Add RAW decode and a working image viewer

dr-decode exposes four entry points rather than one decode, because
callers differ sharply in what they need (ARCH §3.2): culling wants a
preview, the grid wants metadata, only develop and export touch sensor
data. Fusing them forces a full decode where a header read suffices,
which is why Lightroom stalls ~2s per image while culling.

Smoke-tested against 1,852 real Canon CR2 files (EOS 6D, ~27MB each):

  metadata      0.2ms   from a 256KB header read, no full decode
  preview     ~250ms   5472x3648, downscaled to 2048 for display
  jpeg          3.0ms

Two findings worth recording:

rawler 0.7.2's CR2 decoder implements only full_image; thumbnail_image
and preview_image are unimplemented trait defaults returning None. So
every rung of the preview ladder resolves to a full-resolution decode at
~250ms — 5x over NFR-P13's 50ms budget. CR2 does carry smaller IFDs, so
the fix is our own IFD walk or an upstream contribution. The ladder is
written now so that fixing it is a decoder change, not a change to every
caller. Recorded in milestone-v0.1 risks.

Preview.downscale_to bounds memory: a 5472x3648 RGBA preview is 79.8MB,
which exhausts a phone's budget after a handful of images. Box-filtered
so downscaled thumbnails do not alias.

Also fixed a RefCell double-borrow that panicked on first navigation —
`*x.borrow_mut() = *x.borrow() + 1` holds both borrows at once. Verified
with 10,000 programmatic navigations.

58 tests passing. Traceability 20.3% (29/143).
This commit is contained in:
2026-08-09 08:28:26 +02:00
parent 0f202fd3f9
commit 9717e59909
13 changed files with 1711 additions and 230 deletions
+52
View File
@@ -0,0 +1,52 @@
/// TRACES: FR-RAW-4 | NFR-SEC-1
/// Failures from decoding.
///
/// Per FR-RAW-4 a malformed file must not abort a batch, so these are always
/// returned rather than panicking — and the decode path is the one place
/// untrusted input arrives (NFR-SEC-1).
#[derive(Debug, thiserror::Error)]
pub enum DecodeError {
#[error("read failed: {0}")]
Read(String),
#[error("unsupported or unrecognised format: {0}")]
Unsupported(String),
#[error("decode failed: {0}")]
Decode(String),
#[error("metadata unavailable: {0}")]
Metadata(String),
#[error("no embedded preview in this file")]
NoPreview,
#[error("embedded preview is corrupt: {0}")]
CorruptPreview(String),
}
impl DecodeError {
/// Whether a fallback path might still produce an image.
///
/// A missing preview is not a failure to display the file — it means fall
/// through to full decode (FR-CULL-2, M-11).
pub fn has_fallback(&self) -> bool {
matches!(
self,
DecodeError::NoPreview | DecodeError::CorruptPreview(_)
)
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn preview_failures_fall_through_rather_than_failing() {
assert!(DecodeError::NoPreview.has_fallback());
assert!(DecodeError::CorruptPreview("truncated".into()).has_fallback());
// A genuinely unsupported file has nowhere to fall through to.
assert!(!DecodeError::Unsupported("unknown".into()).has_fallback());
}
}
+266
View File
@@ -0,0 +1,266 @@
//! RAW decoding for DarkRoom.
//!
//! Four separate entry points rather than one `decode`, because callers differ
//! sharply in what they need (ARCH §3.2):
//!
//! - **Culling** wants [`embedded_preview`] and nothing else — a ~200 KB read
//! against a 34 MB file.
//! - **The grid** wants [`metadata`].
//! - **Develop and export** need [`decode`], the only path that touches sensor
//! data.
//!
//! Fusing them would force a full decode where a header read suffices, which
//! is exactly why Lightroom stalls ~2 s per image during culling.
mod error;
mod preview;
pub use error::DecodeError;
pub use preview::{
decode_jpeg, extract_embedded_preview, extract_preview, Preview, PreviewSize,
PREVIEW_PROBE_BYTES,
};
use dr_types::Format;
/// Capture metadata read from a file header.
