ImageApi/src/exif.rs

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};
use image::DynamicImage;
use log::debug;
use serde::{Deserialize, Serialize};

#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct ExifData {
    pub camera_make: Option<String>,
    pub camera_model: Option<String>,
    pub lens_model: Option<String>,
    pub width: Option<i32>,
    pub height: Option<i32>,
    pub orientation: Option<i32>,
    pub gps_latitude: Option<f64>,
    pub gps_longitude: Option<f64>,
    pub gps_altitude: Option<f64>,
    pub focal_length: Option<f64>,
    pub aperture: Option<f64>,
    pub shutter_speed: Option<String>,
    pub iso: Option<i32>,
    pub date_taken: Option<i64>,
}

/// TIFF-based RAW formats where `JPEGInterchangeFormat` offsets are
/// absolute file offsets (the file itself is a TIFF container).
pub fn is_tiff_raw(path: &Path) -> bool {
    matches!(
        path.extension()
            .and_then(|e| e.to_str())
            .map(|s| s.to_lowercase())
            .as_deref(),
        Some(
            "tiff" | "tif" | "nef" | "cr2" | "arw" | "dng" | "raf" | "orf" | "rw2" | "pef" | "srw"
        )
    )
}

/// 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, ifd)?
        .value
        .get_uint(0)?;
    let length = exif
        .get_field(Tag::JPEGInterchangeFormatLength, ifd)?
        .value
        .get_uint(0)?;
    if length == 0 {
        return None;
    }

    let mut file = File::open(path).ok()?;
    file.seek(SeekFrom::Start(offset as u64)).ok()?;
    let mut buf = vec![0u8; length as usize];
    file.read_exact(&mut buf).ok()?;

    if buf.len() < 2 || buf[0] != 0xFF || buf[1] != 0xD8 {
        return None;
    }

    Some(buf)
}

/// Shell out to `exiftool -j -G -n <path>` and return the per-file tag map.
///
/// `-j` requests JSON; the response is always an array of one element per
/// input path. `-G` prefixes each key with the group name (`EXIF:Make`,
/// `MakerNotes:LensInfo`, `File:FileSize`, …) so a UI can group the dump.
/// `-n` returns numeric / raw values rather than exiftool's pretty-printed
/// human strings, which keeps the output stable for clients that want to
/// reformat (e.g. divide a focal-length numerator/denominator).
///
/// Returns:
///  - `Ok(Some(value))` — the parsed object for this file.
///  - `Ok(None)` — exiftool ran but the array was empty / not an object.
///  - `Err(_)` — exiftool isn't on PATH, the spawn failed, or its stderr
///    indicates an unsupported file. Caller surfaces a 503 / 422.
///
/// Used by `GET /image/exif/full` to power Apollo's DETAILS modal "FULL
/// EXIF" pane. Per-file shell-out is fine for this on-demand surface;
/// the indexer does NOT call this on the hot path (kamadak-exif covers
/// the indexed columns; exiftool is the slow-path preview helper).
pub fn read_full_exif_via_exiftool(path: &Path) -> Result<Option<serde_json::Value>> {
    let output = Command::new("exiftool")
        .arg("-j")
        .arg("-G")
        .arg("-n")
        .arg(path)
        .output()
        .map_err(|e| anyhow!("exiftool spawn failed (is it on PATH?): {}", e))?;

    if !output.status.success() {
        let stderr = String::from_utf8_lossy(&output.stderr);
        return Err(anyhow!(
            "exiftool exited with {}: {}",
            output.status,
            stderr.trim()
        ));
    }

    let parsed: serde_json::Value = serde_json::from_slice(&output.stdout)
        .map_err(|e| anyhow!("exiftool returned non-JSON output: {}", e))?;

    // `-j` always wraps the result in an array — pull out the first object.
    let arr = parsed
        .as_array()
        .ok_or_else(|| anyhow!("expected JSON array from exiftool -j"))?;
    Ok(arr.first().cloned())
}

