dorfteich/apps/api/src/import-export/pond-archive.e2e.db.test.ts
Claude Opus 5 1b992c8626
All checks were successful
CI / Lint, typecheck, test (pull_request) Successful in 7m22s
CI / Build container images (pull_request) Successful in 11s
CI / Auth e2e pack (pull_request) Successful in 9m39s
CI / Import/export fidelity gate (pull_request) Successful in 1m4s
#305: a full pond archive before deletion and before purge
Deleting a pond already had a strict prompt — typing the pond name, stricter
than a confirm dialog. That was never the gap. The gap is that the person who
deletes it loses access the moment they do: the pond leaves their view, only a
Site Admin can bring it back, and the export is no longer reachable for them.
So the archive is offered INSIDE the deletion flow, before the button.

What it contains, and why it is not the existing export:

- Every page the requester may read, as Markdown, as before.
- **Every attachment of the pond**, not only the embedded ones. An
  attachment nobody put on a page would otherwise vanish unnoticed — which
  is the whole reason this issue exists.
- `manifest.json`: pond settings (EFFECTIVE, defaults filled in — a
  preservation format must not require its reader to know Dorfteich's
  defaults), labels, the page hierarchy and sort keys, comments, and
  attachment metadata including the #199 hash so a reader can verify bytes.
  It extends the #210 manifest rather than adding a second descriptor, and
  carries an explicit `formatVersion`.
- `README.txt`, because the manifest is for machines: whoever unpacks a
  folder of Markdown a year from now must not believe they hold a one-click
  restore.

Decisions worth naming:

- **"Complete" describes the RESULT, not the route.** A pond admin who may
  read every page gets `complete: true`; only an archive that actually
  leaves pages out is incomplete. The Site-Admin route skips the read filter
  (an archive taken before an irreversible purge must not depend on which
  ponds the operator happens to be a member of) — those are two different
  questions and the first version of this conflated them.
- **The omission is named before the download**, with its number, in the UI
  and in the manifest. An archive silently missing content is worse than no
  archive, because it ends the search.
- **Not downloading stays allowed.** A pond of test pages should not require
  one, and the server cannot tell whether a file arrived anyway — so the
  finality is stated in text instead of enforced.
- **A plain link, not fetch-into-a-blob.** The api streams the ZIP; buffering
  a whole pond in the tab to draw a progress bar would trade memory for
  cosmetics. The browser reports progress and completion; what it cannot say
  — that the archive is being BUILT — is announced in a live region.
- Read trail unchanged in kind (ADR 0023): one `export` event per classified
  page before any classified byte enters the stream. Attachments never travel
  without their page, so the same events cover them.
- New audit action `pond.archived` (catalogue v1.7) with page and attachment
  counts, omitted pages, and completeness.

Format documented in `docs/architecture/pond-archive-format.md`, including
what is deliberately NOT in it (history, permissions, trash).

Verified by hand, not only asserted: a real pond's archive downloaded and
unpacked — README, manifest, three page files, the media file; the manifest's
effective settings, per-page classification, the VS-NfD frontmatter and
marking preserved in the classified page's Markdown, and the attachment's
sha256 present. Plus six api tests (including that an unembedded attachment
travels and that a Site Admin gets a complete archive without membership) and
the a11y pack 11/11 in both schemes, which now also scans the pond settings
screen.

Not done, because there is nothing to attach it to: the Site Admin's purge
dialog (#193) exists only as an api endpoint — there is no pond-trash UI in
the web app. The api half is here and tested, so it becomes a link when that
screen is built.
2026-08-01 19:36:10 +02:00

