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

// Equivalence of the stored (stacked) and the assembled layout of a panel detector.
//
// One synthetic detector, recorded twice: as an assembled image (panels where they are on the plane, gaps
// masked) and as the stacked array a panel detector stores (panels one under the other, in four
// orientations, no gaps), with the DetectorModules that place the stacked panels on the plane. Both carry
// the same value in every physical pixel, so anything computed on the plane must come out the same.
//
// [PanelLayout] cases check what is already layout-correct. The [PanelLayoutTodo] cases are hidden: they
// state the equivalence each later stage has to deliver, and fail until it does. A stage that converts a
// consumer retags its case [PanelLayout]:
//   stage 1 - dense maps: PanelLayout_AzintMapping, PanelLayout_ResolutionMask (done)
//   stage 2 - sparse/Bragg: PanelLayout_BraggIntegration
//   stage 3 - per-panel spot finding: PanelLayout_SpotsNeverCrossPanels (+ PanelLayout_SpotFinderParity on a
//             GPU); the raster algorithms on the plane raster: PanelLayout_AssembleToPlane,
//             PanelLayout_ShadowFinder, PanelLayout_BeamCenterFFT, PanelLayout_DetectorDiagnostic - each
//             comparing the stacked layout with the assembled image cut to the raster.

#include <catch2/catch_all.hpp>

#include <cmath>
#include <map>
#include <vector>

#include "../common/AssembleToPlane.h"
#include "../common/AzimuthalIntegrationMapping.h"
#include "../common/CUDAWrapper.h"
#include "../common/BraggIntegrationSettings.h"
#include "../common/DetectorModules.h"
#include "../common/DetectorSetup.h"
#include "../common/DiffractionExperiment.h"
#include "../common/PixelMask.h"
#include "../common/Reflection.h"
#include "../image_analysis/beam_stop/ShadowFinder.h"
#include "../image_analysis/bragg_integration/BraggIntegrationEngineCPU.h"
#include "../image_analysis/geom_refinement/BeamCenterFFT.h"
#include "../image_analysis/image_preprocessing/ImagePreprocessorBuffer.h"
#include "../image_analysis/roi/ROIIntegrationCPU.h"
#include "../image_analysis/spot_finding/AdaptiveSpotFinderCPU.h"
#include "../image_analysis/spot_finding/ImageSpotFinderCPU.h"
#include "../image_analysis/spot_finding/SpotUtils.h"
#include "../rugnux/DiagnosticOutput.h"
#ifdef JFJOCH_USE_CUDA
#include "../image_analysis/bragg_integration/BraggIntegrationEngineGPU.h"
#include "../image_analysis/image_preprocessing/ImagePreprocessorBufferGPU.h"
#include "../image_analysis/spot_finding/AdaptiveSpotFinderGPU.h"
#include "../image_analysis/spot_finding/ImageSpotFinderGPU.h"
#endif

namespace {

// One panel as stored, and the plane the four of them are placed on.
constexpr int64_t PW = 96, PH = 64, NPANELS = 4;
constexpr int64_t PLANE_W = 220, PLANE_H = 200;

// Panel p is stored at rows [p * PH, (p + 1) * PH) and placed 2 x 2 on the plane with gaps of 8 and 16 px.
DetectorModules StackedPanels() {
    auto panel = [](int64_t p, double ox, double oy, double fx, double fy, double sx, double sy) {
        DetectorModule m;
        m.x0 = 0;
        m.y0 = p * PH;
        m.width = PW;
        m.height = PH;
        m.ox = ox; m.oy = oy;
        m.fx = fx; m.fy = fy;
        m.sx = sx; m.sy = sy;
        return m;
    };
    return DetectorModules({
        panel(0, 10, 10, 1, 0, 0, 1),        // as stored:     x  10..105, y  10..73
        panel(1, 209, 73, -1, 0, 0, -1),     // turned 180:    x 114..209, y  10..73
        panel(2, 73, 90, 0, 1, -1, 0),       // turned 90:     x  10..73,  y  90..185
        panel(3, 120, 185, 0, -1, 1, 0)      // turned -90:    x 120..183, y  90..185
    });
}

struct Spot {
    double x, y;   // on the plane
};

// Spots well inside their panels: more than the spot finder's 15 px window from every panel edge.
const std::vector<Spot> INTERIOR_SPOTS = {{50.3, 40.7}, {80.5, 45.3}, {160.6, 30.2}, {40.4, 140.8}, {150.2, 130.5}};

