quak backup writes each original's EXIF, XMP and dimensions into its JSON (closes #167)

Each file's JSON gains imageMetadata, what extractImageMetadata finds in
the stored original (for a live photo, its image), or the reason the
read failed in imageMetadataError; a failed read fails neither the file
nor the run. A video is not read. An original is read when the run
stores it or when its JSON has neither field; otherwise the field is
carried over from that JSON, so a run does not read every original
again. The hand-built JPEG fixtures move to test/exif-jpeg.ts so the
backup tests can use them.

Judgement call: an original with nothing to record gets imageMetadata
{} instead of no field, so it is not read again on every run.

Model: opus-5-5

test/cli/backup.test.ts

@@ -33,6 +33,7 @@
  */
 
 import {
+    chmodSync,
     existsSync,
     lstatSync,
     mkdirSync,
@@ -53,12 +54,16 @@ import { runBackup, type BackupLibrary } from "../../src/backup.js";
 import { Library } from "../../src/library/index.js";
 import type { ContentSource } from "../../src/library/content.js";
 import type { CollectionsPage, FilesPage } from "../../src/client.js";
+import { extractImageMetadata } from "../../src/metadata-backup.js";
 import type { MLData } from "../../src/mldata-fetch.js";
 import type { Collection, EnteFile } from "../../src/model/types.js";
+import { HEIC_WITH_EXIF } from "../exif-heic.js";
+import { JPEG_WITH_EXIF } from "../exif-jpeg.js";
 import {
     asLivePhoto,
     cdnSource,
     IMAGE,
+    livePhotoHash,
     livePhotoZip,
     VIDEO,
 } from "../live-photo.js";
@@ -1018,6 +1023,179 @@ describe("account and album records", () => {
     });
 });
 