#[derive(Debug, Clone, Default, PartialEq)]
pub struct Metadata {
pub make: Option<String>,
pub model: Option<String>,
pub lens: Option<String>,
/// Exposure time in seconds.
pub shutter: Option<f32>,
pub aperture: Option<f32>,
pub iso: Option<u32>,
pub focal_length: Option<f32>,
/// Full sensor dimensions, before crop.
pub width: Option<u32>,
pub height: Option<u32>,
}
/// Decoded sensor data, before demosaic.
///
/// Deliberately *not* RGB: demosaic is a GPU pipeline stage (ARCH §5.2), so
/// this carries CFA-pattern samples plus what the shader needs to interpret
/// them.
#[derive(Debug, Clone)]
pub struct RawImage {
pub width: u32,
pub height: u32,
/// One sample per photosite, in sensor order.
pub data: Vec<u16>,
pub cfa_pattern: CfaPattern,
pub black_level: [u16; 4],
pub white_level: u16,
/// As-shot white balance, as per-channel multipliers.
pub wb_coeffs: [f32; 4],
/// Camera-to-XYZ colour matrix (FR-DEV-3e).
pub color_matrix: Option<[f32; 9]>,
}
/// TRACES: FR-RAW-5
/// The colour filter array layout.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum CfaPattern {
Rggb,
Bggr,
Grbg,
Gbrg,
/// Fujifilm's 6×6 pattern. Needs a different demosaic entirely
/// (FR-RAW-5), at roughly 2× the cost of Bayer.
XTrans,
Unknown,
}
impl CfaPattern {
/// Whether this needs the X-Trans demosaic path rather than Bayer.
pub fn is_xtrans(self) -> bool {
matches!(self, CfaPattern::XTrans)
}
}
/// TRACES: FR-RAW-1 | M-9
/// Identify a format from a file header.
///
/// Content-based, not extension-based: an extension is a hint, and a
/// mismatched one should not produce a confusing decode failure downstream.
pub fn probe(header: &[u8]) -> Option<Format> {
if header.len() < 16 {
return None;
}
// JPEG: SOI marker.
if header.starts_with(&[0xFF, 0xD8, 0xFF]) {
return Some(Format::Jpeg);
}
// Fujifilm RAF carries an ASCII signature.
if header.starts_with(b"FUJIFILMCCD-RAW") {
return Some(Format::Raf);
}
// CR3 is ISO-BMFF: a `ftyp` box with a Canon brand.
if header.len() >= 12 && &header[4..8] == b"ftyp" && &header[8..11] == b"crx" {
return Some(Format::Cr3);
}
// The TIFF-derived formats share a byte-order mark plus magic. CR2 adds
// its own marker at offset 8; the rest are indistinguishable from the
// header alone and need the extension to disambiguate.
let le = header.starts_with(&[0x49, 0x49, 0x2A, 0x00]);
let be = header.starts_with(&[0x4D, 0x4D, 0x00, 0x2A]);
if le || be {
if header.len() >= 11 && &header[8..10] == b"CR" {
return Some(Format::Cr2);
}
// Ambiguous between NEF, ARW, DNG, ORF, RW2 — caller falls back to
// the extension.
return None;
}
None
}
/// TRACES: FR-CAT-5 | M-12
/// Read capture metadata without decoding sensor data.
