Compare commits

3 Commits
Author SHA1 Message Date
sneak 76141ae919 feat(library/store): on-disk JSON metadata store for the local cache
check / check (push) Successful in 13s
Add `MetadataStore` (src/library/store.ts): one metadata.json holding the
user id, schema version, collections cursor, and decrypted collection and
file records. Loaded whole into RAM with Maps for id lookups; rewritten
whole through the download layer's fsync atomic writer (temp, fsync,
rename, dir fsync). Binary keys are base64-encoded on disk. A missing,
unparseable, or wrong-schema file loads as an empty store, because the
file is only a cache the refresh unit repopulates. Directory 0700, file
0600, matching session.json. No lock file; no sync() beyond the writer.

This unit only stores; issue 42's refresh unit populates it. (closes #41)

Model: opus-4-8
2026-09-22 10:46:17 +00:00
sneak 15ceac857a test(library/store): metadata store round-trip, empty-on-corrupt, perms
Failing first: the on-disk JSON metadata store does not exist yet. These
tests fix its contract before the implementation lands — round-trip
fidelity including the binary keys, missing/corrupt files loading empty, a
schema-version mismatch discarded as stale cache, atomic writes leaving no
temp sibling, and directory 0700 / file 0600 permissions.

Model: opus-4-8
2026-09-22 10:46:02 +00:00
clawbot 42a6c17d49 Resumable, deletion-aware collection and file enumeration (closes #38)
check / check (push) Successful in 24s
Adds collectionsSince/filesSince taking a starting cursor, returning the resumable max-updationTime cursor and a separate list of tombstoned ids; filesSince throws instead of looping when the server reports hasMore without advancing (closes #7). listCollections/listFiles stay as thin, unaffected wrappers.

Model: opus-4-8
2026-09-22 12:37:09 +02:00
6 changed files with 924 additions and 33 deletions
+9
View File
@@ -18,6 +18,15 @@ Update the README API reference section to match the current implementation.
# Completed Steps
- 2026-09-22: Added resumable, deletion-aware enumeration to `Client` (issue 38,
closes issue 7). `collectionsSince`/`filesSince` take a starting cursor,
decrypt live records, surface tombstoned ids in a separate `deleted` list (a
tombstone has nothing to decrypt, so it is a bare id, not a hollow record),
and return the max `updationTime` seen as the cursor to resume from.
`filesSince` refuses to loop when the diff reports `hasMore` without advancing
the cursor (issue 7). `listCollections`/`listFiles` are now thin wrappers that
enumerate from `sinceTime: 0` and drop deletions, so existing callers are
unaffected.
- 2026-09-22: Carried file size, thumbnail size, and the deletion flag through
`decryptFile` (issue 37, foundation for the cache/API design). Live files now
populate `file.size`/`thumbnail.size` from the server's `info` (left
+107 -32
View File
@@ -37,6 +37,22 @@ export interface ClientSnapshot {
publicKey: string;
}
// The result of a resumable enumeration. Live decrypted records and deleted
// ids are kept apart on purpose: a tombstone carries no key or metadata to
// decrypt, so it is a bare id rather than a hollowed-out record. `cursor` is
// the max `updationTime` seen, to pass back into the next call.
export interface CollectionsPage {
collections: Collection[];
deleted: number[];
cursor: number;
}
export interface FilesPage {
files: EnteFile[];
deleted: number[];
cursor: number;
}
export class Client {
private readonly api: ApiClient;
private readonly email: string;
@@ -150,52 +166,111 @@ export class Client {
this.api.clearAuthToken();
}
async listCollections(): Promise<Collection[]> {
// Enumerate collections changed since `sinceTime`. Live collections are
// decrypted; tombstoned ones (isDeleted) are surfaced as bare ids. The
// returned cursor is the max `updationTime` seen — including tombstones, so
// the next sync resumes past them — falling back to `sinceTime` when the
// response is empty. `/collections/v2` returns the whole changed set in one
// response, so there is no pagination here.
async collectionsSince(args: {
sinceTime: number;
}): Promise<CollectionsPage> {
this.assertLoggedIn();
const { collections } = await this.api.getJSON<{
const { collections: raws } = await this.api.getJSON<{
collections: RawCollection[];
}>("/collections/v2", { sinceTime: 0 });
// The sync API keeps returning deleted collections as tombstones
// (isDeleted: true); their diff endpoint 404s, so drop them.