DiffractionExperiment Experiment(int64_t width, int64_t height, const DetectorModules &modules) {
    DiffractionExperiment x(DetDECTRIS(width, height, "PanelLayout", ""));
    // Beam in the gap cross; at 30 mm the plane reaches about 2 A in its corners.
    x.DetectorDistance_mm(30.0f).IncidentEnergy_keV(WVL_1A_IN_KEV).BeamX_pxl(110.0f).BeamY_pxl(82.0f);
    x.ImportBraggIntegrationSettings(BraggIntegrationSettings());
    x.Modules(modules);
    return x;
}

// The same detector, assembled and stacked.
struct Scene {
    DetectorModules modules = StackedPanels();
    DiffractionExperiment assembled = Experiment(PLANE_W, PLANE_H, {});
    DiffractionExperiment stacked = Experiment(PW, NPANELS * PH, modules);
    ImagePreprocessorBuffer assembled_image{PLANE_W * PLANE_H};
    ImagePreprocessorBuffer stacked_image{PW * NPANELS * PH};
    PixelMask assembled_mask;
    PixelMask stacked_mask{PW, NPANELS * PH};

    // Assembled pixel at the plane position of a stacked pixel (the placements are whole-pixel).
    static size_t AssembledIndex(double px, double py) {
        return static_cast<size_t>(std::lround(py)) * PLANE_W + static_cast<size_t>(std::lround(px));
    }

    explicit Scene(const std::vector<Spot> &spots) {
        auto value = [&](double px, double py) {
            double v = 2.0;
            for (const auto &s: spots) {
                const double dx = px - s.x, dy = py - s.y;
                v += 800.0 * std::exp(-(dx * dx + dy * dy) / (2.0 * 1.3 * 1.3));
            }
            return static_cast<int32_t>(std::lround(v));
        };
        // Gaps are what the preprocessor makes of a masked pixel.
        for (size_t i = 0; i < assembled_image.size(); i++)
            assembled_image[i] = INT32_MIN;
        std::vector<uint32_t> gaps(PLANE_W * PLANE_H, 1u << PixelMask::ModuleGapPixelBit);
        modules.ForEachPixel(PW, NPANELS * PH, [&](int64_t, size_t i, double px, double py) {
            stacked_image[i] = value(px, py);
            assembled_image[AssembledIndex(px, py)] = value(px, py);
            gaps[AssembledIndex(px, py)] = 0;
        });
        assembled_mask = PixelMask(gaps);
    }
};

std::vector<SpotToSave> FindSpots(const DiffractionExperiment &x, const ImagePreprocessorBuffer &image,
                                  float snr = 0.0f) {
    SpotFindingSettings settings;
    settings.signal_to_noise_threshold = snr;
    settings.photon_count_threshold = 20;
    settings.min_pix_per_spot = 1;
    settings.high_res_gap_Q_recipA = std::nullopt;
    ImageSpotFinderCPU finder(static_cast<int32_t>(x.GetXPixelsNum()), static_cast<int32_t>(x.GetYPixelsNum()));
    finder.SetPanels(x.GetModules());
    finder.SetResolutionMask(std::vector<bool>(x.GetPixelsNum(), false));
    DataMessage msg{};
    msg.number = 0;
    SpotAnalyze(x, settings, finder.Run(image, settings), msg);
    return msg.spots;
}

// Every spot of `a` has one in `b` at the same plane position, and the counts agree.
void CheckSameSpots(const std::vector<SpotToSave> &a, const std::vector<SpotToSave> &b) {
    REQUIRE(a.size() == b.size());
    for (const auto &s: a) {
        size_t matched = 0;
        for (const auto &t: b)
            if (std::hypot(s.x - t.x, s.y - t.y) < 1e-3) {
                CHECK(s.intensity == t.intensity);
                CHECK(s.d_A == Catch::Approx(t.d_A));
                matched++;
            }
        CHECK(matched == 1);
    }
}

