gotosocial/internal/federation/dereferencing/dereferencer.go
kim 6c9d8e78eb
[feature] status refetch support (#1690)
* revamp http client to not limit requests, instead use sender worker

Signed-off-by: kim <grufwub@gmail.com>

* remove separate sender worker pool, spawn 2*GOMAXPROCS batch senders each time, no need for transport cache sweeping

Signed-off-by: kim <grufwub@gmail.com>

* improve batch senders to keep popping recipients until remote URL found

Signed-off-by: kim <grufwub@gmail.com>

* fix recipient looping issue

Signed-off-by: kim <grufwub@gmail.com>

* move request id ctx key to gtscontext, finish filling out more code comments, add basic support for not logging client IP

Signed-off-by: kim <grufwub@gmail.com>

* first draft of status refetching logic

Signed-off-by: kim <grufwub@gmail.com>

* fix testrig to use new federation alloc func signature

Signed-off-by: kim <grufwub@gmail.com>

* fix log format directive

Signed-off-by: kim <grufwub@gmail.com>

* add status fetched_at migration

Signed-off-by: kim <grufwub@gmail.com>

* remove unused / unchecked for error types

Signed-off-by: kim <grufwub@gmail.com>

* add back the used type...

Signed-off-by: kim <grufwub@gmail.com>

* add separate internal getStatus() function for derefThread() that doesn't recurse

Signed-off-by: kim <grufwub@gmail.com>

* improved mention and media attachment error handling

Signed-off-by: kim <grufwub@gmail.com>

* fix log and error format directives

Signed-off-by: kim <grufwub@gmail.com>

* update account deref to match status deref changes

Signed-off-by: kim <grufwub@gmail.com>

* very small code formatting change to make things clearer

Signed-off-by: kim <grufwub@gmail.com>

* add more code comments

Signed-off-by: kim <grufwub@gmail.com>

* improved code commenting

Signed-off-by: kim <grufwub@gmail.com>

* only check for required further derefs if needed

Signed-off-by: kim <grufwub@gmail.com>

* improved cache invalidation

Signed-off-by: kim <grufwub@gmail.com>

* tweak cache restarting to use a (very small) backoff

Signed-off-by: kim <grufwub@gmail.com>

* small readability changes and fixes

Signed-off-by: kim <grufwub@gmail.com>

* fix account sync issues

Signed-off-by: kim <grufwub@gmail.com>

* fix merge conflicts + update account enrichment to accept already-passed accountable

Signed-off-by: kim <grufwub@gmail.com>

* remove secondary function declaration

Signed-off-by: kim <grufwub@gmail.com>

* normalise dereferencer get status / account behaviour, fix remaining tests

Signed-off-by: kim <grufwub@gmail.com>

* fix remaining rebase conflicts, finish commenting code

Signed-off-by: kim <grufwub@gmail.com>

* appease the linter

Signed-off-by: kim <grufwub@gmail.com>

* add source file header

Signed-off-by: kim <grufwub@gmail.com>

* update to use TIMESTAMPTZ column type instead of just TIMESTAMP

Signed-off-by: kim <grufwub@gmail.com>

* don't pass in 'updated_at' to UpdateEmoji()