return collections
.filter((raw) => !raw.isDeleted)
.map((raw) =>
decryptCollection(
raw,
{
masterKey: this.masterKey,
publicKey: this.publicKey,
secretKey: this.secretKey,
},
this.userID,
),
);
}>("/collections/v2", { sinceTime: args.sinceTime });
const collections: Collection[] = [];
const deleted: number[] = [];
let cursor = args.sinceTime;
for (const raw of raws) {
if (raw.isDeleted) {
deleted.push(raw.id);
} else {
collections.push(
decryptCollection(
raw,
{
masterKey: this.masterKey,
publicKey: this.publicKey,
secretKey: this.secretKey,
},
this.userID,
),
);
}
if (raw.updationTime > cursor) cursor = raw.updationTime;
}
return { collections, deleted, cursor };
}
async listFiles(
collectionID: number,
collectionKey: Uint8Array,
): Promise<EnteFile[]> {
// Enumerate a collection's files changed since `sinceTime`, paginating the
// diff from that cursor. Live rows are decrypted; tombstoned ones are
// surfaced as bare ids. Returns the final cursor to resume from.
async filesSince(args: {
collectionID: number;
collectionKey: Uint8Array;
sinceTime: number;
}): Promise<FilesPage> {
this.assertLoggedIn();
const allFiles: EnteFile[] = [];
let sinceTime = 0;
const { collectionID, collectionKey } = args;
const files: EnteFile[] = [];
const deleted: number[] = [];
let cursor = args.sinceTime;
for (;;) {
const { diff, hasMore } = await this.api.getJSON<{
diff: RawEnteFile[];
hasMore: boolean;
}>("/collections/v2/diff", { collectionID, sinceTime });
}>("/collections/v2/diff", { collectionID, sinceTime: cursor });
let pageMax = cursor;
for (const raw of diff) {
if (!raw.isDeleted) {
allFiles.push(decryptFile(raw, collectionKey));
}
if (raw.updationTime > sinceTime) {
sinceTime = raw.updationTime;
if (raw.isDeleted) {
deleted.push(raw.id);
} else {
files.push(decryptFile(raw, collectionKey));
}
if (raw.updationTime > pageMax) pageMax = raw.updationTime;
}
if (!hasMore) break;
if (!hasMore) {
cursor = pageMax;
break;
}
// The server says there is more, but this page did not advance the
// cursor: following hasMore would refetch the same page forever
// (#7). Stop with a clear error instead of looping.
if (pageMax <= cursor) {
throw new Error(
`/collections/v2/diff for collection ${collectionID} ` +
`returned hasMore with a cursor that did not advance ` +
`(stuck at ${cursor}); refusing to loop`,
);
}
cursor = pageMax;
}
return allFiles;
return { files, deleted, cursor };
}
// Whole-account listing: every live collection, deletions hidden. A thin
// wrapper over `collectionsSince` from the beginning of time.
async listCollections(): Promise<Collection[]> {
const { collections } = await this.collectionsSince({ sinceTime: 0 });
return collections;
}
// Every live file in a collection, deletions hidden. A thin wrapper over
// `filesSince` from the beginning of time.
async listFiles(
collectionID: number,
collectionKey: Uint8Array,
): Promise<EnteFile[]> {
const { files } = await this.filesSince({
collectionID,
collectionKey,
sinceTime: 0,
});
return files;
}
async downloadFile(
+7 -1
View File
@@ -1,6 +1,12 @@
export const VERSION = "0.0.0";
export { Client, type LoginOptions, type ClientSnapshot } from "./client.js";
export {
Client,
type LoginOptions,
type ClientSnapshot,
type CollectionsPage,
type FilesPage,
} from "./client.js";
export {
ApiClient,
ApiError,
+188
View File
@@ -0,0 +1,188 @@
// On-disk JSON metadata store for the local cache.
//
// The store keeps one `metadata.json` file holding the account's server
// state: the user id, a schema version, the cursor for the incremental
// collections listing, and the decrypted collection and file records. The
// whole file is read into RAM on load and rewritten as a whole on save; there
// is no partial update and no lock file. A separate refresh unit populates the
// store from the server — this module only stores what it is given.
