SonicForgeStudio/native_bridge/src/RenderJob.cpp

// native_bridge/src/RenderJob.cpp
// Offline render mode (Phase 0 of PLAN_REPLACE_PEDALBOARD_NATIVE_BRIDGE.md):
// `daw_vst_bridge --render <job.json> --out <clip.wav>` renders MIDI notes
// through the same instrument engines as realtime (SF2/SFZ/VST3/VST2) and
// writes a 16-bit stereo WAV. No GUI, no SHM, no Tauri parent — pure CLI.
//
// JSON parsing uses the public-domain sheredom/json.h vendored with the VST3
// SDK (vst3sdk/public.sdk/source/vst/moduleinfo/json.h) — no new dependency.
#include "RenderJob.h"
#include "NativeInstrumentEngine.h"

// sheredom/json.h (public domain, vendored with the VST3 SDK) is header-only
// and needed for SF2/SFZ render even without the VST3 SDK — include it directly.
#include "vst3sdk/public.sdk/source/vst/moduleinfo/json.h"
#ifdef HAVE_VST3SDK
#include "public.sdk/source/vst/vstpresetfile.h"
#include "public.sdk/source/common/memorystream.h"
using Steinberg::int32;
using Steinberg::uint32;
#endif

#ifdef _WIN32
#ifndef NOMINMAX
#define NOMINMAX
#endif
#include <windows.h>
#endif

#include <algorithm>
#include <cmath>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <fstream>
#include <iostream>
#include <iterator>
#include <string>
#include <vector>

namespace {

// --- sheredom/json.h helpers -------------------------------------------------
const json_object_element_s* member(const json_object_s* o, const char* key) {
    for (const json_object_element_s* e = o ? o->start : nullptr; e; e = e->next)
        if (e->name && e->name->string && std::strcmp(e->name->string, key) == 0)
            return e;
    return nullptr;
}

const json_value_s* memberValue(const json_object_s* o, const char* key) {
    const json_object_element_s* m = member(o, key);
    return m ? m->value : nullptr;
}

std::string memberString(const json_object_s* o, const char* key, const std::string& def) {
    const json_value_s* v = memberValue(o, key);
    if (v && v->type == json_type_string) {
        const auto* s = static_cast<const json_string_s*>(v->payload);
        return std::string(s->string, s->string_size);
    }
    return def;
}

bool memberNumber(const json_object_s* o, const char* key, double& out) {
    const json_value_s* v = memberValue(o, key);
    if (v && v->type == json_type_number) {
        out = std::atof(static_cast<const json_number_s*>(v->payload)->number);
        return true;
    }
    return false;
}

int64_t memberInt(const json_object_s* o, const char* key, int64_t def) {
    double d;
    return memberNumber(o, key, d) ? (int64_t)d : def;
}

// --- WAV writer (stdlib only, 16-bit PCM stereo, little-endian) --------------
void writeU16(std::ofstream& f, uint16_t v) {
    char b[2] = { (char)(v & 0xFF), (char)((v >> 8) & 0xFF) };
    f.write(b, 2);
}
void writeU32(std::ofstream& f, uint32_t v) {
    char b[4] = { (char)(v & 0xFF), (char)((v >> 8) & 0xFF),
                  (char)((v >> 16) & 0xFF), (char)((v >> 24) & 0xFF) };
    f.write(b, 4);
}
void writeWavHeader(std::ofstream& f, uint32_t sampleRate) {
    f.write("RIFF", 4);
    writeU32(f, 36);          // patched in finishWav
    f.write("WAVE", 4);
    f.write("fmt ", 4);
    writeU32(f, 16);          // fmt chunk size
    writeU16(f, 1);           // PCM
    writeU16(f, 2);           // stereo
    writeU32(f, sampleRate);
    writeU32(f, sampleRate * 4);  // byte rate
    writeU16(f, 4);               // block align
    writeU16(f, 16);              // bits per sample
    f.write("data", 4);
    writeU32(f, 0);           // patched in finishWav
}
void finishWav(std::ofstream& f, uint64_t dataBytes) {
    f.seekp(4);
    writeU32(f, (uint32_t)(36 + dataBytes));
    f.seekp(40);
    writeU32(f, (uint32_t)dataBytes);
    f.flush();
}
void writeFrames(std::ofstream& f, const float* L, const float* R, uint32_t n) {
    for (uint32_t i = 0; i < n; ++i) {
        auto cl = [](float v) -> int {
            if (v > 1.0f) v = 1.0f;
            else if (v < -1.0f) v = -1.0f;
            return (int)(v * 32767.0f);
        };
        writeU16(f, (uint16_t)cl(L[i]));
        writeU16(f, (uint16_t)cl(R[i]));
    }
}

