quak backup writes the account and album records backup-metadata writes #175

Merged
clawbot merged 1 commits from issue-166-backup-account-and-album-records into next 2026-10-06 07:13:26 +02:00
5 changed files with 159 additions and 10 deletions
+12 -2
View File
@@ -599,8 +599,8 @@ the smallest does not.
per unique file, two for a live photo: see
below)
YYYY-MM-DD.<fileID>.json the file's basic metadata fields quak
keeps, its private and public magic
metadata, and its ML data
keeps, its update time, its private and
public magic metadata, and its ML data
YYYY-MM-DD.<fileID>.livephoto.json
which of a live photo's two files is which
collections/
@@ -608,6 +608,7 @@ the smallest does not.
<title> -> ../../YYYY/YYYY-MM/YYYY-MM-DD/YYYY-MM-DD.<fileID>.<ext>
(symlink)
<name>.json collection metadata + file list
account.json the account's email and user ID
failures.json files that failed and have not yet succeeded
```
@@ -619,6 +620,15 @@ name as uploaded, case kept, or `.bin` when it has none or it holds anything but
letters and digits. When the date or the time zone changes, the next run saves
the original at its new path and leaves the old copy where it is.
`account.json` holds the account's `email` and `userID`, as `backup-metadata`
writes it. A collection's JSON holds its `id`, `name`, `type`, `ownerID`,
`isShared` and `updationTime`, its `magicMetadata`, `pubMagicMetadata` and
`sharedMagicMetadata` when it has them, as `backup-metadata`'s
`_collection.json` does, and `files`, each file's `id` and `metadata`. A file's
JSON holds its `id`, `collectionID`, `ownerID`, `metadata` and `updationTime`,
and its `magicMetadata` and `pubMagicMetadata` when it has them. Update times
are in microseconds, as Ente records them.
A file's JSON holds Ente's ML data for it (its faces and its CLIP embedding) as
`mlData`, the same payload `backup-metadata` writes; a file Ente has no ML data
for has no `mlData`. The backup waits for the library's ML data fetch to finish
+6
View File
@@ -25,6 +25,12 @@ declares one.
# Completed Steps
- 2026-10-06: `quak backup` writes the account and album records
`backup-metadata` writes (issue 166): `account.json` with the account's
`email` and `userID`, and in each album's JSON its `ownerID`, `isShared`,
`updationTime` and, when present, its three layers of magic metadata. Each
file's JSON gains its `updationTime`.
- 2026-10-05: `quak backup` writes each file's ML data (its faces and CLIP
embedding) into the file's JSON as `mlData`, the payload
`lib.mldata.forFile()` returns (issue 163). `lib.backup()` waits for an ML
+36 -7
View File
@@ -14,6 +14,7 @@
// the file's ML data
// collections/<name>/<title> symlink to the original
// collections/<name>.json per-collection metadata
// account.json the account's email and user ID
// failures.json durable ledger of unresolved failures
//
// A live photo's original is its image and its video, each with its own
@@ -64,7 +65,7 @@ import {
} from "./library/content.js";
import { representative } from "./library/records.js";
import type { MLData } from "./mldata-fetch.js";
import type { Collection, EnteFile } from "./model/types.js";
import type { Collection, EnteFile, FileMetadata } from "./model/types.js";
export type ProgressCallback = (message: string) => void;
@@ -108,6 +109,8 @@ export interface BackupResult {
// The slice of the library that backup drives. `Library` implements it; a test
// can drive backup with a stand-in.
export interface BackupLibrary {
// The account the library belongs to.
whoami(): { email: string; userID: number };
refresh(): Promise<void>;
listCollections(): Collection[];
listFiles(collectionID: number): EnteFile[];
@@ -363,6 +366,7 @@ const writeSidecar = (
collectionID: file.collectionID,
ownerID: file.ownerID,
metadata: file.metadata,
updationTime: file.updationTime,
};
if (file.magicMetadata) meta.magicMetadata = file.magicMetadata;
if (file.pubMagicMetadata) meta.pubMagicMetadata = file.pubMagicMetadata;
@@ -371,6 +375,29 @@ const writeSidecar = (
writeFileSync(path, JSON.stringify(meta, null, 2));
};
// The album's JSON: its basic fields, its magic metadata, and its files.
const writeAlbumJSON = (
path: string,
c: Collection,
files: { id: number; metadata: FileMetadata }[],
): void => {
const album: Record<string, unknown> = {
id: c.id,
name: c.name,
type: c.type,
ownerID: c.ownerID,
isShared: c.isShared,
updationTime: c.updationTime,
};
if (c.magicMetadata) album.magicMetadata = c.magicMetadata;
if (c.pubMagicMetadata) album.pubMagicMetadata = c.pubMagicMetadata;
if (c.sharedMagicMetadata) {
album.sharedMagicMetadata = c.sharedMagicMetadata;
}
album.files = files;
writeFileSync(path, JSON.stringify(album, null, 2));
};
export const runBackup = async (
lib: BackupLibrary,
opts: BackupOptions,
@@ -393,6 +420,11 @@ export const runBackup = async (
const collectionsDir = join(downloadDirectory, "collections");
const thumbnailsDir = join(downloadDirectory, "thumbnails");
mkdirSync(collectionsDir, { recursive: true });
const { email, userID } = lib.whoami();
writeFileSync(
join(downloadDirectory, "account.json"),
JSON.stringify({ email, userID }, null, 2),
);
if (includeThumbnails) mkdirSync(thumbnailsDir, { recursive: true });
removeLeftoverTempFiles(thumbnailsDir);
for (const dir of dateFolders(downloadDirectory)) {
@@ -618,13 +650,10 @@ export const runBackup = async (
}
}
writeFileSync(
writeAlbumJSON(
join(collectionsDir, `${colDirName}.json`),
JSON.stringify(
{ id: c.id, name: c.name, type: c.type, files: metaFiles },
null,
2,
),
c,
metaFiles,
);
}
+3 -1
View File
@@ -571,7 +571,8 @@ export class Library {
// when it fails. Then puts pending originals at their save paths as
// `Photo.download()` does (and optional thumbnails) through the content
// cache and pools, waits for an ML data fetch, and rebuilds the derived
// symlink/JSON views from the model, each file's JSON with its ML data.