251 lines
9.5 KiB
TypeScript

import { INestApplication } from '@nestjs/common';
import { PondArchiveManifest } from '@dorfteich/shared';
import { PrismaClient } from '@prisma/client';
import { unzipSync } from 'fflate';
import request from 'supertest';
import { afterAll, beforeAll, describe, expect, it } from 'vitest';
import { AuthTokensService } from '../auth/auth-tokens.service';
import { FilesService } from '../files/files.service';
import { createTestApp, sessionCookieOf } from '../testing/test-app';
import { createTestPrisma, deletePondsWhere, hasTestDb, uniqueSuffix } from '../testing/test-db';
import { UsersService } from '../users/users.service';
const PNG_BASE64 =
'iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAC0lEQVR42mP8z8BQDwAEhQGAhKmMIQAAAABJRU5ErkJggg==';
function entries(buffer: Buffer): Record<string, Uint8Array> {
return unzipSync(new Uint8Array(buffer));
}
/** supertest parses text by default — a ZIP has to be collected as bytes. */
function asBinary(req: request.Test): request.Test {
return req.parse((res, cb) => {
const chunks: Buffer[] = [];
res.on('data', (chunk: Buffer) => chunks.push(chunk));
res.on('end', () => cb(null, Buffer.concat(chunks)));
});
}
function manifestOf(buffer: Buffer): PondArchiveManifest {
const raw = entries(buffer)['manifest.json'];
return JSON.parse(Buffer.from(raw!).toString('utf8')) as PondArchiveManifest;
}
/**
* The full pond archive (issue #305). What separates it from the Markdown
* export is exactly what is asserted here: EVERY attachment travels, not only
* the embedded ones, and the manifest carries what Markdown cannot — settings,
* labels, comments and the hierarchy.
*/
describe.skipIf(!hasTestDb)('pond archive (e2e, issue #305)', () => {
let app: INestApplication;
let prisma: PrismaClient;
let files: FilesService;
const suffix = uniqueSuffix();
const password = 'archiviere den ganzen teich 1';
const owner = { username: `arch-${suffix}` };
const admin = { username: `archadm-${suffix}` };
let ownerId: string;
let ownerCookie: string;
let adminCookie: string;
let pondId: string;
let parentPageId: string;
const api = () => request(app.getHttpServer());
beforeAll(async () => {
prisma = createTestPrisma();
await prisma.rateLimit.deleteMany({});
app = await createTestApp();
files = app.get(FilesService);
const users = app.get(UsersService);
const tokens = app.get(AuthTokensService);
const ownerUser = await users.createUser({
username: owner.username,
email: `${owner.username}@example.org`,
displayName: `Archive Owner ${suffix}`,
password,
locale: 'en',
});
ownerId = ownerUser.id;
await api()
.post('/api/v1/auth/verify-email')
.send({ token: await tokens.issue(ownerUser.id, 'EMAIL_VERIFICATION', 600) })
.expect(204);
ownerCookie = sessionCookieOf(
await api()
.post('/api/v1/auth/login')
.send({ usernameOrEmail: owner.username, password })
.expect(200),
);
const adminUser = await users.createUser({
username: admin.username,
email: `${admin.username}@example.org`,
displayName: `Archive Admin ${suffix}`,
password,
locale: 'en',
});
await users.markEmailVerified(adminUser.id);
await prisma.user.update({ where: { id: adminUser.id }, data: { isSiteAdmin: true } });
adminCookie = sessionCookieOf(
await api()
.post('/api/v1/auth/login')
.send({ usernameOrEmail: admin.username, password })
.expect(200),
);
pondId = (await prisma.pond.findFirstOrThrow({ where: { ownerId, type: 'PERSONAL' } })).id;
// A parent and a child page, so the hierarchy has something to state.
const parent = await prisma.page.create({
data: {
pondId,
title: 'Archive Parent',
slug: 'archive-parent',
ydocState: new Uint8Array(),
sortKey: 'a',
createdBy: ownerId,
contentCache: {
create: { plainText: 'Parent body', markdown: 'Parent body', html: '', outline: [] },
},
},
});
parentPageId = parent.id;
await prisma.page.create({
data: {
pondId,
parentId: parent.id,
title: 'Archive Child',
slug: 'archive-child',
ydocState: new Uint8Array(),
sortKey: 'b',
createdBy: ownerId,
contentCache: {
create: { plainText: 'Child body', markdown: 'Child body', html: '', outline: [] },
},
},
});
const label = await prisma.label.create({
data: { pondId, name: `Archive Label ${suffix}`, color: '#2f6f4f' },
});
await prisma.pageLabel.create({ data: { pageId: parent.id, labelId: label.id } });
await prisma.comment.create({
data: { pageId: parent.id, authorId: ownerId, body: 'A remark worth keeping.' },
});
});
afterAll(async () => {
