gotosocial/internal/federation/dereferencing/thread.go

242 lines
7.4 KiB
Go
Raw Normal View History

/*
GoToSocial
2021-12-20 17:42:19 +00:00
Copyright (C) 2021-2022 GoToSocial Authors admin@gotosocial.org
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"
"fmt"
"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/gotosocial/internal/ap"
"github.com/superseriousbusiness/gotosocial/internal/config"
[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"
"github.com/superseriousbusiness/gotosocial/internal/uris"
)
// DereferenceThread takes a statusable (something that has withReplies and withInReplyTo),
// and dereferences statusables in the conversation.
//
// This process involves working up and down the chain of replies, and parsing through the collections of IDs
// presented by remote instances as part of their replies collections, and will likely involve making several calls to
// multiple different hosts.
func (d *deref) DereferenceThread(ctx context.Context, username string, statusIRI *url.URL) error {
[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
l := log.WithFields(kv.Fields{
{"username", username},
{"statusIRI", statusIRI},
}...)
l.Trace("entering DereferenceThread")
// if it's our status we already have everything stashed so we can bail early
[chore] Global server configuration overhaul (#575) * move config flag names and usage to config package, rewrite config package to use global Configuration{} struct Signed-off-by: kim <grufwub@gmail.com> * improved code comment Signed-off-by: kim <grufwub@gmail.com> * linter Signed-off-by: kim <grufwub@gmail.com> * fix unmarshaling Signed-off-by: kim <grufwub@gmail.com> * remove kim's custom go compiler changes Signed-off-by: kim <grufwub@gmail.com> * generate setter and flag-name functions, implement these in codebase Signed-off-by: kim <grufwub@gmail.com> * update deps Signed-off-by: kim <grufwub@gmail.com> * small change Signed-off-by: kim <grufwub@gmail.com> * appease the linter... Signed-off-by: kim <grufwub@gmail.com> * move configuration into ConfigState structure, ensure reloading to/from viper settings to keep in sync Signed-off-by: kim <grufwub@gmail.com> * lint Signed-off-by: kim <grufwub@gmail.com> * update code comments Signed-off-by: kim <grufwub@gmail.com> * fix merge issue Signed-off-by: kim <grufwub@gmail.com> * fix merge issue Signed-off-by: kim <grufwub@gmail.com> * improved version string (removes time + go version) Signed-off-by: kim <grufwub@gmail.com> * fix version string build to pass test script + consolidate logic in func Signed-off-by: kim <grufwub@gmail.com> * add license text, update config.Defaults comment Signed-off-by: kim <grufwub@gmail.com> * add license text to generated config helpers file Signed-off-by: kim <grufwub@gmail.com> * defer unlock on config.Set___(), to ensure unlocked on panic Signed-off-by: kim <grufwub@gmail.com> * make it more obvious which cmd flags are being attached Signed-off-by: kim <grufwub@gmail.com>
2022-05-30 12:41:24 +00:00
if statusIRI.Host == config.GetHost() {
l.Trace("iri belongs to us, bailing")
return nil
}
// first make sure we have this status in our db
_, statusable, err := d.GetRemoteStatus(ctx, username, statusIRI, true, false)
if err != nil {
return fmt.Errorf("DereferenceThread: error getting initial status with id %s: %s", statusIRI.String(), err)
}
// first iterate up through ancestors, dereferencing if necessary as we go
if err := d.iterateAncestors(ctx, username, *statusIRI); err != nil {
return fmt.Errorf("error iterating ancestors of status %s: %s", statusIRI.String(), err)
}
// now iterate down through descendants, again dereferencing as we go
if err := d.iterateDescendants(ctx, username, *statusIRI, statusable); err != nil {
return fmt.Errorf("error iterating descendants of status %s: %s", statusIRI.String(), err)
}
return nil
}
// iterateAncestors has the goal of reaching the oldest ancestor of a given status, and stashing all statuses along the way.
func (d *deref) iterateAncestors(ctx context.Context, username string, statusIRI url.URL) error {
[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
l := log.WithFields(kv.Fields{
{"username", username},
{"statusIRI", statusIRI},
}...)