//
// The file is a cache, so it is never trusted to exist or to be intact: a
// missing or unreadable file loads as an empty store rather than an error, and
// the refresh unit then repopulates it.
import { mkdir, chmod, readFile } from "node:fs/promises";
import { dirname } from "node:path";
import { writeAtomic } from "../download/index.js";
import type { Collection, EnteFile, Microseconds } from "../model/types.js";
// Bumped only when the on-disk shape changes incompatibly. A file written
// under a different version is discarded on load (see `load`): re-fetching
// from the server is always safe and cheaper than migrating a cache.
export const METADATA_SCHEMA_VERSION = 1;
// Directory and file modes match `session.json`: the records hold decrypted
// key material, so on a shared machine only the owner may read them.
const DIR_MODE = 0o700;
const FILE_MODE = 0o600;
// On-disk shapes. They mirror the in-memory model exactly except for the
// binary `key`, which JSON cannot hold and which is stored as base64.
type StoredCollection = Omit<Collection, "key"> & { key: string };
type StoredFile = Omit<EnteFile, "key"> & { key: string };
interface StoredMetadata {
schemaVersion: number;
userID: number;
collectionsSinceTime: Microseconds;
collections: StoredCollection[];
files: StoredFile[];
}
const encodeKey = (key: Uint8Array): string =>
Buffer.from(key).toString("base64");
const decodeKey = (encoded: string): Uint8Array =>
new Uint8Array(Buffer.from(encoded, "base64"));
// A file membership is identified by the pair (collectionID, fileID): the same
// underlying file can belong to several collections, each a distinct record
// with its own key.
const fileKey = (collectionID: number, fileID: number): string =>
`${collectionID}:${fileID}`;
export class MetadataStore {
readonly path: string;
readonly schemaVersion = METADATA_SCHEMA_VERSION;
userID = 0;
collectionsSinceTime: Microseconds = 0;
private readonly collections = new Map<number, Collection>();
private readonly files = new Map<string, EnteFile>();
private constructor(path: string) {
this.path = path;
}
// Load the store at `path`. A missing file, an unreadable one, unparseable
// contents, or a mismatched schema version all yield an empty store bound
// to that path — never a thrown error, because the file is only a cache.
static async load(path: string): Promise<MetadataStore> {
const store = new MetadataStore(path);
let raw: string;
try {
raw = await readFile(path, "utf8");
} catch {
return store;
}
try {
const parsed = JSON.parse(raw) as StoredMetadata;
if (parsed.schemaVersion !== METADATA_SCHEMA_VERSION) {
return store;
}
store.userID = parsed.userID ?? 0;
store.collectionsSinceTime = parsed.collectionsSinceTime ?? 0;
for (const stored of parsed.collections ?? []) {
const collection: Collection = {
...stored,
key: decodeKey(stored.key),
};
store.collections.set(collection.id, collection);
}
for (const stored of parsed.files ?? []) {
const file: EnteFile = {
...stored,
key: decodeKey(stored.key),
};
store.files.set(fileKey(file.collectionID, file.id), file);
}
} catch {
// Any corruption discards the partial result: a half-read cache is
// worse than an empty one, since the refresh unit will rebuild it.
return new MetadataStore(path);
}
return store;
}
// Rewrite the whole file. The directory is created 0700 and the file left
// 0600; the write itself is the download layer's durable atomic writer
// (temp file, fsync, rename, dir fsync), so a reader never sees a partial
// file and a crash cannot leave a truncated one. There is no lock file and
// no `sync()` beyond the writer's own fsyncs.
async save(): Promise<void> {
const model: StoredMetadata = {
schemaVersion: METADATA_SCHEMA_VERSION,
userID: this.userID,
collectionsSinceTime: this.collectionsSinceTime,
collections: [...this.collections.values()].map((c) => ({
...c,
key: encodeKey(c.key),
})),
files: [...this.files.values()].map((f) => ({
...f,
key: encodeKey(f.key),
})),
};
const dir = dirname(this.path);
// chmod after mkdir so the mode is 0700 even when the directory
// already existed with a looser mode; mkdir alone would not tighten
// an existing directory.
await mkdir(dir, { recursive: true, mode: DIR_MODE });
await chmod(dir, DIR_MODE);
const payload = new TextEncoder().encode(
JSON.stringify(model, null, 2),
);
await writeAtomic(this.path, payload);
// The atomic writer's temp file inherits the default mode; tighten the
// renamed file to 0600. The 0700 directory already keeps other users
// out during the brief window before this runs.
