Jungfraujoch/reader/HDF5ImageLocator.h

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

#pragma once

#include <map>
#include <memory>
#include <optional>
#include <string>
#include <vector>

#include "../writer/HDF5Objects.h"      // HDF5ReadOnlyFile, HDF5VirtualDatasetMapping, HDF5DataSetLayout
#include "../common/JFJochMessages.h"   // FileWriterFormat, HDF5DataSourceMessage

// Turns a global image number into the HDF5 file + local index that physically holds its pixels,
// for all three on-disk layouts (legacy linked data files, VDS, contiguous/integrated). This is
// the part of the reader whose "links to files stay" constant: it knows where the raw images
// live, independent of which master file the per-image metadata is read from.
//
// Open data-file handles are cached, so scanning many images (e.g. reprocessing) does not reopen
// the same file on every read. HDF5 is not thread-safe, so every call must be made with the
// global hdf5_mutex held by the caller; the locator does no locking of its own.
class HDF5ImageLocator {
public:
    struct Location {
        std::shared_ptr<HDF5ReadOnlyFile> file;
        uint32_t local_index = 0;
        // Path the file was opened from. Needed to open it a second time as a plain file, for the
        // positional reads HDF5ImageSource does outside the mutex.
        std::string path;
        // Where the images sit INSIDE that file. /entry/data/data everywhere DECTRIS writes, but a
        // VDS names its source dataset and is free to name another one, so take it at its word.
        std::string dataset = "/entry/data/data";
    };

    // One data file of a legacy multi-file dataset, with the dataset the master's link names
    // inside it - the same "take the link at its word" the VDS branch already does.
    struct LegacyFile {
        std::string path;
        std::string dataset;
    };

    // Layout description, filled by the reader once the master file has been parsed. All paths
    // are absolute: legacy data files and VDS mapping filenames are resolved relative to the
    // master before being handed over, so the locator never deals with relative paths.
    struct Layout {
        FileWriterFormat format = FileWriterFormat::NoFile;
        HDF5DataSetLayout data_layout = HDF5DataSetLayout::CONTIGUOUS;
        std::shared_ptr<HDF5ReadOnlyFile> master_file;
        std::string master_filename;
        std::vector<LegacyFile> legacy_files;
        size_t images_per_file = 1;
        std::vector<HDF5VirtualDatasetMapping> vds_mappings;
    };

    void Configure(Layout layout);
    void Clear();

    // Resolve a global image number to {file, local index}. Throws if the image is not covered
    // by the layout. Does not bounds-check against the total image count - the caller does that.
    Location Resolve(int64_t global_image) const;

    // Source mapping for re-writing a derived file (e.g. _process.h5) so it links back to the
    // original pixel sources rather than to a master. total_images is supplied by the caller.
    // stride is the step between consecutive images of the derived file in the SOURCE: image i of the
    // output comes from source image first_image + i * stride. It has to match the stride the caller
    // processed with, or the pictures and the per-image analysis in the derived file describe
    // different frames.
    std::vector<HDF5DataSourceMessage> GetSourceMapping(uint64_t first_image,
                                                        std::optional<uint64_t> image_count,
                                                        uint64_t total_images,
                                                        uint64_t stride = 1) const;

private:
    Layout layout_;
    mutable std::map<std::string, std::shared_ptr<HDF5ReadOnlyFile> > file_cache_;
    std::shared_ptr<HDF5ReadOnlyFile> OpenCached(const std::string &path) const;
};