Files
nexarch/dms/internal/documentapi/handler_test.go
T
patrickandClaude Sonnet 5 43574f7872 DOC-17: malware-scan-vor-ablage
ClamAV-Anbindung (clamd-INSTREAM-Protokoll) als verpflichtender Scan-Schritt
vor Ablage. Fund fuehrt zu vollstaendiger Entfernung von Dateiobjekt und
Dokument plus Audit-Event statt stiller Ablage; Sichtbarkeit in
Listen/Direktzugriff gesperrt bis scan_status=clean. EICAR-Erkennung real
gegen installierten clamd verifiziert (dabei Null-Byte-Antwort-Bug
gefunden und behoben).

Nebenbei: fehlende trashed_at-Spalte in drei Test-Schemata (DOC-11-Luecke)
nachgetragen.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-09-18 00:41:52 +02:00

209 lines
8.0 KiB
Go

package documentapi
import (
"bytes"
"context"
"fmt"
"net/http"
"net/http/httptest"
"os"
"testing"
"time"
"github.com/jackc/pgx/v5/pgxpool"
dmscrypto "gitea.perlbach24.de/scripte/nexarch/dms/internal/crypto"
"gitea.perlbach24.de/scripte/nexarch/dms/internal/storage"
)
type fakeKEKProvider struct{ kek []byte }
func (f *fakeKEKProvider) TenantKEK(ctx context.Context, tenantSlug string) ([]byte, error) {
return f.kek, nil
}
type noopUsageReporter struct{}
func (noopUsageReporter) Report(ctx context.Context, tenantSlug, metric string, delta int64) error {
return nil
}
func setupTest(t *testing.T) (*httptest.Server, *pgxpool.Pool, *storage.Service, *dmscrypto.Service, string) {
t.Helper()
dsn := os.Getenv("TEST_TENANT_DSN")
if dsn == "" {
t.Skip("TEST_TENANT_DSN nicht gesetzt, Integrationstest uebersprungen")
}
ctx := context.Background()
pool, err := pgxpool.New(ctx, dsn)
if err != nil {
t.Fatalf("pool: %v", err)
}
t.Cleanup(func() { pool.Close() })
if _, err := pool.Exec(ctx, `
CREATE EXTENSION IF NOT EXISTS pgcrypto;
CREATE TABLE IF NOT EXISTS users (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(), email TEXT NOT NULL UNIQUE, name TEXT NOT NULL,
status TEXT NOT NULL DEFAULT 'active', created_at TIMESTAMPTZ NOT NULL DEFAULT now(), updated_at TIMESTAMPTZ NOT NULL DEFAULT now()
);
CREATE TABLE IF NOT EXISTS documents (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(), folder_id UUID,
title TEXT NOT NULL, current_revision_id UUID, created_by UUID NOT NULL REFERENCES users(id),
trashed_at TIMESTAMPTZ,
created_at TIMESTAMPTZ NOT NULL DEFAULT now(), updated_at TIMESTAMPTZ NOT NULL DEFAULT now(), deleted_at TIMESTAMPTZ
);
CREATE TABLE IF NOT EXISTS file_revisions (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(), document_id UUID NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
revision_number INT NOT NULL, storage_key TEXT NOT NULL, checksum_sha256 TEXT NOT NULL,
size_bytes BIGINT NOT NULL, mime_type TEXT NOT NULL, created_by UUID NOT NULL REFERENCES users(id),
created_at TIMESTAMPTZ NOT NULL DEFAULT now(), wrapped_dek BYTEA,
UNIQUE (document_id, revision_number)
);
CREATE TABLE IF NOT EXISTS revision_scans (
revision_id UUID PRIMARY KEY REFERENCES file_revisions(id) ON DELETE CASCADE,
status TEXT NOT NULL CHECK (status IN ('pending', 'processing', 'clean', 'infected')),
finding TEXT, created_at TIMESTAMPTZ NOT NULL DEFAULT now(), updated_at TIMESTAMPTZ NOT NULL DEFAULT now()
);
`); err != nil {
t.Fatalf("schema: %v", err)
}
t.Cleanup(func() {
_, _ = pool.Exec(context.Background(), `TRUNCATE revision_scans, file_revisions, documents, users CASCADE`)
})
storageSvc := storage.NewService(storage.NewLocalDriver(t.TempDir(), []byte("secret"), "https://files.example.test"), noopUsageReporter{}, "acme")
cryptoSvc := dmscrypto.NewService(&fakeKEKProvider{kek: bytes.Repeat([]byte{0x33}, dmscrypto.KEKSize)})
server := NewServer(pool, storageSvc, cryptoSvc, "acme")
mux := http.NewServeMux()
server.RegisterRoutes(mux)
httpServer := httptest.NewServer(mux)
t.Cleanup(httpServer.Close)
return httpServer, pool, storageSvc, cryptoSvc, "acme"
}
func createDocument(t *testing.T, pool *pgxpool.Pool, storageSvc *storage.Service, cryptoSvc *dmscrypto.Service, tenantSlug string, content []byte) string {
t.Helper()
ctx := context.Background()
var userID string
if err := pool.QueryRow(ctx, `
INSERT INTO users (email, name) VALUES ($1, 'Test-Benutzer') RETURNING id
`, fmt.Sprintf("docapi-test-%d@example.test", time.Now().UnixNano())).Scan(&userID); err != nil {
t.Fatalf("testbenutzer anlegen: %v", err)
}
var documentID string
if err := pool.QueryRow(ctx, `