await chmod(this.path, FILE_MODE);
}
getCollection(id: number): Collection | undefined {
return this.collections.get(id);
}
listCollections(): Collection[] {
return [...this.collections.values()];
}
putCollection(collection: Collection): void {
this.collections.set(collection.id, collection);
}
// Removing a collection also drops its file memberships: a file record is
// only meaningful as part of a collection the cache still knows about.
deleteCollection(id: number): void {
this.collections.delete(id);
for (const [key, file] of this.files) {
if (file.collectionID === id) {
this.files.delete(key);
}
}
}
getFile(collectionID: number, fileID: number): EnteFile | undefined {
return this.files.get(fileKey(collectionID, fileID));
}
listFiles(collectionID: number): EnteFile[] {
return [...this.files.values()].filter(
(f) => f.collectionID === collectionID,
);
}
putFile(file: EnteFile): void {
this.files.set(fileKey(file.collectionID, file.id), file);
}
deleteFile(collectionID: number, fileID: number): void {
this.files.delete(fileKey(collectionID, fileID));
}
}
+367
View File
@@ -0,0 +1,367 @@
/**
* Tests for the resumable, deletion-aware enumeration variants on `Client`:
* `collectionsSince` and `filesSince`.
*
* The whole-account methods `listCollections` / `listFiles` always start at
* `sinceTime: 0` and hide deletions. The cache refresh needs the opposite:
* start from a saved cursor, learn what was deleted, and get back a cursor to
* resume from next time. These two methods provide that.
*
* The return shape keeps live records and tombstones apart — `collections` /
* `files` are decrypted live records, `deleted` is a plain list of the ids the
* server tombstoned. A tombstone carries no decryptable key or metadata, so it
* is a bare id rather than a hollowed-out `Collection` / `EnteFile`.
*
* All tests inject a fake `fetch` and drive a real `Client` (built with
* `Client.fromJSON`) so the decryption path runs for real. Live rows are built
* with libsodium exactly as the server would encrypt them; tombstone rows carry
* only the fields the code reads (`id`, `updationTime`, `isDeleted`), because
* they are never decrypted.
*/
import sodium from "libsodium-wrappers-sumo";
import { beforeAll, describe, expect, it } from "vitest";
import { init, toBase64 } from "../../src/crypto/index.js";
import { Client, type ClientSnapshot } from "../../src/client.js";
// ---------------------------------------------------------------------------
// Fixtures
// ---------------------------------------------------------------------------
const USER_ID = 42;
interface Keys {
masterKey: Uint8Array;
publicKey: Uint8Array;
secretKey: Uint8Array;
}
const buildKeys = (): Keys => {
const kp = sodium.crypto_box_keypair();
return {
masterKey: sodium.crypto_secretbox_keygen(),
publicKey: kp.publicKey,
secretKey: kp.privateKey,
};
};
const snapshotFor = (keys: Keys): ClientSnapshot => ({
email: "user@example.com",
userID: USER_ID,
token: "test-token",
masterKey: toBase64(keys.masterKey),
secretKey: toBase64(keys.secretKey),
publicKey: toBase64(keys.publicKey),
});
const secretboxEncrypt = (
plaintext: Uint8Array,
key: Uint8Array,
): { ciphertext: Uint8Array; nonce: Uint8Array } => {
const nonce = sodium.randombytes_buf(sodium.crypto_secretbox_NONCEBYTES);
return {
ciphertext: sodium.crypto_secretbox_easy(plaintext, nonce, key),
nonce,
};
};
/** An owned collection row as the server sends it, keyed under the master key. */
const ownedCollectionRow = (
masterKey: Uint8Array,
opts: { id: number; name: string; updationTime: number },
): Record<string, unknown> => {
const collectionKey = sodium.crypto_secretbox_keygen();
const { ciphertext: encKey, nonce: keyNonce } = secretboxEncrypt(
collectionKey,
masterKey,
);
const { ciphertext: encName, nonce: nameNonce } = secretboxEncrypt(
new TextEncoder().encode(opts.name),
collectionKey,
);
return {
id: opts.id,
owner: { id: USER_ID },
encryptedKey: toBase64(encKey),
