// SPDX-FileCopyrightText: 2025 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only

#pragma once


#include <cstddef>
#include <functional>
#include <vector>

#include "ImageSpotFinder.h"
#include "SpotFindingSettings.h"
#include "../../common/AzimuthalIntegrationMapping.h"
#include "../../common/DiffractionSpot.h"

// This is "slow" spot finder for image-based analysis
// To complement "fast" PSI detector module based spot finder
// This one is expected to be used in cases, where images are already assembled
// and it aims for 100 ms execution

class ImageSpotFinderCPU : public ImageSpotFinder {
    // Output of the first pass, and the exclusion mask for the second.
    std::vector<uint32_t> first_pass_buffer;

    // One detection pass. prev_strong is the previous pass's bitmap, or nullptr for the first pass;
    // a pixel set in it is treated as INT32_MAX, i.e. kept out of every local background it would
    // fall into, and reported strong.
    //
    // With candidates set (SNR test only), the window sums of every candidate pixel are also recorded
    // in candidate_windows, in pixel order, and fill_row (see DetectAt) is called.
    void DetectPass(const ImagePreprocessorBuffer &image, const SpotFindingSettings &settings,
                    const uint32_t *prev_strong, std::vector<uint32_t> &out,
                    const uint32_t *candidates = nullptr,
                    const std::function<void(int32_t)> &fill_row = {});

    // Local-box sums (centre pixel included) of one candidate pixel, as the first pass saw them.
    struct CandidateWindow {
        int32_t pxl;
        int64_t sum, sum2, valid;
    };
    std::vector<CandidateWindow> candidate_windows;
    // Where the first pass's own result is read by DetectAt - within NBX of a candidate - per row and
    // 32-column block. Elsewhere that pass keeps its sums but skips the test.
    std::vector<uint8_t> first_pass_needed;

protected:
    // Detect, but with the result wanted only at the candidate pixels (packed like output_buffer):
    // output_buffer ends up holding (Detect's result & candidates). The second pass is not run over
    // the image: a candidate's second-pass window is its first-pass window with the pixels the first
    // pass found strong taken out, and those are few, so they are subtracted from the sums the first
    // pass recorded. Integer sums and the same test, so the bits are exactly Detect's.
    //
    // fill_row(row), when given, sets the candidates of that row: it is called once for every row, in
    // order, before any candidate of the row is read, when the pass is about to read the row anyway.
    void DetectAt(const ImagePreprocessorBuffer &image, const SpotFindingSettings &settings,
                  const std::vector<uint32_t> &candidates,
                  const std::function<void(int32_t)> &fill_row = {});

public:
    ImageSpotFinderCPU(int32_t width, int32_t height);
    void Detect(const ImagePreprocessorBuffer &image, const SpotFindingSettings &settings) override;
};