[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

Author: tsmethurst

README.md

@@ -197,6 +197,7 @@ The following libraries and frameworks are used by GoToSocial, with gratitude 
 - [nfnt/resize](https://github.com/nfnt/resize); convenient image resizing. [ISC License](https://spdx.org/licenses/ISC.html).
 - [oklog/ulid](https://github.com/oklog/ulid); sequential, database-friendly ID generation. [Apache-2.0 License](https://spdx.org/licenses/Apache-2.0.html).
 - [ReneKroon/ttlcache](https://github.com/ReneKroon/ttlcache); in-memory caching. [MIT License](https://spdx.org/licenses/MIT.html).
+- [robfig/cron](https://github.com/robfig/cron); cron job scheduling. [MIT License](https://spdx.org/licenses/MIT.html).
 - [russross/blackfriday](https://github.com/russross/blackfriday); markdown parsing for statuses. [Simplified BSD License](https://spdx.org/licenses/BSD-2-Clause.html).
 - [sirupsen/logrus](https://github.com/sirupsen/logrus); logging. [MIT License](https://spdx.org/licenses/MIT.html).
 - [spf13/cobra](https://github.com/spf13/cobra); command-line tooling. [Apache-2.0 License](https://spdx.org/licenses/Apache-2.0.html).

cmd/gotosocial/flag/server.go

@@ -63,6 +63,7 @@ func Media(cmd *cobra.Command, values config.Values) {
 	cmd.Flags().Int(config.Keys.MediaVideoMaxSize, values.MediaVideoMaxSize, usage.MediaVideoMaxSize)
 	cmd.Flags().Int(config.Keys.MediaDescriptionMinChars, values.MediaDescriptionMinChars, usage.MediaDescriptionMinChars)
 	cmd.Flags().Int(config.Keys.MediaDescriptionMaxChars, values.MediaDescriptionMaxChars, usage.MediaDescriptionMaxChars)
+	cmd.Flags().Int(config.Keys.MediaRemoteCacheDays, values.MediaRemoteCacheDays, usage.MediaRemoteCacheDays)
 }
 
 // Storage attaches flags pertaining to storage config.

cmd/gotosocial/flag/usage.go

@@ -47,6 +47,7 @@ var usage = config.KeyNames{
 	MediaVideoMaxSize:          "Max size of accepted videos in bytes",
 	MediaDescriptionMinChars:   "Min required chars for an image description",
 	MediaDescriptionMaxChars:   "Max permitted chars for an image description",
+	MediaRemoteCacheDays:       "Number of days to locally cache media from remote instances. If set to 0, remote media will be kept indefinitely.",
 	StorageBackend:             "Storage backend to use for media attachments",
 	StorageLocalBasePath:       "Full path to an already-created directory where gts should store/retrieve media files. Subfolders will be created within this dir.",
 	StatusesMaxChars:           "Max permitted characters for posted statuses",