keyDecryptionNonce: toBase64(keyNonce),
encryptedName: toBase64(encName),
nameDecryptionNonce: toBase64(nameNonce),
type: "album",
updationTime: opts.updationTime,
};
};
/** A live file row inside a collection, keyed under that collection's key. */
const fileRow = (
collectionKey: Uint8Array,
opts: { id: number; title: string; updationTime: number },
): Record<string, unknown> => {
const fileKey = sodium.crypto_secretbox_keygen();
const { ciphertext: encFileKey, nonce: fileKeyNonce } = secretboxEncrypt(
fileKey,
collectionKey,
);
const metadata = {
title: opts.title,
fileType: 0,
creationTime: opts.updationTime,
modificationTime: opts.updationTime,
};
const push =
sodium.crypto_secretstream_xchacha20poly1305_init_push(fileKey);
const encMeta = sodium.crypto_secretstream_xchacha20poly1305_push(
push.state,
new TextEncoder().encode(JSON.stringify(metadata)),
null,
sodium.crypto_secretstream_xchacha20poly1305_TAG_FINAL,
);
return {
id: opts.id,
collectionID: 1,
ownerID: USER_ID,
encryptedKey: toBase64(encFileKey),
keyDecryptionNonce: toBase64(fileKeyNonce),
metadata: {
encryptedData: toBase64(encMeta),
decryptionHeader: toBase64(push.header),
},
file: { decryptionHeader: toBase64(sodium.randombytes_buf(24)) },
thumbnail: { decryptionHeader: toBase64(sodium.randombytes_buf(24)) },
updationTime: opts.updationTime,
};
};
/** A tombstone row. Never decrypted, so only these fields are ever read. */
const tombstoneRow = (
id: number,
updationTime: number,
): Record<string, unknown> => ({
id,
updationTime,
isDeleted: true,
});
const jsonResponse = (body: unknown): Response =>
new Response(JSON.stringify(body), {
status: 200,
headers: { "content-type": "application/json" },
});
/**
* A fetch that serves canned responses in order and records the `sinceTime`
* query parameter each request carried, so tests can prove the cursor is
* threaded from one page (and one call) to the next.
*/
const recordingFetch = (
...responses: Response[]
): { fetch: typeof globalThis.fetch; sinceTimes: (string | null)[] } => {
const sinceTimes: (string | null)[] = [];
let i = 0;
const fake = async (input: RequestInfo | URL): Promise<Response> => {
const url =
typeof input === "string"
? input
: input instanceof URL
? input.href
: input.url;
sinceTimes.push(new URL(url).searchParams.get("sinceTime"));
if (i >= responses.length) {
throw new Error(`recordingFetch: no response for call #${i}`);
}
return responses[i++]!;
};
return { fetch: fake as typeof globalThis.fetch, sinceTimes };
};
// ---------------------------------------------------------------------------
// Tests
// ---------------------------------------------------------------------------
describe("Client.filesSince", () => {
beforeAll(async () => {
await init();
await sodium.ready;
});
it("pages from the given cursor, decrypts live rows, and collects tombstones", async () => {
const keys = buildKeys();
const collectionKey = sodium.crypto_secretbox_keygen();
// Page 1 mixes a live file and a tombstone; the tombstone has the
// higher updationTime, so it — not the live row — sets the cursor the
// second page must be fetched from.
const { fetch, sinceTimes } = recordingFetch(
jsonResponse({
diff: [
fileRow(collectionKey, {
id: 1001,
title: "first.jpg",
updationTime: 100,
}),
tombstoneRow(1002, 150),
],
hasMore: true,
}),
jsonResponse({
diff: [
fileRow(collectionKey, {
id: 1003,
title: "second.jpg",
updationTime: 200,
}),
],
hasMore: false,
}),
);
const client = Client.fromJSON(snapshotFor(keys), { fetch });
const { files, deleted, cursor } = await client.filesSince({
collectionID: 1,
collectionKey,
sinceTime: 0,
});
expect(files.map((f) => f.id)).toEqual([1001, 1003]);
expect(files.map((f) => f.metadata.title)).toEqual([
"first.jpg",
"second.jpg",
]);
expect(deleted).toEqual([1002]);
expect(cursor).toBe(200);
// First request started at the caller's cursor; the second resumed
// from the max updationTime seen on the first page (the tombstone's).
