Warp/server/internal/matrix/event/event.go

// Package event is the Matrix event (PDU) core: parsing and validating
// events, computing their hashes and identifiers, signing and verifying
// them, and applying the redaction algorithm.
//
// It is pure library code. Nothing here reaches a database or the network,
// and nothing here decides whether an event is *allowed* — that is the
// auth package. The division matters: these are the operations whose
// results every server in a room must agree on byte for byte, so they are
// kept small, deterministic and heavily tested.
//
// An Event is immutable once parsed. The canonical JSON, the event ID and
// the decoded fields are worked out up front and then only read, which is
// what lets an event be passed around and cached without copying.
//
// # A known gap
//
// Room versions 1 to 5 are allowed to contain integers outside the range
// canonical JSON permits, and the spec asks servers to cope where they
// can. Warp does not: such an event is rejected whatever its room version.
// It only arises for events that were already outside the current grammar
// when they were created, and handling them means a second, lenient
// encoder — which can wait until federation (PLAN.md phase 5) makes old
// rooms reachable at all.
package event

import (
	"encoding/json"
	"errors"
	"fmt"

	"github.com/dariuszjaniak/warp/server/internal/matrix/canonicaljson"
	"github.com/dariuszjaniak/warp/server/internal/matrix/id"
	"github.com/dariuszjaniak/warp/server/internal/matrix/roomversion"
	"github.com/dariuszjaniak/warp/server/internal/matrix/signing"
)

// The event types that carry meaning for the event core itself: the ones
// the authorisation rules turn on, plus the two the redaction algorithm
// treats specially.
const (
	TypeCreate            = "m.room.create"
	TypeMember            = "m.room.member"
	TypeJoinRules         = "m.room.join_rules"
	TypePowerLevels       = "m.room.power_levels"
	TypeThirdPartyInvite  = "m.room.third_party_invite"
	TypeHistoryVisibility = "m.room.history_visibility"
	TypeRedaction         = "m.room.redaction"
	TypeAliases           = "m.room.aliases"
)

// The membership values an m.room.member event may carry.
const (
	MembershipJoin   = "join"
	MembershipLeave  = "leave"
	MembershipInvite = "invite"
	MembershipBan    = "ban"
	MembershipKnock  = "knock"
)

// ErrInvalidEvent is the root of every parsing and validation error here,
// so a caller that only needs to answer M_BAD_JSON can test for it.
var ErrInvalidEvent = errors.New("invalid event")

// Event is a parsed, structurally valid PDU.
//
// "Structurally valid" is a lower bar than "allowed in the room": an Event
// has the fields the spec requires, of the right types and within the size
// limits, and its ID has been computed. Whether it may actually be added to
// the room is a question for the auth package.
type Event struct {
	rules  roomversion.Rules
	raw    []byte
	id     string
	fields fields
}

// fields are the event properties the server itself reads. Anything else
// stays in raw, untouched, because a server must pass through properties it
// does not understand rather than dropping them.
type fields struct {
	RoomID         string             `json:"room_id"`
	Type           string             `json:"type"`
	StateKey       *string            `json:"state_key"`
	Sender         string             `json:"sender"`
	Content        json.RawMessage    `json:"content"`
	PrevEvents     []string           `json:"prev_events"`
	AuthEvents     []string           `json:"auth_events"`
	Depth          int64              `json:"depth"`
	OriginServerTS int64              `json:"origin_server_ts"`
	Hashes         hashes             `json:"hashes"`
	Signatures     signing.Signatures `json:"signatures"`
	Unsigned       json.RawMessage    `json:"unsigned"`

	// Redacts is the top-level property m.room.redaction used up to room
	// version 10. From version 11 the target is content.redacts instead,
	// where the redaction algorithm and therefore the signature can cover
	// it; Redacts is populated from whichever place this room version uses.
	Redacts string `json:"redacts"`
}

type hashes struct {
	SHA256 string `json:"sha256"`
}

// Parse validates an event and works out its ID.
//
// raw is canonicalised first, so an event may arrive with its keys in any
// order — what it may not do is use a float, an out-of-range integer or
// invalid UTF-8, because then there are no canonical bytes to hash and no
// two servers would agree on its ID.
func Parse(raw []byte, rules roomversion.Rules) (*Event, error) {
	canonical, err := canonicaljson.Encode(raw)
	if err != nil {
		return nil, fmt.Errorf("%w: %w", ErrInvalidEvent, err)
	}

	e := &Event{rules: rules, raw: canonical}
	if err := json.Unmarshal(canonical, &e.fields); err != nil {
		return nil, fmt.Errorf("%w: %w", ErrInvalidEvent, err)
	}
	if err := e.validate(); err != nil {
		return nil, err
	}

	// From room version 11 the redaction target lives in the content. Read
	// it from there so that the rest of the server can ask one question.
	if rules.RedactsInContent && e.fields.Type == TypeRedaction {
		var content struct {
			Redacts string `json:"redacts"`
		}
		if err := json.Unmarshal(e.fields.Content, &content); err != nil {
			return nil, fmt.Errorf("%w: m.room.redaction content: %w", ErrInvalidEvent, err)
		}
		e.fields.Redacts = content.Redacts
	}

	if e.id, err = computeEventID(canonical, rules); err != nil {
		return nil, err
	}
	return e, nil
}

// Accessors. They return the decoded fields; the JSON-valued ones hand back
// the event's own storage, which callers must treat as read-only.