/// 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())
}

/// Write GPS lat/lon into the file's EXIF in place via exiftool. Touches
/// nothing else — camera, dates, MakerNote, etc. all stay as-is. Uses
/// `-overwrite_original` so no `.orig` sidecar is left behind (the
/// caller's responsibility to back up the file system if they want
/// rollback). Returns Err if exiftool isn't on PATH, the file format
/// doesn't support EXIF, lat/lon are out of range, or exiftool prints
/// to stderr.
///
/// We pass lat/lon as positive decimal numbers and let the *Ref tags
/// carry the sign (N/S, E/W). exiftool happily accepts signed decimals
/// too, but the explicit ref form is unambiguous across exiftool
/// versions and matches what cameras write.
pub fn write_gps(path: &Path, lat: f64, lon: f64) -> Result<()> {
    if !supports_exif(path) {
        return Err(anyhow!(
            "Format does not support EXIF GPS write: {}",
            path.display()
        ));
    }
    if !(-90.0..=90.0).contains(&lat) || !(-180.0..=180.0).contains(&lon) {
        return Err(anyhow!("GPS coordinates out of range: {}, {}", lat, lon));
    }
    let lat_ref = if lat >= 0.0 { "N" } else { "S" };
    let lon_ref = if lon >= 0.0 { "E" } else { "W" };
    let lat_abs = lat.abs();
    let lon_abs = lon.abs();
    let output = Command::new("exiftool")
        .arg("-overwrite_original")
        .arg("-P")
        .arg(format!("-GPSLatitude={}", lat_abs))
        .arg(format!("-GPSLatitudeRef={}", lat_ref))
        .arg(format!("-GPSLongitude={}", lon_abs))
        .arg(format!("-GPSLongitudeRef={}", lon_ref))
        .arg(path)
        .output()
        .map_err(|e| anyhow!("exiftool spawn failed (is it on PATH?): {}", e))?;
    if !output.status.success() {
        let stderr = String::from_utf8_lossy(&output.stderr);
        return Err(anyhow!(
            "exiftool failed (exit {}): {}",
            output.status.code().unwrap_or(-1),
            stderr.trim()
        ));
    }
    Ok(())
}

pub fn supports_exif(path: &Path) -> bool {
    if let Some(ext) = path.extension() {
        let ext_lower = ext.to_string_lossy().to_lowercase();
        matches!(
            ext_lower.as_str(),
            // JPEG formats
            "jpg" | "jpeg" |
            // TIFF and RAW formats based on TIFF
            "tiff" | "tif" | "nef" | "cr2" | "cr3" | "arw" | "dng" | "raf" | "orf" | "rw2" | "pef" | "srw" |
            // HEIF and variants
            "heif" | "heic" | "avif" |
            // PNG
            "png" |
            // WebP
            "webp"
        )
    } else {
        false
    }
}

pub fn extract_exif_from_path(path: &Path) -> Result<ExifData> {
    debug!("Extracting EXIF from: {:?}", path);

    if !supports_exif(path) {
        return Err(anyhow!("File type does not support EXIF"));
    }

    let file = File::open(path)?;
    let mut bufreader = BufReader::new(file);

    let exifreader = Reader::new();
    let exif = exifreader.read_from_container(&mut bufreader)?;

    let mut data = ExifData::default();

    for field in exif.fields() {
        match field.tag {
            Tag::Make => {
                data.camera_make = get_string_value(field);
            }
            Tag::Model => {
                data.camera_model = get_string_value(field);
            }
            Tag::LensModel => {
                data.lens_model = get_string_value(field);
            }
            Tag::PixelXDimension | Tag::ImageWidth => {
                if data.width.is_none() {
                    data.width = get_u32_value(field).map(|v| v as i32);
                }
            }
            Tag::PixelYDimension | Tag::ImageLength => {
                if data.height.is_none() {
                    data.height = get_u32_value(field).map(|v| v as i32);
                }
            }
            Tag::Orientation => {
                data.orientation = get_u32_value(field).map(|v| v as i32);
            }
            Tag::FocalLength => {
                data.focal_length = get_rational_value(field);
            }
            Tag::FNumber => {
                data.aperture = get_rational_value(field);
            }
            Tag::ExposureTime => {
                data.shutter_speed = get_rational_string(field);
            }
            Tag::PhotographicSensitivity | Tag::ISOSpeed => {
                if data.iso.is_none() {
                    data.iso = get_u32_value(field).map(|v| v as i32);
                }
            }
            Tag::DateTime | Tag::DateTimeOriginal => {
                if data.date_taken.is_none() {
                    data.date_taken = parse_exif_datetime(field);
                }
            }
            _ => {}
        }
    }

