Mail-Graveyard/backend/06-mbox_test.go
DonVoo 9f5cc59af7 Stabilize mail identity: canonical hash, index drift, HTML panic
Behebt drei Fehler derselben Klasse: an jeder Stelle wurde derselbe Wert
zweimal berechnet, statt einmal berechnet und weitergereicht - und die
beiden Berechnungen liefen auseinander.

1. Instabiler Ersatzschluessel (bug-hashkey-instabil.md)
   Mails ohne Message-ID bekamen sha256 ueber die IMAP-Rohbytes, der
   Reindex hashte dieselbe Mail ueber die mbox-gespeicherten Bytes
   (>From-Quoting, andere Zeilenenden) -> zwei Schluessel, 4.024
   Doppel-Eintraege in copied.
   Fix: canonicalMessageBytes() bringt beide Seiten auf eine Form
   (>From zurueckdrehen, CRLF->LF, Trailing-Newlines weg). Alle Pfade
   (Index, Migration, Viewer, Dedup) nutzen dieselbe Funktion.
   body_sha256 in copied + mbox_index, UNIQUE erweitert.

2. Index-Drift (bug-index-drift.md)
   Der plain-mbox-Reader las nach Datei-Position statt nach dem
   gespeicherten file_offset. Weil SQLITE_BUSY (busy_timeout=0) je
   Ordner einen Index-Eintrag verschluckt hatte, war ab dieser Luecke
   alles um 1 verschoben: Klick auf Mail X zeigte Mail X+1.
   Betroffen genau die 6 Ordner mit Busy-Fehler beim Rettungslauf.
   Fix: busy_timeout=10000, Lesen ueber file_offset, --reindex --rebuild.

3. HTML-Vorschau-Panic (bug-htmltotext-panic.md)
   replaceCaseInsensitive/stripHTMLBlock indizierten mit Offsets aus
   strings.ToLower(s) in s - ToLower ist nicht byte-laengen-erhaltend
   (z.B. U+0130). ~0,1% der Mails brachten die Vorschau zum Absturz.
   Fix: asciiFoldIndex() sucht direkt auf den Original-Bytes; zusaetzlich
   Rohtext-Fallback, damit keine archivierte Mail unsichtbar wird.

Weiter: Archiv-zuerst-Reihenfolge (mbox_done/target_done) - ein
sterbendes Ziel kostet keine Archiv-Kopie mehr; Dedup vergleicht
zusaetzlich den Inhalt und schuetzt byte-verschiedene Varianten.

WICHTIG: Die 62.073 alten Alias-Zeilen in copied bleiben bewusst
erhalten. Sie sehen wie Muell aus, sind aber die Zeilen, auf die der
alte Schluessel matcht - ein Loeschen wuerde Mails erneut in fremde
Postfaecher kopieren.

Verifiziert: go test ./... gruen; 58.051 Archivmails, 0 ohne
copied-Zeile; Drift 0 ueber alle 69 Ordner; 2.000 HTTP-Stichproben
ueber 8 Ordner: 0 falsche Zuordnung, 0 Panics; Watcher 220 + 60 Mails
archived=0 target=0 errors=0. Live als Image fix-identity2-20260716.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-16 13:22:27 +02:00

540 lines
17 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

package backend
import (
"bytes"
"database/sql"
"os"
"path/filepath"
"strings"
"testing"
"time"
"github.com/klauspost/compress/zstd"
)
func TestZstdMboxRoundTripAndIndexRead(t *testing.T) {
oldCfg, oldDB := Cfg, DB
root := t.TempDir()
t.Cleanup(func() {
if DB != nil {
_ = DB.Close()
}
Cfg, DB = oldCfg, oldDB
})
Cfg = Config{
DBPath: filepath.Join(root, "mail-graveyard.db"),
MboxRoot: filepath.Join(root, "backup"),
MboxCompression: "zstd",
}
if err := ConnectDB(true); err != nil {
t.Fatal(err)
}
if err := SaveArchiveMailbox("archive"); err != nil {
t.Fatal(err)
}
if err := SaveAccount(Account{
