Merge pull request 'feat/raw-thumb-embedded-preview' (#59) from feat/raw-thumb-embedded-preview into master

Reviewed-on: #59

CLAUDE.md

@@ -111,6 +111,15 @@ All database access goes through trait-based DAOs (e.g., `ExifDao`, `SqliteExifD
 2. Creates 200x200 thumbnails in THUMBNAILS directory (mirrors source structure)
 3. Videos: extracts frame at 3-second mark via ffmpeg
 4. Images: uses `image` crate for JPEG/PNG processing
+5. RAW formats (NEF/CR2/ARW/DNG/etc.): the `image` crate can't decode RAW
+   pixel data, so the pipeline pulls an embedded JPEG preview instead. Fast
+   path is `exif::read_jpeg_at_ifd` against IFD0 (PRIMARY) and IFD1
+   (THUMBNAIL) — covers most older bodies and DNGs. Slow-path fallback shells
+   out to **`exiftool`** for `PreviewImage` / `JpgFromRaw` / `OtherImage`,
+   which reaches MakerNote / SubIFD-hosted previews kamadak-exif can't see
+   (e.g. Nikon's `PreviewIFD`, where modern Nikon bodies store the full-res
+   review JPEG). All candidates are pooled and the largest valid JPEG wins.
+   See `src/exif.rs::extract_embedded_jpeg_preview`.
 
 **File Watching:**
 Runs in background thread with two-tier strategy:
@@ -364,6 +373,8 @@ Configurable env:
 
 ## Dependencies of Note
 
+### Rust crates
+
 - **actix-web**: HTTP framework
 - **diesel**: ORM for SQLite
 - **jsonwebtoken**: JWT implementation
@@ -374,3 +385,18 @@ Configurable env:
 - **opentelemetry**: Distributed tracing
 - **bcrypt**: Password hashing
 - **infer**: Magic number file type detection
+
+### External binaries (must be on `PATH`)
+
+- **`ffmpeg`** — video thumbnail extraction (`StreamActor`, HLS pipeline) and
+  the HEIF/HEIC/NEF/ARW thumbnail fallback in `generate_image_thumbnail_ffmpeg`.
+  Required for any deploy that holds video or HEIF files.
+- **`exiftool`** — optional but strongly recommended for RAW-heavy libraries.
+  The thumbnail pipeline shells out to it as the slow-path fallback for
+  embedded preview extraction (Nikon MakerNote `PreviewIFD`, Canon SubIFDs,
+  etc. — anything kamadak-exif's IFD0/IFD1 readers can't reach). Without
+  exiftool installed, RAWs whose preview lives outside IFD0/IFD1 will fall
+  through to ffmpeg, which often produces black thumbnails. Install via
+  package manager: `apt install libimage-exiftool-perl`,
+  `brew install exiftool`, `winget install OliverBetz.ExifTool`, or
+  `choco install exiftool`.

README.md

@@ -28,14 +28,31 @@ Builds used in development: the `gyan.dev` full build on Windows, and distro `ff
 packages on Linux work fine. If HEIC thumbnails silently fail, check
 `ffmpeg -formats | grep heif` to confirm HEIF support.
 
-### RAW photo thumbnails (no extra dependency)
+### RAW photo thumbnails
 RAW formats (ARW, NEF, CR2, CR3, DNG, RAF, ORF, RW2, PEF, SRW, TIFF) are thumbnailed
-by reading the embedded JPEG preview from the TIFF IFD1 using `kamadak-exif`. No
-external RAW decoder (libraw / dcraw) is required. Files without an embedded preview
-fall back to ffmpeg (works for most NEF files), and anything that still can't be
-decoded is marked with a `<thumb>.unsupported` sentinel in the thumbnail directory
-so we don't retry it every scan. Delete those sentinels to force retries after a
-tooling upgrade.
+by reading an embedded JPEG preview out of the TIFF container — no external RAW
+decoder (libraw / dcraw) is involved. The pipeline tries two layers in order and
+keeps the largest valid JPEG:
+
+1. **Fast path (no extra dependency)** — `kamadak-exif` reads
+   `JPEGInterchangeFormat` from IFD0 / IFD1 directly. Covers older bodies and
+   most DNGs.
+2. **`exiftool` fallback (recommended for RAW-heavy libraries)** — shells out
+   to extract `PreviewImage` / `JpgFromRaw` / `OtherImage`, which reaches
+   MakerNote and SubIFD-hosted previews kamadak-exif can't see (e.g. Nikon's
+   `PreviewIFD`, where modern Nikon bodies stash the full-res review JPEG).
+   If `exiftool` isn't on `PATH` this layer is skipped silently and only the
+   fast-path result is used.
+
+Install `exiftool` via your package manager:
+- macOS: `brew install exiftool`
+- Linux (Debian/Ubuntu): `apt install libimage-exiftool-perl`
+- Windows: `winget install OliverBetz.ExifTool` or `choco install exiftool`
+
+Files where neither layer produces a valid preview fall back to ffmpeg. Anything
+that still can't be decoded is marked with a `<thumb>.unsupported` sentinel in
+the thumbnail directory so we don't retry it every scan. Delete those sentinels
+(and any cached black thumbnails) to force retries after a tooling upgrade.
 