// One scheduled MIDI event at an absolute sample position. kind: 0=noteOn
// (a=pitch,b=velocity 1..127), 1=noteOff (a=pitch), 2=CC (a=cc,b=value),
// 3=program change (a=program).
struct Ev { uint64_t sample; uint8_t kind; uint32_t a; uint32_t b; };

#ifdef HAVE_VST3SDK
// --- base64 (RFC 4648) - same helpers as Vst3Instrument.cpp -----------------
static const char* kBase64Tbl = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
static std::string base64Encode(const uint8_t* data, size_t len) {
    std::string out;
    out.reserve(((len + 2) / 3) * 4);
    for (size_t i = 0; i < len; i += 3) {
        uint32_t n = (uint32_t)data[i] << 16;
        if (i + 1 < len) n |= (uint32_t)data[i + 1] << 8;
        if (i + 2 < len) n |= (uint32_t)data[i + 2];
        out += kBase64Tbl[(n >> 18) & 63];
        out += kBase64Tbl[(n >> 12) & 63];
        out += (i + 1 < len) ? kBase64Tbl[(n >> 6) & 63] : '=';
        out += (i + 2 < len) ? kBase64Tbl[n & 63] : '=';
    }
    return out;
}
static int b64val(unsigned char c) {
    if (c >= 'A' && c <= 'Z') return c - 'A';
    if (c >= 'a' && c <= 'z') return c - 'a' + 26;
    if (c >= '0' && c <= '9') return c - '0' + 52;
    if (c == '+') return 62;
    if (c == '/') return 63;
    return -1;
}
static bool base64Decode(const std::string& in, std::vector<uint8_t>& out) {
    out.clear();
    out.reserve((in.size() / 4) * 3);
    uint32_t acc = 0;
    int bits = 0;
    for (unsigned char ch : in) {
        if (ch == '=' || ch == '\n' || ch == '\r' || ch == ' ') continue;
        int v = b64val(ch);
        if (v < 0) return false;
        acc = (acc << 6) | (uint32_t)v;
        bits += 6;
        if (bits >= 8) {
            bits -= 8;
            out.push_back((uint8_t)((acc >> bits) & 0xFF));
        }
    }
    return true;
}

// --- Phase 1: .vstpreset import (VST3 SDK binary chunk format, NOT ZIP) ----
// Pedalboard's VST3Plugin.preset_data is exactly the SDK preset file: 'VST3'
// magic + class id + chunk list (Comp/Cont entries). Parse it with
// PresetFile, rewrap component/controller states into the bridge blob
// [4B BE compLen][comp][4B BE ctrlLen][ctrl] (loadSerializedState's format),
// and hand it to the engine so restoreState() applies it to the live instance.
bool applyVst3Preset(INativeInstrument* inst, const std::string& presetB64) {
    std::vector<uint8_t> file;
    if (!base64Decode(presetB64, file) || file.size() < 8) {
        std::cerr << "[RenderJob] preset: bad base64 payload" << std::endl;
        return false;
    }
    if (std::memcmp(file.data(), "VST3", 4) != 0) {
        std::cerr << "[RenderJob] preset: not a VST3 preset file (bad magic)" << std::endl;
        return false;
    }
    Steinberg::MemoryStream stream;
    if (stream.write(file.data(), (int32)file.size(), nullptr) != Steinberg::kResultOk) {
        std::cerr << "[RenderJob] preset: cannot write memory stream" << std::endl;
        return false;
    }
    stream.seek(0, Steinberg::IBStream::kIBSeekSet, nullptr);
    Steinberg::Vst::PresetFile pf(&stream);
    if (!pf.readChunkList()) {
        std::cerr << "[RenderJob] preset: cannot read chunk list" << std::endl;
        return false;
    }
    auto readChunk = [&](Steinberg::Vst::ChunkType which, std::vector<uint8_t>& out) -> bool {
        const Steinberg::Vst::PresetFile::Entry* e = pf.getEntry(which);
        if (!e) return true;  // chunk absent - leave empty
        bool seeked = (which == Steinberg::Vst::kComponentState) ? pf.seekToComponentState()
                                                                 : pf.seekToControllerState();
        if (!seeked) return false;
        out.resize((size_t)e->size);
        if (e->size == 0) return true;  // empty chunk (e.g. Cont in Nexus)
        int32 got = 0;
        return stream.read(out.data(), (int32)e->size, &got) == Steinberg::kResultOk &&
               got == e->size;
    };
    std::vector<uint8_t> comp, ctrl;
    if (!readChunk(Steinberg::Vst::kComponentState, comp) ||
        !readChunk(Steinberg::Vst::kControllerState, ctrl)) {
        std::cerr << "[RenderJob] preset: failed reading component/controller chunks" << std::endl;
        return false;
    }
    std::vector<uint8_t> blob;
    auto append32 = [&blob](uint32_t v) {
        blob.push_back((uint8_t)(v >> 24));
        blob.push_back((uint8_t)(v >> 16));
        blob.push_back((uint8_t)(v >> 8));
        blob.push_back((uint8_t)v);
    };
    append32((uint32_t)comp.size());
    blob.insert(blob.end(), comp.begin(), comp.end());
    append32((uint32_t)ctrl.size());
    blob.insert(blob.end(), ctrl.begin(), ctrl.end());
    inst->loadSerializedState(base64Encode(blob.data(), blob.size()));
    return true;
}
#endif // HAVE_VST3SDK

