Files
stalwart-migrator/internal/applyplan/roles_test.go
T
jcoffey-dev 2ca9522f9a Fix two defects a production-clone dress rehearsal exposed
Streamed a clone of a production store into the smoke VM - 3.6 GB, 12,361
settings, 6 accounts across 9 domains - and migrated it 0.15.5 -> 0.16.14
with the tool's own phases. The migration succeeded. Two defects surfaced
that no smaller instance could have shown, plus one finding worth recording.

1. Account roles broke on production-shaped names. v0.16 stores an account
   as a local part plus a domain reference: a v0.15 account named
   "[email protected]" becomes name "john" with a domainId. The generator
   passed the full address and the server rejected it outright ("Invalid
   email local part"), failing the apply. The smoke instance used bare
   usernames - alice, bob - and never exercised this.

   Fixed to use the local part. And because local parts are unique only
   within a domain - [email protected] and [email protected] both become
   "postmaster" - an ambiguous one is now refused with a warning rather
   than risking an upsert that grants Admin to the wrong account. Verified
   on the clone: the one admin came out with roles {"@type": "Admin"} and
   the other five accounts untouched.

2. Cutover's health check conflated liveness with credentials. A config
   fallback-admin does not survive the migration - v0.16's config is a
   store pointer, so the old [authentication.fallback-admin] block simply
   ceases to exist - so the credentials supplied for the pre-migration
   instance came back 401 on the migrated one, and the check reported the
   service as never having answered. It had answered; it was up and serving
   on all ten ports. Liveness and credentials are now separate: any
   response proves the service is up, and credentials that stopped working
   are a warning that names this cause.

Also recorded: a failed apply leaves the store in bootstrap mode, where
only Bootstrap objects are accessible. A half-applied plan is not a
partially configured server but an unusable one.

Timing, which is the other reason to rehearse: the recovery-mode conversion
of that 3.6 GB store took 2 seconds. A migration window is dominated by
waiting and verification, not data volume.

No production data in this commit; fixtures use example.net and the shapes
involved.
2026-08-23 22:32:17 -07:00