docs/configuration/media.md

@@ -28,4 +28,15 @@ media-description-min-chars: 0
 # Examples: [500, 1000, 1500]
 # Default: 500
 media-description-max-chars: 500
+
+# Int. Number of days to cache media from remote instances before they are removed from the cache.
+# A job will run every day at midnight to clean up any remote media older than the given amount of days.
+#
+# When remote media is removed from the cache, it is deleted from storage but the database entries for the media
+# are kept so that it can be fetched again if requested by a user.
+#
+# If this is set to 0, then media from remote instances will be cached indefinitely.
+# Examples: [30, 60, 7, 0]
+# Default: 30
+media-remote-cache-days: 30
 ```

example/config.yaml

@@ -205,6 +205,17 @@ media-description-min-chars: 0
 # Default: 500
 media-description-max-chars: 500
 
+# Int. Number of days to cache media from remote instances before they are removed from the cache.
+# A job will run every day at midnight to clean up any remote media older than the given amount of days.
+#
+# When remote media is removed from the cache, it is deleted from storage but the database entries for the media
+# are kept so that it can be fetched again if requested by a user.
+#
+# If this is set to 0, then media from remote instances will be cached indefinitely.
+# Examples: [30, 60, 7, 0]
+# Default: 30
+media-remote-cache-days: 30
+
 ##########################
 ##### STORAGE CONFIG #####
 ##########################

go.mod

@@ -18,12 +18,13 @@ require (
 	github.com/google/uuid v1.3.0
 	github.com/gorilla/websocket v1.4.2
 	github.com/h2non/filetype v1.1.3
-	github.com/jackc/pgconn v1.10.1
-	github.com/jackc/pgx/v4 v4.14.1
+	github.com/jackc/pgconn v1.11.0
+	github.com/jackc/pgx/v4 v4.15.0
 	github.com/microcosm-cc/bluemonday v1.0.16
 	github.com/mitchellh/mapstructure v1.4.3
 	github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646
 	github.com/oklog/ulid v1.3.1
+	github.com/robfig/cron/v3 v3.0.1
 	github.com/russross/blackfriday/v2 v2.1.0
 	github.com/sirupsen/logrus v1.8.1
 	github.com/spf13/cobra v1.2.1
@@ -34,15 +35,15 @@ require (
 	github.com/superseriousbusiness/exif-terminator v0.1.0
 	github.com/superseriousbusiness/oauth2/v4 v4.3.2-SSB
 	github.com/tdewolff/minify/v2 v2.9.22
-	github.com/uptrace/bun v1.0.19
+	github.com/uptrace/bun v1.0.20
 	github.com/uptrace/bun/dialect/pgdialect v1.0.19
 	github.com/uptrace/bun/dialect/sqlitedialect v1.0.19
 	github.com/wagslane/go-password-validator v0.3.0
 	golang.org/x/crypto v0.0.0-20211209193657-4570a0811e8b
 	golang.org/x/oauth2 v0.0.0-20211104180415-d3ed0bb246c8
 	golang.org/x/text v0.3.7
 	gopkg.in/mcuadros/go-syslog.v2 v2.3.0
-	modernc.org/sqlite v1.14.2
+	modernc.org/sqlite v1.14.6
 	mvdan.cc/xurls/v2 v2.3.0
 )
 
@@ -84,7 +85,7 @@ require (
 	github.com/jackc/pgpassfile v1.0.0 // indirect
 	github.com/jackc/pgproto3/v2 v2.2.0 // indirect
 	github.com/jackc/pgservicefile v0.0.0-20200714003250-2b9c44734f2b // indirect
-	github.com/jackc/pgtype v1.9.1 // indirect
+	github.com/jackc/pgtype v1.10.0 // indirect
 	github.com/jinzhu/inflection v1.0.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/kballard/go-shellquote v0.0.0-20180428030007-95032a82bc51 // indirect
@@ -108,7 +109,7 @@ require (
 	github.com/vmihailenco/tagparser/v2 v2.0.0 // indirect
 	golang.org/x/mod v0.5.1 // indirect
 	golang.org/x/net v0.0.0-20211209124913-491a49abca63 // indirect
-	golang.org/x/sys v0.0.0-20211210111614-af8b64212486 // indirect
+	golang.org/x/sys v0.0.0-20220114195835-da31bd327af9 // indirect
 	golang.org/x/tools v0.1.8 // indirect
 	golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1 // indirect
 	google.golang.org/appengine v1.6.7 // indirect
@@ -118,9 +119,9 @@ require (
 	gopkg.in/yaml.v2 v2.4.0 // indirect
 	gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b // indirect
 	lukechampine.com/uint128 v1.1.1 // indirect
-	modernc.org/cc/v3 v3.35.18 // indirect
-	modernc.org/ccgo/v3 v3.12.92 // indirect
-	modernc.org/libc v1.11.101 // indirect
+	modernc.org/cc/v3 v3.35.22 // indirect
+	modernc.org/ccgo/v3 v3.15.13 // indirect
+	modernc.org/libc v1.14.5 // indirect
 	modernc.org/mathutil v1.4.1 // indirect
 	modernc.org/memory v1.0.5 // indirect
 	modernc.org/opt v0.1.1 // indirect