gotosocial/internal/db/bundb/media.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

242 lines
7.7 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 bundb
import (
"context"
"errors"
"time"
"github.com/superseriousbusiness/gotosocial/internal/db"
"github.com/superseriousbusiness/gotosocial/internal/gtscontext"
"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
"github.com/superseriousbusiness/gotosocial/internal/log"
"github.com/superseriousbusiness/gotosocial/internal/state"
"github.com/uptrace/bun"
)
type mediaDB struct {
conn *DBConn
state *state.State
}
func (m *mediaDB) GetAttachmentByID(ctx context.Context, id string) (*gtsmodel.MediaAttachment, db.Error) {
return m.getAttachment(
ctx,
"ID",
func(attachment *gtsmodel.MediaAttachment) error {
return m.conn.NewSelect().
Model(attachment).
Where("? = ?", bun.Ident("media_attachment.id"), id).
Scan(ctx)
},
id,
)
}
func (m *mediaDB) GetAttachmentsByIDs(ctx context.Context, ids []string) ([]*gtsmodel.MediaAttachment, error) {
attachments := make([]*gtsmodel.MediaAttachment, 0, len(ids))
for _, id := range ids {
// Attempt fetch from DB
attachment, err := m.GetAttachmentByID(ctx, id)
if err != nil {
log.Errorf(ctx, "error getting attachment %q: %v", id, err)
continue
}
// Append attachment
attachments = append(attachments, attachment)
}
return attachments, nil
}
func (m *mediaDB) getAttachment(ctx context.Context, lookup string, dbQuery func(*gtsmodel.MediaAttachment) error, keyParts ...any) (*gtsmodel.MediaAttachment, db.Error) {
return m.state.Caches.GTS.Media().Load(lookup, func() (*gtsmodel.MediaAttachment, error) {
var attachment gtsmodel.MediaAttachment
// Not cached! Perform database query
if err := dbQuery(&attachment); err != nil {
return nil, m.conn.ProcessError(err)
}
return &attachment, nil
}, keyParts...)
}
func (m *mediaDB) PutAttachment(ctx context.Context, media *gtsmodel.MediaAttachment) error {
return m.state.Caches.GTS.Media().Store(media, func() error {
_, err := m.conn.NewInsert().Model(media).Exec(ctx)
return m.conn.ProcessError(err)
})
}
func (m *mediaDB) UpdateAttachment(ctx context.Context, media *gtsmodel.MediaAttachment, columns ...string) error {
media.UpdatedAt = time.Now()
if len(columns) > 0 {
// If we're updating by column, ensure "updated_at" is included.
columns = append(columns, "updated_at")
}
return m.state.Caches.GTS.Media().Store(media, func() error {
_, err := m.conn.NewUpdate().
Model(media).
Where("? = ?", bun.Ident("media_attachment.id"), media.ID).
Column(columns...).
Exec(ctx)
return m.conn.ProcessError(err)
})
}
func (m *mediaDB) DeleteAttachment(ctx context.Context, id string) error {
defer m.state.Caches.GTS.Media().Invalidate("ID", id)
// Load media into cache before attempting a delete,
// as we need it cached in order to trigger the invalidate
// callback. This in turn invalidates others.
_, err := m.GetAttachmentByID(gtscontext.SetBarebones(ctx), id)
if err != nil {
if errors.Is(err, db.ErrNoEntries) {
// not an issue.
err = nil
}
return err
}
// Finally delete media from DB.
_, err = m.conn.NewDelete().
TableExpr("? AS ?", bun.Ident("media_attachments"), bun.Ident("media_attachment")).
Where("? = ?", bun.Ident("media_attachment.id"), id).
Exec(ctx)
return m.conn.ProcessError(err)
}
func (m *mediaDB) GetRemoteOlderThan(ctx context.Context, olderThan time.Time, limit int) ([]*gtsmodel.MediaAttachment, db.Error) {
attachmentIDs := []string{}
q := m.conn.
NewSelect().
TableExpr("? AS ?", bun.Ident("media_attachments"), bun.Ident("media_attachment")).
