gotosocial/internal/federation/dereferencing/thread.go

460 lines
14 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"
"errors"
"net/http"
"net/url"
[chore] use our own logging implementation (#716) * first commit Signed-off-by: kim <grufwub@gmail.com> * replace logging with our own log library Signed-off-by: kim <grufwub@gmail.com> * fix imports Signed-off-by: kim <grufwub@gmail.com> * fix log imports Signed-off-by: kim <grufwub@gmail.com> * add license text Signed-off-by: kim <grufwub@gmail.com> * fix package import cycle between config and log package Signed-off-by: kim <grufwub@gmail.com> * fix empty kv.Fields{} being passed to WithFields() Signed-off-by: kim <grufwub@gmail.com> * fix uses of log.WithFields() with whitespace issues and empty slices Signed-off-by: kim <grufwub@gmail.com> * *linter related grumbling* Signed-off-by: kim <grufwub@gmail.com> * gofmt the codebase! also fix more log.WithFields() formatting issues Signed-off-by: kim <grufwub@gmail.com> * update testrig code to match new changes Signed-off-by: kim <grufwub@gmail.com> * fix error wrapping in non fmt.Errorf function Signed-off-by: kim <grufwub@gmail.com> * add benchmarking of log.Caller() vs non-cached Signed-off-by: kim <grufwub@gmail.com> * fix syslog tests, add standard build tags to test runner to ensure consistency Signed-off-by: kim <grufwub@gmail.com> * make syslog tests more robust Signed-off-by: kim <grufwub@gmail.com> * fix caller depth arithmatic (is that how you spell it?) Signed-off-by: kim <grufwub@gmail.com> * update to use unkeyed fields in kv.Field{} instances Signed-off-by: kim <grufwub@gmail.com> * update go-kv library Signed-off-by: kim <grufwub@gmail.com> * update libraries list Signed-off-by: kim <grufwub@gmail.com> * fuck you linter get nerfed Signed-off-by: kim <grufwub@gmail.com> Co-authored-by: tobi <31960611+tsmethurst@users.noreply.github.com>
2022-07-19 08:47:55 +00:00
"codeberg.org/gruf/go-kv"
"github.com/superseriousbusiness/activity/pub"
"github.com/superseriousbusiness/activity/streams/vocab"
"github.com/superseriousbusiness/gotosocial/internal/ap"
"github.com/superseriousbusiness/gotosocial/internal/config"
"github.com/superseriousbusiness/gotosocial/internal/db"
"github.com/superseriousbusiness/gotosocial/internal/gtscontext"
"github.com/superseriousbusiness/gotosocial/internal/gtserror"
"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
[chore] use our own logging implementation (#716) * first commit Signed-off-by: kim <grufwub@gmail.com> * replace logging with our own log library Signed-off-by: kim <grufwub@gmail.com> * fix imports Signed-off-by: kim <grufwub@gmail.com> * fix log imports Signed-off-by: kim <grufwub@gmail.com> * add license text Signed-off-by: kim <grufwub@gmail.com> * fix package import cycle between config and log package Signed-off-by: kim <grufwub@gmail.com> * fix empty kv.Fields{} being passed to WithFields() Signed-off-by: kim <grufwub@gmail.com> * fix uses of log.WithFields() with whitespace issues and empty slices Signed-off-by: kim <grufwub@gmail.com> * *linter related grumbling* Signed-off-by: kim <grufwub@gmail.com> * gofmt the codebase! also fix more log.WithFields() formatting issues Signed-off-by: kim <grufwub@gmail.com> * update testrig code to match new changes Signed-off-by: kim <grufwub@gmail.com> * fix error wrapping in non fmt.Errorf function Signed-off-by: kim <grufwub@gmail.com> * add benchmarking of log.Caller() vs non-cached Signed-off-by: kim <grufwub@gmail.com> * fix syslog tests, add standard build tags to test runner to ensure consistency Signed-off-by: kim <grufwub@gmail.com> * make syslog tests more robust Signed-off-by: kim <grufwub@gmail.com> * fix caller depth arithmatic (is that how you spell it?) Signed-off-by: kim <grufwub@gmail.com> * update to use unkeyed fields in kv.Field{} instances Signed-off-by: kim <grufwub@gmail.com> * update go-kv library Signed-off-by: kim <grufwub@gmail.com> * update libraries list Signed-off-by: kim <grufwub@gmail.com> * fuck you linter get nerfed Signed-off-by: kim <grufwub@gmail.com> Co-authored-by: tobi <31960611+tsmethurst@users.noreply.github.com>
2022-07-19 08:47:55 +00:00
"github.com/superseriousbusiness/gotosocial/internal/log"
)
// maxIter defines how many iterations of descendants or
// ancesters we are willing to follow before returning error.
