Files
selfpost/internal/store/sendlog_test.go
T
mixandClaude Opus 5.5 60c7b85f84
test / test (push) Canceled after 0s
findings of the reviews of audit stage 1
Technical review (Opus) and security review (Fable) of 9efc9c7..a59e3d4;
reports in the session's scratchpad. Fixed:

- B1 (verified bug): store.UpdateStatus read before writing in its
  transaction; a commit by another connection in between (the dmarc-ingest
  process opens the same file) failed it at once with "database is locked"
  and the delivery line was lost. The first statement is now a write.
- R3: a delivery line updated every row of its queue id and recipient; it
  now updates only the newest (Postfix reuses short ids). The sweep closes
  by row id (QueuedDelivery.ID, CloseUnreported(id)).
- R4: a contradicted sweep keeps a mark, reason "reconcile-contradicted",
  instead of losing which row it was.
- R1: contradicted cannot see a lost line (never read late). New counter
  reconcile_missed: at close, the sweep looks for the row's delivery line
  in mail.log and mail.log.1 (QueueLines). 0007 edited - it has run on no
  database but throwaway stands.
- R2: queued_over_lifetime cannot measure "what removing the sweep would
  leave" while the sweep runs; its text now says rows stuck despite the
  sweep, and the rule uses closed - missed - contradicted.
- cert-reload (R5, R6, R7, security medium/low): both files copied to .new
  and the copies checked as a pair before both are renamed; acts on the copy
  only when postconf says Postfix reads it; a failed reload is retried next
  pass; umask 077; says so when the mounted files cannot be read. The e2e
  case asserts Postfix reads the copy, the copy equals the mount, the key is
  600 root.
- Security low: a recipient with a quoted local part - the journal cut
  "a b"@x at the space, deliveryRe cut "a>b"@x at the ">" - matched no
  delivery line and was closed by the sweep. cleanAddress ends a bracketed
  address at the first ">" outside quotes; deliveryRe takes the recipient
  up to the ">, " before relay= (test fixtures given the relay= every real
  delivery line has).
- Security low: postqueue -p's error carries at most 512 bytes of output.
- Nits: addDeliveryLogDay refuses a column not on its list; the truncation
  test checks its message.
- To stage 2b (page wording, mockup-first): the history step of a bounced
  row says the receiving server refused it, false for a row the sweep
  closed. To the owner when stage 2b is reached: since M13 the "deferred"
  figure counts whole messages too, which "Connections turned away" would
  not name.

Found while verifying: the e2e's main positive path failed once with "553
not owned by user app1" - an smtpd idle from before the panel's reload took
the connection in the reload's second. Measured on the stand (one-off
probe, not committed): sending 0, 10, 40, 110 s after the save (two seconds
at the soonest) always met an smtpd started after the reload. The e2e now
waits for the sender map after each application it creates
(waitForSenderMap: AUTH, MAIL, RCPT, RSET - no message, no row), and the
level-1 case uses it instead of its own loop.

Docs: architecture § Queue reconcile, schema-migrations (rows 7 and 8,
chain head 8), CHANGELOG, audit plan (stage 1 note, the measured window,
a new stage 2b line: 62 lines), roadmap 15/62.

Evidence on the test server for this tree: go vet clean, go test ./... 23
packages ok, make e2e exit 0 (renewed certificate, hung panel, level 1 at
49/60).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 15:21:52 +03:00

355 lines
12 KiB
Go

package store
import (
"sort"
"strings"
"testing"
"time"
)
// readSendLog returns every send_log row ordered by id. The monitoring UI has
// no equivalent read query, so tests read the table directly.
type sendLogRow struct {
QueueID string
Domain string
AppLogin string
From string
To string
Subject string
Status string
}
func readSendLog(t *testing.T, s *Store) []sendLogRow {
t.Helper()
rows, err := s.db.Query(
`SELECT queue_id, domain, app_login, from_addr, to_addr, subject, status
FROM send_log ORDER BY id`)
if err != nil {
t.Fatalf("query send_log: %v", err)
}
defer rows.Close()
var out []sendLogRow
for rows.Next() {
var r sendLogRow
if err := rows.Scan(&r.QueueID, &r.Domain, &r.AppLogin, &r.From, &r.To, &r.Subject, &r.Status); err != nil {
t.Fatalf("scan: %v", err)
}
out = append(out, r)
}
return out
}
func TestInsertQueuedAndUpdateStatus(t *testing.T) {
st := openTestStore(t)
// Two recipients on the same queue-id → two independent rows (architecture.md
// § Persistence).