expect(sinceTimes).toEqual(["0", "150"]);
});
it("fetches only newer rows when the returned cursor is passed back in", async () => {
const keys = buildKeys();
const collectionKey = sodium.crypto_secretbox_keygen();
const { fetch, sinceTimes } = recordingFetch(
jsonResponse({ diff: [], hasMore: false }),
);
const client = Client.fromJSON(snapshotFor(keys), { fetch });
const result = await client.filesSince({
collectionID: 1,
collectionKey,
sinceTime: 200,
});
expect(result.files).toEqual([]);
expect(result.deleted).toEqual([]);
// An empty diff advances nothing: the cursor falls back to the input.
expect(result.cursor).toBe(200);
expect(sinceTimes).toEqual(["200"]);
});
it("stops and throws when the server claims more but does not advance (#7)", async () => {
const keys = buildKeys();
const collectionKey = sodium.crypto_secretbox_keygen();
// hasMore is true, but the page's max updationTime (50) does not exceed
// the cursor the request was made with (50). Following hasMore here
// would refetch this same page forever.
const { fetch, sinceTimes } = recordingFetch(
jsonResponse({ diff: [tombstoneRow(1, 50)], hasMore: true }),
jsonResponse({ diff: [tombstoneRow(1, 50)], hasMore: true }),
);
const client = Client.fromJSON(snapshotFor(keys), { fetch });
await expect(
client.filesSince({
collectionID: 1,
collectionKey,
sinceTime: 50,
}),
).rejects.toThrow(/not advance|non-advancing/i);
// It gave up after the first page rather than looping.
expect(sinceTimes).toEqual(["50"]);
});
});
describe("Client.collectionsSince", () => {
beforeAll(async () => {
await init();
await sodium.ready;
});
it("decrypts live collections, collects tombstones, and returns a cursor", async () => {
const keys = buildKeys();
const { fetch, sinceTimes } = recordingFetch(
jsonResponse({
collections: [
ownedCollectionRow(keys.masterKey, {
id: 1,
name: "Vacation",
updationTime: 100,
}),
tombstoneRow(3, 150),
],
}),
);
const client = Client.fromJSON(snapshotFor(keys), { fetch });
const { collections, deleted, cursor } = await client.collectionsSince({
sinceTime: 0,
});
expect(collections.map((c) => c.id)).toEqual([1]);
expect(collections[0]!.name).toBe("Vacation");
expect(deleted).toEqual([3]);
// The tombstone's updationTime advances the cursor too, so the next
// sync starts after it rather than seeing it again.
expect(cursor).toBe(150);
expect(sinceTimes).toEqual(["0"]);
});
it("falls back to the input cursor on an empty response", async () => {
const keys = buildKeys();
const { fetch, sinceTimes } = recordingFetch(
jsonResponse({ collections: [] }),
);
const client = Client.fromJSON(snapshotFor(keys), { fetch });
const result = await client.collectionsSince({ sinceTime: 150 });
expect(result.collections).toEqual([]);
expect(result.deleted).toEqual([]);
expect(result.cursor).toBe(150);
expect(sinceTimes).toEqual(["150"]);
});
});
describe("Client list wrappers still hide deletions", () => {
beforeAll(async () => {
await init();
await sodium.ready;
});
it("listFiles drops tombstones and returns only live files", async () => {
const keys = buildKeys();
const collectionKey = sodium.crypto_secretbox_keygen();
const { fetch, sinceTimes } = recordingFetch(
jsonResponse({
diff: [
fileRow(collectionKey, {
id: 7,
title: "keep.jpg",
updationTime: 100,
}),
tombstoneRow(8, 150),
],
hasMore: false,
}),
);
const client = Client.fromJSON(snapshotFor(keys), { fetch });
const files = await client.listFiles(1, collectionKey);
expect(files.map((f) => f.id)).toEqual([7]);
// The wrapper starts a full enumeration from zero.
expect(sinceTimes).toEqual(["0"]);
});
});
+246
View File
@@ -0,0 +1,246 @@
/**
* Tests for the on-disk JSON metadata store (`MetadataStore`).
*
* The store is the local cache the library keeps of the account's server
* state: one `metadata.json` file holding the user id, a schema version, the
* cursor for the incremental collections listing, and the decrypted
* collection and file records. The whole file is read into RAM on load and
* rewritten as a whole on save. A separate refresh unit (issue #42) is what
* populates it; this unit only stores.