Column("media_attachment.id").
Where("? = ?", bun.Ident("media_attachment.cached"), true).
Where("? < ?", bun.Ident("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, &attachmentIDs); err != nil {
return nil, m.conn.ProcessError(err)
}
return m.GetAttachmentsByIDs(ctx, attachmentIDs)
}
func (m *mediaDB) CountRemoteOlderThan(ctx context.Context, olderThan time.Time) (int, db.Error) {
q := m.conn.
NewSelect().
TableExpr("? AS ?", bun.Ident("media_attachments"), bun.Ident("media_attachment")).
Column("media_attachment.id").
Where("? = ?", bun.Ident("media_attachment.cached"), true).
Where("? < ?", bun.Ident("media_attachment.created_at"), olderThan).
WhereGroup(" AND ", whereNotEmptyAndNotNull("media_attachment.remote_url"))
count, err := q.Count(ctx)
if err != nil {
return 0, m.conn.ProcessError(err)
}
return count, nil
}
func (m *mediaDB) GetAvatarsAndHeaders(ctx context.Context, maxID string, limit int) ([]*gtsmodel.MediaAttachment, db.Error) {
attachmentIDs := []string{}
q := m.conn.NewSelect().
TableExpr("? AS ?", bun.Ident("media_attachments"), bun.Ident("media_attachment")).
Column("media_attachment.id").
WhereGroup(" AND ", func(innerQ *bun.SelectQuery) *bun.SelectQuery {
return innerQ.
WhereOr("? = ?", bun.Ident("media_attachment.avatar"), true).
WhereOr("? = ?", bun.Ident("media_attachment.header"), true)
}).
Order("media_attachment.id DESC")
if maxID != "" {
q = q.Where("? < ?", bun.Ident("media_attachment.id"), maxID)
}
if limit != 0 {
q = q.Limit(limit)
}
if err := q.Scan(ctx, &attachmentIDs); err != nil {
return nil, m.conn.ProcessError(err)
}
return m.GetAttachmentsByIDs(ctx, attachmentIDs)
}
func (m *mediaDB) GetLocalUnattachedOlderThan(ctx context.Context, olderThan time.Time, limit int) ([]*gtsmodel.MediaAttachment, db.Error) {
attachmentIDs := []string{}
q := m.conn.
NewSelect().
TableExpr("? AS ?", bun.Ident("media_attachments"), bun.Ident("media_attachment")).
Column("media_attachment.id").
Where("? = ?", bun.Ident("media_attachment.cached"), true).
Where("? = ?", bun.Ident("media_attachment.avatar"), false).
Where("? = ?", bun.Ident("media_attachment.header"), false).
Where("? < ?", bun.Ident("media_attachment.created_at"), olderThan).
Where("? IS NULL", bun.Ident("media_attachment.remote_url")).
Where("? IS NULL", bun.Ident("media_attachment.status_id")).
Order("media_attachment.created_at DESC")
if limit != 0 {
q = q.Limit(limit)
}
if err := q.Scan(ctx, &attachmentIDs); err != nil {
return nil, m.conn.ProcessError(err)
}
return m.GetAttachmentsByIDs(ctx, attachmentIDs)
}
func (m *mediaDB) CountLocalUnattachedOlderThan(ctx context.Context, olderThan time.Time) (int, db.Error) {
q := m.conn.
NewSelect().
TableExpr("? AS ?", bun.Ident("media_attachments"), bun.Ident("media_attachment")).
Column("media_attachment.id").
Where("? = ?", bun.Ident("media_attachment.cached"), true).
Where("? = ?", bun.Ident("media_attachment.avatar"), false).
Where("? = ?", bun.Ident("media_attachment.header"), false).
Where("? < ?", bun.Ident("media_attachment.created_at"), olderThan).
Where("? IS NULL", bun.Ident("media_attachment.remote_url")).
Where("? IS NULL", bun.Ident("media_attachment.status_id"))
count, err := q.Count(ctx)
if err != nil {
return 0, m.conn.ProcessError(err)
}
return count, nil
}