// Integrate predictions placed on the plane: on the assembled image directly, on the stacked one through
// the panel table - PlaneToPanel in, ImageToPlane of the same panel out. Keyed by h.
std::map<int, Reflection> Integrate(const DiffractionExperiment &x, const PixelMask &mask,
                                    const ImagePreprocessorBuffer &image, const std::vector<Spot> &spots,
                                    bool gpu = false) {
    const auto &modules = x.GetModules();
    const auto geom = x.GetDiffractionGeometry();
    std::vector<Reflection> predicted;
    std::map<int, int64_t> panel_of;
    for (size_t i = 0; i < spots.size(); i++) {
        const auto p = modules.PlaneToPanel(spots[i].x, spots[i].y);
        REQUIRE(p.has_value());
        Reflection r{};
        r.h = static_cast<int>(i) + 1; r.k = 0; r.l = 1;
        r.predicted_x = static_cast<float>(p->x);
        r.predicted_y = static_cast<float>(p->y);
        r.d = geom.PxlToRes(static_cast<float>(spots[i].x), static_cast<float>(spots[i].y));
        r.prescaling_corr = 1.0f;
        r.partiality = 1.0f;
        predicted.push_back(r);
        panel_of[r.h] = p->panel;
    }
    std::vector<Reflection> integrated;
#ifdef JFJOCH_USE_CUDA
    if (gpu) {
        auto stream = std::make_shared<CudaStream>();
        ImagePreprocessorBufferGPU gpu_image(image.size());
        for (size_t i = 0; i < image.size(); i++)
            gpu_image[i] = image[i];
        REQUIRE(cudaMemcpyAsync(gpu_image.getGPUBuffer(), gpu_image.getBuffer().data(), image.size() * sizeof(int32_t),
                                cudaMemcpyHostToDevice, *stream) == cudaSuccess);
        BraggIntegrationEngineGPU engine(x, stream, mask);
        integrated = engine.Run(gpu_image, predicted, predicted.size(), 0);
    }
#endif
    if (!gpu) {
        BraggIntegrationEngineCPU engine(x, mask);
        integrated = engine.Run(image, predicted, predicted.size(), 0);
    }
    std::map<int, Reflection> out;
    for (auto r: integrated) {
        const int64_t panel = panel_of.at(r.h);
        const auto [px, py] = modules.ImageToPlane(panel, r.predicted_x, r.predicted_y);
        r.predicted_x = static_cast<float>(px);
        r.predicted_y = static_cast<float>(py);
        const auto [ox, oy] = modules.ImageToPlane(panel, r.observed_x, r.observed_y);
        r.observed_x = static_cast<float>(ox);
        r.observed_y = static_cast<float>(oy);
        out[r.h] = r;
    }
    return out;
}

}  // namespace

// The panel table itself: every stored pixel is visited once and lands on a free plane pixel, plane ->
// panel inverts it, a gap is on no panel, and the plane bounds hold every panel.
TEST_CASE("PanelLayout_PanelTable", "[PanelLayout]") {
    const DetectorModules modules = StackedPanels();
    const PlaneBox box = modules.PlaneBounds(PW, NPANELS * PH);
    CHECK(box.x0 == 9.5);
    CHECK(box.y0 == 9.5);
    CHECK(box.x1 == 209.5);
    CHECK(box.y1 == 185.5);

    std::vector<int> visits(PW * NPANELS * PH, 0), on_plane(PLANE_W * PLANE_H, 0);
    modules.ForEachPixel(PW, NPANELS * PH, [&](int64_t panel, size_t i, double px, double py) {
        visits[i]++;
        on_plane[Scene::AssembledIndex(px, py)]++;
        CHECK(panel == static_cast<int64_t>(i / (PW * PH)));
        const auto p = modules.PlaneToPanel(px, py);
        REQUIRE(p.has_value());
        CHECK(p->panel == panel);
        CHECK(static_cast<size_t>(std::lround(p->y)) * PW + static_cast<size_t>(std::lround(p->x)) == i);
        const auto [qx, qy] = modules.PlaneToImage(panel, px, py);
        CHECK(qx == Catch::Approx(p->x));
        CHECK(qy == Catch::Approx(p->y));
    });
    for (int v: visits)
        CHECK(v == 1);
    for (int v: on_plane)
        CHECK(v <= 1);

    CHECK_FALSE(modules.PlaneToPanel(110.0, 40.0).has_value());   // gap between panels 0 and 1
    CHECK_FALSE(modules.PlaneToPanel(110.0, 82.0).has_value());   // gap cross, where the beam is