const where = { pond: { owner: { username: { contains: suffix } } } };
await prisma.comment.deleteMany({ where: { page: where } });
await prisma.attachment.deleteMany({ where });
await prisma.pageLabel.deleteMany({ where: { page: where } });
await prisma.label.deleteMany({ where });
await prisma.page.deleteMany({ where });
await prisma.roleGrant.deleteMany({ where });
await deletePondsWhere(prisma, { owner: { username: { contains: suffix } } });
await prisma.user.deleteMany({ where: { username: { contains: suffix } } });
await prisma.$disconnect();
await app.close();
});
it('contains EVERY attachment, not only the embedded ones', async () => {
// The gap this whole issue exists for: an attachment nobody embedded
// would vanish unnoticed with the Markdown export.
const orphan = await files.upload({ id: ownerId } as never, pondId, {
buffer: Buffer.from(PNG_BASE64, 'base64'),
size: 70,
originalname: 'never-embedded.png',
} as never);
const res = await asBinary(api().get(`/api/v1/ponds/${pondId}/archive`))
.set('Cookie', ownerCookie)
.expect(200);
expect(res.headers['content-type']).toContain('application/zip');
const names = Object.keys(entries(res.body as Buffer));
expect(names).toContain('manifest.json');
expect(names).toContain('README.txt');
expect(names).toContain('pages/archive-parent.md');
expect(names).toContain('pages/archive-child.md');
expect(names.some((name) => name.startsWith(`media/${orphan.id}.`))).toBe(true);
const manifest = manifestOf(res.body as Buffer);
expect(manifest.attachments.map((a) => a.id)).toContain(orphan.id);
// The Markdown export would have shipped no media at all here.
expect(manifest.attachments.length).toBeGreaterThan(0);
});
it('states the hierarchy, labels, comments and settings in the manifest', async () => {
const res = await asBinary(api().get(`/api/v1/ponds/${pondId}/archive`))
.set('Cookie', ownerCookie)
.expect(200);
const manifest = manifestOf(res.body as Buffer);
expect(manifest.kind).toBe('dorfteich-pond-archive');
expect(manifest.formatVersion).toBe(1);
expect(manifest.complete).toBe(true);
expect(manifest.omittedPages).toBe(0);
const child = manifest.pages.find((page) => page.slug === 'archive-child');
// The hierarchy is exactly what a folder of Markdown cannot express.
expect(child?.parentId).toBe(parentPageId);
expect(manifest.labels.some((label) => label.name.includes(suffix))).toBe(true);
expect(manifest.comments.map((comment) => comment.body)).toContain('A remark worth keeping.');
// A display name, not an account id — the archive outlives the account.
expect(manifest.comments[0]?.author).toContain('Archive Owner');
// Pond settings ride along; fonts are always present through the schema
// defaults, so their presence proves the settings object is real.
expect(manifest.pond.settings).toHaveProperty('fonts');
});
it('tells a requester before the download how much they would get', async () => {
const preview = await api()
.get(`/api/v1/ponds/${pondId}/archive/preview`)
.set('Cookie', ownerCookie)
.expect(200);
expect(preview.body.omittedPages).toBe(0);
expect(preview.body.includedPages).toBe(preview.body.totalPages);
expect(preview.body.complete).toBe(true);
});
it('audits the download with counts and completeness', async () => {
await asBinary(api().get(`/api/v1/ponds/${pondId}/archive`))
.set('Cookie', ownerCookie)
.expect(200);
const entry = await prisma.auditEntry.findFirst({
where: { action: 'pond.archived', targetId: pondId },
orderBy: { at: 'desc' },
});
expect(entry).not.toBeNull();
expect(entry!.details).toMatchObject({ complete: true, omittedPages: 0 });
});
it('gives the Site Admin a complete archive without pond membership', async () => {
// The purge dialog's archive must not depend on which ponds the operator
// happens to be a member of — this admin is a member of none.
const preview = await api()
.get(`/api/v1/admin/trash/ponds/${pondId}/archive/preview`)
.set('Cookie', adminCookie)
.expect(200);
expect(preview.body.complete).toBe(true);
expect(preview.body.omittedPages).toBe(0);
const res = await asBinary(api().get(`/api/v1/admin/trash/ponds/${pondId}/archive`))
.set('Cookie', adminCookie)
.expect(200);
expect(manifestOf(res.body as Buffer).pages.length).toBe(preview.body.totalPages);
});
it('keeps the admin archive away from an ordinary pond admin', async () => {
await api()
.get(`/api/v1/admin/trash/ponds/${pondId}/archive`)
.set('Cookie', ownerCookie)
.expect(403);
});
});