Name: "test-account",
SrcHost: "source.example",
SrcPort: 993,
SrcSecurity: "tls",
SrcUser: "source@example.com",
SrcPass: "x",
DstHost: "target.example",
DstPort: 993,
DstSecurity: "tls",
DstUser: "target@example.com",
DstPass: "x",
MboxDir: "archive",
Active: true,
}); err != nil {
t.Fatal(err)
}
account, err := GetAccount("test-account")
if err != nil {
t.Fatal(err)
}
msg := RawMessage{
MessageID: "zstd-test@example.com",
InternalDate: time.Date(2026, 7, 14, 10, 11, 12, 0, time.UTC),
Body: []byte("Message-ID: <zstd-test@example.com>\r\n" +
"From: Sender <sender@example.com>\r\n" +
"Subject: Zstd Test\r\n" +
"Date: Tue, 14 Jul 2026 10:11:12 +0000\r\n" +
"\r\n" +
"Hello\r\nFrom inside body\r\n"),
}
writer, err := NewMboxWriter(filepath.Join(Cfg.MboxRoot, "archive"))
if err != nil {
t.Fatal(err)
}
info, err := writer.Append("INBOX", msg)
if err != nil {
t.Fatal(err)
}
if err := SaveMboxIndex(MboxIndexEntry{
AccountID: account.ID,
Folder: "INBOX",
MessageID: msg.MessageID,
Subject: info.Subject,
From: info.From,
Date: info.Date,
FileOffset: info.FileOffset,
FrameLen: info.FrameLen,
InnerOffset: info.InnerOffset,
InnerLen: info.InnerLen,
}); err != nil {
t.Fatal(err)
}
compressed, err := os.ReadFile(info.Path)
if err != nil {
t.Fatal(err)
}
dec, err := zstd.NewReader(nil)
if err != nil {
t.Fatal(err)
}
defer dec.Close()
plain, err := dec.DecodeAll(compressed, nil)
if err != nil {
t.Fatal(err)
}
if want := mboxRecord(msg); !bytes.Equal(plain, want) {
t.Fatalf("zstd round-trip differs: got %d bytes, want %d", len(plain), len(want))
}
entries, err := ReadMboxList(info.Path)
if err != nil {
t.Fatal(err)
}
if len(entries) != 1 || entries[0].Index != 0 || entries[0].Subject != "Zstd Test" {
t.Fatalf("unexpected index list: %#v", entries)
}
raw, err := ReadMboxMessage(info.Path, entries[0].Index)
if err != nil {
t.Fatal(err)
}
if !bytes.Contains(raw, []byte("Hello")) || bytes.Contains(raw, []byte(">From inside body")) {
t.Fatalf("unexpected message body: %q", raw)
}
}
func TestPlainMboxPartialIndexIsRebuiltBeforeList(t *testing.T) {
oldCfg, oldDB := Cfg, DB
root := t.TempDir()
t.Cleanup(func() {
if DB != nil {
_ = DB.Close()
}
Cfg, DB = oldCfg, oldDB
})
Cfg = Config{
DBPath: filepath.Join(root, "mail-graveyard.db"),
MboxRoot: filepath.Join(root, "backup"),
MboxCompression: "none",
}
if err := ConnectDB(true); err != nil {
t.Fatal(err)
}
if err := SaveArchiveMailbox("archive"); err != nil {
t.Fatal(err)
}
if err := SaveAccount(Account{
Name: "test-account",
SrcHost: "source.example",
SrcPort: 993,
SrcSecurity: "tls",
SrcUser: "source@example.com",
SrcPass: "x",
DstHost: "target.example",
DstPort: 993,
DstSecurity: "tls",
DstUser: "target@example.com",
DstPass: "x",
MboxDir: "archive",
Active: true,
}); err != nil {
t.Fatal(err)
}
account, err := GetAccount("test-account")
if err != nil {
t.Fatal(err)
}
writer, err := NewMboxWriter(filepath.Join(Cfg.MboxRoot, "archive"))
if err != nil {
t.Fatal(err)
}
first := testRawMessage("first@example.com", "First")
firstInfo, err := writer.Append("INBOX", first)
if err != nil {
t.Fatal(err)
}
if err := SaveMboxIndex(MboxIndexEntry{