Signed-off-by: kim <grufwub@gmail.com>

* use new ap.Resolve{Account,Status}able() functions

Signed-off-by: kim <grufwub@gmail.com>

* remove the somewhat confusing rescoping of the same variable names

Signed-off-by: kim <grufwub@gmail.com>

* update migration file name, improved database delete error returns

Signed-off-by: kim <grufwub@gmail.com>

* formatting

Signed-off-by: kim <grufwub@gmail.com>

* improved multi-delete database functions to minimise DB calls

Signed-off-by: kim <grufwub@gmail.com>

* remove unused type

Signed-off-by: kim <grufwub@gmail.com>

* fix delete statements

Signed-off-by: kim <grufwub@gmail.com>

---------

Signed-off-by: kim <grufwub@gmail.com>
2023-05-12 11:15:54 +02:00

113 lines
7.2 KiB
Go

// GoToSocial
// Copyright (C) GoToSocial Authors admin@gotosocial.org
// SPDX-License-Identifier: AGPL-3.0-or-later
//
// 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 dereferencing
import (
"context"
"net/url"
"sync"
"codeberg.org/gruf/go-mutexes"
"github.com/superseriousbusiness/gotosocial/internal/ap"
"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
"github.com/superseriousbusiness/gotosocial/internal/media"
"github.com/superseriousbusiness/gotosocial/internal/state"
"github.com/superseriousbusiness/gotosocial/internal/transport"
"github.com/superseriousbusiness/gotosocial/internal/typeutils"
)
// Dereferencer wraps logic and functionality for doing dereferencing of remote accounts, statuses, etc, from federated instances.
type Dereferencer interface {
// GetAccountByURI will attempt to fetch an accounts by its URI, first checking the database. In the case of a newly-met remote model, or a remote model
// whose last_fetched date is beyond a certain interval, the account will be dereferenced. In the case of dereferencing, some low-priority account information
// may be enqueued for asynchronous fetching, e.g. featured account statuses (pins). An ActivityPub object indicates the account was dereferenced.
GetAccountByURI(ctx context.Context, requestUser string, uri *url.URL) (*gtsmodel.Account, ap.Accountable, error)
// GetAccountByUsernameDomain will attempt to fetch an accounts by its username@domain, first checking the database. In the case of a newly-met remote model,
// or a remote model whose last_fetched date is beyond a certain interval, the account will be dereferenced. In the case of dereferencing, some low-priority
// account information may be enqueued for asynchronous fetching, e.g. featured account statuses (pins). An ActivityPub object indicates the account was dereferenced.
GetAccountByUsernameDomain(ctx context.Context, requestUser string, username string, domain string) (*gtsmodel.Account, ap.Accountable, error)
// RefreshAccount updates the given account if remote and last_fetched is beyond fetch interval, or if force is set. An updated account model is returned,
// but in the case of dereferencing, some low-priority account information may be enqueued for asynchronous fetching, e.g. featured account statuses (pins).
// An ActivityPub object indicates the account was dereferenced (i.e. updated).
RefreshAccount(ctx context.Context, requestUser string, account *gtsmodel.Account, apubAcc ap.Accountable, force bool) (*gtsmodel.Account, ap.Accountable, error)
// RefreshAccountAsync enqueues the given account for an asychronous update fetching, if last_fetched is beyond fetch interval, or if forcc is set.
// This is a more optimized form of manually enqueueing .UpdateAccount() to the federation worker, since it only enqueues update if necessary.
RefreshAccountAsync(ctx context.Context, requestUser string, account *gtsmodel.Account, apubAcc ap.Accountable, force bool)
// GetStatusByURI will attempt to fetch a status by its URI, first checking the database. In the case of a newly-met remote model, or a remote model
// whose last_fetched date is beyond a certain interval, the status will be dereferenced. In the case of dereferencing, some low-priority status information
// may be enqueued for asynchronous fetching, e.g. dereferencing the remainder of the status thread. An ActivityPub object indicates the status was dereferenced.
GetStatusByURI(ctx context.Context, requestUser string, uri *url.URL) (*gtsmodel.Status, ap.Statusable, error)
// RefreshStatus updates the given status if remote and last_fetched is beyond fetch interval, or if force is set. An updated status model is returned,
// but in the case of dereferencing, some low-priority status information may be enqueued for asynchronous fetching, e.g. dereferencing the remainder of the
// status thread. An ActivityPub object indicates the status was dereferenced (i.e. updated).
RefreshStatus(ctx context.Context, requestUser string, status *gtsmodel.Status, apubStatus ap.Statusable, force bool) (*gtsmodel.Status, ap.Statusable, error)
// RefreshStatusAsync enqueues the given status for an asychronous update fetching, if last_fetched is beyond fetch interval, or if force is set.
// This is a more optimized form of manually enqueueing .UpdateStatus() to the federation worker, since it only enqueues update if necessary.
RefreshStatusAsync(ctx context.Context, requestUser string, status *gtsmodel.Status, apubStatus ap.Statusable, force bool)
GetRemoteInstance(ctx context.Context, username string, remoteInstanceURI *url.URL) (*gtsmodel.Instance, error)
DereferenceAnnounce(ctx context.Context, announce *gtsmodel.Status, requestingUsername string) error
GetRemoteMedia(ctx context.Context, requestingUsername string, accountID string, remoteURL string, ai *media.AdditionalMediaInfo) (*media.ProcessingMedia, error)
GetRemoteEmoji(ctx context.Context, requestingUsername string, remoteURL string, shortcode string, domain string, id string, emojiURI string, ai *media.AdditionalEmojiInfo, refresh bool) (*media.ProcessingEmoji, error)
Handshaking(username string, remoteAccountID *url.URL) bool
}
type deref struct {
state *state.State
typeConverter typeutils.TypeConverter
transportController transport.Controller
mediaManager media.Manager
derefAvatars map[string]*media.ProcessingMedia
derefAvatarsMu mutexes.Mutex
derefHeaders map[string]*media.ProcessingMedia
derefHeadersMu mutexes.Mutex
derefEmojis map[string]*media.ProcessingEmoji
derefEmojisMu mutexes.Mutex
handshakes map[string][]*url.URL
handshakeSync sync.Mutex // mutex to lock/unlock when checking or updating the handshakes map
}
// NewDereferencer returns a Dereferencer initialized with the given parameters.
func NewDereferencer(state *state.State, typeConverter typeutils.TypeConverter, transportController transport.Controller, mediaManager media.Manager) Dereferencer {
return &deref{
state: state,
typeConverter: typeConverter,
transportController: transportController,
mediaManager: mediaManager,
derefAvatars: make(map[string]*media.ProcessingMedia),
derefHeaders: make(map[string]*media.ProcessingMedia),
derefEmojis: make(map[string]*media.ProcessingEmoji),
handshakes: make(map[string][]*url.URL),
// use wrapped mutexes to allow safely deferring unlock
// even when more granular locks are required (only unlocks once).
derefAvatarsMu: mutexes.WithSafety(mutexes.New()),
derefHeadersMu: mutexes.WithSafety(mutexes.New()),
derefEmojisMu: mutexes.WithSafety(mutexes.New()),
}
}