//! Shared image decoding.
//!
//! Exists so there is exactly ONE way to turn a file on disk into a `DynamicImage` in this
//! codebase. Two properties have to hold everywhere an image is decoded, and both were
//! previously re-derived per call site — which is how they drifted apart:
//!
//! - **EXIF orientation must be applied.** Phones do not rotate sensor data; they record how
//!   the camera was held in a tag and store the pixels as shot. `image::open` and
//!   `ImageReader::decode` both hand back the raw pixels and ignore that tag, and re-encoding
//!   to JPEG writes no EXIF, so the derivative is permanently sideways while the untouched
//!   original still renders upright. The compression worker was fixed; the export worker was
//!   not, so every portrait photo came out sideways in the keepsake's HTML viewer.
//! - **Decode limits must be set.** The upload body cap bounds the file on disk, but a small
//!   file can decode to enormous dimensions (a ~1 MB image expanding to 50k×50k px), OOM-ing
//!   the box. `image::open` applies NO limits at all, so the export path was also decoding
//!   arbitrary user-supplied images unbounded.

use anyhow::{Context, Result};
use image::{DynamicImage, ImageDecoder};
use std::path::Path;

/// Bounds for any decode of user-supplied image data. The per-axis cap covers any real phone
/// photo; `max_alloc` bounds the decoded buffer — but only because `decode_oriented` reserves
/// against it explicitly, see there.
///
/// Sized against the deployment: the app container is capped at 1 GiB and the compression
/// worker runs `compression_concurrency` decodes at once (default 2), so 256 MiB per decode
/// leaves headroom for the resize buffers and the runtime.
fn decode_limits() -> image::Limits {
    let mut limits = image::Limits::default();
    limits.max_image_width = Some(12_000);
    limits.max_image_height = Some(12_000);
    limits.max_alloc = Some(256 * 1024 * 1024);
    limits
}

/// True when re-running the exact same work on the exact same bytes cannot possibly
/// succeed, so retrying only burns wall-clock and log noise.
///
/// Deliberately narrow. Only the `ImageError` variants that are a property of the *input*
/// count: the file will not shrink, gain codec support, or un-corrupt itself between
/// attempts. `IoError` is excluded on purpose — EMFILE under load, or a momentarily
/// unreadable file, is exactly the transient case the retry exists for. A FULL disk is the
/// one io error that must not be retried either, but for a different reason and with a
/// different remedy; see [`is_storage_full_error`].
pub fn is_permanent_image_error(err: &anyhow::Error) -> bool {
    err.chain().any(|cause| {
        matches!(
            cause.downcast_ref::<image::ImageError>(),
            Some(
                image::ImageError::Limits(_)
                    | image::ImageError::Unsupported(_)
                    | image::ImageError::Decoding(_)
            )
        )
    })
}

/// True when the failure is the media filesystem being out of space.
///
/// Deliberately separate from [`is_permanent_image_error`], which is about the *input*. ENOSPC
/// is about the *host*, and it is the one failure the retry loop actively makes worse: a disk
/// does not drain during six seconds of backoff, so all three attempts fail identically while
/// holding a compression permit that photos are queued behind.
///
/// The give-up path it fed was worse still. It refunded the guest's quota and soft-deleted the
/// row while deliberately RETAINING the original — so the bytes stayed on the full disk, the
/// photo vanished from the feed seconds after a `201 Created`, and the guest was handed back
/// the quota to upload it again into the same full disk. Each round shrank free space further.
pub fn is_storage_full_error(err: &anyhow::Error) -> bool {
    fn is_full(io: &std::io::Error) -> bool {
        // `StorageFull` is the portable classification; the raw ENOSPC catches the paths where
        // the OS error was never mapped to a named kind.
        io.kind() == std::io::ErrorKind::StorageFull || io.raw_os_error() == Some(28)
    }
    err.chain().any(|cause| {
        // `image` wraps the io error in its own variant rather than exposing it as a source,
        // so the plain downcast alone would miss every derivative-write failure.
        cause.downcast_ref::<std::io::Error>().is_some_and(is_full)
            || matches!(
                cause.downcast_ref::<image::ImageError>(),
                Some(image::ImageError::IoError(io)) if is_full(io)
            )
    })
}

/// Build a decoder for `path` with the budget enforced, WITHOUT reading any pixels.
///
/// Single source of truth for "may this image be decoded at all": both the upload
/// admission check and the compression worker go through here, so they cannot disagree
/// about what is acceptable.
fn decoder_within_budget(path: &Path) -> Result<impl image::ImageDecoder> {
    let mut reader = image::ImageReader::open(path)
        .context("failed to open image")?
        .with_guessed_format()
        .context("failed to read image header")?;
    let mut limits = decode_limits();
    reader.limits(limits.clone());

