exif(): read HEIF/HEIC originals with exifreader (closes #145)

`photo.exif()` and `quak backup-metadata --exif` now read EXIF through `exifreader`. HEIC/HEIF originals get EXIF, including a live photo's image, as do the other formats `exifreader` reads. It replaces `exif-reader` and the hand-written JPEG scan. `PhotoExif` is unchanged.

The `backup-metadata` dump now holds `exifreader`'s tag output, with unnamed tags keyed `undefined-` plus their number. GPS altitude without a reference counts as above sea level. A latitude or longitude without its hemisphere tag, an unreadable text tag, and a date the parser rejects each give no field.

Licence: `exifreader` is MPL-2.0, used unmodified.

Model: opus-5-5

src/exif.ts

@@ -1,60 +1,34 @@
-// EXIF in a JPEG's bytes. `backup-metadata --exif` records the whole EXIF block
-// it finds; `Photo.exif()` returns the common fields picked from it here.
+// EXIF in an original's bytes, read with exifreader, which reads it from JPEG,
+// HEIC/HEIF, AVIF, PNG, WebP and the other image formats it supports.
+// `backup-metadata --exif` records every EXIF tag it finds except the
+// thumbnail's; `Photo.exif()` returns the common fields picked from them here.
 
-import exifReader from "exif-reader";
+import ExifReader, { type ExpandedTags } from "exifreader";
 
-// Find the raw EXIF APP1 segment in JPEG bytes. Returns `exif` (the segment
-// data, starting at the "Exif\0\0" header) when there is one, nothing when the
-// bytes are not a JPEG or carry no EXIF, and `error` when the segment layout is
-// malformed. Each segment length is checked against the bytes that remain and
-// each step moves forward by at least 4 bytes, so the scan ends on any input.
-export const extractExifFromJpeg = (
-    buf: Uint8Array,
-): { exif?: Buffer; error?: string } => {
-    if (buf[0] !== 0xff || buf[1] !== 0xd8) return {};
-    let offset = 2;
-    while (offset < buf.length) {
-        if (offset + 2 > buf.length)
-            return { error: `truncated segment marker at byte ${offset}` };
-        if (buf[offset] !== 0xff)
-            return { error: `no segment marker at byte ${offset}` };
-        const marker = buf[offset + 1]!;
-        if (marker === 0xda) return {}; // start of scan, no more markers
-        if (offset + 4 > buf.length)
-            return { error: `truncated segment length at byte ${offset}` };
-        const len = (buf[offset + 2]! << 8) | buf[offset + 3]!;
-        // The length counts its own two bytes, so anything under 2 is invalid.
-        if (len < 2)
-            return {
-                error: `segment length ${len} at byte ${offset} is too small`,
-            };
-        if (offset + 2 + len > buf.length)
-            return {
-                error: `segment length ${len} at byte ${offset} runs past the end of the file`,
-            };
-        if (marker === 0xe1) {
-            // APP1 — check for "Exif\0\0" header. A length under 8 cannot hold
-            // the six-byte header, so the segment is not EXIF; below 6 the
-            // bytes compared would also lie past the segment.
-            if (
-                len >= 8 &&
-                buf[offset + 4] === 0x45 &&
-                buf[offset + 5] === 0x78 &&
-                buf[offset + 6] === 0x69 &&
-                buf[offset + 7] === 0x66
-            ) {
-                return {
-                    exif: Buffer.from(
-                        buf.buffer,
-                        buf.byteOffset + offset + 4,
-                        len - 2,
-                    ),
-                };
-            }
-        }
-        offset += 2 + len;
+// The EXIF tags in `bytes` (`exif`), the GPS position exifreader computes from
+// them (`gps`), and where the EXIF block lies in `bytes` (`metadataRange`).
+// Undefined when exifreader cannot read the file at all, such as a video. An
+// EXIF block it finds but reads no tag from comes back as an empty `exif`.
+// `exif` holds every tag except the thumbnail's; a tag exifreader has no name
+// for is keyed `undefined-<tag number>`. Each tag's `computed` holds its value
+// as a string or number, or as an array of them for a tag with several values,
+// such as `GPSLatitude`'s `[40, 26, 46]`. A fraction with a zero denominator
+// computes to null.
+export const readExifTags = (bytes: Uint8Array): ExpandedTags | undefined => {
+    try {
+        return ExifReader.loadView(
+            new DataView(bytes.buffer, bytes.byteOffset, bytes.byteLength),
+            {
+                expanded: true,
+                computed: true,
+                includeOffsets: true,
+                includeUnknown: true,
+                includeTags: { exif: true, gps: true },
+            },
+        );
+    } catch {
+        return undefined;
     }
-    return { error: "file ends before the image data" };
 };
 
 // The common EXIF fields of an original. Each is absent when the file lacks it.
@@ -63,9 +37,9 @@ export interface PhotoExif {
     model?: string;
     lensModel?: string;
     // When the photo was taken, by the camera's clock. EXIF writes this as text
-    // with no time zone, and exif-reader reads that text as if it were UTC: the
-    // Date's UTC fields are the clock reading, which is the moment it was taken
-    // only when the clock was set to UTC.
+    // with no time zone, and it is read as if it were UTC: the Date's UTC
+    // fields are the clock reading, which is the moment it was taken only when
+    // the clock was set to UTC.
     dateTimeOriginal?: Date;
     // The camera clock's offset from UTC, such as "+02:00".
     offsetTimeOriginal?: string;
@@ -84,56 +58,52 @@ export interface PhotoExif {
     gpsAltitude?: number;
 }
 