} // namespace

int run_render_job(const std::string& jobPath, const std::string& outPath) {
#ifdef _WIN32
    // VST3 hosting needs COM on the loading thread (realtime mode's workers
    // call OleInitialize; here the main thread hosts the plugin).
    CoInitializeEx(nullptr, COINIT_MULTITHREADED);
    struct ComGuard { ~ComGuard() { CoUninitialize(); } } comGuard;
#endif

    int rc = 1;  // default: job/argument error
    std::ofstream wav;
    auto fail = [&](const std::string& msg) {
        std::cerr << "[RenderJob] " << msg << std::endl;
        if (wav.is_open()) wav.close();
        std::remove(outPath.c_str());  // never leave a partial clip behind
    };

    struct RootHolder { json_value_s* p = nullptr; ~RootHolder() { if (p) std::free(p); } } rootH;

    // 1. Read + parse the job.
    std::ifstream in(jobPath, std::ios::binary);
    if (!in) { fail("cannot read job file: " + jobPath); return rc; }
    std::string data((std::istreambuf_iterator<char>(in)), std::istreambuf_iterator<char>());
    if (data.empty()) { fail("job file is empty: " + jobPath); return rc; }

    json_parse_result_s pres = {};
    json_value_s* root = json_parse_ex(data.data(), data.size(), json_parse_flags_default,
                                       nullptr, nullptr, &pres);
    if (!root) {
        fail("job JSON parse error (code " + std::to_string(pres.error) + ")");
        return rc;
    }
    rootH.p = root;
    if (root->type != json_type_object) {
        fail("job root must be a JSON object");
        return rc;
    }
    const json_object_s* job = static_cast<const json_object_s*>(root->payload);

    // 2. Instrument.
    const int64_t itype = memberInt(job, "instrument_type", -1);
    if (itype < 0 || itype > 3) { fail("job missing instrument_type (0=VST3,1=VST2,2=SF2/SF3,3=SFZ)"); return rc; }
    const InstrumentType type = (InstrumentType)itype;
    const std::string pluginPath = memberString(job, "plugin_path", "");
    if (pluginPath.empty()) { fail("job missing plugin_path"); return rc; }
    const std::string preset = memberString(job, "preset", "");

    // 3. Format.
    double srD = 44100.0;
    memberNumber(job, "sample_rate", srD);
    if (srD < 8000.0 || srD > 192000.0) { fail("bad sample_rate: " + std::to_string(srD)); return rc; }
    const uint32_t sampleRate = (uint32_t)srD;
    int64_t block = memberInt(job, "block_size", 256);
    if (block > 256) {
        std::cerr << "[RenderJob] block_size " << block << " > 256 — clamping (VST3 host buffers are prepared at 256)" << std::endl;
        block = 256;
    }
    const uint32_t chunk = (uint32_t)std::max<int64_t>(32, block);
    double bpm = 120.0;
    memberNumber(job, "bpm", bpm);
    bpm = std::max(30.0, bpm);  // mirror plugins.py: max(30.0, bpm)
    const double beatSec = 60.0 / bpm;

