Jungfraujoch/reader/MiniCBF.h

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

#pragma once

#include <array>
#include <cstdint>
#include <optional>
#include <string>
#include <vector>

#include "../common/CompressedImage.h"

// PILATUS miniCBF: an ASCII header, four separator bytes, then one byte-offset compressed image.
// No CIF parser and no libcbf are needed - every value is on a "# " comment line or a MIME line.
namespace minicbf {

// The four bytes that end the MIME header and begin the binary section.
inline constexpr unsigned char BINARY_SEPARATOR[4] = {0x0c, 0x1a, 0x04, 0xd5};

struct Header {
    std::string detector;          // "PILATUS3 6M, S/N 60-0136"
    int64_t nx = 0;                // fast dimension (columns)
    int64_t ny = 0;                // slow dimension (rows)
    int64_t nelem = 0;             // pixel count declared by the MIME header
    double pixel_x_m = 0;
    double pixel_y_m = 0;
    double thickness_m = 0;
    std::string material = "Si";   // NORMALISED: the file says "Silicon", the rest of the code wants "Si"
    double distance_m = 0;
    double beam_x_px = 0;
    double beam_y_px = 0;
    double wavelength_A = 0;
    double start_angle_deg = 0;
    double angle_increment_deg = 0;
    double two_theta_deg = 0;
    // Goniometer head angles and the per-image increment of each, in degrees. A writer spells "this
    // head has no such axis" as -9999, which is a sentinel and not an angle, so an axis the header
    // does not really carry is absent here rather than 9999 degrees away from zero.
    std::optional<double> chi_deg;
    std::optional<double> omega_deg;
    double chi_increment_deg = 0;
    double phi_increment_deg = 0;
    double omega_increment_deg = 0;
    double exposure_s = 0;
    double period_s = 0;
    int64_t count_cutoff = 0;      // saturation
    // "# Polarization 0.990": the fraction of the beam polarized in the horizontal plane (0.5 is
    // unpolarized). Absent where the line is missing or says "None".
    std::optional<double> polarization_fraction;
    std::string axis_name = "omega";
    bool byte_offset = false;      // the only conversion supported

    // The imgCIF axis table the CBF template block carries after the "# " lines, as the file states
    // it: vectors in the imgCIF laboratory frame (Z from the sample towards the source, Y opposite
    // gravity, X completing a right-handed set). Turning them into any other frame is the caller's
    // business, not this format reader's. Most headers carry no such table and leave all of these
    // empty, which is not the same as their stating the usual mounting.
    std::optional<std::array<double, 3>> fast_direction;   // laboratory direction of a +1 column step
    std::optional<std::array<double, 3>> slow_direction;   // ... of a +1 row step
    std::optional<std::array<double, 3>> spindle_axis;     // the base goniometer rotation axis
    // The goniometer rotation axis carried by the base one, stated in the base axis' own frame. A
    // head whose inner circle is INCLINED - a fixed-chi stage, a kappa arm - says so only here: its
    // "# Chi" and "# Kappa" lines read zero because no such circle is driven. Empty where the table
    // states one rotation axis only, which is every Eulerian head.
    std::optional<std::array<double, 3>> inner_spindle_axis;
    std::optional<std::array<double, 3>> detector_axis;    // the detector's own rotation axis: a 2theta arm
    // "# Oscillation_axis X.CW +SLOW". Some writers say which of the two image directions the spindle
    // runs along instead of stating a vector. The axis NAME on that line is a poor discriminator (see
    // ScansPhi, and note that the one header carrying both a name and a table says "X" where its table
    // says Y) but this token is not: where both are present they agree.
    bool spindle_along_slow = false;
};

// Whether the sweep turns PHI rather than the base (omega) axis. What moved is the axis with a
// non-zero increment - a header routinely carries a "# Phi" angle for a phi that stands still - so
// the name is consulted only when no increment is stated at all. It is a poor discriminator: some
// writers put a direction convention there ("X.CW") instead of an axis name.
bool ScansPhi(const Header &h);

// Byte offset of the binary section (just past the separator), or nothing if there is none.
std::optional<size_t> FindBinarySection(const uint8_t *data, size_t size);

// Parse the ASCII header. Pass the bytes BEFORE the separator; headers are not a fixed size (one
// Diamond I24 set carries 6335 bytes, well past a 4 kB guess), so never parse a fixed prefix.
Header ParseHeader(const char *data, size_t size);

// Header + pixels of one file, read from disk.
Header Read(const std::string &path, std::vector<int32_t> &out);

// The same, decoding into memory the caller already has (one read of the file, no extra copy).
// The compressed file is read through scratch, which the caller keeps between frames: a fresh
// vector per image is megabytes of allocation and of zeroing nothing ever reads.
// Throws if the image does not fit in capacity pixels.
Header ReadInto(const std::string &path, int32_t *out, size_t capacity, std::vector<uint8_t> &scratch);

// The whole file read into buf, header parsed and checked, without decoding the pixels: the byte-offset
// stream starts at binary_start. For a consumer that decodes it itself - on the device, where there is one.
Header ReadCompressed(const std::string &path, RawByteBuffer &buf, size_t &binary_start);

// Header only - reads just enough of the file to reach the separator. Cheap enough to call per
// frame for the rotation angles.
Header ReadHeader(const std::string &path);

}  // namespace minicbf