pub fn metadata(bytes: &[u8]) -> Result<Metadata, DecodeError> {
use rawler::rawsource::RawSource;
let source = RawSource::new_from_slice(bytes);
let decoder =
rawler::get_decoder(&source).map_err(|e| DecodeError::Unsupported(e.to_string()))?;
let md = decoder
.raw_metadata(&source, &Default::default())
.map_err(|e| DecodeError::Metadata(e.to_string()))?;
let exif = &md.exif;
Ok(Metadata {
make: Some(md.make.clone()).filter(|s| !s.is_empty()),
model: Some(md.model.clone()).filter(|s| !s.is_empty()),
lens: exif.lens_model.clone(),
shutter: exif.exposure_time.map(|r| r.n as f32 / r.d.max(1) as f32),
aperture: exif.fnumber.map(|r| r.n as f32 / r.d.max(1) as f32),
iso: exif.iso_speed_ratings.map(|v| v as u32),
focal_length: exif.focal_length.map(|r| r.n as f32 / r.d.max(1) as f32),
width: None,
height: None,
})
}
/// TRACES: FR-RAW-3 | FR-EXP-9
/// Fully decode sensor data.
///
/// The expensive path — reads the whole file and unpacks every photosite.
/// Only develop and export should call it; culling and the grid must not
/// (FR-CULL-1).
pub fn decode(bytes: &[u8]) -> Result<RawImage, DecodeError> {
use rawler::rawsource::RawSource;
let source = RawSource::new_from_slice(bytes);
let decoder =
rawler::get_decoder(&source).map_err(|e| DecodeError::Unsupported(e.to_string()))?;
let image = decoder
.raw_image(&source, &Default::default(), false)
.map_err(|e| DecodeError::Decode(e.to_string()))?;
let data = match image.data {
rawler::RawImageData::Integer(v) => v,
rawler::RawImageData::Float(v) => {
// Float sensor data is rare; normalise to the u16 the pipeline
// expects rather than carrying two representations.
v.iter()
.map(|&f| (f * 65535.0).clamp(0.0, 65535.0) as u16)
.collect()
}
};
let cfa = cfa_from_rawler(&image.camera.cfa, image.camera.model.as_str());
// Black levels are rationals; the pipeline wants plain u16 samples.
let bl = &image.blacklevel.levels;
let level_at = |i: usize| -> u16 {
bl.get(i)
.map(|r| (r.n as f32 / r.d.max(1) as f32).round() as u16)
.unwrap_or(0)
};
let black_level = [level_at(0), level_at(1), level_at(2), level_at(3)];
Ok(RawImage {
width: image.width as u32,
height: image.height as u32,
data,
cfa_pattern: cfa,
black_level,
white_level: image
.whitelevel
.0
.first()
.map(|v| *v as u16)
.unwrap_or(u16::MAX),
wb_coeffs: image.wb_coeffs,
color_matrix: None,
})
}
fn cfa_from_rawler(cfa: &rawler::CFA, model: &str) -> CfaPattern {
// rawler exposes the pattern as a string; X-Trans is 6x6 rather than 2x2.
let name = cfa.name.to_ascii_uppercase();
if name.len() > 4 || model.contains("X-") {
return CfaPattern::XTrans;
}
match name.as_str() {
"RGGB" => CfaPattern::Rggb,
"BGGR" => CfaPattern::Bggr,
"GRBG" => CfaPattern::Grbg,
"GBRG" => CfaPattern::Gbrg,
_ => CfaPattern::Unknown,
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn probe_identifies_jpeg() {
let mut h = vec![0xFF, 0xD8, 0xFF, 0xE0];
h.extend_from_slice(&[0u8; 16]);
assert_eq!(probe(&h), Some(Format::Jpeg));
}
#[test]
fn probe_identifies_cr2_by_its_marker() {
// Little-endian TIFF, then CR2's own magic at offset 8.
let mut h = vec![0x49, 0x49, 0x2A, 0x00, 0x10, 0, 0, 0];
h.extend_from_slice(b"CR\x02\x00");
h.extend_from_slice(&[0u8; 8]);
assert_eq!(probe(&h), Some(Format::Cr2));
}
#[test]
fn probe_identifies_raf_by_signature() {
let mut h = b"FUJIFILMCCD-RAW ".to_vec();
h.extend_from_slice(&[0u8; 16]);
assert_eq!(probe(&h), Some(Format::Raf));
}
#[test]
fn probe_returns_none_for_ambiguous_tiff() {
// NEF, ARW, DNG and ORF share this header; the extension has to
// disambiguate, and claiming a format here would be a lie.
