// levelpath.cpp — transcription of FUN_180563440 (LUT curve + band combine)
// and FUN_18056e3e0 (twin-mask factory)
//
// Extracted from: handoff/nls_dasm/f_563440.dis (222 lines)
// Constants from: soothe_mem.bin at ImageBase 0x180000000
//
// Key addresses:
//   0x540000+0x2198 = r13+0x2198 = output accumulator (1024 doubles, stride 0x2000)
//   0x540000+0x188  = band config struct (A, B, C, flag, callback)
//   0x5408b0 = LUT coefficient table (PRNG state)
//   0x540868 = band count (max 6)
//   0x540870 = level weight (float)
//   0x540874 = level-dependent weight (float)
//   0x54087c = band weight (float)
//   0x54088c = sharpness weight (float)
//   0x540658 = window table (2048 floats, live-captured)
//   0x540698 = freq-axis (2049 floats, live-captured)
//   0x5406a8 = warp table (2049 floats)
//   0x5406b8 = warp exponent (float, = A_FIT)

#include <cmath>
#include <algorithm>
#include <cstring>
#include <cstdint>

// Constants extracted from binary
static constexpr float SCALE = 0.0009775171056389809f;  // 1/1023 (DAT_1824c3c54, verified 2026-08-19)
static constexpr float ONE   = 1.0f;                     // DAT_1824c3ea4
static constexpr float TWO   = 2.0f;                     // DAT_1824c41e0
static constexpr float NEG1  = -1.0f;                    // DAT_1824c4680
static constexpr float HALF  = 0.5f;                     // DAT_1824c3d8c
static constexpr float ZERO  = 0.0f;                     // DAT_1824c4140
static constexpr float DEPTH_SCALE = 4.0f;               // DAT_1824c4334
static constexpr float DB_CONV = 8.68588924407959f;      // 20/ln(10) (DAT_1824c43e0)
static constexpr float FLOOR_DB = -6.907755374908447f;   // ln(0.001) (DAT_1824c4704)
static constexpr float FLOOR_LIN = 0.001f;               // exp(FLOOR_DB)
static constexpr double TWO_PI = 6.283185307179586;      // DAT_1824c4248 (2π, twin-mask factory)
static constexpr float SCALE_1024 = 0.0009765625f;       // 1/1024 (DAT_1824c3c50, band LUT apply)
static constexpr float CONST_5 = 5.0f;                   // DAT_1824c4230 (AudioProcessingModule ctor)

// PRNG state offsets from param_1
static constexpr int PRNG_STATE = 0x2404e0;
static constexpr int PRNG_LUT   = 0x5408b0;

// Band config struct layout (offsets from band_base = param_1 + 0x188)
struct BandConfig {
    float A;        // +0x00: start value
    float B;        // +0x04: end value
    float _pad[2];
    float threshold; // +0x0c: threshold (compared to 1.0)
    uint8_t flag;   // +0x10: 0=linear, 1=power-law
    uint8_t _pad2[3];
    float _pad3[15];
    void* callback;  // +0x50: vtable callback (if non-null, use callback)
};

// Structural LUT curve (f_563440.dis, exact transcription 2026-08-19)
// x in [0,1], gamma == band->threshold (offset +0x0c), A=+0x00, B=+0x04
static float eval_lut_bin(float x, const BandConfig* band) {
    float gamma = band->threshold;
    float result;
    if (band->flag == 0) {
        // Linear path (0x563595): t = x^(1/γ) if γ!=1 && x>0; val = A + (B-A)*t
        // decomp: fVar16 = expf(logf(x)/gamma)  (FLOAT log/exp)
        float t = x;
        if (gamma != ONE && x > ZERO) {
            t = expf(logf(x) / gamma);
        }
        result = band->A + (band->B - band->A) * t;
    } else {
        // Power-law path (0x5635cd): t = 2x-1; if γ!=1 && t!=0: t = sign(t)·|t|^(1/γ)
        // val = A + (B-A)·0.5·(1+t); decomp: sign·expf(logf(|t|)/gamma)
        float t = TWO * x - ONE;
        if (gamma != ONE && t != ZERO) {
            float sign = (t < ZERO) ? NEG1 : ONE;
            t = expf(logf(fabsf(t)) / gamma) * sign;
        }
        result = band->A + (band->B - band->A) * HALF * (ONE + t);
    }
    return result;
}

// FUN_180563440: LUT curve evaluation for 0x400 bins
// r13 = context pointer (param_1). Loop counter edi, x = i*SCALE clamp[0,1],
// band config read from r13+0x188 each iteration (rbx), output double at r13+0x198[i*8].
void lut_curve_eval(void* ctx) {
    auto* base = static_cast<uint8_t*>(ctx);
    double* output = reinterpret_cast<double*>(base + 0x198);
    BandConfig* band = reinterpret_cast<BandConfig*>(base + 0x188);
    for (int bin = 0; bin < 0x400; bin++) {   // cmp $0x400 jl
        float x = static_cast<float>(bin) * SCALE;
        x = fminf(x, ONE);
        if (x < ZERO) x = ZERO;
        output[bin] = static_cast<double>(eval_lut_bin(x, band));
    }
}

