#pragma once
#include <cstddef>
#include <cstdint>
#include <complex>
#include "fft_plan.hpp"

namespace fft {

void init_plan(FFTPlan* plan, uint32_t log2N);
void build_twiddle(FFTPlan* plan, double* scratch);
void execute(const FFTPlan* plan, std::complex<double>* buf);
void execute_inverse(const FFTPlan* plan, std::complex<double>* buf);

// Real RFFT: N real → N/2+1 complex (forward)
// N/2+1 complex → N real (inverse)
void execute_real_forward(const FFTPlan* plan, double* real_in, std::complex<double>* complex_out);
void execute_real_inverse(const FFTPlan* plan, std::complex<double>* complex_in, double* real_out);

// Bit-exact RFFT matching plugin's th1a90/th2180 (FMA-complex with buf548/mask598)
// plan: FFTPlan with log2N=12 (N=4096)
// buf548: cos/sin table (size N, 2*double per entry: cos, sin), scale=2^-12
// mask598: SIMD lane masks (size N/4 float: 8×1.0, 8×0.0 periodic)
void execute_real_forward_exact(const FFTPlan* plan, 
    double* real_in, std::complex<double>* complex_out,
    const double* buf548, const float* mask598);
void execute_real_inverse_exact(const FFTPlan* plan,
    std::complex<double>* complex_in, double* real_out,
    const double* buf548, const float* mask598);

// Build plugin's exact buf548 and mask598 tables
void build_buf548(double* buf548, uint32_t N);
void build_mask598(float* mask598, uint32_t N);

}