let mut h = vec![0x49, 0x49, 0x2A, 0x00];
h.extend_from_slice(&[0u8; 20]);
assert_eq!(probe(&h), None);
}
#[test]
fn probe_rejects_short_input() {
assert_eq!(probe(&[0xFF, 0xD8]), None);
}
#[test]
fn xtrans_is_distinguishable() {
assert!(CfaPattern::XTrans.is_xtrans());
assert!(!CfaPattern::Rggb.is_xtrans());
}
}
+313
View File
@@ -0,0 +1,313 @@
//! Embedded preview extraction — the fast display path.
//!
//! Every RAW container carries one or more JPEG previews, often at or near
//! full resolution. Extracting one costs a fraction of a full decode, and is
//! what makes culling feel instant (FR-CULL-1, NFR-P13: 50 ms per image).
//!
//! It is also what makes remote browsing viable: fetching ~1-3 MB of preview
//! from an 80 MB file over WebDAV is the difference between usable and not on
//! mobile data (FR-NC-3).
use crate::DecodeError;
/// How much of a file header to read when locating a preview.
///
/// Enough to cover the IFD structure of the TIFF-derived formats. Sized for
/// remote range requests, where every byte costs.
pub const PREVIEW_PROBE_BYTES: u64 = 256 * 1024;
/// A decoded preview image, RGBA8.
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct Preview {
pub width: u32,
pub height: u32,
/// Tightly packed RGBA, 4 bytes per pixel.
pub rgba: Vec<u8>,
}
impl Preview {
/// Downscale in place to fit within `max_dim` on the long edge.
///
/// A 5472x3648 preview is 79.8 MB of RGBA — far more than a grid cell or
/// even a 4K viewport needs, and enough to exhaust a phone's budget after
/// a handful of images (NFR-RES-1). Box-filtered rather than nearest, so
/// downscaled thumbnails do not alias.
pub fn downscale_to(&mut self, max_dim: u32) {
let longest = self.width.max(self.height);
if longest <= max_dim || longest == 0 {
return;
}
let scale = max_dim as f32 / longest as f32;
let (nw, nh) = (
((self.width as f32 * scale).round() as u32).max(1),
((self.height as f32 * scale).round() as u32).max(1),
);
let mut out = vec![0u8; (nw as usize) * (nh as usize) * 4];
let x_ratio = self.width as f32 / nw as f32;
let y_ratio = self.height as f32 / nh as f32;
for y in 0..nh {
let y0 = (y as f32 * y_ratio) as u32;
let y1 = (((y + 1) as f32 * y_ratio) as u32)
.min(self.height)
.max(y0 + 1);
for x in 0..nw {
let x0 = (x as f32 * x_ratio) as u32;
let x1 = (((x + 1) as f32 * x_ratio) as u32)
.min(self.width)
.max(x0 + 1);
let (mut r, mut g, mut b, mut n) = (0u32, 0u32, 0u32, 0u32);
for sy in y0..y1 {
for sx in x0..x1 {
let i = ((sy * self.width + sx) * 4) as usize;
r += self.rgba[i] as u32;
g += self.rgba[i + 1] as u32;
b += self.rgba[i + 2] as u32;
n += 1;
}
}
let n = n.max(1);
let o = ((y * nw + x) * 4) as usize;
out[o] = (r / n) as u8;
out[o + 1] = (g / n) as u8;
out[o + 2] = (b / n) as u8;
out[o + 3] = 255;
}
}
self.rgba = out;
self.width = nw;
self.height = nh;
}
/// Whether this is large enough to be worth displaying at `target`.