AccountID: account.ID,
Folder: "INBOX",
MessageID: first.MessageID,
Subject: firstInfo.Subject,
From: firstInfo.From,
Date: firstInfo.Date,
FileOffset: firstInfo.FileOffset,
FrameLen: firstInfo.FrameLen,
InnerOffset: firstInfo.InnerOffset,
InnerLen: firstInfo.InnerLen,
}); err != nil {
t.Fatal(err)
}
if err := UpdateMboxIndexState(account.ID, "INBOX", firstInfo.FileOffset+firstInfo.FrameLen); err != nil {
t.Fatal(err)
}
if _, err := writer.Append("INBOX", testRawMessage("second@example.com", "Second")); err != nil {
t.Fatal(err)
}
entries, err := ReadMboxList(firstInfo.Path)
if err != nil {
t.Fatal(err)
}
if len(entries) != 2 {
t.Fatalf("expected rebuilt full list with 2 entries, got %#v", entries)
}
if entries[0].Subject != "Second" || entries[1].Subject != "First" {
t.Fatalf("unexpected entries after reindex: %#v", entries)
}
}
func TestReadMboxMessagesBytesClonesBufferRecords(t *testing.T) {
mbox := []byte(strings.Join([]string{
"From one@example.com Tue Jul 14 10:00:00 2026",
"Message-ID: <one@example.com>",
"Subject: One",
"",
"short",
"From two@example.com Tue Jul 14 10:01:00 2026",
"Message-ID: <two@example.com>",
"Subject: Two",
"",
"this message is deliberately much longer than the first one",
"and has another line",
"From three@example.com Tue Jul 14 10:02:00 2026",
"Message-ID: <three@example.com>",
"Subject: Three",
"",
"tiny",
"",
}, "\n"))
msgs := readMboxMessagesBytes(mbox)
if len(msgs) != 3 {
t.Fatalf("expected 3 messages, got %d", len(msgs))
}
wants := []string{"Subject: One", "Subject: Two", "Subject: Three"}
for i, want := range wants {
if !bytes.Contains(msgs[i], []byte(want)) {
t.Fatalf("message %d does not contain %q: %q", i, want, msgs[i])
}
}
if bytes.Contains(msgs[0], []byte("Subject: Two")) || bytes.Contains(msgs[1], []byte("Subject: Three")) {
t.Fatalf("messages share buffer contents: %#q", msgs)
}
}
func TestPlainIndexedReadUsesOffsetAcrossMissingMiddleIndex(t *testing.T) {
oldCfg, oldDB := Cfg, DB
root := t.TempDir()
t.Cleanup(func() {
if DB != nil {
_ = DB.Close()
}
Cfg, DB = oldCfg, oldDB
})
Cfg = Config{DBPath: filepath.Join(root, "mail-graveyard.db"), MboxRoot: filepath.Join(root, "backup")}
if err := ConnectDB(true); err != nil {
t.Fatal(err)
}
if err := SaveArchiveMailbox("archive"); err != nil {
t.Fatal(err)
}
if err := SaveAccount(Account{
Name: "test-account", SrcHost: "source.example", SrcPort: 993, SrcSecurity: "tls", SrcUser: "source@example.com", SrcPass: "x",
DstHost: "target.example", DstPort: 993, DstSecurity: "tls", DstUser: "target@example.com", DstPass: "x", MboxDir: "archive", Active: true,
}); err != nil {
t.Fatal(err)
}
account, err := GetAccount("test-account")
if err != nil {
t.Fatal(err)
}
writer, err := NewMboxWriter(filepath.Join(Cfg.MboxRoot, "archive"))
if err != nil {
t.Fatal(err)
}
firstInfo, err := writer.Append("INBOX", testRawMessage("first@example.com", "First"))
if err != nil {
t.Fatal(err)
}
if err := SaveMboxIndex(MboxIndexEntry{AccountID: account.ID, Folder: "INBOX", MessageID: "first@example.com", Subject: "First", FileOffset: firstInfo.FileOffset, FrameLen: firstInfo.FrameLen, InnerOffset: firstInfo.InnerOffset, InnerLen: firstInfo.InnerLen}); err != nil {