164 lines
5.7 KiB
Go

// SPDX-FileCopyrightText: 2026 LINUXexpert-org
// SPDX-License-Identifier: GPL-3.0-or-later
package applyplan
import (
"strings"
"testing"
"github.com/LINUXexpert-org/stalwart-migrator/internal/backup"
)
// The exact principal shape a real 0.15.5 reports.
var migratedPrincipals = []backup.Principal{
{ID: 4, Type: "individual", Name: "alice", Emails: []string{"[email protected]"}, Roles: []string{"user"}},
{ID: 5, Type: "individual", Name: "bob", Emails: []string{"[email protected]"}, Roles: []string{"user"}},
{ID: 6, Type: "individual", Name: "sysadmin", Emails: []string{"[email protected]"}, Roles: []string{"admin"}},
{ID: 1, Type: "domain", Name: "smoke.test"},
}
// The failure this exists to prevent: after a real migration the admin
// account authenticated fine and was refused every management call, because
// migrate_v016.py had given it the User role like everyone else.
func TestAccountRolesRestoresTheAdministrator(t *testing.T) {
ops, covered, warnings, err := AccountRoleOperations(migratedPrincipals)
if err != nil {
t.Fatal(err)
}
if len(warnings) != 0 {
t.Errorf("unexpected warnings: %v", warnings)
}
if len(ops) != 1 {
t.Fatalf("generated %d op(s), want 1 - only the admin's role actually changes", len(ops))
}
v := ops[0].Value["role-sysadmin"]
if v == nil {
t.Fatalf("no operation for sysadmin: %+v", ops[0].Value)
}
// Account is multi-variant; without its own @type the upsert is
// rejected outright by the server.
if v["@type"] != "User" {
t.Errorf("@type = %v, want User (the Account variant)", v["@type"])
}
roles, ok := v["roles"].(map[string]any)
if !ok || roles["@type"] != "Admin" {
t.Errorf("roles = %v, want {\"@type\": \"Admin\"}", v["roles"])
}
if len(covered) != 1 {
t.Errorf("covered = %v, want one entry", covered)
}
}
// Ordinary users already get User from the migration. Rewriting every
// account would be a far larger blast radius for no benefit.
func TestAccountRolesLeavesOrdinaryUsersAlone(t *testing.T) {
ops, _, _, err := AccountRoleOperations([]backup.Principal{
{Type: "individual", Name: "alice", Roles: []string{"user"}},
{Type: "individual", Name: "bob", Roles: []string{}},
})
if err != nil {
t.Fatal(err)
}
if len(ops) != 0 {
t.Errorf("generated %d op(s) for plain users, want 0", len(ops))
}
}
func TestAccountRolesSkipsNonIndividuals(t *testing.T) {
ops, _, _, err := AccountRoleOperations([]backup.Principal{
{Type: "domain", Name: "smoke.test", Roles: []string{"admin"}},
{Type: "group", Name: "staff", Roles: []string{"admin"}},
})
if err != nil {
t.Fatal(err)
}
if len(ops) != 0 {
t.Errorf("generated %d op(s) for non-individual principals, want 0", len(ops))
}
}
// v0.15 carries a list, v0.16 one variant. Under-privileging an
// administrator locks them out, so admin wins - and the collapse is
// reported, not silent.
func TestAccountRolesCollapsesMultipleRolesToAdminAndSaysSo(t *testing.T) {
ops, _, warnings, err := AccountRoleOperations([]backup.Principal{
{Type: "individual", Name: "boss", Roles: []string{"user", "admin"}},
})
if err != nil {
t.Fatal(err)
}
if len(ops) != 1 {
t.Fatalf("generated %d op(s), want 1", len(ops))
}
roles := ops[0].Value["role-boss"]["roles"].(map[string]any)
if roles["@type"] != "Admin" {
t.Errorf("roles = %v, want Admin to win", roles)
}
if len(warnings) != 1 || !strings.Contains(warnings[0], "collapsed") {
t.Errorf("warnings = %v, want the collapse reported", warnings)
}
}
func TestAccountRolesReportsRolesItCannotMap(t *testing.T) {
_, _, warnings, err := AccountRoleOperations([]backup.Principal{
{Type: "individual", Name: "auditor", Roles: []string{"compliance-reviewer"}},
})
if err != nil {
t.Fatal(err)
}
if len(warnings) != 1 || !strings.Contains(warnings[0], "compliance-reviewer") {
t.Errorf("warnings = %v, want the unmappable role named", warnings)
}
}
// Found by a dress rehearsal against a clone of production, where accounts
// are named by address. v0.16 stores an account as a local part plus a
// domain reference, and rejects a full address outright ("Invalid email
// local part"). The smoke instance used bare names and never exercised it.
func TestAccountRolesUsesTheLocalPartOfAnEmailStyleName(t *testing.T) {
ops, _, warnings, err := AccountRoleOperations([]backup.Principal{
{Type: "individual", Name: "[email protected]", Emails: []string{"[email protected]"}, Roles: []string{"admin"}},
})
if err != nil {
t.Fatal(err)
}
if len(ops) != 1 {
t.Fatalf("generated %d op(s), want 1", len(ops))
}
v := ops[0].Value["role-john"]
if v == nil {
t.Fatalf("operation not keyed by local part: %+v", ops[0].Value)
}
if v["name"] != "john" {
t.Errorf("name = %v, want the local part \"john\" - the full address is rejected by the server", v["name"])
}
if len(warnings) != 0 {
t.Errorf("unexpected warnings: %v", warnings)
}
}
// Local parts are unique only within a domain. Granting Admin to the wrong
// account is worse than granting it to none.
func TestAccountRolesRefusesAnAmbiguousLocalPart(t *testing.T) {
ops, covered, warnings, err := AccountRoleOperations([]backup.Principal{
{Type: "individual", Name: "[email protected]", Roles: []string{"admin"}},
{Type: "individual", Name: "[email protected]", Roles: []string{"user"}},
})
if err != nil {
t.Fatal(err)
}
if len(ops) != 0 {
t.Errorf("generated %d op(s) for an ambiguous local part, want 0 - it could land on the wrong account", len(ops))
}
if len(covered) != 0 {
t.Errorf("covered = %v, want none", covered)
}
if len(warnings) != 1 || !strings.Contains(warnings[0], "share the local part") {
t.Errorf("warnings = %v, want one explaining the ambiguity", warnings)
}
if !strings.Contains(warnings[0], "by hand") {
t.Errorf("warning %q should tell the operator what to do instead", warnings[0])
}
}