Files
Jungfraujoch/tests/RugnuxLargeTest.cpp
T
leonarski_fandClaude Opus 4.8 abbee2d4dc Remove sample identities from the repository; document the rule
Datasets may be confidential; sample names and measured unit cells committed to
the repo can leak outside the group working on them. Scrub existing occurrences
and add a "No sample identities in the repository" section to CLAUDE.md
(forbidden: sample/dataset names, internal codes, measured cells tied to a
sample; fine: space group / lattice / twinning descriptors).

- Comments: replace internal dataset codes and protein names with the
  crystallographic situation they illustrate (centred vs pseudo-symmetric,
  holohedral, cubic, F-cubic/hexagonal, ...).
- Docs: same, in the analysis/writer/stream references and example configs.
- Tests: rename sample-named identifiers, TEST_CASE names, file prefixes and
  asserted labels to neutral crystallographic names (e.g. tetragonal_uc);
  behaviour unchanged. Reduce the CrystFEL reference PDB to a bare CRYST1 cell
  file (cell.pdb) and rename the reference data file.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-15 17:19:43 +02:00

83 lines
3.2 KiB
C++

// SPDX-FileCopyrightText: 2026 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only
// End-to-end Rugnux runs over real JUNGFRAU datasets that are kept in git-LFS under
// tests/data. They are tagged [large] and SKIP() when the data is not present (e.g. LFS not
// pulled), so the default test run stays fast and CI without the data still passes.
#include <catch2/catch_all.hpp>
#include <catch2/reporters/catch_reporter_event_listener.hpp>
#include <catch2/reporters/catch_reporter_registrars.hpp>
#include <iostream>
#include <thread>
#include "TestData.h"
#include "../common/DiffractionExperiment.h"
#include "../common/IndexingSettings.h"
#include "../reader/JFJochHDF5Reader.h"
#include "../rugnux/Rugnux.h"
namespace {
// Start-up hook: report once whether the large datasets are available, so it is obvious why
// the [large] tests skip when they do.
class LargeDataListener : public Catch::EventListenerBase {
public:
using Catch::EventListenerBase::EventListenerBase;
void testRunStarting(Catch::TestRunInfo const &) override {
const bool rot = jfjoch_test::LargeDataFile("rotation_master.h5").has_value();
std::cout << "[jfjoch_test] large dataset in " << jfjoch_test::LargeDataDir()
<< ": rotation=" << (rot ? "yes" : "no")
<< " ([large] tests skip when absent)" << std::endl;
}
};
int default_threads() {
const unsigned hc = std::thread::hardware_concurrency();
return hc == 0 ? 4 : static_cast<int>(hc);
}
}
CATCH_REGISTER_LISTENER(LargeDataListener)
TEST_CASE("Rugnux_Rotation", "[large]") {
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);
indexing.RotationIndexing(true);
indexing.GeomRefinementAlgorithm(GeomRefinementAlgorithmEnum::BeamCenter);
experiment.ImportIndexingSettings(indexing);
ProcessConfig config;
config.mode = ProcessMode::FullAnalysis;
config.nthreads = default_threads();
config.spot_finding = DiffractionExperiment::DefaultDataProcessingSettings();
config.spot_finding.indexing = true;
config.rotation_indexing = true;
config.two_pass_rotation = true;
config.reuse_rotation_spots = false; // redo spot finding (raw dataset may carry no spots)
Rugnux process(reader, experiment, *dataset->pixel_mask, config);
ProcessResult result;
REQUIRE_NOTHROW(result = process.Run());
CHECK_FALSE(result.cancelled);
CHECK(result.images_processed == reader.GetNumberOfImages());
REQUIRE(result.indexing_rate.has_value());
CHECK(result.indexing_rate.value() > 0.1f); // a real rotation series indexes well
CHECK(result.consensus_cell.has_value());
reader.Close();
REQUIRE(H5Fget_obj_count(H5F_OBJ_ALL, H5F_OBJ_ALL) == 0);
}