// EventID returns the event's identifier, including the '$' sigil.
func (e *Event) EventID() string { return e.id }

// RoomID returns the room this event belongs to. It is empty for an
// m.room.create event in a room version where the room ID *is* the create
// event's ID; use RoomIDOfCreateEvent for that case.
func (e *Event) RoomID() string { return e.fields.RoomID }

// Type returns the event type, such as "m.room.message".
func (e *Event) Type() string { return e.fields.Type }

// Sender returns the user ID that sent the event.
func (e *Event) Sender() string { return e.fields.Sender }

// StateKey returns the state key and whether the event has one. An event
// with a state key is a state event, even if the key is the empty string.
func (e *Event) StateKey() (string, bool) {
	if e.fields.StateKey == nil {
		return "", false
	}
	return *e.fields.StateKey, true
}

// IsState reports whether the event is a state event.
func (e *Event) IsState() bool { return e.fields.StateKey != nil }

// Content returns the event content as JSON.
func (e *Event) Content() json.RawMessage { return e.fields.Content }

// PrevEventIDs returns the event IDs of the events this one follows.
func (e *Event) PrevEventIDs() []string { return e.fields.PrevEvents }

// AuthEventIDs returns the event IDs of the events that authorise this one.
func (e *Event) AuthEventIDs() []string { return e.fields.AuthEvents }

// Depth returns the event's depth in the room DAG.
func (e *Event) Depth() int64 { return e.fields.Depth }

// OriginServerTS returns the origin server's timestamp, in milliseconds
// since the epoch. It is a claim by that server, not a fact: it is used for
// ordering and display, never for authorisation.
func (e *Event) OriginServerTS() int64 { return e.fields.OriginServerTS }

// Unsigned returns the unsigned property, which is not covered by the
// event's hashes or signatures and may differ between servers.
func (e *Event) Unsigned() json.RawMessage { return e.fields.Unsigned }

// Signatures returns the event's signature block.
func (e *Event) Signatures() signing.Signatures { return e.fields.Signatures }

// Redacts returns the event ID an m.room.redaction event targets, from
// wherever this room version keeps it. It is empty on any other event.
func (e *Event) Redacts() string { return e.fields.Redacts }

// Rules returns the room version rules the event was parsed under.
func (e *Event) Rules() roomversion.Rules { return e.rules }

// Version returns the event's room version.
func (e *Event) Version() roomversion.Version { return e.rules.Version }

// JSON returns the event as canonical JSON. The slice is the event's own
// and must not be modified.
func (e *Event) JSON() []byte { return e.raw }

// ContentHash returns the content hash carried in the event, as the
// unpadded base64 string it is stored as.
func (e *Event) ContentHash() string { return e.fields.Hashes.SHA256 }

// Membership returns the membership from an m.room.member event's content.
func (e *Event) Membership() (string, error) {
	if e.fields.Type != TypeMember {
		return "", fmt.Errorf("%s is not an m.room.member event", e.id)
	}
	var content struct {
		Membership string `json:"membership"`
	}
	if err := json.Unmarshal(e.fields.Content, &content); err != nil {
		return "", fmt.Errorf("%w: m.room.member content: %w", ErrInvalidEvent, err)
	}
	return content.Membership, nil
}

// SenderServer returns the server name of the event's sender, which is the
// server that must have signed it.
func (e *Event) SenderServer() (string, error) {
	return id.ServerNameOf(e.fields.Sender)
}

// RoomIDOfCreateEvent returns the room ID an m.room.create event creates,
// in the room versions where the room ID is the create event's own ID with
// a '!' in place of the '$'.
//
// Deriving the room ID this way is what removed the domain from room IDs:
// a room is no longer named after the server that happened to create it.
func RoomIDOfCreateEvent(e *Event) (string, error) {
	if e.fields.Type != TypeCreate {
		return "", fmt.Errorf("%s is not an m.room.create event", e.id)
	}
	if !e.rules.RoomIDIsCreateEventID {
		// In these versions the create event carries the room ID like any
		// other event, so there is nothing to derive.
		return e.fields.RoomID, nil
	}
	return "!" + e.id[1:], nil
}