for _, to := range []string{"a@example.net", "b@example.net"} {
if err := st.InsertQueued(SendLogEntry{
QueueID: "ABC123",
Domain: "example.com",
AppLogin: "app1",
From: "noreply@example.com",
To: to,
Subject: "Hello",
}); err != nil {
t.Fatalf("InsertQueued: %v", err)
}
}
rows := readSendLog(t, st)
if len(rows) != 2 {
t.Fatalf("want 2 rows, got %d: %+v", len(rows), rows)
}
for _, r := range rows {
if r.Status != StatusQueued {
t.Fatalf("new row should be queued, got %q", r.Status)
}
}
// One recipient goes to sent; the other stays queued.
n, err := st.UpdateStatus("ABC123", "a@example.net", StatusSent)
if err != nil {
t.Fatalf("UpdateStatus: %v", err)
}
if n != 1 {
t.Fatalf("want 1 row updated, got %d", n)
}
rows = readSendLog(t, st)
if rows[0].Status != StatusSent || rows[1].Status != StatusQueued {
t.Fatalf("unexpected statuses: %+v", rows)
}
}
func TestUpdateStatusRecipientCaseInsensitive(t *testing.T) {
st := openTestStore(t)
if err := st.InsertQueued(SendLogEntry{QueueID: "Q1", To: "User@Example.NET"}); err != nil {
t.Fatalf("InsertQueued: %v", err)
}
// mail.log may report a differently-cased recipient; matching must still hit.
n, err := st.UpdateStatus("Q1", "user@example.net", StatusBounced)
if err != nil {
t.Fatalf("UpdateStatus: %v", err)
}
if n != 1 {
t.Fatalf("case-insensitive match failed, updated %d rows", n)
}
}
// rowID is the id of the newest send-log row of a queue id.
func rowID(t *testing.T, st *Store, queueID string) int64 {
t.Helper()
var id int64
if err := st.db.QueryRow(`SELECT MAX(id) FROM send_log WHERE queue_id = ?`, queueID).Scan(&id); err != nil {
t.Fatal(err)
}
return id
}
// The sweep closes only what is still queued, and says it was the sweep: a
// status the log wrote stands, whatever the sweep believed when it listed the
// row.
func TestCloseUnreportedClosesOnlyQueuedRows(t *testing.T) {
st := openTestStore(t)
for _, e := range []SendLogEntry{{QueueID: "Q1", To: "Lost@example.net"}, {QueueID: "Q2", To: "done@example.net"}} {
if err := st.InsertQueued(e); err != nil {
t.Fatalf("InsertQueued: %v", err)
}
}
if _, err := st.UpdateStatus("Q2", "done@example.net", StatusSent); err != nil {
t.Fatal(err)
}
if n, err := st.CloseUnreported(rowID(t, st, "Q1")); err != nil || n != 1 {
t.Fatalf("CloseUnreported of a queued row = %d, %v; want 1", n, err)
}
if n, err := st.CloseUnreported(rowID(t, st, "Q2")); err != nil || n != 0 {
t.Fatalf("CloseUnreported of a sent row = %d, %v; want 0", n, err)
}
var status, reason string
for _, c := range []struct{ id, status, reason string }{
{"Q1", StatusBounced, ReasonReconcile},
{"Q2", StatusSent, ""},
} {
if err := st.db.QueryRow(`SELECT status, reason FROM send_log WHERE queue_id = ?`, c.id).Scan(&status, &reason); err != nil {
t.Fatal(err)
}
if status != c.status || reason != c.reason {
t.Errorf("%s: status %q reason %q, want %q %q", c.id, status, reason, c.status, c.reason)
}
}
}
// A delivery line about a row the sweep closed proves the sweep guessed what
// the log could have said: the log's status wins, the row is marked
// reconcile-contradicted, and the day counts one contradiction - once,
// however often the line is read again.
