Thumbnail.Path, recachedAttachment.Thumbnail.Path) // as should the thumbnail
+	suite.EqualValues(testAttachment.FileMeta, recachedAttachment.FileMeta)       // and the filemeta should be the same
+
+	// recached files should be back in storage
+	_, err = suite.storage.Get(recachedAttachment.File.Path)
+	suite.NoError(err)
+	_, err = suite.storage.Get(recachedAttachment.Thumbnail.Path)
+	suite.NoError(err)
+}
+
+func TestPruneRemoteTestSuite(t *testing.T) {
+	suite.Run(t, &PruneRemoteTestSuite{})
+}