    // Empty table: the identity, the whole image one panel -1.
    const DetectorModules none;
    const auto p = none.PlaneToPanel(12.5, -3.0);
    REQUIRE(p.has_value());
    CHECK(p->panel == -1);
    CHECK(p->x == 12.5);
    CHECK(p->y == -3.0);
    CHECK(none.ImageToPlane(-1, 4.0, 5.0) == std::pair{4.0, 5.0});
    const PlaneBox image = none.PlaneBounds(PW, PH);
    CHECK(image.x0 == 0.0);
    CHECK(image.x1 == static_cast<double>(PW));
    size_t n = 0;
    none.ForEachPixel(PW, PH, [&](int64_t panel, size_t i, double px, double py) {
        CHECK(panel == -1);
        CHECK(i == n++);
        CHECK(px == static_cast<double>(i % PW));
        CHECK(py == static_cast<double>(i / PW));
    });
    CHECK(n == static_cast<size_t>(PW * PH));
}

// Spot centroids: found in the image, mapped to the plane by SpotAnalyze. A count threshold on interior
// spots, so the finder's neighbourhood never reaches another panel.
TEST_CASE("PanelLayout_SpotPlaneCoordinates", "[PanelLayout]") {
    const Scene scene(INTERIOR_SPOTS);
    const auto a = FindSpots(scene.assembled, scene.assembled_image);
    const auto s = FindSpots(scene.stacked, scene.stacked_image);
    CHECK(a.size() == INTERIOR_SPOTS.size());
    CheckSameSpots(a, s);
}

// Predictions go plane -> panel -> image and come back to where they were on the plane; the integrated
// spot is observed where it is on the plane in both layouts.
TEST_CASE("PanelLayout_IntegrationRoundTrip", "[PanelLayout]") {
    const Scene scene(INTERIOR_SPOTS);
    const auto a = Integrate(scene.assembled, scene.assembled_mask, scene.assembled_image, INTERIOR_SPOTS);
    const auto s = Integrate(scene.stacked, scene.stacked_mask, scene.stacked_image, INTERIOR_SPOTS);
    REQUIRE(a.size() == INTERIOR_SPOTS.size());
    REQUIRE(s.size() == INTERIOR_SPOTS.size());
    for (const auto &[h, r]: s) {
        const Spot &spot = INTERIOR_SPOTS[h - 1];
        CHECK(r.predicted_x == Catch::Approx(spot.x).margin(1e-3));
        CHECK(r.predicted_y == Catch::Approx(spot.y).margin(1e-3));
        CHECK(r.observed_x == Catch::Approx(a.at(h).observed_x).margin(1e-3));
        CHECK(r.observed_y == Catch::Approx(a.at(h).observed_y).margin(1e-3));
    }
}

// The azimuthal-integration map built per stored pixel through the panel table - same bin, resolution and
// correction as the assembled pixel it lands on. The same for the azimuthal ROI map, and the ROI centre of
// mass comes out on the plane.
TEST_CASE("PanelLayout_AzintMapping", "[PanelLayout]") {
    const Scene scene(INTERIOR_SPOTS);
    const AzimuthalIntegrationMapping a(scene.assembled, scene.assembled_mask);
    const AzimuthalIntegrationMapping s(scene.stacked, scene.stacked_mask);
    size_t bin = 0, resolution = 0, correction = 0;   // pixels that differ
    scene.modules.ForEachPixel(PW, NPANELS * PH, [&](int64_t, size_t i, double px, double py) {
        const size_t j = Scene::AssembledIndex(px, py);
        bin += s.GetPixelToBin()[i] != a.GetPixelToBin()[j];
        resolution += std::fabs(s.Resolution()[i] - a.Resolution()[j]) > 1e-5f * a.Resolution()[j];
        correction += std::fabs(s.Corrections()[i] - a.Corrections()[j]) > 1e-5f * a.Corrections()[j];
    });
    CHECK(bin == 0);
    CHECK(resolution == 0);
    CHECK(correction == 0);

    DiffractionExperiment assembled = scene.assembled, stacked = scene.stacked;
    for (auto *x: {&assembled, &stacked})
        x->ROI().SetROI(ROIDefinition{.azimuthal = {ROIAzimuthal("ring", 3.0f, 8.0f, 20.0f, 250.0f)}});
    const auto a_roi = assembled.ExportROIMap(), s_roi = stacked.ExportROIMap();
    size_t roi = 0, in_roi = 0;
    scene.modules.ForEachPixel(PW, NPANELS * PH, [&](int64_t, size_t i, double px, double py) {
        roi += s_roi[i] != a_roi[Scene::AssembledIndex(px, py)];
        in_roi += s_roi[i] != 0;
    });
    CHECK(roi == 0);
    CHECK(in_roi > 1000);

    std::map<std::string, ROIMessage> a_out, s_out;
    ROIIntegrationCPU(assembled).Run(scene.assembled_image, a_out);
    ROIIntegrationCPU(stacked).Run(scene.stacked_image, s_out);
    CHECK(s_out.at("ring").sum == a_out.at("ring").sum);
    CHECK(s_out.at("ring").pixels == a_out.at("ring").pixels);
    CHECK(s_out.at("ring").x_weighted == a_out.at("ring").x_weighted);
    CHECK(s_out.at("ring").y_weighted == a_out.at("ring").y_weighted);
}

