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

#pragma once

#include "gemmi/grid.hpp"
#include "gemmi/recgrid.hpp"

// The structure factors of a real-space map on the model path (Fcalc from the model density, Fmask
// from the bulk-solvent mask): what gemmi::transform_map_to_f_phi(map, true) returns - the
// conjugated forward transform (F = sum rho exp(+2 pi i h.x)) scaled by V/N, kept for l >= 0 on an (nu, nv, nw/2+1) grid in the map's own XYZ order,
// ready for prepare_asu_data() - computed with FFTW rather than gemmi's single-threaded pocketfft.
// The same transform, not the same bits: the two libraries order their arithmetic differently.
//
// Plans are FFTW_ESTIMATE only - MEASURE would time candidate algorithms and could pick a different
// one from run to run - and made once per grid size and kept, so the rigid body's hundred-odd
// evaluations on one grid plan once. Safe to call from several threads at once.
gemmi::FPhiGrid<float> MapToFPhi(const gemmi::Grid<float> &map);

// The inverse: the real-space map of an (nu, nv, nw/2+1) half-l coefficient grid in XYZ order, as
// get_f_phi_on_grid() fills it - what gemmi::transform_f_phi_grid_to_map() returns (rho = 1/V sum F
// exp(-2 pi i h.x) on an (nu, nv, 2*(nw-1)) grid, NaN coefficients read as zero), computed with FFTW
// under the same planning rules.
gemmi::Grid<float> MapFromFPhi(const gemmi::FPhiGrid<float> &hkl);

// MapFromFPhi's transform itself, for a caller that fills its input: `in`, the (nu, nv, nw/2+1) half-l coefficients
// u fastest as MapFromFPhi hands them to FFTW (conjugated, a NaN as zero), is overwritten, and `out` receives the
// (nu, nv, nw) map before MapFromFPhi's 1/V. Both from fftwf_malloc, as a plan requires.
void MapFromFPhiExecute(int nu, int nv, int nw, std::complex<float> *in, float *out);

// CropHalfL(MapToFPhi(map), reach) on `nthreads` threads, for a map of hundreds of millions of points (the
// molecular transform's box), whose single-threaded transform is minutes of CPU: the r2c along w of every
// (u, v) column, then the 2D transform of every plane l <= reach - each column and each plane by one plan, so
// the result does not depend on the thread count. The same transform as MapToFPhi to float rounding, not bit
// for bit: FFTW's 3D plan orders its arithmetic its own way.
gemmi::FPhiGrid<float> MapToFPhiInParallel(const gemmi::Grid<float> &map, int reach, size_t nthreads);

// The half-l grid `full` with only the indices |k|, l <= reach kept, on a grid of full.nu x (2 reach + 1) x
// (reach + 1) that an index wraps into as it wraps into the whole one (the molecular transform's, which is
// read no further out).
gemmi::FPhiGrid<float> CropHalfL(const gemmi::FPhiGrid<float> &full, int reach);