t.Fatal(err)
}
if _, err := writer.Append("INBOX", testRawMessage("missing@example.com", "Missing middle")); err != nil {
t.Fatal(err)
}
thirdInfo, err := writer.Append("INBOX", testRawMessage("third@example.com", "Third"))
if err != nil {
t.Fatal(err)
}
if err := SaveMboxIndex(MboxIndexEntry{AccountID: account.ID, Folder: "INBOX", MessageID: "third@example.com", Subject: "Third", FileOffset: thirdInfo.FileOffset, FrameLen: thirdInfo.FrameLen, InnerOffset: thirdInfo.InnerOffset, InnerLen: thirdInfo.InnerLen}); err != nil {
t.Fatal(err)
}
if err := UpdateMboxIndexState(account.ID, "INBOX", thirdInfo.FileOffset+thirdInfo.FrameLen); err != nil {
t.Fatal(err)
}
raw, err := ReadMboxMessage(thirdInfo.Path, 1)
if err != nil {
t.Fatal(err)
}
if !bytes.Contains(raw, []byte("Subject: Third")) || bytes.Contains(raw, []byte("Missing middle")) {
t.Fatalf("indexed read drifted to the file position: %q", raw)
}
if err := ReindexMboxFile(account.ID, "INBOX", thirdInfo.Path); err != nil {
t.Fatal(err)
}
for i, subject := range []string{"First", "Missing middle", "Third"} {
raw, err := ReadMboxMessage(thirdInfo.Path, i)
if err != nil {
t.Fatalf("rebuilt index %d: %v", i, err)
}
if !bytes.Contains(raw, []byte("Subject: "+subject)) {
t.Fatalf("rebuilt index %d returned wrong message: %q", i, raw)
}
}
}
func TestConnectDBConfiguresBusyTimeoutAndCopyStages(t *testing.T) {
oldCfg, oldDB := Cfg, DB
root := t.TempDir()
t.Cleanup(func() {
if DB != nil {
_ = DB.Close()
}
Cfg, DB = oldCfg, oldDB
})
Cfg = Config{DBPath: filepath.Join(root, "mail-graveyard.db"), MboxRoot: filepath.Join(root, "backup")}
if err := ConnectDB(true); err != nil {
t.Fatal(err)
}
var timeout int
if err := DB.QueryRow(`PRAGMA busy_timeout`).Scan(&timeout); err != nil {
t.Fatal(err)
}
if timeout != 10000 {
t.Fatalf("busy_timeout=%d, want 10000", timeout)
}
if err := SaveAccount(Account{
Name: "stage-account", SrcHost: "source.example", SrcPort: 993, SrcSecurity: "tls", SrcUser: "source@example.com", SrcPass: "x",
DstHost: "target.example", DstPort: 993, DstSecurity: "tls", DstUser: "target@example.com", DstPass: "x", Active: true,
}); err != nil {
t.Fatal(err)
}
account, err := GetAccount("stage-account")
if err != nil {
t.Fatal(err)
}
if err := MarkMboxCopied(account.ID, "INBOX", "stage@example.com"); err != nil {
t.Fatal(err)
}
state, err := GetCopyState(account.ID, "INBOX", "stage@example.com")
if err != nil {
t.Fatal(err)
}
if !state.MboxDone || state.TargetDone {
t.Fatalf("unexpected mbox-only state: %#v", state)
}
if err := MarkTargetCopied(account.ID, "INBOX", "stage@example.com"); err != nil {
t.Fatal(err)
}
state, err = GetCopyState(account.ID, "INBOX", "stage@example.com")
if err != nil {
t.Fatal(err)
}
if !state.MboxDone || !state.TargetDone {
t.Fatalf("unexpected completed state: %#v", state)
}
first := MessageIdentity{MessageID: "reused@example.com", BodySHA256: bodySHA256([]byte("first"))}
second := MessageIdentity{MessageID: "reused@example.com", BodySHA256: bodySHA256([]byte("second"))}