    // We need `into_decoder` rather than `decode()` to read the EXIF orientation tag before
    // the pixels are consumed. But the two are NOT equivalent on safety: `decode()` performs
    //
    //     limits.reserve(decoder.total_bytes())?;
    //
    // between building the decoder and reading the image, and `into_decoder()` skips it (the
    // crate's own FIXME concedes `from_decoder` doesn't compensate). Nothing else enforces
    // `max_alloc` — the JPEG decoder's `set_limits` only checks support and dimensions — so
    // without the line below the budget is inert and the ONLY bound is the per-axis cap. That
    // leaves 12000x12000 decodable at 412 MiB, and two concurrent at 824 MiB against a 1 GiB
    // container. Re-add it, exactly as `decode()` does.
    let mut decoder = reader.into_decoder().context("failed to decode image")?;
    limits
        .reserve(decoder.total_bytes())
        .context("image too large to decode within the memory budget")?;
    decoder
        .set_limits(limits)
        .context("image too large to decode within the memory budget")?;
    Ok(decoder)
}

/// Megapixels an image would decode to, or `None` if its header can't be read. Used only
/// to put a concrete number in the message the guest sees.
pub fn megapixels(path: &Path) -> Option<f64> {
    let reader = image::ImageReader::open(path)
        .ok()?
        .with_guessed_format()
        .ok()?;
    let (w, h) = reader.into_dimensions().ok()?;
    Some(f64::from(w) * f64::from(h) / 1_000_000.0)
}

/// True when an image cannot be decoded specifically because it would exceed the memory
/// budget — read from the header, no pixels touched.
///
/// Called at upload admission so a guest who sends a 100 MP photo is told at the door, with
/// a reason they can act on, instead of the upload being accepted with a 201 and then
/// silently soft-deleted minutes later when the worker gives up on it.
///
/// Deliberately narrow: ONLY the budget. A corrupt, truncated or unsupported file also
/// fails to build a decoder, but rejecting those here would change a contract the
/// adversarial suite pins on purpose — acceptance follows the magic bytes, and a payload
/// with a valid JPEG header is accepted regardless of what follows it. Those go to the
/// compression worker as before, which handles them gracefully and (since the retry
/// classifier) no longer burns backoff on them.
pub fn exceeds_decode_budget(path: &Path) -> bool {
    match decoder_within_budget(path) {
        Ok(_) => false,
        Err(e) => e.chain().any(|cause| {
            matches!(
                cause.downcast_ref::<image::ImageError>(),
                Some(image::ImageError::Limits(_))
            )
        }),
    }
}

/// Decode an image from disk with decompression-bomb limits applied and its EXIF
/// orientation baked into the pixels.
///
/// Blocking — call inside `spawn_blocking`.
pub fn decode_oriented(path: &Path) -> Result<DynamicImage> {
    let mut decoder = decoder_within_budget(path)?;

    // Cheap, and it happens BEFORE any pixels are read: an oversized image costs a header
    // parse, not an allocation.
    let orientation = decoder
        .orientation()
        .unwrap_or(image::metadata::Orientation::NoTransforms);
    let mut img = DynamicImage::from_decoder(decoder).context("failed to decode image")?;
    img.apply_orientation(orientation);
    Ok(img)
}

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

    /// Shared with the e2e suite rather than duplicating 568 KiB of binary: the same file
    /// drives `02-upload/oversized-image` so both layers assert on one artefact.
    const HUGE: &str = concat!(
        env!("CARGO_MANIFEST_DIR"),
        "/../e2e/fixtures/media/huge-99mp.jpg"
    );

    #[test]
    fn rejects_an_image_that_would_blow_the_allocation_budget() {
        // 11000x9000 = 99 MP. Deliberately UNDER the 12000px per-axis cap, so the axis check
        // cannot reject it — the allocation budget is the only thing that can, which is
        // exactly what makes this a regression test rather than a restatement of the axis cap.
        // 283 MiB decoded as RGB8 against a 256 MiB budget, from 568 KiB on disk.
        //
        // This failed before the guard was restored: `ImageReader::decode` performs
        // `limits.reserve(decoder.total_bytes())`, and `into_decoder()` — which we need for
        // the EXIF tag — skips it, so `max_alloc` was inert and this decoded happily.
        // Map the Ok arm to its dimensions first: on failure `expect_err` Debug-prints the
        // value, and Debug on a DynamicImage dumps every pixel — 283 MiB of output.
        let err = decode_oriented(Path::new(HUGE))
            .map(|img| (img.width(), img.height()))
            .expect_err("a 99 MP image must be refused, not allocated");
        let msg = format!("{err:#}");
        assert!(
            msg.to_lowercase().contains("limit") || msg.to_lowercase().contains("memory"),
            "expected a limits error, got: {msg}"
        );
    }