// The spot finders' resolution mask, per stored pixel through the panel table.
TEST_CASE("PanelLayout_ResolutionMask", "[PanelLayout]") {
    const Scene scene(INTERIOR_SPOTS);
    const auto a = AzimuthalIntegrationMapping(scene.assembled, scene.assembled_mask).ResolutionMaskBits(3.0f, 8.0f);
    const auto s = AzimuthalIntegrationMapping(scene.stacked, scene.stacked_mask).ResolutionMaskBits(3.0f, 8.0f);
    auto bit = [](const std::vector<uint32_t> &v, size_t i) { return (v[i / 32] >> (i % 32)) & 1u; };
    size_t differ = 0;
    scene.modules.ForEachPixel(PW, NPANELS * PH, [&](int64_t, size_t i, double px, double py) {
        differ += bit(*s, i) != bit(*a, Scene::AssembledIndex(px, py));
    });
    CHECK(differ == 0);
}

// Bragg integration on the stacked layout measures what it measures on the assembled image - stencil
// direction, radial background and polarisation taken from the plane position, not the stored one.
// Also with what reads the radial direction hardest: polarisation, a ring elongated by a bandwidth, the
// radial background correction, the owner map, and the box sum. The interior spots moved off the exact
// half pixel: there the profile grid centres on the rounded position, and rounding a half picks the other
// neighbour once a panel is turned.
void CheckBraggIntegration(bool gpu) {
    const std::vector<Spot> spots = {{50.3, 40.7}, {80.4, 45.3}, {160.6, 30.2}, {40.4, 140.8}, {150.2, 130.6}};
    const Scene scene(spots);
    auto setup = [](DiffractionExperiment x, int variant) {
        BraggIntegrationSettings bis = x.GetBraggIntegrationSettings();
        x.PolarizationFactor(0.99f);
        if (variant == 1) {
            x.BandwidthFWHM(0.02f);
            bis.StencilKSigma(2.0f);
        }
        if (variant == 2)
            bis.BackgroundRadialCorrection(true);
        if (variant == 3)
            bis.Overlap(OverlapMode::Exclude);
        if (variant == 4)
            bis.Integrator(IntegratorMode::BoxSum);
        if (variant == 5)
            bis.Integrator(IntegratorMode::ProfileEmpirical);
        x.ImportBraggIntegrationSettings(bis);
        return x;
    };
    for (int variant = 0; variant < 6; variant++) {
        CAPTURE(variant);
        const auto a = Integrate(setup(scene.assembled, variant), scene.assembled_mask, scene.assembled_image, spots,
                                 gpu);
        const auto s = Integrate(setup(scene.stacked, variant), scene.stacked_mask, scene.stacked_image, spots, gpu);
        REQUIRE(s.size() == a.size());
        for (const auto &[h, r]: s) {
            CAPTURE(h);
            CHECK(r.I == Catch::Approx(a.at(h).I).epsilon(1e-5));
            CHECK(r.sigma == Catch::Approx(a.at(h).sigma).epsilon(1e-5));
            CHECK(r.bkg == Catch::Approx(a.at(h).bkg).epsilon(1e-5));
            CHECK(r.image_scale_corr == Catch::Approx(a.at(h).image_scale_corr).epsilon(1e-5));
        }
    }
}

TEST_CASE("PanelLayout_BraggIntegration", "[PanelLayout]") {
    CheckBraggIntegration(false);
}

// The same on the CUDA engine, stacked against assembled on the GPU.
TEST_CASE("PanelLayout_BraggIntegrationGPU", "[PanelLayout][GPU]") {
    if (get_gpu_count() == 0)
        SKIP("No GPU");
    CheckBraggIntegration(true);
}