 ## Environment
 There are a handful of required environment variables to have the API run.

src/exif.rs

@@ -1,6 +1,7 @@
 use std::fs::File;
 use std::io::{BufReader, Read, Seek, SeekFrom};
 use std::path::Path;
+use std::process::Command;
 
 use anyhow::{Result, anyhow};
 use exif::{In, Reader, Tag, Value};
@@ -28,7 +29,7 @@ pub struct ExifData {
 
 /// TIFF-based RAW formats where `JPEGInterchangeFormat` offsets are
 /// absolute file offsets (the file itself is a TIFF container).
-fn is_tiff_raw(path: &Path) -> bool {
+pub fn is_tiff_raw(path: &Path) -> bool {
     matches!(
         path.extension()
             .and_then(|e| e.to_str())
@@ -40,26 +41,18 @@ fn is_tiff_raw(path: &Path) -> bool {
     )
 }
 
-/// Returns the bytes of the embedded JPEG thumbnail in a TIFF-based RAW or
-/// TIFF file. Used to thumbnail formats whose RAW pixel data can't be decoded
-/// by our normal tools (e.g. Sony ARW). Returns `None` if no preview is
-/// present, the file isn't a TIFF container, or the data doesn't look like
-/// a valid JPEG.
-pub fn extract_embedded_jpeg_preview(path: &Path) -> Option<Vec<u8>> {
-    if !is_tiff_raw(path) {
-        return None;
-    }
-
-    let file = File::open(path).ok()?;
-    let mut bufreader = BufReader::new(file);
-    let exif = Reader::new().read_from_container(&mut bufreader).ok()?;
-
+/// Read the JPEG bytes pointed to by `JPEGInterchangeFormat` /
+/// `JPEGInterchangeFormatLength` in a single IFD. Returns `None` on any
+/// failure: tags missing, length zero, file read failure, or bytes that
+/// don't start with the JPEG SOI marker (some MakerNote pointers reference
+/// TIFF-wrapped previews or other non-JPEG payloads we can't load).
+fn read_jpeg_at_ifd(exif: &exif::Exif, path: &Path, ifd: In) -> Option<Vec<u8>> {
     let offset = exif
-        .get_field(Tag::JPEGInterchangeFormat, In::THUMBNAIL)?
+        .get_field(Tag::JPEGInterchangeFormat, ifd)?
         .value
         .get_uint(0)?;
     let length = exif
-        .get_field(Tag::JPEGInterchangeFormatLength, In::THUMBNAIL)?
+        .get_field(Tag::JPEGInterchangeFormatLength, ifd)?
         .value
         .get_uint(0)?;
     if length == 0 {
@@ -71,8 +64,6 @@ pub fn extract_embedded_jpeg_preview(path: &Path) -> Option<Vec<u8>> {
     let mut buf = vec![0u8; length as usize];
     file.read_exact(&mut buf).ok()?;
 
-    // JPEG SOI marker sanity check — MakerNote offsets sometimes point at
-    // TIFF-wrapped previews or other non-JPEG data.
     if buf.len() < 2 || buf[0] != 0xFF || buf[1] != 0xD8 {
         return None;
     }
@@ -80,6 +71,95 @@ pub fn extract_embedded_jpeg_preview(path: &Path) -> Option<Vec<u8>> {
     Some(buf)
 }
 