// symlink/JSON views from the model, each file's JSON with its ML data,
// beside an `account.json` with the account's email and user ID.
// Throws before any network work when no content cache backs the
// originals it must fetch.
backup(opts?: BackupOptions): Promise<BackupResult> {
@@ -589,6 +590,7 @@ export class Library {
const cache = this.cache;
return runBackup(
{
whoami: () => this.client.whoami(),
refresh: () => this.refreshNow(),
listCollections: () => this.store.listCollections(),
listFiles: (id) => this.store.listFiles(id),
+102
View File
@@ -12,6 +12,7 @@
* collections/
* <name>/<title> symlink to the original (rebuilt each run)
* <name>.json per-collection metadata (rebuilt each run)
* account.json the account's email and user ID
* failures.json durable ledger of unresolved failures
*
* The properties that distinguish backup from a naive download loop, and that
@@ -917,6 +918,106 @@ describe("ML data in each file's JSON", () => {
});
});
// The fields `RecordsClient` gives the Vacation album: shared by another
// account, with all three layers of magic metadata.
const SHARED_ALBUM = {
ownerID: 7,
isShared: true,
updationTime: 1700,
magicMetadata: { visibility: 0 },
pubMagicMetadata: { coverID: 100 },
sharedMagicMetadata: { visibility: 2 },
};
// Serves the Vacation album with `SHARED_ALBUM`'s fields, and each file with
// the update time 5000 + its ID.
class RecordsClient extends MockClient {
override async collectionsSince(): Promise<CollectionsPage> {
const page = await super.collectionsSince();
return {
...page,
collections: page.collections.map((c) =>
c.id === 1 ? { ...c, ...SHARED_ALBUM } : c,
),
};
}
override async filesSince(args: {
collectionID: number;
}): Promise<FilesPage> {
const page = await super.filesSince(args);
return {
...page,
files: page.files.map((f) => ({
...f,
updationTime: 5000 + f.id,
})),
};
}
}
// The JSON the backup in `outDir` wrote for the album named `name`.
const albumJSON = (outDir: string, name: string): Record<string, unknown> =>
JSON.parse(
readFileSync(join(outDir, "collections", `${name}.json`), "utf-8"),
);
describe("account and album records", () => {
it("writes account.json with the account's email and user ID", async () => {
const lib = await openLibrary(stubSource());
const outDir = join(root, "backup");
await lib.backup({ downloadDirectory: outDir });
expect(
JSON.parse(readFileSync(join(outDir, "account.json"), "utf-8")),
).toEqual({ email: "backup@example.com", userID: USER_ID });
await lib.close();
});
it("writes each album's owner, sharing, update time and magic metadata into its JSON", async () => {
const lib = await openLibrary(stubSource(), new RecordsClient());
const outDir = join(root, "backup");
await lib.backup({ downloadDirectory: outDir });
expect(albumJSON(outDir, "Vacation")).toEqual({
id: 1,
name: "Vacation",
type: "album",
...SHARED_ALBUM,
files: [
{ id: 100, metadata: file(100, 1, "beach.jpg").metadata },
{ id: 101, metadata: file(101, 1, "sunset.jpg").metadata },
],
});
// An album with no magic metadata gets no magic metadata fields.
expect(albumJSON(outDir, "Work")).toEqual({
id: 2,
name: "Work",
type: "album",
ownerID: USER_ID,
isShared: false,
updationTime: 1,
files: [
{ id: 200, metadata: file(200, 2, "diagram.png").metadata },
],
});
await lib.close();
});
it("writes each file's update time into its JSON", async () => {
const lib = await openLibrary(stubSource(), new RecordsClient());
const outDir = join(root, "backup");
await lib.backup({ downloadDirectory: outDir });
for (const fileID of [100, 101, 200]) {
expect(fileJSON(outDir, fileID).updationTime).toBe(5000 + fileID);
}
await lib.close();
});
});
// Every entry under collections/, one level of directories deep, with each
// symlink's target.
const tree = (outDir: string): string[] => {
@@ -962,6 +1063,7 @@ describe("backup album folders", () => {
},
fetchMLData: async () => {},
mlData: async () => undefined,
whoami: () => ({ email: "backup@example.com", userID: USER_ID }),
});
const albumID = (outDir: string, jsonName: string): number =>