    // 4. MIDI events (mirror vst_engine.midi_events_to_messages semantics:
    // CC0 bank select + program change at t=0, noteOn at start, noteOff at
    // start+duration, all sample-accurate).
    std::vector<Ev> evs;
    if (memberValue(job, "soundfont_bank")) {
        evs.push_back({0, 2, 0, (uint32_t)(memberInt(job, "soundfont_bank", 0) & 0x7F)});
    }
    if (memberValue(job, "soundfont_program")) {
        evs.push_back({0, 3, (uint32_t)(memberInt(job, "soundfont_program", 0) & 0x7F), 0});
    }
    const json_value_s* nv = memberValue(job, "notes");
    if (!nv || nv->type != json_type_array) { fail("job missing notes array"); return rc; }
    const json_array_s* notes = static_cast<const json_array_s*>(nv->payload);
    if (notes->length == 0) { fail("job notes array is empty"); return rc; }
    uint64_t totalNeeded = 1024;  // mirror plugins.py: max(total_needed, 1024)
    for (const json_array_element_s* el = notes->start; el; el = el->next) {
        const json_value_s* v = el->value;
        if (!v || v->type != json_type_object) continue;
        const json_object_s* n = static_cast<const json_object_s*>(v->payload);
        const uint32_t pitch = (uint32_t)(memberInt(n, "pitch", 60) & 0x7F);
        double velF = 0.8;
        memberNumber(n, "velocity", velF);
        int vel = (int)(velF * 127.0);           // mirror plugins.py: int(vel*127)
        vel = std::max(0, std::min(127, vel));
        const double startBeat = [&] { double d = 0.0; memberNumber(n, "start_beat", d); return d; }();
        const double durBeats = [&] { double d = 1.0; memberNumber(n, "duration_beats", d); return d; }();
        const uint64_t startSample = (uint64_t)std::llround(startBeat * beatSec * sampleRate);
        const uint64_t endSample = (uint64_t)std::llround((startBeat + durBeats) * beatSec * sampleRate);
        evs.push_back({startSample, 0, pitch, (uint32_t)vel});
        evs.push_back({endSample, 1, pitch, 0});
        if (endSample > totalNeeded) totalNeeded = endSample;
    }
    std::stable_sort(evs.begin(), evs.end(),
                     [](const Ev& a, const Ev& b) { return a.sample < b.sample; });

    // 5. Load the instrument headless (same create_instrument path as realtime).
    InstrumentEngineManager mgr;
    if (!mgr.assign(0, type, pluginPath, sampleRate, chunk)) {
        rc = 2;  // load failure
        fail("instrument load FAILED type=" + std::to_string((int)type) + " path=" + pluginPath);
        return rc;
    }
    std::cout << "[RenderJob] instrument loaded type=" << (int)type
              << " path=" << pluginPath << " sr=" << sampleRate
              << " samples=" << totalNeeded << " bpm=" << bpm << std::endl;

    if (!preset.empty()) {
        if (type != InstrumentType::VST3) {
            std::cerr << "[RenderJob] preset ignored for non-VST3 type " << (int)type
                      << " (SF2/SFZ use soundfont_bank/soundfont_program)" << std::endl;
#ifdef HAVE_VST3SDK
        } else if (!applyVst3Preset(mgr.get(0), preset)) {
            fail("preset import FAILED for " + pluginPath);
            return rc;  // rc stays 1: job/argument error
        } else {
            std::cout << "[RenderJob] preset imported (VST3 .vstpreset) type=" << (int)type << std::endl;
        }
#else
        } else {
            std::cerr << "[RenderJob] preset ignored: built without VST3 SDK" << std::endl;
        }
#endif
    }

    // 6. Offline render loop — same dispatch/render split as the realtime
    // loop: events whose sample time has passed are dispatched first, then
    // each upcoming event splits the chunk so it lands at sample offset 0 of
    // the next rendered sub-block.
    wav.open(outPath, std::ios::binary);
    if (!wav) { fail("cannot open output: " + outPath); return rc; }
    writeWavHeader(wav, sampleRate);
    std::vector<float> L(chunk), R(chunk);
    uint64_t dataBytes = 0;
    uint64_t pos = 0;
    size_t ei = 0;
    auto dispatch = [&](const Ev& e) {
        switch (e.kind) {
            case 0: mgr.noteOn(0, e.a, e.b / 127.0f); break;
            case 1: mgr.noteOff(0, e.a); break;
            case 2: mgr.controlChange(0, e.a, e.b); break;
            case 3: mgr.programChange(0, e.a); break;
            default: break;
        }
    };
    auto render = [&](uint64_t from, uint64_t to) {
        const uint32_t n = (uint32_t)(to - from);
        mgr.renderAll(L.data(), R.data(), n);
        writeFrames(wav, L.data(), R.data(), n);
        dataBytes += (uint64_t)n * 4;
    };
    while (pos < totalNeeded) {
        const uint64_t chunkEnd = std::min(pos + chunk, (uint64_t)totalNeeded);
        while (ei < evs.size() && evs[ei].sample <= pos) { dispatch(evs[ei]); ++ei; }
        while (ei < evs.size() && evs[ei].sample < chunkEnd) {
            const uint64_t off = evs[ei].sample;
            if (off > pos) { render(pos, off); pos = off; }
            dispatch(evs[ei]);
            ++ei;
        }
        if (pos < chunkEnd) { render(pos, chunkEnd); pos = chunkEnd; }
    }
    finishWav(wav, dataBytes);
    wav.close();

    if (mgr.isCrashed(0)) {
        rc = 3;
        fail("plugin crashed inside processAudioBlock — clip invalid, muted channel");
        return rc;
    }
    std::cout << "[RenderJob] wrote " << outPath << " (" << totalNeeded
              << " samples, " << (dataBytes / 4) << " frames)" << std::endl;
    rc = 0;
    return rc;
}