*
* Four contracts are load-bearing and each is exercised below:
*
* 1. **Round-trip fidelity.** Everything put into the store — including the
* binary decryption keys, which JSON cannot hold directly and which the
* store base64-encodes — comes back byte-for-byte after a save and a fresh
* load. A cache that quietly dropped or mangled a field would hand the
* caller wrong keys or stale metadata.
*
* 2. **A missing or corrupt file loads as an empty store, never an error.**
* The file is only a cache: if it is absent (first run) or unreadable
* (interrupted write on an older build, disk corruption, hand-editing),
* the right answer is to start empty and let the refresh unit repopulate,
* not to crash the whole library.
*
* 3. **Writes are atomic and durable.** The store reuses the same
* fsync-before-rename atomic writer the download layer uses, so a reader
* never sees a half-written file and a crash cannot leave a truncated one.
* The observable consequence tested here is that a save leaves exactly the
* destination file behind — no temporary sibling — and that overwriting an
* existing store preserves a complete, re-loadable file.
*
* 4. **Permissions match `session.json`.** The directory is `0700` and the
* file is `0600`, because the records contain decrypted key material and
* must not be readable by other users on a shared machine.
*/
import { describe, it, expect, beforeEach, afterEach } from "vitest";
import {
mkdtempSync,
rmSync,
readdirSync,
statSync,
writeFileSync,
mkdirSync,
} from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
import {
MetadataStore,
METADATA_SCHEMA_VERSION,
} from "../../src/library/store.js";
import type { Collection, EnteFile } from "../../src/model/types.js";
// A representative decrypted collection, including a binary key and all three
// magic-metadata layers, so the round-trip test proves every field survives.
const sampleCollection = (): Collection => ({
id: 12345,
ownerID: 42,
key: new Uint8Array([1, 2, 3, 4, 5, 6, 7, 8]),
name: "Holiday 2026",
type: "album",
updationTime: 1_700_000_000_000_000,
isShared: true,
magicMetadata: { visibility: 0 },
pubMagicMetadata: { subType: 0, coverID: 999 },
sharedMagicMetadata: { note: "shared with a friend" },
});
// A representative decrypted file membership: metadata, both blob headers, a
// binary key, a content hash, and file/thumbnail sizes.
const sampleFile = (): EnteFile => ({
id: 67890,
collectionID: 12345,
ownerID: 42,
key: new Uint8Array([9, 8, 7, 6, 5, 4, 3, 2, 1]),
metadata: {
title: "IMG_0001.jpg",
fileType: "image",
creationTime: 1_699_000_000_000_000,
modificationTime: 1_699_000_500_000_000,
latitude: 52.52,
longitude: 13.405,
hash: "sha256:deadbeef",
},
magicMetadata: { editedName: "sunset" },
pubMagicMetadata: { editedTime: 1_699_000_600_000_000 },
file: { decryptionHeader: "ZmlsZUhlYWRlcg==", size: 4_194_304 },
thumbnail: { decryptionHeader: "dGh1bWJIZWFkZXI=", size: 8192 },
updationTime: 1_700_000_100_000_000,
});
describe("MetadataStore", () => {
let dir: string;
let path: string;
beforeEach(() => {
dir = mkdtempSync(join(tmpdir(), "quak-store-"));
// Deliberately nest the store one level below the temp dir so save()
// has to create its own directory and set its mode.
path = join(dir, "cache", "metadata.json");
});
afterEach(() => {
rmSync(dir, { recursive: true, force: true });
});
it("round-trips the whole model, keys and all", async () => {
const store = await MetadataStore.load(path);
store.userID = 42;
store.collectionsSinceTime = 1_700_000_000_000_000;
store.putCollection(sampleCollection());
store.putFile(sampleFile());
await store.save();
const reloaded = await MetadataStore.load(path);
expect(reloaded.userID).toBe(42);
expect(reloaded.collectionsSinceTime).toBe(1_700_000_000_000_000);
// The binary key must come back as the exact bytes, not a base64
// string or a plain object of numbered keys.