if err := MarkIdentityCopied(account.ID, "INBOX", first); err != nil {
t.Fatal(err)
}
state, err = GetCopyIdentityState(account.ID, "INBOX", second)
if err != nil {
t.Fatal(err)
}
if state.MboxDone || state.TargetDone {
t.Fatalf("byte-different message with reused ID was hidden: %#v", state)
}
}
func TestIdentitySchemaUpgradePreservesLegacyAliases(t *testing.T) {
oldCfg, oldDB := Cfg, DB
root := t.TempDir()
path := filepath.Join(root, "legacy.db")
rawDB, err := sql.Open("sqlite", path)
if err != nil {
t.Fatal(err)
}
legacySchema := []string{
`CREATE TABLE accounts(id INTEGER PRIMARY KEY)`,
`INSERT INTO accounts(id) VALUES(7)`,
`CREATE TABLE copied(account_id INTEGER NOT NULL, folder TEXT NOT NULL, message_id TEXT NOT NULL, mbox_done INTEGER NOT NULL DEFAULT 1, target_done INTEGER NOT NULL DEFAULT 1, copied_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP, UNIQUE(account_id, folder, message_id))`,
`INSERT INTO copied(account_id, folder, message_id, mbox_done, target_done) VALUES(7, 'INBOX.Newbies ', 'sha256:legacy-raw', 1, 0)`,
`CREATE TABLE mbox_index(account_id INTEGER NOT NULL, folder TEXT NOT NULL, seq INTEGER NOT NULL, message_id TEXT NOT NULL, subject TEXT NOT NULL DEFAULT '', from_addr TEXT NOT NULL DEFAULT '', date TEXT NOT NULL DEFAULT '', file_offset INTEGER NOT NULL, frame_len INTEGER NOT NULL, inner_offset INTEGER NOT NULL DEFAULT 0, inner_len INTEGER NOT NULL, UNIQUE(account_id, folder, message_id))`,
`INSERT INTO mbox_index(account_id, folder, seq, message_id, file_offset, frame_len, inner_len) VALUES(7, 'INBOX.Newbies ', 0, 'sha256:legacy-raw', 0, 10, 10)`,
`CREATE TABLE mbox_index_state(account_id INTEGER NOT NULL, folder TEXT NOT NULL, indexed_bytes INTEGER NOT NULL DEFAULT 0, UNIQUE(account_id, folder))`,
`INSERT INTO mbox_index_state(account_id, folder, indexed_bytes) VALUES(7, 'INBOX.Newbies ', 10)`,
}
for _, stmt := range legacySchema {
if _, err := rawDB.Exec(stmt); err != nil {
_ = rawDB.Close()
t.Fatal(err)
}
}
if err := rawDB.Close(); err != nil {
t.Fatal(err)
}
if DB != nil {
_ = DB.Close()
}
t.Cleanup(func() {
if DB != nil {
_ = DB.Close()
}
Cfg, DB = oldCfg, oldDB
})
Cfg = Config{DBPath: path, MboxRoot: filepath.Join(root, "backup")}
if err := ConnectDB(false); err != nil {
t.Fatal(err)
}
var messageID, bodyHash string
var mboxDone, targetDone int
if err := DB.QueryRow(`SELECT message_id, body_sha256, mbox_done, target_done FROM copied WHERE account_id=7`).Scan(&messageID, &bodyHash, &mboxDone, &targetDone); err != nil {
t.Fatal(err)
}
if messageID != "sha256:legacy-raw" || bodyHash != "" || mboxDone != 1 || targetDone != 0 {
t.Fatalf("legacy alias changed during upgrade: id=%q hash=%q stages=%d/%d", messageID, bodyHash, mboxDone, targetDone)
}
var indexedBytes int64
if err := DB.QueryRow(`SELECT indexed_bytes FROM mbox_index_state WHERE account_id=7 AND folder='INBOX.Newbies '`).Scan(&indexedBytes); err != nil {
t.Fatal(err)
}
if indexedBytes != -1 {
t.Fatalf("identity-less index was not invalidated: %d", indexedBytes)
}
stableHash := bodySHA256([]byte("archived body"))
if err := ReplaceMboxIndex(7, "INBOX.Newbies", []MboxIndexEntry{{BodySHA256: stableHash, FrameLen: 10, InnerLen: 10}}, 10); err != nil {
