// render48k.cpp — 48000/N=4096 internal-grid renderer (BITEXACT_PLAN step 6, path b).
//
// Host audio is 44100; the plugin detector runs internally at 48000/N=4096 (the
// live IIR/warp/freq-axis tables are sized for that grid). This tool mirrors that:
//   1. read input WAV (44100 host samples)
//   2. resample 44100 -> 48000  (libsamplerate, SINC best)
//   3. SpectralProcessor(4096, 1024, 48000) with the given bands
//   4. resample 48000 -> 44100
//   5. write 24-bit output WAV (matches reference format)
// Usage: render48k <in.wav> <out.wav> [fc,q,sens[,scale] ...]  (comma bands, like framed_test)
#include "spectral.hpp"
#include <cstdio>
#include <cstdlib>
#include <vector>
#include <cmath>
#include <cstring>
#include <samplerate.h>

static int g_in_ch = 1;

static bool load_wav(const char* path, std::vector<float>& out, int& sr) {
    FILE* f = fopen(path, "rb");
    if (!f) return false;
    char hdr[44];
    if (fread(hdr, 1, 44, f) != 44) return false;
    sr = *(int*)(hdr + 24);
    int ch = *(short*)(hdr + 22);
    int bits = *(short*)(hdr + 34);
    // scan chunks to find data chunk size (hdr[40] may be bext/junk size)
    int data = 0;
    int64_t pos = 12;
    fseek(f, 12, SEEK_SET);
    while (pos < 32 * 1024 * 1024) {
        char cid[4]; int csize;
        if (fread(cid, 1, 4, f) < 4 || fread(&csize, 4, 1, f) < 1) break;
        pos += 8;
        if (memcmp(cid, "data", 4) == 0) { data = csize; break; }
        pos += csize;
        int skip = csize;
        if (csize % 2) skip++;  // odd chunk size padded
        fseek(f, skip, SEEK_CUR);
    }
    if (!data) { fclose(f); return false; }
    int n = data / (ch * (bits / 8));
    g_in_ch = ch;
    out.resize(n);
    if (bits == 16) {
        std::vector<short> raw(n * ch);
        fread(raw.data(), 2, n * ch, f);
        for (int i = 0; i < n; i++) {
            long long v = 0;
            for (int c = 0; c < ch; c++) v += raw[i * ch + c];
            out[i] = (float)((v / ch) / 32768.0);
        }
    } else if (bits == 24) {
        std::vector<unsigned char> raw(n * ch * 3);
        fread(raw.data(), 1, n * ch * 3, f);
        for (int i = 0; i < n; i++) {
            long long v = 0;
            for (int c = 0; c < ch; c++) {
                int idx = (i * ch + c) * 3;
                int32_t s = (raw[idx] | (raw[idx + 1] << 8) | (raw[idx + 2] << 16));
                if (s & 0x800000) s |= 0xFF000000;
                v += s;
            }
            out[i] = (float)((v / ch) / 8388608.0);
        }
    } else return false;
    fclose(f);
    return true;
}

static bool save_wav24(const char* path, const std::vector<float>& x, int sr) {
    FILE* f = fopen(path, "wb");
    if (!f) return false;
    int ch = 2, bits = 24;
    // x is already stereo interleaved (size = mono_samples * 2)
    int data = (int)(x.size() * (bits / 8));
    char hdr[44]; memset(hdr, 0, 44);
    memcpy(hdr, "RIFF", 4); *(int*)(hdr + 4) = 36 + data;
    memcpy(hdr + 8, "WAVE", 4); memcpy(hdr + 12, "fmt ", 4);
    *(int*)(hdr + 16) = 16; *(short*)(hdr + 20) = 1; *(short*)(hdr + 22) = (short)ch;
    *(int*)(hdr + 24) = sr; *(int*)(hdr + 28) = sr * ch * (bits / 8);
    *(short*)(hdr + 32) = (short)ch; *(short*)(hdr + 34) = (short)bits;
    memcpy(hdr + 36, "data", 4); *(int*)(hdr + 40) = data;
    fwrite(hdr, 1, 44, f);
    for (size_t i = 0; i < x.size(); i++) {
        int32_t v = (int32_t)(std::max(-1.0f, std::min(1.0f, x[i])) * 8388607.0f);
        unsigned char b0 = v & 0xFF, b1 = (v >> 8) & 0xFF, b2 = (v >> 16) & 0xFF;
        fwrite(&b0, 1, 1, f); fwrite(&b1, 1, 1, f); fwrite(&b2, 1, 1, f);
    }
    fclose(f);
    return true;
}

static std::vector<float> resample(const std::vector<float>& in, int src_sr, int dst_sr) {
    double frac = (double)dst_sr / src_sr;
    int out_len = (int)(in.size() * frac) + 16;
    std::vector<float> buf(out_len);
    SRC_DATA sd;
    sd.data_in = in.data(); sd.input_frames = (long)in.size();
    sd.data_out = buf.data(); sd.output_frames = out_len;
    sd.src_ratio = frac; sd.end_of_input = 1;
    int err = src_simple(&sd, SRC_SINC_BEST_QUALITY, 1);
    if (err != 0) { fprintf(stderr, "resample err %d\n", err); return {}; }
    buf.resize(sd.output_frames_gen);
    return buf;
}

int main(int argc, char** argv) {
    if (argc < 3) { fprintf(stderr, "usage: %s in.wav out.wav [fc,q,sens[,scale] ...]\n", argv[0]); return 1; }
    std::vector<float> x; int sr;
    if (!load_wav(argv[1], x, sr)) { fprintf(stderr, "cannot load %s\n", argv[1]); return 1; }

    std::vector<DetectorBand> bands;
    for (int i = 3; i < argc; i++) {
        if (!strchr(argv[i], ',')) continue;
        float fc, q, sens, scl = 1.0f;
        if (sscanf(argv[i], "%f,%f,%f,%f", &fc, &q, &sens, &scl) < 3) continue;
        DetectorBand b; b.fc = fc; b.q = q; b.sens = sens; b.level_scale = scl;
        bands.push_back(b);
    }
    if (bands.empty()) bands.push_back({1000.0f, 1.0f, 12.0f});

    auto x48 = resample(x, sr, 48000);
    if (x48.empty()) return 1;

    SpectralProcessor sp(4096, 1024, 48000.0f);
    sp.setDetectorParams(bands);
    std::vector<float> y48(x48.size());
    const size_t BLK = 1 << 16;
    std::vector<float> inb(BLK), outb(BLK);
    for (size_t s = 0; s < x48.size(); s += BLK) {
        size_t n = std::min(BLK, x48.size() - s);
        memcpy(inb.data(), x48.data() + s, n * sizeof(float));
        for (size_t i = n; i < BLK; i++) inb[i] = 0.0f;
        sp.processBlock(inb.data(), outb.data(), BLK, 1);
        memcpy(y48.data() + s, outb.data(), n * sizeof(float));
    }
    auto y = resample(y48, 48000, 44100);
    if ((int)y.size() > (int)x.size()) y.resize(x.size());

    // write stereo 24-bit
    std::vector<float> yst(y.size() * 2);
    for (size_t i = 0; i < y.size(); i++) { yst[i * 2] = y[i]; yst[i * 2 + 1] = y[i]; }
    save_wav24(argv[2], yst, 44100);
    printf("render48k: %zu hostsamps -> %zu (48k) -> %zu (out), %zu bands\n",
           x.size(), x48.size(), y.size(), bands.size());
    (void)g_in_ch;
    return 0;
}