const collection = reloaded.getCollection(12345);
expect(collection).toEqual(sampleCollection());
expect(collection?.key).toBeInstanceOf(Uint8Array);
const file = reloaded.getFile(12345, 67890);
expect(file).toEqual(sampleFile());
expect(file?.key).toBeInstanceOf(Uint8Array);
expect(reloaded.listCollections()).toHaveLength(1);
expect(reloaded.listFiles(12345)).toHaveLength(1);
});
it("writes the declared schema version", async () => {
const store = await MetadataStore.load(path);
await store.save();
const reloaded = await MetadataStore.load(path);
expect(reloaded.schemaVersion).toBe(METADATA_SCHEMA_VERSION);
});
it("loads an empty store when the file is missing", async () => {
const store = await MetadataStore.load(path);
expect(store.userID).toBe(0);
expect(store.listCollections()).toEqual([]);
expect(store.getCollection(1)).toBeUndefined();
});
it("loads an empty store when the file is corrupt", async () => {
mkdirSync(join(dir, "cache"), { recursive: true });
writeFileSync(path, "{ this is not valid json ][");
const store = await MetadataStore.load(path);
expect(store.listCollections()).toEqual([]);
expect(store.listFiles(12345)).toEqual([]);
});
it("loads an empty store when the schema version does not match", async () => {
// A cache written by a future build with an incompatible schema is
// discarded rather than misread; the refresh unit repopulates it.
mkdirSync(join(dir, "cache"), { recursive: true });
writeFileSync(
path,
JSON.stringify({
schemaVersion: METADATA_SCHEMA_VERSION + 1,
userID: 42,
collectionsSinceTime: 0,
collections: [],
files: [],
}),
);
const store = await MetadataStore.load(path);
expect(store.userID).toBe(0);
expect(store.listCollections()).toEqual([]);
});
it("creates the directory 0700 and the file 0600", async () => {
const store = await MetadataStore.load(path);
store.putCollection(sampleCollection());
await store.save();
// Directory 0700, file 0600: on a shared machine the decrypted keys
// in this file must be readable only by their owner. Mask to the
// permission bits; the file-type bits are not part of the assertion.
expect(statSync(join(dir, "cache")).mode & 0o777).toBe(0o700);
expect(statSync(path).mode & 0o777).toBe(0o600);
});
it("leaves exactly the destination behind, with no temp sibling", async () => {
const store = await MetadataStore.load(path);
store.putCollection(sampleCollection());
await store.save();
// The atomic writer stages a temporary file and renames it into
// place; on success nothing temporary is left in the directory.
expect(readdirSync(join(dir, "cache"))).toEqual(["metadata.json"]);
});
it("overwrites an existing store atomically and stays re-loadable", async () => {
const first = await MetadataStore.load(path);
first.userID = 1;
first.putCollection(sampleCollection());
await first.save();
const second = await MetadataStore.load(path);
second.userID = 2;
second.deleteCollection(12345);
await second.save();
const reloaded = await MetadataStore.load(path);
expect(reloaded.userID).toBe(2);
expect(reloaded.getCollection(12345)).toBeUndefined();
expect(readdirSync(join(dir, "cache"))).toEqual(["metadata.json"]);
});
it("deletes a collection together with its file memberships", async () => {
const store = await MetadataStore.load(path);
store.putCollection(sampleCollection());
store.putFile(sampleFile());
store.deleteCollection(12345);
expect(store.getCollection(12345)).toBeUndefined();
expect(store.getFile(12345, 67890)).toBeUndefined();
expect(store.listFiles(12345)).toEqual([]);
});
it("scopes file records to their collection membership", async () => {
// The same underlying file can be a member of two collections, each a
// separate record with its own key. Storing one must not touch the
// other, and lookups are per membership.
const store = await MetadataStore.load(path);
const inA = sampleFile();
const inB: EnteFile = {
...sampleFile(),
collectionID: 55555,
key: new Uint8Array([100, 101, 102]),
};
store.putFile(inA);
store.putFile(inB);
expect(store.getFile(12345, 67890)?.key).toEqual(inA.key);
expect(store.getFile(55555, 67890)?.key).toEqual(inB.key);
expect(store.listFiles(12345)).toHaveLength(1);
expect(store.listFiles(55555)).toHaveLength(1);
store.deleteFile(12345, 67890);
expect(store.getFile(12345, 67890)).toBeUndefined();
expect(store.getFile(55555, 67890)?.key).toEqual(inB.key);
});
});