DarkRoom/core/dr-decode/src/preview.rs

//! 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());
    }
}