+/// Tags exiftool exposes for embedded JPEG previews, in priority order. The
+/// largest valid JPEG returned by any of them wins. Different camera makers
+/// stash their largest preview under different names: Nikon's full-res
+/// preview lives under `PreviewImage` in the MakerNote `PreviewIFD`, Canon /
+/// Sony often expose theirs as `JpgFromRaw`, and `OtherImage` is a catch-all
+/// some sub-IFD chains use.
+const EXIFTOOL_PREVIEW_TAGS: &[&str] = &["PreviewImage", "JpgFromRaw", "OtherImage"];
+
+/// Shell out to `exiftool -b -<tag>` for one tag. Returns the response bytes
+/// only if exiftool succeeded AND the bytes start with the JPEG SOI marker
+/// (some MakerNote tags hold TIFF-wrapped previews or other non-JPEG payloads
+/// we can't load).
+fn extract_exiftool_tag(path: &Path, tag: &str) -> Option<Vec<u8>> {
+    let output = Command::new("exiftool")
+        .arg("-b")
+        .arg(format!("-{}", tag))
+        .arg(path)
+        .output()
+        .ok()?;
+
+    if !output.status.success() {
+        return None;
+    }
+    let bytes = output.stdout;
+    if bytes.len() < 2 || bytes[0] != 0xFF || bytes[1] != 0xD8 {
+        return None;
+    }
+    Some(bytes)
+}
+
+/// Try each EXIFTOOL_PREVIEW_TAGS in turn and return the largest valid JPEG.
+/// If `exiftool` isn't on PATH the very first spawn returns `None` and we
+/// silently bail — callers fall back to whatever the IFD0/IFD1 fast path
+/// found.
+fn extract_preview_via_exiftool(path: &Path) -> Option<Vec<u8>> {
+    let mut best: Option<Vec<u8>> = None;
+    for &tag in EXIFTOOL_PREVIEW_TAGS {
+        let Some(bytes) = extract_exiftool_tag(path, tag) else {
+            continue;
+        };
+        match &best {
+            None => best = Some(bytes),
+            Some(b) if b.len() < bytes.len() => best = Some(bytes),
+            _ => {}
+        }
+    }
+    best
+}
+
+/// Returns the bytes of the embedded JPEG preview in a TIFF-based RAW or
+/// TIFF file. Used to thumbnail formats whose RAW pixel data can't be decoded
+/// by our normal tools (e.g. Sony ARW), and to serve a usable full-size
+/// image for clients that can't decode the RAW container directly. Returns
+/// `None` if no preview is present, the file isn't a TIFF container, or the
+/// data doesn't look like a valid JPEG.
+///
+/// Strategy:
+///   1. Fast path: read `JPEGInterchangeFormat` from IFD0 (PRIMARY) and IFD1
+///      (THUMBNAIL) directly via kamadak-exif. No subprocess, no external
+///      dependency.
+///   2. Slow path: shell out to `exiftool -b -<tag>` for each of
+///      `PreviewImage` / `JpgFromRaw` / `OtherImage`. kamadak-exif can't
+///      reach SubIFDs or MakerNote sub-IFDs, but most modern Nikon bodies
+///      stash their large preview JPEG in the Nikon MakerNote's PreviewIFD;
+///      Canon / Sony often use `JpgFromRaw` in a SubIFD chain. Skipped
+///      gracefully if exiftool isn't on PATH.
+///
+/// All candidates are pooled and the largest valid JPEG wins, so a deploy
+/// without exiftool degrades to "fast-path only" behavior rather than
+/// breaking outright.
+pub fn extract_embedded_jpeg_preview(path: &Path) -> Option<Vec<u8>> {
+    if !is_tiff_raw(path) {
+        return None;
+    }
+
+    let file = File::open(path).ok()?;
+    let mut bufreader = BufReader::new(file);
+    let exif = Reader::new().read_from_container(&mut bufreader).ok()?;
+
+    let primary = read_jpeg_at_ifd(&exif, path, In::PRIMARY);
+    let thumbnail = read_jpeg_at_ifd(&exif, path, In::THUMBNAIL);
+    let exiftool = extract_preview_via_exiftool(path);
+
+    [primary, thumbnail, exiftool]
+        .into_iter()
+        .flatten()
+        .max_by_key(|v| v.len())
+}
+
 pub fn supports_exif(path: &Path) -> bool {
     if let Some(ext) = path.extension() {
         let ext_lower = ext.to_string_lossy().to_lowercase();

src/main.rs

@@ -215,6 +215,23 @@ async fn get_image(
             }
         }
 
+        // Full-size requests for RAW formats (NEF/CR2/ARW/etc.) can't just
+        // NamedFile-stream the original bytes — browsers won't decode the
+        // RAW container, so a `<img src=...>` lands as a broken image. Serve
+        // the embedded JPEG preview instead (typically the camera's in-body
+        // review JPEG, ~1–2 MP). Falls through to NamedFile if no preview is
+        // available, which preserves the historical behavior for callers
+        // that genuinely want the original bytes.
+        if image_size == PhotoSize::Full && exif::is_tiff_raw(&path) {
+            if let Some(preview) = exif::extract_embedded_jpeg_preview(&path) {
+                span.set_status(Status::Ok);
+                return HttpResponse::Ok()
+                    .content_type("image/jpeg")
+                    .insert_header(("Cache-Control", "public, max-age=3600"))
+                    .body(preview);
+            }
+        }
+
         if let Ok(file) = NamedFile::open(&path) {
             span.set_status(Status::Ok);
             // Enable ETag and set cache headers for full images (1 hour cache)