    #[test]
    fn an_oversized_image_is_a_permanent_failure() {
        // The retry loop must not burn 2s + 4s of backoff on this: the file will not shrink
        // between attempts, so all three attempts reach the identical conclusion.
        let err = decode_oriented(Path::new(HUGE))
            .map(|img| (img.width(), img.height()))
            .expect_err("fixture must exceed the budget");
        assert!(
            is_permanent_image_error(&err),
            "a Limits error can never succeed on retry: {err:#}"
        );
    }

    #[test]
    fn a_plain_io_error_is_not_permanent() {
        // The mirror that keeps the classifier honest. EMFILE under load, or a momentary
        // unreadable file, is exactly what the retry exists for — misclassifying those as
        // permanent would turn a transient blip back into the data loss round 1 fixed.
        // (A FULL disk is its own case now; see the storage-full tests below.)
        let err = decode_oriented(Path::new("/nonexistent/definitely-not-here.jpg"))
            .map(|img| (img.width(), img.height()))
            .expect_err("a missing file must error");
        assert!(
            !is_permanent_image_error(&err),
            "an IO error must stay retryable: {err:#}"
        );
    }

    #[test]
    fn a_full_disk_is_recognised_through_both_wrappers() {
        // The two shapes ENOSPC actually arrives in. A bare io::Error is what `tokio::fs` and
        // `std::fs` produce; the `image` crate wraps its own in `ImageError::IoError`, which is
        // NOT reachable via `source()` — so a chain walk that only downcast to io::Error would
        // miss every derivative-write failure, i.e. the exact case this classifier exists for.
        let bare = anyhow::Error::from(std::io::Error::from(std::io::ErrorKind::StorageFull))
            .context("failed to write the preview");
        assert!(is_storage_full_error(&bare), "bare io::Error: {bare:#}");

        let wrapped = anyhow::Error::from(image::ImageError::IoError(std::io::Error::from(
            std::io::ErrorKind::StorageFull,
        )))
        .context("failed to save the display derivative");
        assert!(
            is_storage_full_error(&wrapped),
            "ImageError::IoError: {wrapped:#}"
        );
    }

    #[test]
    fn an_ordinary_io_error_is_not_a_full_disk() {
        // Keeps the classifier from swallowing the general case: only ENOSPC may skip the retry
        // and take the keep-the-row branch. Anything else must still be retried and, if it keeps
        // failing, soft-deleted as before.
        let missing = decode_oriented(Path::new("/nonexistent/definitely-not-here.jpg"))
            .map(|img| (img.width(), img.height()))
            .expect_err("a missing file must error");
        assert!(
            !is_storage_full_error(&missing),
            "a missing file is not a full disk: {missing:#}"
        );
    }

    #[test]
    fn admission_rejects_only_the_over_budget_case() {
        // Admission and processing must agree about SIZE — a photo accepted at the door and
        // then rejected by the worker for being too big is the failure this pair prevents.
        assert!(
            exceeds_decode_budget(Path::new(HUGE)),
            "admission must reject what the decoder rejects for size"
        );
        let ordinary = concat!(
            env!("CARGO_MANIFEST_DIR"),
            "/../e2e/fixtures/media/portrait-exif6.jpg"
        );
        assert!(
            !exceeds_decode_budget(Path::new(ordinary)),
            "admission must accept an ordinary photo"
        );
    }

    #[test]
    fn admission_does_not_reject_a_merely_undecodable_file() {
        // The narrowing that keeps the adversarial contract intact: a payload with valid
        // JPEG magic bytes and nothing behind them cannot be decoded, but acceptance follows
        // the magic bytes by design (07-adversarial/file-upload-attacks). It is the worker's
        // job to fail it, not admission's — admission is only the resource guard.
        let dir = std::env::temp_dir().join("eventsnap-imaging-test");
        std::fs::create_dir_all(&dir).expect("tmp dir");
        let stub = dir.join("magic-only.jpg");
        let mut bytes = vec![0u8; 1024];
        bytes[..3].copy_from_slice(&[0xFF, 0xD8, 0xFF]);
        std::fs::write(&stub, &bytes).expect("write stub");

        assert!(
            !exceeds_decode_budget(&stub),
            "a corrupt file is not an over-budget file"
        );
        assert!(
            decode_oriented(&stub)
                .map(|i| (i.width(), i.height()))
                .is_err(),
            "...but it must still fail in the worker"
        );
        let _ = std::fs::remove_file(&stub);
    }

    #[test]
    fn still_decodes_an_ordinary_photo_and_applies_orientation() {
        // The guard must not have become a blanket refusal. This fixture is 40x20 stored with
        // EXIF Orientation=6, so a correct decode returns it rotated to 20x40 portrait.
        let path = concat!(
            env!("CARGO_MANIFEST_DIR"),
            "/../e2e/fixtures/media/portrait-exif6.jpg"
        );
        let img = decode_oriented(Path::new(path)).expect("an ordinary photo must decode");
        assert_eq!(
            (img.width(), img.height()),
            (20, 40),
            "EXIF orientation must still be applied after restoring the guard"
        );
    }
}