// Spot finding per panel. Two half spots on the facing edges of panels 0 and 1 as stored - adjacent rows of
// the stacked array, 139 px apart on the plane - stay two spots, and the local-background (SNR) finder
// agrees with the assembled image: its windows stop at the panel edge, as they stop at the masked gap on
// the assembled image (16 px there, wider than the window's 15), instead of reaching into the other spot.
TEST_CASE("PanelLayout_SpotsNeverCrossPanels", "[PanelLayout]") {
    // Panel 0 stored row 63 and panel 1 stored row 0, both at stored column 30.
    const std::vector<Spot> edge = {{40.0, 73.0}, {179.0, 73.0}};
    const Scene scene(edge);
    const auto a = FindSpots(scene.assembled, scene.assembled_image);
    CHECK(a.size() == 2);
    CheckSameSpots(a, FindSpots(scene.stacked, scene.stacked_image));
    const auto a_snr = FindSpots(scene.assembled, scene.assembled_image, 3.0f);
    CHECK(a_snr.size() == 2);
    CheckSameSpots(a_snr, FindSpots(scene.stacked, scene.stacked_image, 3.0f));

    const Scene interior(INTERIOR_SPOTS);
    CheckSameSpots(FindSpots(interior.assembled, interior.assembled_image, 3.0f),
                   FindSpots(interior.stacked, interior.stacked_image, 3.0f));
}

#ifdef JFJOCH_USE_CUDA
// The GPU finders (local box, adaptive, and the device connected components) work panel by panel as the CPU
// ones do: on the stacked edge scene the same components, in the same order, on the same panels.
TEST_CASE("PanelLayout_SpotFinderParity", "[PanelLayout]") {
    if (get_gpu_count() == 0) {
        WARN("No CUDA GPU present. Skipping PanelLayout_SpotFinderParity");
        return;
    }
    const Scene scene({{40.0, 73.0}, {179.0, 73.0}, {50.3, 40.7}, {40.4, 140.8}});
    const DiffractionExperiment &x = scene.stacked;
    const auto w = static_cast<int32_t>(x.GetXPixelsNum()), h = static_cast<int32_t>(x.GetYPixelsNum());
    ImagePreprocessorBufferGPU buffer(x.GetPixelsNum());
    for (size_t i = 0; i < buffer.size(); i++)
        buffer[i] = scene.stacked_image[i];
    REQUIRE(cudaMemcpy(buffer.getGPUBuffer(), buffer.getBuffer().data(), x.GetPixelsNum() * sizeof(int32_t),
                       cudaMemcpyHostToDevice) == cudaSuccess);
    REQUIRE(cudaDeviceSynchronize() == cudaSuccess);

    const auto same = [&](const std::vector<DiffractionSpot> &cpu, const std::vector<DiffractionSpot> &gpu) {
        REQUIRE(cpu.size() == gpu.size());
        for (size_t i = 0; i < cpu.size(); i++) {
            CHECK(cpu[i].RawCoord().x == gpu[i].RawCoord().x);
            CHECK(cpu[i].RawCoord().y == gpu[i].RawCoord().y);
            CHECK(cpu[i].Count() == gpu[i].Count());
            CHECK(cpu[i].Panel() == gpu[i].Panel());
            const auto c = cpu[i].RawCoord();
            CHECK(cpu[i].Panel() == x.GetModules().ModuleOfImagePixel(c.x, c.y));
        }
    };
    const std::vector<bool> no_mask(x.GetPixelsNum(), false);
    auto stream = std::make_shared<CudaStream>();

    SpotFindingSettings settings;
    settings.signal_to_noise_threshold = 3.0f;
    settings.photon_count_threshold = 20;
    settings.min_pix_per_spot = 1;
    ImageSpotFinderCPU cpu(w, h);
    ImageSpotFinderGPU gpu(w, h, stream);
    for (ImageSpotFinder *f: {static_cast<ImageSpotFinder *>(&cpu), static_cast<ImageSpotFinder *>(&gpu)}) {
        f->SetPanels(x.GetModules());
        f->SetResolutionMask(no_mask);
    }
    const auto cpu_spots = cpu.Run(buffer, settings);
    CHECK(cpu_spots.size() == 4);
    same(cpu_spots, gpu.Run(buffer, settings));

