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

// Checks that the results which depend on the architecture, the compiler or the standard library are
// the same everywhere: the bitshuffle/LZ4 path (hperf SSE2/AVX2 on x86, NEON on aarch64, SSE2 under
// MSVC) and an end-to-end run of the analysis. Golden values were taken on x86-64 Linux; an arm64
// or MSVC build that disagrees has a portability defect, not a new reference.

#include <catch2/catch_all.hpp>

#include <cstring>
#include <thread>

#include "TestData.h"
#include "../compression/JFJochCompressor.h"
#include "../compression/JFJochDecompress.h"
#include "../common/JFJochMath.h"
#include "../writer/HDF5Objects.h"
#include "../image_analysis/indexing/IndexerFactory.h"
#include "../reader/JFJochHDF5Reader.h"
#include "../rugnux/Rugnux.h"

namespace {
    // FNV-1a, spelled out: std::hash is not the same function on every standard library.
    uint64_t Fnv1a(const void *data, size_t size) {
        auto p = static_cast<const uint8_t *>(data);
        uint64_t h = 1469598103934665603ULL;
        for (size_t i = 0; i < size; i++) {
            h ^= p[i];
            h *= 1099511628211ULL;
        }
        return h;
    }

    uint64_t SplitMix64(uint64_t &state) {
        uint64_t z = (state += 0x9e3779b97f4a7c15ULL);
        z = (z ^ (z >> 30)) * 0xbf58476d1ce4e5b9ULL;
        z = (z ^ (z >> 27)) * 0x94d049bb133111ebULL;
        return z ^ (z >> 31);
    }
}

// compression_benchmark.h5 holds 25 int16 frames, bitshuffle/LZ4 (HDF5 filter 32008). One frame is
// read three ways - the raw chunk decoded by the hperf path and by the classic bitshuffle, and
// through the HDF5 filter - and all three must give the frame whose hash was recorded on x86.
TEST_CASE("Portable_BSLZ4_BenchmarkFrameGoldenHash", "[portable][compression]") {
    RegisterHDF5Filter();
    HDF5ReadOnlyFile file("../../tests/test_data/compression_benchmark.h5");
    HDF5DataSet dataset(file, "/entry/data/data");
    HDF5DataSpace file_space(dataset);
    const auto dims = file_space.GetDimensions();
    REQUIRE(dims.size() == 3);
    const size_t npixel = dims[1] * dims[2];

    const std::pair<hsize_t, uint64_t> golden[] = {
            {0, 0xaffea29c511b6ec2ULL},
            {24, 0xe46913009c95a1f1ULL}
    };

    for (const auto &[frame, hash]: golden) {
        std::vector<uint8_t> chunk;
        dataset.ReadDirectChunk(chunk, {frame, 0, 0});

        std::vector<int16_t> hperf, classic, filtered(npixel);
        JFJochDecompress(hperf, CompressionAlgorithm::BSHUF_LZ4, chunk, npixel, true);
        JFJochDecompress(classic, CompressionAlgorithm::BSHUF_LZ4, chunk, npixel, false);
        dataset.ReadVector(filtered, {frame, 0, 0}, {1, dims[1], dims[2]});

        CHECK(Fnv1a(hperf.data(), hperf.size() * sizeof(int16_t)) == hash);
        CHECK(hperf == classic);
        CHECK(hperf == filtered);
    }
}

// The encoder must write the same bytes everywhere: a file is decoded on a different machine from
// the one that wrote it, and the header of every block is big-endian regardless of the host.
TEST_CASE("Portable_BSLZ4_EncodeGoldenHash", "[portable][compression]") {
    uint64_t state = 42;
    std::vector<uint32_t> image(1024 * 1024 + 13);   // a tail that is not a whole block
    for (auto &v: image)
        v = (SplitMix64(state) % 16 == 0) ? SplitMix64(state) % 200 : 0;

    JFJochBitShuffleCompressor compressor(CompressionAlgorithm::BSHUF_LZ4);
    auto compressed = compressor.Compress(image);
    CHECK(compressed.size() == 562349);
    CHECK(Fnv1a(compressed.data(), compressed.size()) == 0x874e45eb17a51ed2ULL);

    std::vector<uint32_t> decoded;
    JFJochDecompress(decoded, CompressionAlgorithm::BSHUF_LZ4, compressed, image.size());
    CHECK(decoded == image);
}