const maxIter = 1000
[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 09:15:54 +00:00
func (d *deref) dereferenceThread(ctx context.Context, username string, statusIRI *url.URL, status *gtsmodel.Status, statusable ap.Statusable) {
// Ensure that ancestors have been fully dereferenced
if err := d.DereferenceStatusAncestors(ctx, username, status); err != nil {
log.Error(ctx, err)
}
// Ensure that descendants have been fully dereferenced
if err := d.DereferenceStatusDescendants(ctx, username, statusIRI, statusable); err != nil {
log.Error(ctx, err)
}
}
func (d *deref) DereferenceStatusAncestors(
ctx context.Context,
username string,
status *gtsmodel.Status,
) error {
// Start log entry with fields
l := log.WithContext(ctx).
WithFields(kv.Fields{
{"username", username},
{"original", status.URI},
}...)
// Keep track of already dereferenced statuses
// for this ancestor thread to prevent recursion.
derefdStatuses := make(map[string]struct{}, 10)
// Mark given status as the one
// we're currently working on.
current := status
for i := 0; i < maxIter; i++ {
if current.InReplyToURI == "" {
// Status has no parent, we've
// reached the top of the chain.
return nil
}
// Add new log fields for this iteration.
l = l.WithFields(kv.Fields{
{"current", current.URI},
{"parent", current.InReplyToURI},
}...)
l.Trace("following status ancestors")
// Check whether this parent has already been deref'd.
if _, ok := derefdStatuses[current.InReplyToURI]; ok {
l.Warn("self referencing status ancestors")
return nil
}
// Add this status URI to map of deref'd.
derefdStatuses[current.URI] = struct{}{}
if current.InReplyToID != "" {
// We already have an InReplyToID set. This means
// the status's parent has, at some point, been
// inserted into the database, either because it
// is a status from our instance, or a status from
// remote that we've dereferenced before, or found
// out about in some other way.
//
// Working on this assumption, check if the parent
// status exists, either as a copy pinned on the
// current status, or in the database.
if current.InReplyTo != nil {
// We have the parent already, and the child
// doesn't need to be updated; keep iterating
// from this parent upwards.
current = current.InReplyTo
continue
}
// Parent isn't pinned to this status (yet), see
// if we can get it from the db (we should be
// able to, since it has an ID already).
parent, err := d.state.DB.GetStatusByID(
gtscontext.SetBarebones(ctx),
current.InReplyToID,
)
if err != nil && !errors.Is(err, db.ErrNoEntries) {
// Real db error, stop.
return gtserror.Newf("db error getting status %s: %w", current.InReplyToID, err)
}
if parent != nil {
// We got the parent from the db, and the child
// doesn't need to be updated; keep iterating
// from this parent upwards.
current.InReplyTo = parent
current = parent
continue
}
// If we arrive here, we know this child *did* have
// a parent at some point, but it no longer exists in
// the database, presumably because it's been deleted
// by another action.
//
// TODO: clean this up in a nightly task.
l.Warn("orphaned status (parent no longer exists)")
return nil // Cannot iterate further.
}
// If we reach this point, we know the status has
// an InReplyToURI set, but it doesn't yet have an
// InReplyToID, which means that the parent status
// has not yet been dereferenced.
inReplyToURI, err := url.Parse(current.InReplyToURI)
if err != nil || inReplyToURI == nil {
// Parent URI is not something we can handle.
l.Warn("orphaned status (invalid InReplyToURI)")
return nil //nolint:nilerr
}
// Parent URI is valid, try to get it.
// getStatusByURI guards against the following conditions:
// - refetching recently fetched statuses (recursion!)
// - remote domain is blocked (will return unretrievable)
// - any http type error for a new status returns unretrievable
parent, _, err := d.getStatusByURI(ctx, username, inReplyToURI)
if err == nil {
// We successfully fetched the parent.
// Update current status with new info.
current.InReplyToID = parent.ID
current.InReplyToAccountID = parent.AccountID
if err := d.state.DB.UpdateStatus(
ctx, current,
"in_reply_to_id",
"in_reply_to_account_id",
); err != nil {
return gtserror.Newf("db error updating status %s: %w", current.ID, err)
}
// Mark parent as next status to
// work on, and keep iterating.
current = parent
continue
}
// We could not fetch the parent, check if we can do anything
// useful with the error. For example, HTTP status code returned
// from remote may indicate that the parent has been deleted.
switch code := gtserror.StatusCode(err); {
case code == http.StatusGone:
// 410 means the status has definitely been deleted.