INSERT INTO documents (title, created_by) VALUES ('Testdokument', $1) RETURNING id
`, userID).Scan(&documentID); err != nil {
t.Fatalf("dokument anlegen: %v", err)
}
env, err := cryptoSvc.Seal(ctx, tenantSlug, bytes.NewReader(content))
if err != nil {
t.Fatalf("seal: %v", err)
}
var buf bytes.Buffer
if _, err := buf.ReadFrom(env.Ciphertext); err != nil {
t.Fatalf("chiffretext lesen: %v", err)
}
storageKey := storage.ObjectKey(documentID, "1")
var revisionID string
if err := pool.QueryRow(ctx, `
INSERT INTO file_revisions (document_id, revision_number, storage_key, checksum_sha256, size_bytes, mime_type, created_by, wrapped_dek)
VALUES ($1, 1, $2, 'x', $3, 'application/octet-stream', $4, $5)
RETURNING id
`, documentID, storageKey, len(content), userID, env.WrappedDEK).Scan(&revisionID); err != nil {
t.Fatalf("revision anlegen: %v", err)
}
if _, err := pool.Exec(ctx, `UPDATE documents SET current_revision_id = $2 WHERE id = $1`, documentID, revisionID); err != nil {
t.Fatalf("aktuelle revision setzen: %v", err)
}
if _, err := storageSvc.Put(ctx, storageKey, bytes.NewReader(buf.Bytes()), int64(buf.Len()), "application/octet-stream"); err != nil {
t.Fatalf("objekt ablegen: %v", err)
}
return documentID
}
const minimalPDF = "%PDF-1.4\n1 0 obj<</Type/Catalog/Pages 2 0 R>>endobj\n2 0 obj<</Type/Pages/Kids[3 0 R]/Count 1>>endobj\n3 0 obj<</Type/Page/Parent 2 0 R/MediaBox[0 0 200 200]>>endobj\nxref\n0 4\n0000000000 65535 f \ntrailer<</Size 4/Root 1 0 R>>\nstartxref\n0\n%%EOF"
// Akzeptanzkriterium 1 + Pruefung: PDF wird ohne Download-Zwang
// ausgeliefert - korrekter, ueber Magic-Bytes bestimmter Content-Type und
// "inline" statt "attachment".
func TestHandleContent_ServesPDFInlineWithCorrectContentType(t *testing.T) {
server, pool, storageSvc, cryptoSvc, tenant := setupTest(t)
documentID := createDocument(t, pool, storageSvc, cryptoSvc, tenant, []byte(minimalPDF))
resp, err := http.Get(server.URL + "/documents/" + documentID + "/content")
if err != nil {
t.Fatalf("get: %v", err)
}
defer func() { _ = resp.Body.Close() }()
if resp.StatusCode != http.StatusOK {
t.Fatalf("status = %d, want 200", resp.StatusCode)
}
if ct := resp.Header.Get("Content-Type"); ct != "application/pdf" {
t.Errorf("content-type = %q, want application/pdf", ct)
}
disposition := resp.Header.Get("Content-Disposition")
if disposition != "inline" {
t.Errorf("content-disposition = %q, want \"inline\" (kein download-zwang)", disposition)
}
var buf bytes.Buffer
_, _ = buf.ReadFrom(resp.Body)
if buf.String() != minimalPDF {
t.Error("ausgelieferter inhalt stimmt nicht mit dem original ueberein")
}
}
// Akzeptanzkriterium 3 + Pruefung: grosse Dokumente werden seitenweise
// nachgeladen - echter HTTP-Range-Request liefert einen Teilbereich mit
// Status 206, nicht das gesamte Dokument.
func TestHandleContent_SupportsRangeRequestsForPartialLoading(t *testing.T) {
server, pool, storageSvc, cryptoSvc, tenant := setupTest(t)
// Groesserer, deterministischer Inhalt, damit ein Range-Request
// tatsaechlich nur einen Teil zurueckliefert.
content := bytes.Repeat([]byte("0123456789"), 10000) // 100.000 bytes
documentID := createDocument(t, pool, storageSvc, cryptoSvc, tenant, content)
req, _ := http.NewRequest(http.MethodGet, server.URL+"/documents/"+documentID+"/content", nil)
req.Header.Set("Range", "bytes=100-199")
resp, err := http.DefaultClient.Do(req)
if err != nil {
t.Fatalf("get: %v", err)
}
defer func() { _ = resp.Body.Close() }()
if resp.StatusCode != http.StatusPartialContent {
t.Fatalf("status = %d, want 206 (Partial Content)", resp.StatusCode)
}
var buf bytes.Buffer
_, _ = buf.ReadFrom(resp.Body)
if buf.Len() != 100 {
t.Fatalf("erwartet 100 bytes teilinhalt, hatte %d", buf.Len())
}
if !bytes.Equal(buf.Bytes(), content[100:200]) {
t.Error("teilinhalt stimmt nicht mit dem erwarteten byte-bereich des originals ueberein")
}
}
// Nachweis des Fehlerverhaltens: unbekanntes Dokument liefert 404, kein
// Absturz.
func TestHandleContent_UnknownDocumentReturns404(t *testing.T) {
server, _, _, _, _ := setupTest(t)
resp, err := http.Get(server.URL + "/documents/00000000-0000-0000-0000-000000000000/content")
if err != nil {
t.Fatalf("get: %v", err)
}
defer func() { _ = resp.Body.Close() }()
if resp.StatusCode != http.StatusNotFound {
t.Fatalf("status = %d, want 404", resp.StatusCode)
}
}