#pragma once
#include "face_utils.hpp"

#include <cstdint>
#include <iostream>

// ── FaceAlignerFunc ───────────────────────────────────────────────────────────
/// TRACES: AR-005, AR-028, AR-029, AR-030 | SR-002
///
// KPN node: applies a 5-point similarity transform to each detected face,
// producing a 112×112 BGR crop suitable for ArcFace inference.
//
// Alignment is an Umeyama least-squares fit over all five landmarks (AR-005),
// not a robust one: a RANSAC fit discards the very landmarks AR-030 reads.
//
// This is also where the AR-028 quality vector is filled in, because this is
// where the inputs to it already exist:
//
//   - **Visibility** (AR-030) is the fit's residual, and is genuinely free — the
//     transform is computed for the warp regardless, and the residual is what
//     that fit could not explain.
//   - **Sharpness** (AR-029) is measured on the crop this node just produced,
//     which is the only place it *can* be measured: the aligned canvas is what
//     makes the number scale-normalised, and downstream of the embedder the crop
//     is only forwarded for debug rendering. It is not free — 33 us per face
//     single-threaded (cvtColor, one Laplacian, two meanStdDev over 112x112) —
//     but it is two orders below the embedder inference it qualifies, and it
//     runs per face rather than per frame, so a landscape shot costs nothing.
//
// Size, the third axis, is `bbox` and needs no work here.
//
// No face is admitted unscored: every face in the output carries both numbers,
// so a negative value downstream is a bug rather than a poor-quality face.
// Nothing is dropped or discounted on quality — that is AR-030's discount and
// VR-012's knee, both still open.
//
// Degenerate detections (where the fit fails) cannot be scored, since there is
// no crop and no residual to score, and are therefore dropped — but they are
// **counted**, not silently discarded. A nonzero tally means the detector is
// emitting landmark sets the aligner cannot use, which is a fact about the
// detector; losing it leaves a hole in the dump that looks like footage with
// no faces in it.

struct FaceAlignerFunc {
    static constexpr std::string_view label() { return "face_aligner"; }

    AlignedSceneFrame operator()(SceneFrame sf) {
        if (sf.source.eof) {
            report();
            return {std::move(sf.source), {}, {}};
        }
        if (sf.faces.empty())
            return {std::move(sf.source), {}, {}};

        std::vector<DetectedFace> good_faces;
        std::vector<cv::Mat>      crops;
        good_faces.reserve(sf.faces.size());
        crops.reserve(sf.faces.size());

        for (auto& face : sf.faces) {
            // The AR-030 misfit comes from the transform the warp already needs,
            // so visibility costs no extra fit.
            float residual = -1.f;
            cv::Mat crop = align_face(sf.source.image, face.landmarks, &residual);
            if (crop.empty()) {
                ++degenerate_;
                continue;
            }
            face.alignment_residual = residual;
            face.sharpness          = crop_sharpness(crop);
            good_faces.push_back(face);
            crops.push_back(std::move(crop));
            ++scored_;
        }

        return {std::move(sf.source), std::move(good_faces), std::move(crops)};
    }

    /// Faces that carry a full quality vector, and faces the fit could not use.
    uint64_t scored()     const { return scored_; }
    uint64_t degenerate() const { return degenerate_; }

private:
    // Reported once at EOF rather than per occurrence: a run with a systematic
    // landmark problem would otherwise emit one line per face for the length of
    // a film, which is how the count came to be ignored.
    void report() {
        if (reported_) return;
        reported_ = true;
        if (degenerate_)
            std::cerr << "[face_aligner] " << degenerate_ << " of "
                      << (degenerate_ + scored_)
                      << " detections had a degenerate landmark fit and were dropped"
                         " (no crop, so no embedding and no quality vector)\n";
    }

    uint64_t scored_{0};
    uint64_t degenerate_{0};
    bool     reported_{false};
};