+// exifreader gives "<faulty value>" for a tag whose value lies outside the
+// file; that tag is left out like one the file lacks.
 const asString = (v: unknown): string | undefined =>
-    typeof v === "string" && v.length > 0 ? v : undefined;
+    typeof v === "string" && v.length > 0 && v !== "<faulty value>"
+        ? v
+        : undefined;
 
 const asNumber = (v: unknown): number | undefined =>
     typeof v === "number" && Number.isFinite(v) ? v : undefined;
 
-const asDate = (v: unknown): Date | undefined =>
-    v instanceof Date && !Number.isNaN(v.getTime()) ? v : undefined;
-
-// EXIF writes a GPS coordinate as three numbers: degrees, minutes and seconds.
-// This is them as decimal degrees, negated when `negative`.
-const asDegrees = (v: unknown, negative: boolean): number | undefined => {
-    if (!Array.isArray(v) || v.length !== 3) return undefined;
-    const [d, m, s] = v.map(asNumber);
-    if (d === undefined || m === undefined || s === undefined) return undefined;
-    const degrees = d + m / 60 + s / 3600;
-    return negative ? -degrees : degrees;
+// EXIF writes a date and time as "2021:07:15 14:30:00". This is that reading
+// in a Date's UTC fields.
+const asDate = (v: unknown): Date | undefined => {
+    const m =
+        typeof v === "string"
+            ? /^(\d{4}):(\d{2}):(\d{2}) (\d{2}:\d{2}:\d{2})$/.exec(v)
+            : null;
+    if (!m) return undefined;
+    const date = new Date(`${m[1]}-${m[2]}-${m[3]}T${m[4]}Z`);
+    return Number.isNaN(date.getTime()) ? undefined : date;
 };
 
-// The common fields of a JPEG's EXIF block: `{}` when the bytes are not a JPEG,
-// have no EXIF block, or exif-reader cannot parse it.
+// The common fields of an original's EXIF: `{}` when the file has no EXIF,
+// exifreader cannot read its EXIF, or it is not an image exifreader reads.
 export const readPhotoExif = (bytes: Uint8Array): PhotoExif => {
-    const { exif } = extractExifFromJpeg(bytes);
-    if (exif === undefined) return {};
-    let tags: ReturnType<typeof exifReader>;
-    try {
-        tags = exifReader(exif);
-    } catch {
-        return {};
-    }
-    const image = tags.Image ?? {};
-    const photo = tags.Photo ?? {};
-    const gps = tags.GPSInfo ?? {};
-    const altitude = asNumber(gps.GPSAltitude);
+    const tags = readExifTags(bytes);
+    const exif = tags?.exif;
+    const gps = tags?.gps;
+    const altitude = asNumber(exif?.GPSAltitude?.computed);
     const fields: PhotoExif = {
-        make: asString(image.Make),
-        model: asString(image.Model),
-        lensModel: asString(photo.LensModel),
-        dateTimeOriginal: asDate(photo.DateTimeOriginal),
-        offsetTimeOriginal: asString(photo.OffsetTimeOriginal),
-        exposureTime: asNumber(photo.ExposureTime),
-        fNumber: asNumber(photo.FNumber),
-        iso: asNumber(photo.ISOSpeedRatings),
-        focalLength: asNumber(photo.FocalLength),
-        orientation: asNumber(image.Orientation),
-        gpsLatitude: asDegrees(gps.GPSLatitude, gps.GPSLatitudeRef === "S"),
-        gpsLongitude: asDegrees(gps.GPSLongitude, gps.GPSLongitudeRef === "W"),
+        make: asString(exif?.Make?.computed),
+        model: asString(exif?.Model?.computed),
+        lensModel: asString(exif?.LensModel?.computed),
+        dateTimeOriginal: asDate(exif?.DateTimeOriginal?.computed),
+        offsetTimeOriginal: asString(exif?.OffsetTimeOriginal?.computed),
+        exposureTime: asNumber(exif?.ExposureTime?.computed),
+        fNumber: asNumber(exif?.FNumber?.computed),
+        // Only when the tag holds a single number, as most cameras write it.
+        iso: asNumber(exif?.ISOSpeedRatings?.computed),
+        focalLength: asNumber(exif?.FocalLength?.computed),
+        orientation: asNumber(exif?.Orientation?.computed),
+        gpsLatitude: asNumber(gps?.Latitude),
+        gpsLongitude: asNumber(gps?.Longitude),
         // A GPSAltitudeRef of 1 means the altitude is below sea level.
         gpsAltitude:
-            altitude !== undefined && gps.GPSAltitudeRef === 1
+            altitude !== undefined && exif?.GPSAltitudeRef?.value === 1
                 ? -altitude
                 : altitude,
     };