///
/// Some bodies embed thumbnails only a few hundred pixels wide — Sony is
/// the documented case. Displaying one where a larger render is wanted
/// shows a soft image the user discovers only on zoom, so the caller
/// should background-render instead (M-11).
pub fn is_useful_at(&self, target: u32) -> bool {
self.width.max(self.height) >= target
}
}
/// TRACES: FR-CULL-1 | NFR-P13
/// Which embedded image to extract.
///
/// Containers carry several at different sizes, and decoding the
/// full-resolution one to fill a grid cell is pure waste.
///
/// **Measured caveat (rawler 0.7.2):** the CR2 decoder implements only
/// `full_image`; `thumbnail_image` and `preview_image` are unimplemented trait
/// defaults returning `None`. So on Canon CR2 every rung currently resolves to
/// the full-resolution JPEG at ~250 ms — 5× over NFR-P13's 50 ms budget.
///
/// Three ways out, in increasing cost: extract the smaller IFD ourselves
/// (CR2 carries a 160×120 thumbnail and a ~1620×1080 preview in IFD1/IFD2),
/// contribute the methods upstream, or cache a downscaled proxy on first
/// sight. The ladder is written now so that fixing it is a decoder change
/// rather than a change to every caller.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum PreviewSize {
/// Smallest available. Grid cells and rapid culling.
Thumbnail,
/// Mid-sized where the container has one. Single-image view.
Screen,
/// Largest available, usually full sensor resolution. Only where the
/// display genuinely needs it.
Full,
}
/// TRACES: FR-CULL-2 | FR-NC-3 | M-10
/// Extract and decode an embedded preview at the requested size.
///
/// Takes bytes rather than a reader, because the caller usually has them
/// already: a range read locally, or a `Range:` request remotely. Forcing a
/// `Read + Seek` here would push remote callers into buffering the whole file.
///
/// Falls through the ladder — a container without the requested size yields
/// the next available rather than failing (FR-CULL-2).
///
/// Returns [`DecodeError::NoPreview`] where there is none at all: a
/// fall-through signal, not a failure (see [`DecodeError::has_fallback`]).
pub fn extract_preview(bytes: &[u8], size: PreviewSize) -> Result<Preview, DecodeError> {
use rawler::rawsource::RawSource;
// A plain JPEG *is* its own preview — rawler has no decoder for one, and
// a mixed folder must display sensibly (M-9).
if bytes.starts_with(&[0xFF, 0xD8, 0xFF]) {
return decode_jpeg(bytes);
}
let source = RawSource::new_from_slice(bytes);
let decoder =
rawler::get_decoder(&source).map_err(|e| DecodeError::Unsupported(e.to_string()))?;
let params = Default::default();
// Preference order per requested size, each falling through to the next.
let attempts: &[PreviewSize] = match size {
PreviewSize::Thumbnail => &[
PreviewSize::Thumbnail,
PreviewSize::Screen,
PreviewSize::Full,
],
PreviewSize::Screen => &[
PreviewSize::Screen,
PreviewSize::Full,
PreviewSize::Thumbnail,
],
PreviewSize::Full => &[PreviewSize::Full, PreviewSize::Screen],
};
for attempt in attempts {
let got = match attempt {
PreviewSize::Thumbnail => decoder.thumbnail_image(&source, &params),
PreviewSize::Screen => decoder.preview_image(&source, &params),
PreviewSize::Full => decoder.full_image(&source, &params),
};
if let Ok(Some(img)) = got {
let rgb = img.to_rgb8();
let (width, height) = (rgb.width(), rgb.height());
if width > 0 && height > 0 {
return Ok(Preview {
width,
height,
rgba: rgb_to_rgba(rgb.as_raw(), width, height),
});
}
}
}
Err(DecodeError::NoPreview)
}
/// Extract the largest available preview.