t.Fatal(err)
}
if err := DB.QueryRow(`SELECT mbox_done, target_done FROM copied WHERE account_id=7 AND folder='INBOX.Newbies' AND message_id='' AND body_sha256=?`, stableHash).Scan(&mboxDone, &targetDone); err != nil {
t.Fatal(err)
}
if mboxDone != 1 || targetDone != 0 {
t.Fatalf("reindex lost pending target state from legacy alias: %d/%d", mboxDone, targetDone)
}
if err := RemoveMboxIndexFolderAliases(7, map[string]bool{"INBOX.Newbies": true}); err != nil {
t.Fatal(err)
}
var staleIndex, preservedAlias int
if err := DB.QueryRow(`SELECT count(*) FROM mbox_index WHERE account_id=7 AND folder='INBOX.Newbies '`).Scan(&staleIndex); err != nil {
t.Fatal(err)
}
if err := DB.QueryRow(`SELECT count(*) FROM copied WHERE account_id=7 AND folder='INBOX.Newbies ' AND message_id='sha256:legacy-raw'`).Scan(&preservedAlias); err != nil {
t.Fatal(err)
}
if staleIndex != 0 || preservedAlias != 1 {
t.Fatalf("folder alias cleanup stale_index=%d preserved_copy_alias=%d", staleIndex, preservedAlias)
}
}
func TestHTMLToTextHandlesUnicodeBeforeCaseInsensitiveTags(t *testing.T) {
tests := []struct {
name string
in string
want []string
drop []string
}{
{
name: "turkish dotted i",
in: "<p>Turkish İ test</p><BR>x",
want: []string{"Turkish İ test", "x"},
},
{
name: "kelvin sign",
in: "<DIV>Kelvin test</DIV><Br/>x",
want: []string{"Kelvin test", "x"},
},
{
name: "mixed blocks and repeated replacements",
in: "İ<style>bad </STYLE><P>first</P><script>bad İ</SCRIPT><DIV>second</DIV><BR />third",
want: []string{"İ", "first", "", "second", "third"},
drop: []string{"bad"},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := htmlToText(tt.in)
for _, want := range tt.want {
if !strings.Contains(got, want) {
t.Fatalf("htmlToText(%q) = %q, missing %q", tt.in, got, want)
}
}
for _, drop := range tt.drop {
if strings.Contains(got, drop) {
t.Fatalf("htmlToText(%q) = %q, unexpectedly contains %q", tt.in, got, drop)
}
}
})
}
}
func TestASCIIFoldIndexReturnsOriginalByteOffset(t *testing.T) {
for _, tt := range []struct {
s string
needle string
want int
}{
{"İİ<BR>x", "<br>", len("İİ")},
{"</DIV>", "</div>", len("")},
{"prefix<Br />suffix", "<br />", len("prefix")},
} {
if got := asciiFoldIndex(tt.s, tt.needle); got != tt.want {
t.Fatalf("asciiFoldIndex(%q, %q) = %d, want %d", tt.s, tt.needle, got, tt.want)
}
}
}
func TestMessageBodyPanicFallsBackToRawMessage(t *testing.T) {
raw := []byte("Subject: Evidence\r\n\r\nraw body")
got := renderMessageBodySafely(raw, "test account=archive folder=INBOX seq=7", func() string {
panic("synthetic parser failure")
})
if !strings.Contains(got, "Darstellung fehlgeschlagen") || !strings.Contains(got, string(raw)) {
t.Fatalf("panic fallback did not preserve raw message: %q", got)
}
}
func testRawMessage(id, subject string) RawMessage {
return RawMessage{
MessageID: id,
InternalDate: time.Date(2026, 7, 14, 10, 11, 12, 0, time.UTC),
Body: []byte("Message-ID: <" + id + ">\r\n" +
"From: Sender <sender@example.com>\r\n" +
"Subject: " + subject + "\r\n" +
"Date: Tue, 14 Jul 2026 10:11:12 +0000\r\n" +
"\r\n" +
"Hello\r\n"),
}
}