func TestUpdateStatusCountsAContradictedSweep(t *testing.T) {
st := openTestStore(t)
if err := st.InsertQueued(SendLogEntry{QueueID: "Q1", To: "a@example.net"}); err != nil {
t.Fatal(err)
}
if _, err := st.CloseUnreported(rowID(t, st, "Q1")); err != nil {
t.Fatal(err)
}
for i := 0; i < 2; i++ {
if n, err := st.UpdateStatus("Q1", "A@example.net", StatusSent); err != nil || n != 1 {
t.Fatalf("UpdateStatus = %d, %v", n, err)
}
}
var status, reason string
if err := st.db.QueryRow(`SELECT status, reason FROM send_log WHERE queue_id = 'Q1'`).Scan(&status, &reason); err != nil {
t.Fatal(err)
}
if status != StatusSent || reason != ReasonReconcileContradicted {
t.Fatalf("status %q reason %q, want sent and %s", status, reason, ReasonReconcileContradicted)
}
days, err := st.DeliveryLogDays()
if err != nil {
t.Fatal(err)
}
if len(days) != 1 || days[0].Contradicted != 1 {
t.Fatalf("days = %+v, want one day with one contradiction", days)
}
}
// Postfix reuses a short queue id once its message has left the queue; a
// line about the message of today rewrites today's row, not the months-old
// one of the same id and recipient.
func TestUpdateStatusRewritesOnlyTheNewestRow(t *testing.T) {
st := openTestStore(t)
for i := 0; i < 2; i++ {
if err := st.InsertQueued(SendLogEntry{QueueID: "REUSED", To: "a@example.net"}); err != nil {
t.Fatal(err)
}
}
old := rowID(t, st, "REUSED") - 1
if _, err := st.db.Exec(`UPDATE send_log SET status = ? WHERE id = ?`, StatusSent, old); err != nil {
t.Fatal(err)
}
if n, err := st.UpdateStatus("REUSED", "a@example.net", StatusBounced); err != nil || n != 1 {
t.Fatalf("UpdateStatus = %d, %v; want 1 row", n, err)
}
var status string
if err := st.db.QueryRow(`SELECT status FROM send_log WHERE id = ?`, old).Scan(&status); err != nil {
t.Fatal(err)
}
if status != StatusSent {
t.Fatalf("the old row became %q, want it left sent", status)
}
}
// The reconcile sweep asks for the rows old enough that Postfix should have
// reported on them by now. A message accepted moments ago is simply in flight,
// and one the milter refused never reached the queue at all, so neither is the
// sweep's business.
func TestListQueuedOlderThan(t *testing.T) {
st := openTestStore(t)
for _, e := range []SendLogEntry{
{QueueID: "OLD1", To: "stale@example.net"},
{QueueID: "NEW1", To: "fresh@example.net"},
} {
if err := st.InsertQueued(e); err != nil {
t.Fatalf("InsertQueued: %v", err)
}
}
// A row the milter refused: no queue-id, and a status the sweep never sees.
if err := st.InsertRejected(SendLogEntry{To: "refused@example.net"}); err != nil {
t.Fatalf("InsertRejected: %v", err)
}
// A row that has already been delivered, aged the same as the stale one.
if err := st.InsertQueued(SendLogEntry{QueueID: "DONE1", To: "done@example.net"}); err != nil {
t.Fatalf("InsertQueued: %v", err)
}
if _, err := st.UpdateStatus("DONE1", "done@example.net", StatusSent); err != nil {
t.Fatalf("UpdateStatus: %v", err)
}
cutoff := time.Now().UTC().Add(-2 * time.Minute)
backdate(t, st, "OLD1", cutoff.Add(-time.Hour))
backdate(t, st, "DONE1", cutoff.Add(-time.Hour))
got, err := st.ListQueuedOlderThan(cutoff)
if err != nil {
t.Fatalf("ListQueuedOlderThan: %v", err)
}
if len(got) != 1 || got[0] != (QueuedDelivery{ID: got[0].ID, QueueID: "OLD1", To: "stale@example.net"}) {
t.Fatalf("got %+v, want only the stale queued row", got)
}
}
// backdate rewrites a row's acceptance time, so a test can age it past a cutoff
// without waiting.
func backdate(t *testing.T, s *Store, queueID string, at time.Time) {
t.Helper()
if _, err := s.db.Exec(
`UPDATE send_log SET created_at = ? WHERE queue_id = ?`,
at.UTC().Format(time.RFC3339), queueID,
); err != nil {
t.Fatalf("backdate %s: %v", queueID, err)
}
}
func TestUpdateStatusNoMatch(t *testing.T) {
st := openTestStore(t)
if err := st.InsertQueued(SendLogEntry{QueueID: "Q1", To: "a@example.net"}); err != nil {
t.Fatalf("InsertQueued: %v", err)
}
// A queue-id/recipient the milter never recorded must be a no-op, not an error.
