Warp/server/internal/syncapi/token.go

package syncapi

import (
	"fmt"
	"strconv"
	"strings"

	"github.com/dariuszjaniak/warp/server/internal/storage"
)

// Token is a position in every stream a sync response carries.
//
// A sync response is assembled from streams that move independently: room
// events, read receipts, to-device messages, account data and presence. A
// client that has seen receipt 7 but only event 4 has to be able to say so
// in the one opaque string the API gives it, so the token names a position
// in each.
//
// The wire form is
//
//	s{pdu}_{receipt}_{to_device}_{account_data}_{presence}
//
// with trailing zeroes left off, so a client that has only ever seen room
// events carries "s12" rather than "s12_0_0_0_0". The leading "s" is there
// to make a token recognisable in a log and to leave room for a second
// token shape later — Simplified Sliding Sync (PLAN.md phase 10) has its
// own — without any ambiguity about which is which.
//
// The spec says only that the token is opaque, and clients treat it that
// way. It is still worth being readable: a token is the first thing in
// every bug report about /sync.
type Token struct {
	PDU         int64
	Receipt     int64
	ToDevice    int64
	AccountData int64
	Presence    int64
}

// tokenPrefix marks a classic /sync token.
const tokenPrefix = "s"

// IsInitial reports whether the token is the start of every stream, which
// is what a sync with no ?since= means.
func (t Token) IsInitial() bool { return t == Token{} }

// String renders the wire form.
func (t Token) String() string {
	parts := []int64{t.PDU, t.Receipt, t.ToDevice, t.AccountData, t.Presence}
	// Trailing zeroes carry no information, and leaving them off keeps the
	// common token short.
	last := 0
	for i, p := range parts {
		if p != 0 {
			last = i
		}
	}

	var b strings.Builder
	b.WriteString(tokenPrefix)
	for i, p := range parts[:last+1] {
		if i > 0 {
			b.WriteByte('_')
		}
		b.WriteString(strconv.FormatInt(p, 10))
	}
	return b.String()
}

// ParseToken reads a token a client sent back.
//
// An empty string is the initial token: /sync without ?since= and
// /messages without ?from= both mean "from the beginning", and refusing
// the empty string would make every caller special-case it.
//
// A token with fewer fields than this build writes is accepted and the
// missing ones are zero. That is what lets a token stored by a client
// before a stream existed go on working: the stream it did not know about
// reads as "seen nothing", so the client is sent that stream in full once
// and is in step from then on.
func ParseToken(raw string) (Token, error) {
	if raw == "" {
		return Token{}, nil
	}
	body, ok := strings.CutPrefix(raw, tokenPrefix)
	if !ok {
		return Token{}, fmt.Errorf("%q is not a sync token: it must start with %q", raw, tokenPrefix)
	}

	fields := strings.Split(body, "_")
	if len(fields) > 5 {
		return Token{}, fmt.Errorf("%q is not a sync token: it has %d positions, this server writes at most 5",
			raw, len(fields))
	}

	var positions [5]int64
	for i, field := range fields {
		value, err := strconv.ParseInt(field, 10, 64)
		// The PDU position alone may be negative: /messages hands out
		// positions inside history backfilled from other servers, which
		// is numbered downwards from -1. Every other stream starts at 0.
		if err != nil || (value < 0 && i > 0) {
			return Token{}, fmt.Errorf("%q is not a sync token: position %d is %q", raw, i+1, field)
		}
		positions[i] = value
	}
	return Token{
		PDU:         positions[0],
		Receipt:     positions[1],
		ToDevice:    positions[2],
		AccountData: positions[3],
		Presence:    positions[4],
	}, nil
}

// tokenAt is the token naming the top of every stream, which is what a
// sync response hands back when it has drained all of them.
func tokenAt(positions storage.StreamPositions) Token {
	return Token{
		PDU:         positions.PDU,
		Receipt:     positions.Receipt,
		ToDevice:    positions.ToDevice,
		AccountData: positions.AccountData,
		Presence:    positions.Presence,
	}
}

// pduToken is the token for a position in the room event stream alone.
//
// It is what /messages and a room's prev_batch hand out: both are about
// room events only, and a token from either has to be usable as a ?since=
// for /sync, where the other streams then read as unseen. That is the
// conservative direction — the client is sent those streams again rather
// than having them skipped.
func pduToken(pos int64) Token { return Token{PDU: pos} }