// FUN_18056e3e0: twin-mask factory
// DECODED (decomp_funs2.txt:7988 + f_56e3e0.dis): fills the 0x400-bin mask
// with a SINGLE scalar  s = 2π / (count·SR), where
//   count = [ctx+0x240080] (int),  SR = [ctx+0x24] (float, internal SR).
// NOT a per-bin twin resonance — a constant fill (the "twin" shape enters
// elsewhere via the LUT curve FUN_180563440). Output mask stride 0x2000/band.
void twin_mask_factory(void* ctx, int band_idx, int n_bins) {
    auto* base = static_cast<uint8_t*>(ctx);
    int count = *reinterpret_cast<int*>(base + 0x240080);
    float sr = *reinterpret_cast<float*>(base + 0x24);
    double s = TWO_PI / (static_cast<double>(count) * static_cast<double>(sr));
    float* mask = reinterpret_cast<float*>(base + 0x4198 + band_idx * 0x2000);
    for (int i = 0; i < 0x400; i++) {
        mask[i] = static_cast<float>(s);
    }
}

// FUN_180563a60: band LUT apply (level -> gain). DECODED (decomp_funs2.txt:8975 + f_563a60.dis).
// For each of 6 bands and 0x400 bins:
//   level_dB   = 20·log10(mask[band][bin])          (logf · 8.6859)
//   level_axis[bin] = bin·(1/1024)                   (SCALE_1024)
//   t          = clamp((dB − A)/(B − A), 0, 1)        (BandConfig ctx+0x180: A,B,gamma,flag)
//   if gamma == 1.0:          val = t
//   elif flag == 0 (linear):  val = t^gamma            (powf, NOT 1/gamma)
//   else (power-law):          val = 0.5·(1 + sign(2t−1)·|2t−1|^gamma)
//   level_axis[bin+1] = val   (pairs level, gain)
// NOTE: this is the INVERSE curve of FUN_180563440 (which uses x^(1/γ)).
void band_lut_apply(void* ctx) {
    auto* base = static_cast<uint8_t*>(ctx);
    float* bandcfg = *reinterpret_cast<float**>(base + 0x180);
    float A = bandcfg[0];
    float B = bandcfg[1];
    float gamma = bandcfg[3];
    float flag = bandcfg[4];
    double* mask = reinterpret_cast<double*>(base + 0x4198);
    for (int band = 0; band < 6; band++) {
        double* m = mask + band * 0x400;
        float* level_gain = *reinterpret_cast<float**>(base + 0xe0 + band * 0x18);
        for (int bin = 0; bin < 0x400; bin++) {
            float db = logf(static_cast<float>(m[bin])) * DB_CONV;
            level_gain[bin * 2] = static_cast<float>(bin) * SCALE_1024;
            float t = (db - A) / (B - A);
            t = std::max(ZERO, std::min(ONE, t));
            float val = t;
            if (gamma != ONE) {
                if (flag == ZERO) {
                    val = powf(t, gamma);
                } else {
                    float u = TWO * t - ONE;
                    float sgn = (u < ZERO) ? NEG1 : ONE;
                    val = HALF * (ONE + sgn * powf(fabsf(u), gamma));
                }
            }
            level_gain[bin * 2 + 1] = val;
        }
    }
}

// ---- mask-accumulator combine kernels (FUN_180529fe0, CRT thunks) ----
// Signatures recovered from raw bytes in the rt snap (objdump of 0x180008d60/5a20/3c40).
//
// 0x8d60 combine3: out[i] = a[i] - b[i]   (vsubpd, 3 pointers; dst is the 3rd arg)
//   In the per-band loop: 0x5406f8[i] = 0x540678[i] - 0x5407c8[i]
void combine_sub(double* out, const double* a, const double* b, int n) {
    for (int i = 0; i < n; i++) out[i] = a[i] - b[i];
}

// 0x5a20: dst[i] += src[i]  (double; kernel 0x18001a5a0)
void acc_add(double* dst, const double* src, int n) {
    for (int i = 0; i < n; i++) dst[i] += src[i];
}

// 0x3c40: dst[i] += a[i] * b[i]  (double; vfmadd213pd)
void acc_fma(double* dst, const double* a, const double* b, int n) {
    for (int i = 0; i < n; i++) dst[i] += a[i] * b[i];
}

// FUN_180529fe0: coefficient setup (from decomp_funs.txt)
void coefficient_setup(void* ctx, int band_idx, int param3, int param4) {
    auto* base = static_cast<uint8_t*>(ctx);
    
    // Lock (atomic flag at 0x2404dc)
    uint32_t* lock = reinterpret_cast<uint32_t*>(base + 0x2404dc);
    // LOCK(); *lock |= 1; UNLOCK();  // simplified
    
    // PRNG state update (LCG)
    int32_t state = *reinterpret_cast<int32_t*>(base + PRNG_STATE);
    state = (state + 0x3cdca) & 0x7fffffff;
    *reinterpret_cast<int32_t*>(base + PRNG_STATE) = state;
    
    // Load LUT coefficients
    float* lut_table = reinterpret_cast<float*>(base + PRNG_LUT);
    float coeff0 = lut_table[state];
    float coeff1 = lut_table[state + 1];
    
    // Generate 6 coefficient pairs
    // Each pair: (coeff_i * scale + offset) * global_scale
    float acc = ZERO;
    for (int i = 0; i < 3; i++) {
        state = (state + 0x140236 + i * 0x10d56) & 0x7fffffff;
        float a = lut_table[state];
        float b = lut_table[state + 1];
        acc += a * b;
    }
    
    // Normalize
    float normalized = acc / static_cast<float>(param3);
    
    // Apply depth scaling: powf(normalized, depth)
    float depth = *reinterpret_cast<float*>(base + 0x2c);
    float depthScaled = powf(normalized, depth);
    
    // Store result
    *reinterpret_cast<float*>(base + 0x54088c) = depthScaled;
    
    // Apply sharpness weight
    float sharpness = *reinterpret_cast<float*>(base + 0x540870);
    depthScaled *= sharpness;
    
    // Invert: gain = 1 - mask
    *reinterpret_cast<float*>(base + 0x54088c) = ONE - depthScaled;
}