n, err := st.UpdateStatus("Q1", "unknown@example.net", StatusSent)
if err != nil {
t.Fatalf("UpdateStatus: %v", err)
}
if n != 0 {
t.Fatalf("want 0 rows updated, got %d", n)
}
}
// The journal is read by principals who are only entitled to part of it, so
// the scope is part of the query rather than something the caller remembers to
// apply afterwards. A filter that states no scope is a caller that has not
// decided who is asking, and the safe answer to that is nothing.
func TestSendLogScopeIsMandatory(t *testing.T) {
st := openTestStore(t)
for _, domain := range []string{"first.example.ru", "second.example.ru"} {
if err := st.InsertQueued(SendLogEntry{
QueueID: "Q-" + domain, Domain: domain, AppLogin: "app-" + domain,
From: "noreply@" + domain, To: "public@example.net", Subject: domain,
}); err != nil {
t.Fatalf("InsertQueued: %v", err)
}
}
for name, tc := range map[string]struct {
filter SendLogFilter
want []string
}{
"no scope": {SendLogFilter{}, nil},
"empty scope": {SendLogFilter{Domains: []string{}}, nil},
"all domains": {SendLogFilter{AllDomains: true}, []string{"first.example.ru", "second.example.ru"}},
"one domain": {SendLogFilter{Domains: []string{"first.example.ru"}}, []string{"first.example.ru"}},
"two domains": {SendLogFilter{Domains: []string{"first.example.ru", "second.example.ru"}}, []string{"first.example.ru", "second.example.ru"}},
"unknown domain": {SendLogFilter{Domains: []string{"third.example.ru"}}, nil},
"filter within": {SendLogFilter{Domain: "first.example.ru", Domains: []string{"first.example.ru", "second.example.ru"}}, []string{"first.example.ru"}},
"filter outside": {SendLogFilter{Domain: "second.example.ru", Domains: []string{"first.example.ru"}}, nil},
"app filter outside": {SendLogFilter{AppLogin: "app-second.example.ru", Domains: []string{"first.example.ru"}}, nil},
} {
rows, err := st.QuerySendLog(tc.filter, 50, 0)
if err != nil {
t.Fatalf("%s: QuerySendLog: %v", name, err)
}
var got []string
for _, r := range rows {
got = append(got, r.Domain)
}
// Which rows came back is the question here; the page's own order is
// newest-first and is tested where it matters.
sort.Strings(got)
if strings.Join(got, ",") != strings.Join(tc.want, ",") {
t.Errorf("%s: rows for %v, want %v", name, got, tc.want)
}
// The count drives pagination, so it has to agree with the page or the
// UI advertises pages of rows the reader is not allowed to see.
n, err := st.CountSendLog(tc.filter)
if err != nil {
t.Fatalf("%s: CountSendLog: %v", name, err)
}
if int(n) != len(tc.want) {
t.Errorf("%s: count %d, want %d", name, n, len(tc.want))
}
}
}
func TestDeleteSendLogBefore(t *testing.T) {
st := openTestStore(t)
// Insert one row, then backdate it beyond the retention window by rewriting
// created_at directly (InsertQueued always stamps "now").
if err := st.InsertQueued(SendLogEntry{QueueID: "OLD", To: "a@example.net"}); err != nil {
t.Fatalf("InsertQueued: %v", err)
}
old := time.Now().UTC().AddDate(0, 0, -100).Format(time.RFC3339)
if _, err := st.db.Exec(`UPDATE send_log SET created_at = ? WHERE queue_id = 'OLD'`, old); err != nil {
t.Fatalf("backdate: %v", err)
}
if err := st.InsertQueued(SendLogEntry{QueueID: "NEW", To: "b@example.net"}); err != nil {
t.Fatalf("InsertQueued: %v", err)
}
cutoff := time.Now().UTC().AddDate(0, 0, -90)
n, err := st.DeleteSendLogBefore(cutoff)
if err != nil {
t.Fatalf("DeleteSendLogBefore: %v", err)
}
if n != 1 {
t.Fatalf("want 1 row pruned, got %d", n)
}
rows := readSendLog(t, st)
if len(rows) != 1 || rows[0].QueueID != "NEW" {
t.Fatalf("retention kept wrong rows: %+v", rows)
}
}