// SPDX-FileCopyrightText: 2026 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only

#pragma once

#include <cstdint>
#include <cstddef>
#include <vector>
#include "../common/CompressedImage.h"
#include "../common/DiffractionExperiment.h"
#include "../common/PixelMask.h"
#include "ImagePreprocessorBuffer.h"

struct alignas(8) ImageStatistics {
    unsigned long long error_pixel_count = 0;
    unsigned long long saturated_pixel_count = 0;
    unsigned long long masked_pixel_count = 0;
    long long max_value = INT64_MIN;
    long long min_value = INT64_MAX;
};

class ImagePreprocessor {
protected:
    const size_t npixels;
    const DiffractionExperiment &experiment;
    const int64_t saturation_limit;
public:
    ImagePreprocessor(const DiffractionExperiment &experiment);
    virtual ~ImagePreprocessor() = default;
    virtual ImageStatistics Analyze(ImagePreprocessorBuffer &processed_image, const uint8_t *decompressed_image, CompressedImageMode image_mode) = 0;

    // Analyze straight from the COMPRESSED image, decompressing wherever the implementation prefers.
    // The GPU implementation uploads the compressed chunk and decodes it on the device, so only a few
    // MB cross PCIe instead of the whole frame and the host never decompresses at all.
    // Returns false when this implementation cannot handle the image - the CPU preprocessor always,
    // and the GPU one for any algorithm without a device decoder - and the caller then decompresses
    // on the host and calls Analyze() as before. Keeping the fallback explicit means a format we
    // cannot decode on the device is a slower path, never a wrong answer.
    virtual bool AnalyzeCompressed(ImagePreprocessorBuffer &processed_image, const CompressedImage &image,
                                   ImageStatistics &stats) { return false; }

    // Device time the last AnalyzeCompressed() spent getting the chunk across and decompressing it,
    // so the caller can still report a decompression cost once the host no longer does the work.
    // Meaningless unless the previous call returned true.
    [[nodiscard]] virtual float GetLastDecompressionTime_s() const { return 0.0f; }

    // Resize the buffer an image will be decompressed into and page-lock it, so that the host->device
    // copy of Analyze() is a real DMA. Without page-locking the driver stages the copy through its own
    // pinned pool, which is a host-side copy on the calling thread: it does not overlap and it degrades
    // badly with the number of workers. Nothing to do on the CPU.
    virtual void PinInputBuffer(std::vector<uint8_t> &buffer, size_t size) {}
};