    const AzimuthalIntegrationMapping mapping(x, scene.stacked_mask);
    SpotFindingSettings adaptive = settings;
    adaptive.adaptive_threshold = true;
    adaptive.false_pixels_per_frame = 10.0f;
    AdaptiveSpotFinderCPU adaptive_cpu(mapping);
    AdaptiveSpotFinderGPU adaptive_gpu(mapping, stream);
    for (ImageSpotFinder *f: {static_cast<ImageSpotFinder *>(&adaptive_cpu), static_cast<ImageSpotFinder *>(&adaptive_gpu)}) {
        f->SetPanels(x.GetModules());
        f->SetResolutionMask(no_mask);
    }
    const auto adaptive_spots = adaptive_cpu.Run(buffer, adaptive);
    CHECK(adaptive_spots.size() == 4);
    same(adaptive_spots, adaptive_gpu.Run(buffer, adaptive));
}
#endif

namespace {

// The raster the stacked panels are assembled to starts at the plane origin and ends at the last panel
// pixel, so it is the assembled image cut to its size: the same picture, in which the raster algorithms
// must find the same answer for both layouts.
template<class T>
std::vector<T> CutToRaster(const std::vector<T> &assembled, const PlaneRaster &r) {
    std::vector<T> out;
    for (int64_t j = 0; j < r.height; j++)
        for (int64_t i = 0; i < r.width; i++)
            out.push_back(assembled[(r.y0 + j) * PLANE_W + r.x0 + i]);
    return out;
}

PlaneRaster StackedRaster() {
    return PlaneRasterOf(StackedPanels(), PW, NPANELS * PH);
}

// A plane picture: background b, nothing inside the disk of radius r about the beam and along an arm running
// right of it, and a ring of radius 60 about (cx, cy).
std::vector<int32_t> Frame(const DetectorModules &modules, int64_t width, int64_t height, bool stacked,
                           double r, double cx, double cy) {
    const auto value = [&](double px, double py) {
        const double dx = px - 110.0, dy = py - 82.0;
        if (dx * dx + dy * dy <= r * r || (dx >= 0 && std::fabs(dy) <= 4.0))
            return int32_t{0};
        const double ring = std::hypot(px - cx, py - cy) - 60.0;
        return static_cast<int32_t>(4 + std::lround(20.0 * std::exp(-ring * ring / 8.0)));
    };
    std::vector<int32_t> out(static_cast<size_t>(width * height), INT32_MIN);
    if (stacked)
        modules.ForEachPixel(width, height, [&](int64_t, size_t i, double px, double py) { out[i] = value(px, py); });
    else
        StackedPanels().ForEachPixel(PW, NPANELS * PH, [&](int64_t, size_t, double px, double py) {
            out[std::lround(py) * width + std::lround(px)] = value(px, py);
        });
    return out;
}

// The assembled detector at the raster's size, gaps masked.
struct RasterScene {
    PlaneRaster raster = StackedRaster();
    DiffractionExperiment assembled = Experiment(raster.width, raster.height, {});
    PixelMask assembled_mask;
    DiffractionExperiment stacked = Experiment(PW, NPANELS * PH, StackedPanels());
    PixelMask stacked_mask{PW, NPANELS * PH};

    RasterScene() {
        std::vector<uint32_t> gaps(raster.width * raster.height, 1u << PixelMask::ModuleGapPixelBit);
        StackedPanels().ForEachPixel(PW, NPANELS * PH, [&](int64_t, size_t, double px, double py) {
            gaps[std::lround(py) * raster.width + std::lround(px)] = 0;
        });
        assembled_mask = PixelMask(gaps);
    }
};

}  // namespace

// The panels put together on the plane raster are the assembled image, gaps and all; an empty table is a copy.
TEST_CASE("PanelLayout_AssembleToPlane", "[PanelLayout]") {
    const Scene scene(INTERIOR_SPOTS);
    const PlaneRaster r = StackedRaster();
    CHECK(r.x0 == 0);
    CHECK(r.y0 == 0);
    CHECK(r.width == 210);
    CHECK(r.height == 186);
    const std::vector<int32_t> stacked(scene.stacked_image.data(), scene.stacked_image.data() + scene.stacked_image.size());
    const std::vector<int32_t> assembled(scene.assembled_image.data(),
                                         scene.assembled_image.data() + scene.assembled_image.size());
    const auto plane = AssembleToPlane(scene.modules, stacked, PW, NPANELS * PH, r, INT32_MIN);
    CHECK(plane == CutToRaster(assembled, r));
    CHECK(GatherFromPlane(scene.modules, plane, r, PW, NPANELS * PH, 0) == stacked);

    const DetectorModules none;
    const PlaneRaster image = PlaneRasterOf(none, PLANE_W, PLANE_H);
    CHECK(image.width == PLANE_W);
    CHECK(image.height == PLANE_H);
    CHECK(AssembleToPlane(none, assembled, PLANE_W, PLANE_H, image, 0) == assembled);
    CHECK(GatherFromPlane(none, assembled, image, PLANE_W, PLANE_H, 0) == assembled);
}

