Files
stalwart-migrator/internal/validate/main_test.go
T
jcoffey-dev 3e155fa42c Fix three defects a full VM migration exposed
Ran a complete 0.15.5 -> 0.16.14 migration of the smoke VM, driving the
phases in the order the real pipeline will. It worked - all mail intact and
readable afterwards, all ten listeners up, cutover executed for the first
time ever and checkpoint resume exercised - and it exposed three defects.

1. The converted config was installed root-owned while the service runs as
   its own user. Stalwart crash-looped 28 times on "Failed to read data
   store settings: Permission denied", minutes after the mistake and
   nowhere near it. This is the same ownership trap that retired the
   rollback implementation, in a new place: writing files as root is the
   natural thing for a tool running as root to do, and it is wrong every
   time the service is not root.

   Cutover now installs the config itself, copying ownership and mode from
   the config being replaced.

2. v0.16.14 does not serve /api - the endpoint stalwartapi assumed.
   Confirmed against a fully migrated, fully configured, serving instance
   rather than a sandbox: /api, /api/principal and /jmap/ all 404. The JMAP
   endpoint is the one the session document advertises, which is what RFC
   8620 discovery is for.

   The client now discovers it, re-basing the advertised path onto the
   operator's host: a real instance advertises its canonical public URL
   ("https://mail.smoke.test/jmap/") which frequently isn't reachable from
   where this tool runs. The session is authoritative about the path; the
   operator is authoritative about the host.

3. Dispatching on the urn:stalwart:jmap capability was wrong, because
   NEITHER version advertises it - not 0.15.5, and not a fully migrated
   0.16.14. That sent 0.16 instances down the 0.15 REST path where every
   call 404s. The client probes what the instance actually serves instead.
   Less elegant than a declared capability, with the advantage of being
   true.

Also: a JMAP "forbidden" now explains itself. An account holding the admin
role before the migration was refused x:Account/query afterwards, and a
bare "forbidden" gives an operator nowhere to start. Whether the role
failed to carry or v0.16 wants different permissions was not isolated, and
that question is recorded as open - it gates quota recalculation and any
post-migration validation.

Verified against both live instances: the 0.15.5 reports 3 accounts and its
domain over REST, and the migrated 0.16.14 routes to JMAP, finds the right
endpoint, and returns the explained refusal.
2026-08-23 21:32:30 -07:00

112 lines
3.5 KiB
Go

// SPDX-FileCopyrightText: 2026 LINUXexpert-org
// SPDX-License-Identifier: GPL-3.0-or-later
package validate
import (
"encoding/json"
"fmt"
"net"
"net/http"
"os"
"os/signal"
"strconv"
"strings"
"syscall"
"testing"
)
// TestMain lets this test binary also act as a fake Stalwart binary,
// mirroring internal/recovery's own TestMain - see that package's doc
// comment for why (the standard os/exec "helper process" technique). Beyond
// plain reachability, it also speaks just enough JMAP to serve
// stalwartapi.Client.AccountSnapshot (x:Account/query, x:Account/get,
// session discovery, Mailbox/get) for a single fixed fake account
// "[email protected]", so BootCheck's content-integrity comparison can be
// exercised against a real subprocess rather than mocked in-process. The
// mailbox message count it reports is configurable via
// STALWART_MIGRATOR_TEST_MAILBOX_COUNT (default 42), so tests can produce
// both a matching and a mismatching post-migration snapshot.
func TestMain(m *testing.M) {
if os.Getenv("STALWART_MIGRATOR_TEST_HELPER") == "1" {
runFakeStalwartServer()
return
}
os.Exit(m.Run())
}
func runFakeStalwartServer() {
port := os.Getenv("STALWART_MIGRATOR_TEST_PORT")
messageCount := 42
if v := os.Getenv("STALWART_MIGRATOR_TEST_MAILBOX_COUNT"); v != "" {
if n, err := strconv.Atoi(v); err == nil {
messageCount = n
}
}
ln, err := net.Listen("tcp", "127.0.0.1:"+port)
if err != nil {
fmt.Fprintln(os.Stderr, "fake stalwart: listen:", err)
os.Exit(1)
}
srv := &http.Server{Handler: http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path == "/api/principal" {
w.WriteHeader(http.StatusNotFound) // v0.16 shape: no REST management API
return
}
switch {
case r.Method == http.MethodGet && r.URL.Path == "/.well-known/jmap":
user, _, _ := r.BasicAuth()
if strings.Contains(user, "%") {
json.NewEncoder(w).Encode(map[string]any{
"apiUrl": "http://127.0.0.1:" + port + "/api",
"primaryAccounts": map[string]string{"urn:ietf:params:jmap:mail": "mail-alice"},
})
return
}
json.NewEncoder(w).Encode(map[string]any{
"apiUrl": "http://127.0.0.1:" + port + "/api",
"capabilities": map[string]any{"urn:ietf:params:jmap:core": map[string]any{}, "urn:stalwart:jmap": map[string]any{}},
})
case r.Method == http.MethodPost && r.URL.Path == "/api":
var body map[string]any
json.NewDecoder(r.Body).Decode(&body)
methodCalls, _ := body["methodCalls"].([]any)
if len(methodCalls) == 0 {
w.WriteHeader(http.StatusBadRequest)
return
}
call := methodCalls[0].([]any)
name := call[0].(string)
switch name {
case "x:Account/query":
json.NewEncoder(w).Encode(map[string]any{"methodResponses": []any{
[]any{"x:Account/query", map[string]any{"ids": []string{"a1"}}, "q"},
}})
case "x:Account/get":
json.NewEncoder(w).Encode(map[string]any{"methodResponses": []any{
[]any{"x:Account/get", map[string]any{"list": []map[string]any{
{"id": "a1", "name": "[email protected]", "domainId": "example.com"},
}}, "g"},
}})
case "Mailbox/get":
json.NewEncoder(w).Encode(map[string]any{"methodResponses": []any{
[]any{"Mailbox/get", map[string]any{"list": []map[string]any{
{"name": "Inbox", "totalEmails": messageCount},
}}, "m"},
}})
default:
w.WriteHeader(http.StatusBadRequest)
}
default:
w.WriteHeader(http.StatusOK)
}
})}
go srv.Serve(ln)
sigCh := make(chan os.Signal, 1)
signal.Notify(sigCh, syscall.SIGTERM)
<-sigCh
os.Exit(0)
}