l.Trace("entering iterateAncestors")
// if it's our status we don't need to dereference anything so we can immediately move up the chain
[chore] Global server configuration overhaul (#575) * move config flag names and usage to config package, rewrite config package to use global Configuration{} struct Signed-off-by: kim <grufwub@gmail.com> * improved code comment Signed-off-by: kim <grufwub@gmail.com> * linter Signed-off-by: kim <grufwub@gmail.com> * fix unmarshaling Signed-off-by: kim <grufwub@gmail.com> * remove kim's custom go compiler changes Signed-off-by: kim <grufwub@gmail.com> * generate setter and flag-name functions, implement these in codebase Signed-off-by: kim <grufwub@gmail.com> * update deps Signed-off-by: kim <grufwub@gmail.com> * small change Signed-off-by: kim <grufwub@gmail.com> * appease the linter... Signed-off-by: kim <grufwub@gmail.com> * move configuration into ConfigState structure, ensure reloading to/from viper settings to keep in sync Signed-off-by: kim <grufwub@gmail.com> * lint Signed-off-by: kim <grufwub@gmail.com> * update code comments Signed-off-by: kim <grufwub@gmail.com> * fix merge issue Signed-off-by: kim <grufwub@gmail.com> * fix merge issue Signed-off-by: kim <grufwub@gmail.com> * improved version string (removes time + go version) Signed-off-by: kim <grufwub@gmail.com> * fix version string build to pass test script + consolidate logic in func Signed-off-by: kim <grufwub@gmail.com> * add license text, update config.Defaults comment Signed-off-by: kim <grufwub@gmail.com> * add license text to generated config helpers file Signed-off-by: kim <grufwub@gmail.com> * defer unlock on config.Set___(), to ensure unlocked on panic Signed-off-by: kim <grufwub@gmail.com> * make it more obvious which cmd flags are being attached Signed-off-by: kim <grufwub@gmail.com>
2022-05-30 12:41:24 +00:00
if statusIRI.Host == config.GetHost() {
l.Trace("iri belongs to us, moving up to next ancestor")
// since this is our status, we know we can extract the id from the status path
_, id, err := uris.ParseStatusesPath(&statusIRI)
if err != nil {
return err
}
status, err := d.db.GetStatusByID(ctx, id)
if err != nil {
return err
}
if status.InReplyToURI == "" {
// status doesn't reply to anything
return nil
}
nextIRI, err := url.Parse(status.URI)
if err != nil {
return err
}
return d.iterateAncestors(ctx, username, *nextIRI)
}
// If we reach here, we're looking at a remote status
_, statusable, err := d.GetRemoteStatus(ctx, username, &statusIRI, true, false)
if err != nil {
l.Debugf("couldn't get remote status %s: %s; can't iterate any more ancestors", statusIRI.String(), err)
return nil
}
inReplyTo := ap.ExtractInReplyToURI(statusable)
if inReplyTo == nil || inReplyTo.String() == "" {
// status doesn't reply to anything
return nil
}
// now move up to the next ancestor
return d.iterateAncestors(ctx, username, *inReplyTo)
}
func (d *deref) iterateDescendants(ctx context.Context, username string, statusIRI url.URL, statusable ap.Statusable) error {
[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
l := log.WithFields(kv.Fields{
{"username", username},
{"statusIRI", statusIRI},
}...)
l.Trace("entering iterateDescendants")
// if it's our status we already have descendants stashed so we can bail early
[chore] Global server configuration overhaul (#575) * move config flag names and usage to config package, rewrite config package to use global Configuration{} struct Signed-off-by: kim <grufwub@gmail.com> * improved code comment Signed-off-by: kim <grufwub@gmail.com> * linter Signed-off-by: kim <grufwub@gmail.com> * fix unmarshaling Signed-off-by: kim <grufwub@gmail.com> * remove kim's custom go compiler changes Signed-off-by: kim <grufwub@gmail.com> * generate setter and flag-name functions, implement these in codebase Signed-off-by: kim <grufwub@gmail.com> * update deps Signed-off-by: kim <grufwub@gmail.com> * small change Signed-off-by: kim <grufwub@gmail.com> * appease the linter... Signed-off-by: kim <grufwub@gmail.com> * move configuration into ConfigState structure, ensure reloading to/from viper settings to keep in sync Signed-off-by: kim <grufwub@gmail.com> * lint Signed-off-by: kim <grufwub@gmail.com> * update code comments Signed-off-by: kim <grufwub@gmail.com> * fix merge issue Signed-off-by: kim <grufwub@gmail.com> * fix merge issue Signed-off-by: kim <grufwub@gmail.com> * improved version string (removes time + go version) Signed-off-by: kim <grufwub@gmail.com> * fix version string build to pass test script + consolidate logic in func Signed-off-by: kim <grufwub@gmail.com> * add license text, update config.Defaults comment Signed-off-by: kim <grufwub@gmail.com> * add license text to generated config helpers file Signed-off-by: kim <grufwub@gmail.com> * defer unlock on config.Set___(), to ensure unlocked on panic Signed-off-by: kim <grufwub@gmail.com> * make it more obvious which cmd flags are being attached Signed-off-by: kim <grufwub@gmail.com>