// Update this status to reflect that, then bail.
l.Debug("orphaned status: parent returned 410 Gone")
current.InReplyToURI = ""
if err := d.state.DB.UpdateStatus(
ctx, current,
"in_reply_to_uri",
); err != nil {
return gtserror.Newf("db error updating status %s: %w", current.ID, err)
}
return nil
case code != 0:
// We had a code, but not one indicating deletion, log the code
// but don't return error or update the status; we can try again later.
l.Warnf("orphaned status: http error dereferencing parent: %v)", err)
return nil
case gtserror.Unretrievable(err):
// Not retrievable for some other reason, so just
// bail for now; we can try again later if necessary.
l.Warnf("orphaned status: parent unretrievable: %v)", err)
return nil
default:
// Some other error that stops us in our tracks.
return gtserror.Newf("error dereferencing parent %s: %w", current.InReplyToURI, err)
}
}
return gtserror.Newf("reached %d ancestor iterations for %q", maxIter, status.URI)
}
func (d *deref) DereferenceStatusDescendants(ctx context.Context, username string, statusIRI *url.URL, parent ap.Statusable) error {
statusIRIStr := statusIRI.String()
[chore] use our own logging implementation (#716) * first commit Signed-off-by: kim <grufwub@gmail.com> * replace logging with our own log library Signed-off-by: kim <grufwub@gmail.com> * fix imports Signed-off-by: kim <grufwub@gmail.com> * fix log imports Signed-off-by: kim <grufwub@gmail.com> * add license text Signed-off-by: kim <grufwub@gmail.com> * fix package import cycle between config and log package Signed-off-by: kim <grufwub@gmail.com> * fix empty kv.Fields{} being passed to WithFields() Signed-off-by: kim <grufwub@gmail.com> * fix uses of log.WithFields() with whitespace issues and empty slices Signed-off-by: kim <grufwub@gmail.com> * *linter related grumbling* Signed-off-by: kim <grufwub@gmail.com> * gofmt the codebase! also fix more log.WithFields() formatting issues Signed-off-by: kim <grufwub@gmail.com> * update testrig code to match new changes Signed-off-by: kim <grufwub@gmail.com> * fix error wrapping in non fmt.Errorf function Signed-off-by: kim <grufwub@gmail.com> * add benchmarking of log.Caller() vs non-cached Signed-off-by: kim <grufwub@gmail.com> * fix syslog tests, add standard build tags to test runner to ensure consistency Signed-off-by: kim <grufwub@gmail.com> * make syslog tests more robust Signed-off-by: kim <grufwub@gmail.com> * fix caller depth arithmatic (is that how you spell it?) Signed-off-by: kim <grufwub@gmail.com> * update to use unkeyed fields in kv.Field{} instances Signed-off-by: kim <grufwub@gmail.com> * update go-kv library Signed-off-by: kim <grufwub@gmail.com> * update libraries list Signed-off-by: kim <grufwub@gmail.com> * fuck you linter get nerfed Signed-off-by: kim <grufwub@gmail.com> Co-authored-by: tobi <31960611+tsmethurst@users.noreply.github.com>
2022-07-19 08:47:55 +00:00
// Start log entry with fields
l := log.WithContext(ctx).
WithFields(kv.Fields{
{"username", username},
{"status", statusIRIStr},
}...)
// Log function start
l.Trace("beginning")
// OUR instance hostname.
localhost := config.GetHost()
// Keep track of already dereferenced collection
// pages for this thread to prevent recursion.
derefdPages := make(map[string]struct{}, 10)
// frame represents a single stack frame when
// iteratively derefencing status descendants.
type frame struct {
// page is the current activity streams
// collection page we are on (as we often
// push a frame to stack mid-paging).
page ap.CollectionPageable
// pageURI is the URI string of
// the frame's collection page
// (is useful for logging).
pageURI string
// items is the entity iterator for frame's page.
items vocab.ActivityStreamsItemsPropertyIterator
}
var (
// current stack frame
current *frame
// stack is a list of "shelved" descendand iterator
// frames. this is pushed to when a child status frame
// is found that we need to further iterate down, and
// popped from into 'current' when that child's tree
// of further descendants is exhausted.