    // Extract GPS coordinates
    if let Some(lat) = extract_gps_coordinate(&exif, Tag::GPSLatitude, Tag::GPSLatitudeRef) {
        data.gps_latitude = Some(lat);
    }
    if let Some(lon) = extract_gps_coordinate(&exif, Tag::GPSLongitude, Tag::GPSLongitudeRef) {
        data.gps_longitude = Some(lon);
    }
    if let Some(alt) = extract_gps_altitude(&exif) {
        data.gps_altitude = Some(alt);
    }

    debug!("Extracted EXIF data: {:?}", data);
    Ok(data)
}

/// Read just the EXIF Orientation tag (1..=8) from a file. Cheaper than a
/// full `extract_exif_from_path` when the caller only needs orientation —
/// e.g. the thumbnail pipeline, which has to bake the rotation into the
/// resized pixels because the saved thumb has no EXIF chunk for the browser
/// to apply.
pub fn read_orientation(path: &Path) -> Option<i32> {
    let file = File::open(path).ok()?;
    let mut reader = BufReader::new(file);
    let exif = Reader::new().read_from_container(&mut reader).ok()?;
    let field = exif.get_field(Tag::Orientation, In::PRIMARY)?;
    get_u32_value(field).map(|v| v as i32)
}

/// Apply an EXIF Orientation (1..=8) to a `DynamicImage`, returning a
/// canonically-oriented copy. Orientations:
///   1 → as-is, 2 → flipH, 3 → rot180, 4 → flipV,
///   5 → rot90CW + flipH, 6 → rot90CW, 7 → rot270CW + flipH, 8 → rot270CW.
/// Anything else (missing tag, garbage values) is returned unchanged.
pub fn apply_orientation(img: DynamicImage, orientation: i32) -> DynamicImage {
    match orientation {
        2 => img.fliph(),
        3 => img.rotate180(),
        4 => img.flipv(),
        5 => img.rotate90().fliph(),
        6 => img.rotate90(),
        7 => img.rotate270().fliph(),
        8 => img.rotate270(),
        _ => img,
    }
}

fn get_string_value(field: &exif::Field) -> Option<String> {
    match &field.value {
        Value::Ascii(vec) => {
            if let Some(bytes) = vec.first() {
                String::from_utf8(bytes.to_vec())
                    .ok()
                    .map(|s| s.trim_end_matches('\0').to_string())
            } else {
                None
            }
        }
        _ => {
            let display = field.display_value().to_string();
            if display.is_empty() {
                None
            } else {
                Some(display)
            }
        }
    }
}

fn get_u32_value(field: &exif::Field) -> Option<u32> {
    match &field.value {
        Value::Short(vec) => vec.first().map(|&v| v as u32),
        Value::Long(vec) => vec.first().copied(),
        _ => None,
    }
}

fn get_rational_value(field: &exif::Field) -> Option<f64> {
    match &field.value {
        Value::Rational(vec) => {
            if let Some(rational) = vec.first() {
                if rational.denom == 0 {
                    None
                } else {
                    Some(rational.num as f64 / rational.denom as f64)
                }
            } else {
                None
            }
        }
        _ => None,
    }
}

fn get_rational_string(field: &exif::Field) -> Option<String> {
    match &field.value {
        Value::Rational(vec) => {
            if let Some(rational) = vec.first() {
                if rational.denom == 0 {
                    None
                } else if rational.num < rational.denom {
                    Some(format!("{}/{}", rational.num, rational.denom))
                } else {
                    let value = rational.num as f64 / rational.denom as f64;
                    Some(format!("{:.2}", value))
                }
            } else {
                None
            }
        }
        _ => None,
    }
}

fn parse_exif_datetime(field: &exif::Field) -> Option<i64> {
    if let Some(datetime_str) = get_string_value(field) {
        use chrono::NaiveDateTime;

