quak/test/cli/metadata-exif.test.ts

/**
 * Tests for reading EXIF (`src/exif.ts`) and the image metadata
 * `quak backup-metadata --exif` records.
 *
 * The originals come from users' libraries, so a truncated or corrupt file
 * must neither hang the read nor throw out of it: `readPhotoExif` gives `{}`,
 * and `backup-metadata` tells an EXIF block it cannot read apart from a file
 * that simply has no EXIF, carrying the reason in `exifError`. Each JPEG below
 * is a short hand-built byte array; the HEIC is a real file.
 */

import { describe, expect, it } from "vitest";
import { readPhotoExif } from "../../src/exif.js";
import { extractImageMetadata } from "../../src/metadata-backup.js";
import { HEIC_WITH_EXIF } from "../exif-heic.js";

const SOI = [0xff, 0xd8]; // start of image
const SOS = [0xff, 0xda, 0x00, 0x02]; // start of scan
const EXIF_HEADER = [0x45, 0x78, 0x69, 0x66, 0x00, 0x00]; // "Exif\0\0"
const APP0 = [0xff, 0xe0, 0x00, 0x04, 0x00, 0x00];
const ZERO_LENGTH_APP0 = [0xff, 0xe0, 0x00, 0x00];

// A big-endian TIFF block with one IFD entry: Orientation (0x0112), SHORT, 6.
const TIFF_ORIENTATION_6 = [
    0x4d, 0x4d, 0x00, 0x2a, 0x00, 0x00, 0x00, 0x08, 0x00, 0x01, 0x01, 0x12,
    0x00, 0x03, 0x00, 0x00, 0x00, 0x01, 0x00, 0x06, 0x00, 0x00, 0x00, 0x00,
    0x00, 0x00,
];

// An APP1 segment whose length field matches its data.
const app1 = (data: number[]): number[] => {
    const len = data.length + 2;
    return [0xff, 0xe1, len >> 8, len & 0xff, ...data];
};

const bytes = (...parts: number[][]): Uint8Array =>
    new Uint8Array(parts.flat());

describe("readPhotoExif", () => {
    it("reads the common fields of a valid JPEG", () => {
        const data = [...EXIF_HEADER, ...TIFF_ORIENTATION_6];
        expect(readPhotoExif(bytes(SOI, app1(data), SOS))).toStrictEqual({
            orientation: 6,
        });
    });

    it.each([
        [
            "a file that is not an image",
            new TextEncoder().encode("just some text, not an image"),
        ],
        [
            "a PNG without EXIF",
            bytes([0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a]),
        ],
        ["a JPEG without EXIF", bytes(SOI, APP0, SOS)],
        // A length under 8 cannot hold the six-byte "Exif\0\0" header. This one
        // has length 7 and holds only "Exif\0", so a read past its end would
        // take the next segment's bytes as EXIF.
        [
            "an APP1 segment too short to hold the Exif header",
            bytes(SOI, app1(EXIF_HEADER.slice(0, 5)), SOS),
        ],
        [
            "an APP1 segment holding just the Exif header",
            bytes(SOI, app1(EXIF_HEADER), SOS),
        ],
        [
            "a JPEG truncated inside a segment header",
            bytes(SOI, [0xff, 0xe1, 0x00]),
        ],
        ["a JPEG that ends before the image data", bytes(SOI, APP0)],
        // A length of 0 would step a scan by 2 bytes at a time through the
        // rest of the file, reading garbage as markers.
        [
            "a zero-length segment",
            bytes(
                SOI,
                ZERO_LENGTH_APP0,
                ZERO_LENGTH_APP0,
                ZERO_LENGTH_APP0,
                ZERO_LENGTH_APP0,
                SOS,
            ),
        ],
        ["a segment length of 1", bytes(SOI, [0xff, 0xe0, 0x00, 0x01], SOS)],
        // APP1 claims 0x4000 bytes but only the "Exif\0\0" header follows.
        [
            "a segment length that runs past the end of the file",
            bytes(SOI, [0xff, 0xe1, 0x40, 0x00], EXIF_HEADER),
        ],
        // "XX" where the TIFF byte order belongs.
        [
            "an EXIF block that cannot be parsed",
            bytes(SOI, app1([...EXIF_HEADER, 0x58, 0x58]), SOS),
        ],
    ])("returns no fields for %s", (_, input) => {
        expect(readPhotoExif(input)).toStrictEqual({});
    });
});

describe("extractImageMetadata", () => {
    it("parses EXIF from a valid JPEG", () => {
        const meta = extractImageMetadata(
            bytes(SOI, app1([...EXIF_HEADER, ...TIFF_ORIENTATION_6]), SOS),
        );
        expect(meta?.exifError).toBeUndefined();
        expect(meta?.exif).toMatchObject({ Orientation: { value: 6 } });
    });

    it("parses EXIF from a HEIC", () => {
        const meta = extractImageMetadata(HEIC_WITH_EXIF);
        expect(meta?.exifError).toBeUndefined();
        expect(meta?.exif).toMatchObject({
            Make: { value: ["Canon"] },
            Model: { value: ["EOS R5"] },
            DateTimeOriginal: { value: ["2021:07:15 14:30:00"] },
            Orientation: { value: 6 },
            GPSLatitudeRef: { value: ["N"] },
        });
    });

    it("returns nothing for a file that is not an image", () => {
        const text = new TextEncoder().encode("just some text, not an image");
        expect(extractImageMetadata(text)).toBeUndefined();
    });

    it("records the reason when the JPEG is malformed", () => {
        const meta = extractImageMetadata(
            bytes(SOI, [0xff, 0xe1, 0x40, 0x00], EXIF_HEADER),
        );
        expect(meta?.exif).toBeUndefined();
        expect(meta?.exifError).toBe(
            "no tag could be read from the EXIF block",
        );
    });

    it("keeps the raw bytes and the reason when EXIF cannot be parsed", () => {
        // The raw bytes are the whole EXIF block as exifreader finds it: for a
        // JPEG, the APP1 segment, marker and length included.
        const segment = app1([...EXIF_HEADER, 0x58, 0x58]);
        const meta = extractImageMetadata(bytes(SOI, segment, SOS));
        expect(meta?.exif).toBeUndefined();
        expect(meta?.exifRaw).toBe(Buffer.from(segment).toString("base64"));
        expect(meta?.exifError).toBe(
            "no tag could be read from the EXIF block",
        );
    });
});