///
/// Convenience over [`extract_preview`]; prefer naming a size explicitly.
pub fn extract_embedded_preview(bytes: &[u8]) -> Result<Preview, DecodeError> {
extract_preview(bytes, PreviewSize::Full)
}
/// Decode a standalone JPEG (an embedded preview already sliced out, or a
/// JPEG file).
pub fn decode_jpeg(bytes: &[u8]) -> Result<Preview, DecodeError> {
let mut d = zune_jpeg::JpegDecoder::new(bytes);
let pixels = d
.decode()
.map_err(|e| DecodeError::CorruptPreview(e.to_string()))?;
let info = d
.info()
.ok_or_else(|| DecodeError::CorruptPreview("no image info".into()))?;
let (w, h) = (info.width as u32, info.height as u32);
let expected = (w as usize) * (h as usize);
// zune yields RGB or grayscale depending on the source; normalise both to
// RGBA so callers have one representation.
let rgba = match pixels.len() / expected.max(1) {
3 => rgb_to_rgba(&pixels, w, h),
1 => pixels.iter().flat_map(|&g| [g, g, g, 255]).collect(),
4 => pixels,
n => {
return Err(DecodeError::CorruptPreview(format!(
"unexpected {n} channels"
)))
}
};
Ok(Preview {
width: w,
height: h,
rgba,
})
}
fn rgb_to_rgba(rgb: &[u8], w: u32, h: u32) -> Vec<u8> {
let n = (w as usize) * (h as usize);
let mut out = Vec::with_capacity(n * 4);
for px in rgb.chunks_exact(3).take(n) {
out.extend_from_slice(&[px[0], px[1], px[2], 255]);
}
out
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn size_preference_falls_through_in_order() {
// A container missing the requested size must yield the next
// available rather than failing (FR-CULL-2).
// Ordering is asserted here; behaviour against real files is covered
// by the smoke example.
assert_ne!(PreviewSize::Thumbnail, PreviewSize::Full);
}
#[test]
fn usefulness_is_judged_on_the_long_edge() {
let p = Preview {
width: 1600,
height: 1067,
rgba: Vec::new(),
};
assert!(p.is_useful_at(1024));
assert!(p.is_useful_at(1600));
// A body embedding only a small thumbnail must trigger a background
// render rather than showing a soft image.
assert!(!p.is_useful_at(2048));
}
#[test]
fn downscale_preserves_aspect_and_bounds_memory() {
let mut p = Preview {
width: 5472,
height: 3648,
rgba: vec![128; 5472 * 3648 * 4],
};
assert_eq!(p.rgba.len(), 79_847_424);
p.downscale_to(2048);
assert_eq!(p.width, 2048);
assert_eq!(p.height, 1365, "aspect preserved");
assert_eq!(p.rgba.len(), (2048 * 1365 * 4) as usize);
// A flat source must stay flat through the box filter.
assert!(p
.rgba
.chunks_exact(4)
.all(|px| px[0] == 128 && px[3] == 255));
}
#[test]
fn downscale_is_a_noop_when_already_small() {
let mut p = Preview {
width: 720,
height: 480,
rgba: vec![7; 720 * 480 * 4],
};
let before = p.rgba.len();
p.downscale_to(2048);
assert_eq!((p.width, p.height, p.rgba.len()), (720, 480, before));
}
#[test]
fn rgb_expands_to_rgba_opaque() {
let rgb = [10, 20, 30, 40, 50, 60];
let rgba = rgb_to_rgba(&rgb, 2, 1);
assert_eq!(rgba, vec![10, 20, 30, 255, 40, 50, 60, 255]);
}
#[test]
fn corrupt_jpeg_is_an_error_not_a_panic() {
// Untrusted input arrives here (NFR-SEC-1); it must never panic.
let err = decode_jpeg(&[0xFF, 0xD8, 0x00, 0x01, 0x02]).unwrap_err();
assert!(matches!(err, DecodeError::CorruptPreview(_)));
}
#[test]
fn empty_input_is_an_error_not_a_panic() {
assert!(decode_jpeg(&[]).is_err());
}
}