        // EXIF datetime format: "YYYY:MM:DD HH:MM:SS"
        // Note: EXIF dates are local time without timezone info
        // We return the timestamp as if it were UTC, and the client will display it as-is
        NaiveDateTime::parse_from_str(&datetime_str, "%Y:%m:%d %H:%M:%S")
            .ok()
            .map(|dt| dt.and_utc().timestamp())
    } else {
        None
    }
}

fn extract_gps_coordinate(exif: &exif::Exif, coord_tag: Tag, ref_tag: Tag) -> Option<f64> {
    let coord_field = exif.get_field(coord_tag, In::PRIMARY)?;
    let ref_field = exif.get_field(ref_tag, In::PRIMARY)?;

    let coordinates = match &coord_field.value {
        Value::Rational(vec) => {
            if vec.len() < 3 {
                return None;
            }
            let degrees = vec[0].num as f64 / vec[0].denom as f64;
            let minutes = vec[1].num as f64 / vec[1].denom as f64;
            let seconds = vec[2].num as f64 / vec[2].denom as f64;
            degrees + (minutes / 60.0) + (seconds / 3600.0)
        }
        _ => return None,
    };

    let reference = get_string_value(ref_field)?;
    let sign = if reference.starts_with('S') || reference.starts_with('W') {
        -1.0
    } else {
        1.0
    };

    Some(coordinates * sign)
}

fn extract_gps_altitude(exif: &exif::Exif) -> Option<f64> {
    let alt_field = exif.get_field(Tag::GPSAltitude, In::PRIMARY)?;

    match &alt_field.value {
        Value::Rational(vec) => {
            if let Some(rational) = vec.first() {
                if rational.denom == 0 {
                    None
                } else {
                    let altitude = rational.num as f64 / rational.denom as f64;

                    // Check if below sea level
                    if let Some(ref_field) = exif.get_field(Tag::GPSAltitudeRef, In::PRIMARY)
                        && let Some(ref_val) = get_u32_value(ref_field)
                        && ref_val == 1
                    {
                        return Some(-altitude);
                    }

                    Some(altitude)
                }
            } else {
                None
            }
        }
        _ => None,
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_supports_exif_jpeg() {
        assert!(supports_exif(Path::new("test.jpg")));
        assert!(supports_exif(Path::new("test.jpeg")));
        assert!(supports_exif(Path::new("test.JPG")));
    }

    #[test]
    fn test_supports_exif_raw_formats() {
        assert!(supports_exif(Path::new("test.nef"))); // Nikon
        assert!(supports_exif(Path::new("test.NEF")));
        assert!(supports_exif(Path::new("test.cr2"))); // Canon
        assert!(supports_exif(Path::new("test.cr3"))); // Canon
        assert!(supports_exif(Path::new("test.arw"))); // Sony
        assert!(supports_exif(Path::new("test.dng"))); // Adobe DNG
    }

    #[test]
    fn test_supports_exif_tiff() {
        assert!(supports_exif(Path::new("test.tiff")));
        assert!(supports_exif(Path::new("test.tif")));
        assert!(supports_exif(Path::new("test.TIFF")));
    }

    #[test]
    fn test_supports_exif_heif() {
        assert!(supports_exif(Path::new("test.heif")));
        assert!(supports_exif(Path::new("test.heic")));
        assert!(supports_exif(Path::new("test.avif")));
    }

    #[test]
    fn test_supports_exif_png_webp() {
        assert!(supports_exif(Path::new("test.png")));
        assert!(supports_exif(Path::new("test.PNG")));
        assert!(supports_exif(Path::new("test.webp")));
        assert!(supports_exif(Path::new("test.WEBP")));
    }

    #[test]
    fn test_supports_exif_unsupported() {
        assert!(!supports_exif(Path::new("test.mp4")));
        assert!(!supports_exif(Path::new("test.mov")));
        assert!(!supports_exif(Path::new("test.txt")));
        assert!(!supports_exif(Path::new("test.gif")));
    }

    #[test]
    fn test_supports_exif_no_extension() {
        assert!(!supports_exif(Path::new("test")));
    }
}