// The beam stop - a disk on the beam in the gap cross, reaching onto all four panels, and an arm across the
// gap between panels 0 and 1 - is found on the plane: each stored pixel gets the mask of the assembled pixel
// it is.
TEST_CASE("PanelLayout_ShadowFinder", "[PanelLayout]") {
    const RasterScene rs;
    ShadowFinder assembled(rs.assembled, rs.assembled_mask);
    ShadowFinder stacked(rs.stacked, rs.stacked_mask);
    std::vector<std::vector<int32_t>> frames;
    std::vector<uint8_t> buffer;
    for (int f = 0; f < 12; f++) {
        frames.push_back(Frame({}, rs.raster.width, rs.raster.height, false, 25.0, 110.0, 82.0));
        DataMessage a{};
        a.image = CompressedImage(frames.back(), rs.raster.width, rs.raster.height);
        assembled.AddImage(a, buffer);
        frames.push_back(Frame(StackedPanels(), PW, NPANELS * PH, true, 25.0, 110.0, 82.0));
        DataMessage s{};
        s.image = CompressedImage(frames.back(), PW, NPANELS * PH);
        stacked.AddImage(s, buffer);
    }
    const auto a = assembled.GetMask();
    const auto s = stacked.GetMask();
    REQUIRE(s.size() == static_cast<size_t>(PW * NPANELS * PH));
    size_t shadowed = 0, differ = 0;
    StackedPanels().ForEachPixel(PW, NPANELS * PH, [&](int64_t, size_t i, double px, double py) {
        shadowed += s[i] != 0;
        differ += s[i] != a[std::lround(py) * rs.raster.width + std::lround(px)];
    });
    CHECK(shadowed > 500);
    CHECK(differ == 0);
}

// The point-symmetry capture scores the plane raster and reports plane coordinates: the same shortlist from
// both layouts, led by the centre of the ring.
TEST_CASE("PanelLayout_BeamCenterFFT", "[PanelLayout]") {
    const RasterScene rs;
    const auto to_float = [](const std::vector<int32_t> &v) {
        std::vector<float> out;
        for (int32_t i: v)
            out.push_back(i == INT32_MIN ? NAN : static_cast<float>(i));
        return out;
    };
    const auto a = FindBeamCenterFFT(rs.assembled, to_float(Frame({}, rs.raster.width, rs.raster.height, false,
                                                                    0.0, 104.0, 95.0)));
    const auto s = FindBeamCenterFFT(rs.stacked, to_float(Frame(StackedPanels(), PW, NPANELS * PH, true,
                                                                 0.0, 104.0, 95.0)));
    REQUIRE(!a.point.empty());
    REQUIRE(s.point.size() == a.point.size());
    for (size_t i = 0; i < a.point.size(); i++) {
        CHECK(s.point[i].beam_x_pxl == a.point[i].beam_x_pxl);
        CHECK(s.point[i].beam_y_pxl == a.point[i].beam_y_pxl);
        CHECK(s.point[i].score == a.point[i].score);
    }
    CHECK(s.margin_point == a.margin_point);
}

// The diagnostic picture shows the detector as it is, gaps in the gap colour: the same JPEG from both layouts.
TEST_CASE("PanelLayout_DetectorDiagnostic", "[PanelLayout]") {
    const RasterScene rs;
    const auto to_float = [](const std::vector<int32_t> &v) {
        std::vector<float> out;
        for (int32_t i: v)
            out.push_back(i == INT32_MIN ? NAN : static_cast<float>(i));
        return out;
    };
    const auto a = RenderDetectorDiagnostic(rs.assembled, rs.assembled_mask,
                                            to_float(Frame({}, rs.raster.width, rs.raster.height, false,
                                                           25.0, 104.0, 95.0)));
    const auto s = RenderDetectorDiagnostic(rs.stacked, rs.stacked_mask,
                                            to_float(Frame(StackedPanels(), PW, NPANELS * PH, true,
                                                           25.0, 104.0, 95.0)));
    CHECK(s == a);
}