// One bitshuffle block through the shipped selector (hperf on x86, classic NEON on aarch64) against
// the classic reference transform, over the element sizes and block tails the file format allows.
TEST_CASE("Portable_BitShuffleBlock_MatchesReference", "[portable][compression]") {
    uint64_t state = 7;
    for (size_t elem: {1, 2, 4, 8}) {
        for (size_t size: {8, 16, 24, 136, 1032, 2040, 2048, 8192}) {
            for (int pattern = 0; pattern < 3; pattern++) {
                std::vector<char> orig(size * elem), ref(size * elem), enc(size * elem),
                        scratch(size * elem), out(size * elem);
                for (size_t i = 0; i < orig.size(); i++) {
                    if (pattern == 0) orig[i] = static_cast<char>(SplitMix64(state));                  // noise
                    else if (pattern == 1) orig[i] = (i % elem == 0) ? static_cast<char>(i % 7) : 0; // counts
                    else orig[i] = static_cast<char>((i % elem == elem - 1) ? 0x80 : 0);           // sign bit
                }
                INFO("elem " << elem << " size " << size << " pattern " << pattern);
                REQUIRE(bshuf_trans_bit_elem(orig.data(), ref.data(), size, elem) >= 0);
                REQUIRE(JFJochBitShuffleBlock(enc.data(), orig.data(), scratch.data(), size, elem) >= 0);
                CHECK(enc == ref);
                REQUIRE(JFJochBitUnshuffleBlock(out.data(), ref.data(), scratch.data(), size, elem) >= 0);
                CHECK(out == orig);
            }
        }
    }
}

// The CPU indexer (FFTW, NEON codelets on arm64) on a synthetic orthorhombic lattice. Named
// explicitly rather than through Auto, so a CUDA build on a runner without a GPU tests it too.
TEST_CASE("Portable_FFTWIndexer_SyntheticLattice", "[portable][Indexing]") {
    const UnitCell uc(39, 45, 78, 90, 90, 90);
    const CrystalLattice cl(uc);

    DiffractionExperiment experiment;
    IndexingSettings settings;
    settings.Algorithm(IndexingAlgorithmEnum::FFTW).FFT_MaxUnitCell_A(250.0).FFT_HighResolution_A(2 * PI / 3.0);
    experiment.ImportIndexingSettings(settings).SetUnitCell(uc);
    auto indexer = CreateIndexer(experiment);
    REQUIRE(indexer);

    std::vector<Coord> spots;
    for (int h = -2; h < 10; h++)
        for (int k = -5; k < 10; k++)
            for (int l = -3; l < 10; l++)
                spots.push_back(h * cl.Astar() + k * cl.Bstar() + l * cl.Cstar());

    const auto result = indexer->Run(spots);
    REQUIRE(result.lattice.size() == 1);
    const auto out = result.lattice[0].GetUnitCell();
    std::array<double, 3> lengths = {out.a, out.b, out.c};
    std::sort(lengths.begin(), lengths.end());
    CHECK(lengths[0] == Catch::Approx(39.0));
    CHECK(lengths[1] == Catch::Approx(45.0));
    CHECK(lengths[2] == Catch::Approx(78.0));
    CHECK(out.alpha == Catch::Approx(90.0));
    CHECK(out.beta == Catch::Approx(90.0));
    CHECK(out.gamma == Catch::Approx(90.0));
}

// End to end on the git-LFS rotation dataset (tests/data, see README.md there): HDF5 read through
// external links, CPU spot finding, the default indexer (FFTW on a CPU build), refinement and
// integration, on a short wedge. SKIPs when LFS was not pulled.
TEST_CASE("Portable_Rugnux_RotationWedge", "[portable][lfs]") {
    const auto master = jfjoch_test::LargeDataFile("rotation_master.h5");
    if (!master)
        SKIP("rotation_master.h5 not available (git-lfs data not pulled)");

    RegisterHDF5Filter();
    JFJochHDF5Reader reader;
    REQUIRE_NOTHROW(reader.ReadFile(*master));
    auto dataset = reader.GetDataset();
    REQUIRE(dataset);

    DiffractionExperiment experiment(dataset->experiment);
    IndexingSettings indexing;
    indexing.Algorithm(IndexingAlgorithmEnum::Auto);
    experiment.ImportIndexingSettings(indexing);

    ProcessConfig config;
    config.mode = ProcessMode::FullAnalysis;
    config.nthreads = std::max(1u, std::thread::hardware_concurrency());
    config.end_image = 4;
    config.spot_finding = DiffractionExperiment::DefaultDataProcessingSettings();
    config.spot_finding.indexing = true;

    Rugnux process(reader, experiment, *dataset->pixel_mask, config);
    ProcessResult result;
    REQUIRE_NOTHROW(result = process.Run());

    CHECK(result.images_processed == 4);
    REQUIRE(result.indexing_rate.has_value());
    CHECK(result.indexing_rate.value() > 0.5f);
    reader.Close();
}