2022-05-30 12:41:24 +00:00
if statusIRI.Host == config.GetHost() {
l.Trace("iri belongs to us, bailing")
return nil
}
replies := statusable.GetActivityStreamsReplies()
if replies == nil || !replies.IsActivityStreamsCollection() {
l.Trace("no replies, bailing")
return nil
}
repliesCollection := replies.GetActivityStreamsCollection()
if repliesCollection == nil {
l.Trace("replies collection is nil, bailing")
return nil
}
first := repliesCollection.GetActivityStreamsFirst()
if first == nil {
l.Trace("replies collection has no first, bailing")
return nil
}
firstPage := first.GetActivityStreamsCollectionPage()
if firstPage == nil {
l.Trace("first has no collection page, bailing")
return nil
}
firstPageNext := firstPage.GetActivityStreamsNext()
if firstPageNext == nil || !firstPageNext.IsIRI() {
l.Trace("next is not an iri, bailing")
return nil
}
var foundReplies int
currentPageIRI := firstPageNext.GetIRI()
pageLoop:
for {
l.Tracef("dereferencing page %s", currentPageIRI)
collectionPage, err := d.DereferenceCollectionPage(ctx, username, currentPageIRI)
if err != nil {
l.Debugf("couldn't get remote collection page %s: %s; breaking pageLoop", currentPageIRI, err)
break pageLoop
}
pageItems := collectionPage.GetActivityStreamsItems()
if pageItems.Len() == 0 {
// no items on this page, which means we're done
break pageLoop
}
// have a look through items and see what we can find
for iter := pageItems.Begin(); iter != pageItems.End(); iter = iter.Next() {
// We're looking for a url to feed to GetRemoteStatus.
// Each item can be either an IRI, or a Note.
// If a note, we grab the ID from it and call it, rather than parsing the note.
var itemURI *url.URL
switch {
case iter.IsIRI():
// iri, easy
itemURI = iter.GetIRI()
case iter.IsActivityStreamsNote():
// note, get the id from it to use as iri
note := iter.GetActivityStreamsNote()
noteID := note.GetJSONLDId()
if noteID != nil && noteID.IsIRI() {
itemURI = noteID.GetIRI()
}
default:
// if it's not an iri or a note, we don't know how to process it
continue
}
[chore] Global server configuration overhaul (#575) * move config flag names and usage to config package, rewrite config package to use global Configuration{} struct Signed-off-by: kim <grufwub@gmail.com> * improved code comment Signed-off-by: kim <grufwub@gmail.com> * linter Signed-off-by: kim <grufwub@gmail.com> * fix unmarshaling Signed-off-by: kim <grufwub@gmail.com> * remove kim's custom go compiler changes Signed-off-by: kim <grufwub@gmail.com> * generate setter and flag-name functions, implement these in codebase Signed-off-by: kim <grufwub@gmail.com> * update deps Signed-off-by: kim <grufwub@gmail.com> * small change Signed-off-by: kim <grufwub@gmail.com> * appease the linter... Signed-off-by: kim <grufwub@gmail.com> * move configuration into ConfigState structure, ensure reloading to/from viper settings to keep in sync Signed-off-by: kim <grufwub@gmail.com> * lint Signed-off-by: kim <grufwub@gmail.com> * update code comments Signed-off-by: kim <grufwub@gmail.com> * fix merge issue Signed-off-by: kim <grufwub@gmail.com> * fix merge issue Signed-off-by: kim <grufwub@gmail.com> * improved version string (removes time + go version) Signed-off-by: kim <grufwub@gmail.com> * fix version string build to pass test script + consolidate logic in func Signed-off-by: kim <grufwub@gmail.com> * add license text, update config.Defaults comment Signed-off-by: kim <grufwub@gmail.com> * add license text to generated config helpers file Signed-off-by: kim <grufwub@gmail.com> * defer unlock on config.Set___(), to ensure unlocked on panic Signed-off-by: kim <grufwub@gmail.com> * make it more obvious which cmd flags are being attached Signed-off-by: kim <grufwub@gmail.com>
2022-05-30 12:41:24 +00:00
if itemURI.Host == config.GetHost() {
// skip if the reply is from us -- we already have it then
continue
}
// we can confidently say now that we found something
foundReplies++
// get the remote statusable and put it in the db
_, statusable, err := d.GetRemoteStatus(ctx, username, itemURI, true, false)
if err == nil {
// now iterate descendants of *that* status
if err := d.iterateDescendants(ctx, username, *itemURI, statusable); err != nil {
continue
}
}
}
nextPage := collectionPage.GetActivityStreamsNext()
if nextPage != nil && nextPage.IsIRI() {
nextPageIRI := nextPage.GetIRI()
l.Tracef("moving on to next page %s", nextPageIRI)
currentPageIRI = nextPageIRI
} else {
l.Trace("no next page, bailing")
break pageLoop
}
}
l.Debugf("foundReplies %d", foundReplies)
return nil
}