+// What a file's JSON holds as `imageMetadata` for an original of `bytes`.
+const imageMetadataOf = (bytes: Uint8Array): unknown =>
+    JSON.parse(JSON.stringify(extractImageMetadata(bytes)));
+
+describe("image metadata in each file's JSON", () => {
+    // Serves `files` in the Vacation album and nothing in Work.
+    class FilesClient extends MockClient {
+        constructor(private readonly files: EnteFile[]) {
+            super();
+        }
+        override async filesSince(args: {
+            collectionID: number;
+        }): Promise<FilesPage> {
+            return {
+                files: args.collectionID === 1 ? this.files : [],
+                deleted: [],
+                cursor: 1,
+            };
+        }
+    }
+
+    // Writes `originals.get(fileID)` as each file's original, looked up at
+    // each fetch, so a test can change it between runs.
+    const bytesSource = (
+        originals: Map<number, Uint8Array>,
+    ): ContentSource => ({
+        original: async ({ file: f, destination }) => {
+            const bytes = originals.get(f.id)!;
+            writeFileSync(destination, bytes);
+            return { bytesWritten: bytes.length };
+        },
+        thumbnail: async () => {
+            throw new Error("no thumbnails in this source");
+        },
+    });
+
+    // A JPEG, a HEIC, a video, and a file holding no image metadata. The
+    // video's bytes are the JPEG's, so reading it would find EXIF.
+    const clip = file(602, 1, "clip.mov");
+    const files = [
+        file(600, 1, "photo.jpg"),
+        file(601, 1, "photo.heic"),
+        { ...clip, metadata: { ...clip.metadata, fileType: "video" as const } },
+        file(603, 1, "notes.png"),
+    ];
+    const originals = (): Map<number, Uint8Array> =>
+        new Map([
+            [600, JPEG_WITH_EXIF],
+            [601, HEIC_WITH_EXIF],
+            [602, JPEG_WITH_EXIF],
+            [603, new TextEncoder().encode("not an image")],
+        ]);
+    const open = (bytes = originals()): Promise<Library> =>
+        openLibrary(bytesSource(bytes), new FilesClient(files));
+
+    // Rewrite the JSON of `fileID` without its image metadata, as an earlier
+    // version of quak wrote it.
+    const dropImageMetadata = (outDir: string, fileID: number): void => {
+        const json = fileJSON(outDir, fileID);
+        delete json.imageMetadata;
+        writeFileSync(saved(outDir, `${fileID}.json`), JSON.stringify(json));
+    };
+
+    it("writes each new original's image metadata, and none for a video", async () => {
+        const lib = await open();
+        const outDir = join(root, "backup");
+
+        const result = await lib.backup({ downloadDirectory: outDir });
+
+        expect(result).toMatchObject({ downloaded: 4, failed: 0 });
+        expect(fileJSON(outDir, 600).imageMetadata).toEqual(
+            imageMetadataOf(JPEG_WITH_EXIF),
+        );
+        expect(fileJSON(outDir, 601).imageMetadata).toEqual(
+            imageMetadataOf(HEIC_WITH_EXIF),
+        );
+        expect(fileJSON(outDir, 602)).not.toHaveProperty("imageMetadata");
+        expect(fileJSON(outDir, 602)).not.toHaveProperty("imageMetadataError");
+        // Empty, so that the next run does not read it again.
+        expect(fileJSON(outDir, 603).imageMetadata).toEqual({});
+        await lib.close();
+    });
+
+    it("reads a live photo's image", async () => {
+        const { file: live, body } = await asLivePhoto(
+            file(500, 1, "IMG_0500.HEIC"),
+            livePhotoZip({ "image.heic": HEIC_WITH_EXIF, "video.mov": VIDEO }),
+            livePhotoHash(HEIC_WITH_EXIF, VIDEO),
+        );
+        const lib = await openLibrary(
+            cdnSource(new Map([[500, body]])),
+            new FilesClient([live]),
+        );
+        const outDir = join(root, "backup");
+
+        await lib.backup({ downloadDirectory: outDir });
+
+        expect(fileJSON(outDir, 500).imageMetadata).toEqual(
+            imageMetadataOf(HEIC_WITH_EXIF),
+        );
+        await lib.close();
+    });
+
+    it("keeps the image metadata of an original stored by an earlier run without reading it again", async () => {
+        const lib = await open();
+        const outDir = join(root, "backup");
+        await lib.backup({ downloadDirectory: outDir });
+        // A read of the original now would give the HEIC's.
+        writeFileSync(saved(outDir, "600.jpg"), HEIC_WITH_EXIF);
+
+        const second = await lib.backup({ downloadDirectory: outDir });
+
+        expect(second).toMatchObject({ downloaded: 0, failed: 0 });
+        expect(fileJSON(outDir, 600).imageMetadata).toEqual(
+            imageMetadataOf(JPEG_WITH_EXIF),
+        );
+        await lib.close();
+    });
+
+    it("reads an original stored by an earlier version, whose JSON has no image metadata", async () => {
+        const lib = await open();
+        const outDir = join(root, "backup");
+        await lib.backup({ downloadDirectory: outDir });
+        dropImageMetadata(outDir, 600);
+
+        const second = await lib.backup({ downloadDirectory: outDir });
+
+        expect(second).toMatchObject({ downloaded: 0, failed: 0 });
+        expect(fileJSON(outDir, 600).imageMetadata).toEqual(
+            imageMetadataOf(JPEG_WITH_EXIF),
+        );
+        await lib.close();
+    });
+
+    it("reads an original the run stores again, though its JSON has image metadata", async () => {
+        const bytes = originals();
+        const lib = await open(bytes);
+        const outDir = join(root, "backup");
+        await lib.backup({ downloadDirectory: outDir });
+        rmSync(saved(outDir, "600.jpg"));
+        bytes.set(600, HEIC_WITH_EXIF);
+
+        const second = await lib.backup({ downloadDirectory: outDir });
+
+        expect(second).toMatchObject({ downloaded: 1, failed: 0 });
+        expect(fileJSON(outDir, 600).imageMetadata).toEqual(
+            imageMetadataOf(HEIC_WITH_EXIF),
+        );
+        await lib.close();
+    });
+
+    // Root ignores file permissions, so this fails when run as root. The
+    // `test` phase of the `Dockerfile` runs as the `node` user.
+    it("gives the reason an original could not be read, failing neither the file nor the run", async () => {
+        const lib = await open();
+        const outDir = join(root, "backup");
+        await lib.backup({ downloadDirectory: outDir });
+        dropImageMetadata(outDir, 600);
+        const original = saved(outDir, "600.jpg");
+        chmodSync(original, 0o000);
+
+        const second = await lib
+            .backup({ downloadDirectory: outDir })
+            .finally(() => chmodSync(original, 0o600));
+
+        expect(second).toMatchObject({ failed: 0, errors: [] });
+        expect(existsSync(join(outDir, "failures.json"))).toBe(false);
+        expect(fileJSON(outDir, 600)).not.toHaveProperty("imageMetadata");
+        expect(fileJSON(outDir, 600).imageMetadataError).toMatch(/EACCES/);
+        await lib.close();
+    });
+});
+
 // Every entry under collections/, one level of directories deep, with each
 // symlink's target.
 const tree = (outDir: string): string[] => {