stack = []*frame{
func() *frame {
// Start input frame is built from the first input.
page, pageURI := getAttachedStatusCollection(parent)
if page == nil {
return nil
}
return &frame{page: page, pageURI: pageURI}
}(),
}
// popStack will remove and return the top frame
// from the stack, or nil if currently empty.
popStack = func() *frame {
if len(stack) == 0 {
return nil
}
// Get frame index
idx := len(stack) - 1
// Pop last frame
frame := stack[idx]
stack = stack[:idx]
return frame
}
)
stackLoop:
for i := 0; i < maxIter; i++ {
// Pop next frame, nil means we are at end
if current = popStack(); current == nil {
return nil
}
pageLoop:
for {
if current.items == nil {
// Get the items associated with this page
items := current.page.GetActivityStreamsItems()
if items == nil {
continue stackLoop
}
// Start off the item iterator
current.items = items.Begin()
}
l.Tracef("following collection page: %s", current.pageURI)
itemLoop:
for {
// Check for remaining iter
if current.items == nil {
break itemLoop
}
// Get current item iterator
itemIter := current.items
// Set the next available iterator
current.items = itemIter.Next()
// Check for available IRI on item
itemIRI, _ := pub.ToId(itemIter)
if itemIRI == nil {
continue itemLoop
}
if itemIRI.Host == localhost {
// This child is one of ours,
continue itemLoop
}
[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 09:15:54 +00:00
// Dereference the remote status and store in the database.
// getStatusByURI guards against the following conditions:
// - refetching recently fetched statuses (recursion!)
// - remote domain is blocked (will return unretrievable)
// - any http type error for a new status returns unretrievable
[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 09:15:54 +00:00
_, statusable, err := d.getStatusByURI(ctx, username, itemIRI)
if err != nil {
if !gtserror.Unretrievable(err) {
l.Errorf("error dereferencing remote status %s: %v", itemIRI, err)
}
[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 09:15:54 +00:00
continue itemLoop
}
if statusable == nil {
// A nil statusable return from
// getStatusByURI() indicates a
// remote status that was already
// dereferenced recently (so no
// need to go through descendents).
continue itemLoop
}
// Extract any attached collection + URI from status.
page, pageURI := getAttachedStatusCollection(statusable)
if page == nil {
continue itemLoop
}
// Put current and next frame at top of stack
stack = append(stack, current, &frame{
pageURI: pageURI,
page: page,
})
// Now start at top of loop
continue stackLoop
}
// Get the current page's "next" property.
pageNext := current.page.GetActivityStreamsNext()
if pageNext == nil || !pageNext.IsIRI() {
continue stackLoop
}
// Get the IRI of the "next" property.
pageNextURI := pageNext.GetIRI()
pageNextURIStr := pageNextURI.String()
// Check whether this page has already been deref'd.
if _, ok := derefdPages[pageNextURIStr]; ok {
l.Warnf("self referencing collection page(s): %s", pageNextURIStr)
continue stackLoop
}
// Mark this collection page as deref'd.
derefdPages[pageNextURIStr] = struct{}{}
// Dereference this next collection page by its IRI.
[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 09:15:54 +00:00
collectionPage, err := d.dereferenceCollectionPage(ctx,
username,
pageNextURI,
[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 09:15:54 +00:00
)
if err != nil {
l.Errorf("error dereferencing collection page %q: %s", pageNextURIStr, err)
continue stackLoop
}
// Set the next collection page.
current.page = collectionPage
current.pageURI = pageNextURIStr
continue pageLoop
}
}
return gtserror.Newf("reached %d descendant iterations for %q", maxIter, statusIRIStr)
}
// getAttachedStatusCollection is a small utility function to fetch the first page
// of an attached activity streams collection from a provided statusable object .
func getAttachedStatusCollection(status ap.Statusable) (page ap.CollectionPageable, uri string) { //nolint:gocritic
// Look for an attached status replies (as collection)
replies := status.GetActivityStreamsReplies()
if replies == nil {
return nil, ""
}
// 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
page = first.GetActivityStreamsCollectionPage()
if page == nil {
return nil, ""
}
if pageID := page.GetJSONLDId(); pageID != nil {
// By default use collection JSONLD ID
return page, pageID.Get().String()
} else if statusID := status.GetJSONLDId(); statusID != nil {
// Else, if possible use status JSONLD ID
return page, statusID.Get().String()
} else {
// MUST have some kind of ID
return nil, ""
}
}