[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, 24 insertions, 0 deletions

diff --git a/internal/db/bundb/media.go b/internal/db/bundb/media.go
index f24ea0407..4da80e757 100644
--- a/internal/db/bundb/media.go
+++ b/internal/db/bundb/media.go
@@ -20,6 +20,7 @@ package bundb
 
 import (
 	"context"
+	"time"
 
 	"github.com/superseriousbusiness/gotosocial/internal/db"
 	"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
@@ -48,3 +49,26 @@ func (m *mediaDB) GetAttachmentByID(ctx context.Context, id string) (*gtsmodel.M
 	}
 	return attachment, nil
 }
+
+func (m *mediaDB) GetRemoteOlderThan(ctx context.Context, olderThan time.Time, limit int) ([]*gtsmodel.MediaAttachment, db.Error) {
+	attachments := []*gtsmodel.MediaAttachment{}
+
+	q := m.conn.
+		NewSelect().
+		Model(&attachments).
+		Where("media_attachment.cached = true").
+		Where("media_attachment.avatar = false").
+		Where("media_attachment.header = false").
+		Where("media_attachment.created_at < ?", olderThan).
+		WhereGroup(" AND ", whereNotEmptyAndNotNull("media_attachment.remote_url")).
+		Order("media_attachment.created_at DESC")
+
+	if limit != 0 {
+		q = q.Limit(limit)
+	}
+
+	if err := q.Scan(ctx); err != nil {
+		return nil, m.conn.ProcessError(err)
+	}
+	return attachments, nil
+}