gotosocial/internal/federation/dereferencing/collectionpage.go

135 lines
4.4 KiB
Go
Raw Normal View History

// 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"
"encoding/json"
"net/url"
2021-11-13 19:29:43 +03:00
"github.com/superseriousbusiness/activity/streams"
"github.com/superseriousbusiness/activity/streams/vocab"
"github.com/superseriousbusiness/gotosocial/internal/ap"
"github.com/superseriousbusiness/gotosocial/internal/gtserror"
"github.com/superseriousbusiness/gotosocial/internal/log"
)
[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 12:15:54 +03:00
// dereferenceCollectionPage returns the activitystreams CollectionPage at the specified IRI, or an error if something goes wrong.
func (d *Dereferencer) dereferenceCollectionPage(ctx context.Context, username string, pageIRI *url.URL) (ap.CollectionPageIterator, error) {
[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 12:15:54 +03:00
if blocked, err := d.state.DB.IsDomainBlocked(ctx, pageIRI.Host); blocked || err != nil {
return nil, gtserror.Newf("domain %s is blocked", pageIRI.Host)
}
transport, err := d.transportController.NewTransportForUsername(ctx, username)
if err != nil {
return nil, gtserror.Newf("error creating transport: %w", err)
}
b, err := transport.Dereference(ctx, pageIRI)
if err != nil {
return nil, gtserror.Newf("error deferencing %s: %w", pageIRI.String(), err)
}
m := make(map[string]interface{})
if err := json.Unmarshal(b, &m); err != nil {
return nil, gtserror.Newf("error unmarshalling bytes into json: %w", err)
}
t, err := streams.ToType(ctx, m)
if err != nil {
return nil, gtserror.Newf("error resolving json into ap vocab type: %w", err)
}
page, err := ap.ToCollectionPageIterator(t)
if err != nil {
return nil, gtserror.Newf("error resolving vocab type as page: %w", err)
}
return page, nil
}
// getAttachedStatusCollection is a small utility function to fetch the first page of an
// attached activity streams collection from a provided statusable object, along with a URI.
func getAttachedStatusCollectionPage(status ap.Statusable) (ap.CollectionPageIterator, string) { //nolint:gocritic
// Look for an attached status replies (as collection)
replies := status.GetActivityStreamsReplies()
if replies == nil {
return nil, ""
}
// Look for an attached collection page, wrap and return.
if page := getRepliesCollectionPage(replies); page != nil {
return ap.WrapCollectionPage(page), getIDString(page)
}
// Look for an attached ordered collection page, wrap and return.
if page := getRepliesOrderedCollectionPage(replies); page != nil {
return ap.WrapOrderedCollectionPage(page), getIDString(page)
}
log.Warnf(nil, "replies without collection page: %s", getIDString(status))
return nil, ""
}
func getRepliesCollectionPage(replies vocab.ActivityStreamsRepliesProperty) vocab.ActivityStreamsCollectionPage {
// Get the status replies collection
collection := replies.GetActivityStreamsCollection()
if collection == nil {
return nil
}
// Get the "first" property of the replies collection
first := collection.GetActivityStreamsFirst()
if first == nil {
return nil
}
// Return the first activity stream collection page
return first.GetActivityStreamsCollectionPage()
}
func getRepliesOrderedCollectionPage(replies vocab.ActivityStreamsRepliesProperty) vocab.ActivityStreamsOrderedCollectionPage {
// Get the status replies collection
collection := replies.GetActivityStreamsOrderedCollection()
if collection == nil {
return nil
}
// Get the "first" property of the replies collection
first := collection.GetActivityStreamsFirst()
if first == nil {
return nil
}
// Return the first activity stream collection page
return first.GetActivityStreamsOrderedCollectionPage()
}
// getIDString is shorthand to fetch an ID URI string from AP type with attached JSONLDId.
func getIDString(a ap.WithJSONLDId) string {
id := a.GetJSONLDId()
if id == nil {
return ""
}
uri := id.Get()
if uri == nil {
return ""
}
return uri.String()
}