voice-to-notes/python/build_sidecar.py

#!/usr/bin/env python3
"""Build the Voice to Notes sidecar as a standalone binary using PyInstaller.

Usage:
    python build_sidecar.py [--cpu-only]

Produces a directory `dist/voice-to-notes-sidecar/` containing the frozen
sidecar binary and all dependencies. The main binary is renamed to include
the Tauri target triple for externalBin resolution.
"""

from __future__ import annotations

import argparse
import os
import platform
import shutil
import stat
import subprocess
import sys
import urllib.request
import zipfile
from pathlib import Path

SCRIPT_DIR = Path(__file__).resolve().parent
DIST_DIR = SCRIPT_DIR / "dist"
BUILD_DIR = SCRIPT_DIR / "build"
SPEC_FILE = SCRIPT_DIR / "voice_to_notes.spec"

# Static ffmpeg download URLs (GPL-licensed builds)
FFMPEG_URLS: dict[str, str] = {
    "linux-x86_64": "https://johnvansickle.com/ffmpeg/releases/ffmpeg-release-amd64-static.tar.xz",
    "darwin-x86_64": "https://evermeet.cx/ffmpeg/getrelease/zip",
    "darwin-arm64": "https://evermeet.cx/ffmpeg/getrelease/zip",
    "win32-x86_64": "https://www.gyan.dev/ffmpeg/builds/ffmpeg-release-essentials.zip",
}


def get_target_triple() -> str:
    """Determine the Tauri-compatible target triple for the current platform."""
    machine = platform.machine().lower()
    system = platform.system().lower()

    arch_map = {
        "x86_64": "x86_64",
        "amd64": "x86_64",
        "aarch64": "aarch64",
        "arm64": "aarch64",
    }
    arch = arch_map.get(machine, machine)

    if system == "linux":
        return f"{arch}-unknown-linux-gnu"
    elif system == "darwin":
        return f"{arch}-apple-darwin"
    elif system == "windows":
        return f"{arch}-pc-windows-msvc"
    else:
        return f"{arch}-unknown-{system}"


def _has_uv() -> bool:
    """Check if uv is available."""
    try:
        subprocess.run(["uv", "--version"], capture_output=True, check=True)
        return True
    except (FileNotFoundError, subprocess.CalledProcessError):
        return False


def create_venv_and_install(cpu_only: bool) -> Path:
    """Create a fresh venv and install dependencies.

    Uses uv if available (much faster), falls back to standard venv + pip.
    """
    venv_dir = BUILD_DIR / "sidecar-venv"
    if venv_dir.exists():
        shutil.rmtree(venv_dir)

    use_uv = _has_uv()

    if use_uv:
        print(f"[build] Creating venv with uv at {venv_dir}")
        subprocess.run(
            ["uv", "venv", "--python", f"{sys.version_info.major}.{sys.version_info.minor}",
             str(venv_dir)],
            check=True,
        )
    else:
        print(f"[build] Creating venv at {venv_dir}")
        subprocess.run([sys.executable, "-m", "venv", str(venv_dir)], check=True)

    # Determine python path inside venv
    if sys.platform == "win32":
        python = str(venv_dir / "Scripts" / "python.exe")
    else:
        python = str(venv_dir / "bin" / "python")

    def pip_install(*args: str) -> None:
        """Install packages. Pass package names and flags only, not 'install'."""
        if use_uv:
            # Use --python with the venv directory (not the python binary) for uv
            subprocess.run(
                ["uv", "pip", "install", "--python", str(venv_dir), *args],
                check=True,
            )
        else:
            subprocess.run([python, "-m", "pip", "install", *args], check=True)

    if not use_uv:
        # Upgrade pip (uv doesn't need this)
        pip_install("--upgrade", "pip", "setuptools", "wheel")

    # Install torch (CPU-only to avoid bundling ~2GB of CUDA libs)
    if cpu_only:
        print("[build] Installing PyTorch (CPU-only)")
        pip_install(
            "torch", "torchaudio",
            "--index-url", "https://download.pytorch.org/whl/cpu",
        )
    else:
        print("[build] Installing PyTorch (default, may include CUDA)")
        pip_install("torch", "torchaudio")

    # Install project and dev deps (includes pyinstaller)
    print("[build] Installing project dependencies")
    pip_install("-e", f"{SCRIPT_DIR}[dev]")

    return Path(python)


def run_pyinstaller(python: Path) -> Path:
    """Run PyInstaller using the spec file."""
    print("[build] Running PyInstaller")
    subprocess.run(
        [str(python), "-m", "PyInstaller", "--clean", "--noconfirm", str(SPEC_FILE)],
        cwd=str(SCRIPT_DIR),
        check=True,
    )
    output_dir = DIST_DIR / "voice-to-notes-sidecar"
    if not output_dir.exists():
        raise RuntimeError(f"PyInstaller output not found at {output_dir}")
    return output_dir


def download_ffmpeg(output_dir: Path) -> None:
    """Download a static ffmpeg/ffprobe binary for the current platform."""
    system = sys.platform
    machine = platform.machine().lower()
    if machine in ("amd64", "x86_64"):
        machine = "x86_64"
    elif machine in ("aarch64", "arm64"):
        machine = "arm64"

    key = f"{system}-{machine}"
    if system == "win32":
        key = f"win32-{machine}"
    elif system == "linux":
        key = f"linux-{machine}"

    url = FFMPEG_URLS.get(key)
    if not url:
        print(f"[build] Warning: No ffmpeg download URL for platform {key}, skipping")
        return

    print(f"[build] Downloading ffmpeg for {key}")
    tmp_path = output_dir / "ffmpeg_download"
    try:
        urllib.request.urlretrieve(url, str(tmp_path))

        if url.endswith(".tar.xz"):
            # Linux static build
            import tarfile
            with tarfile.open(str(tmp_path), "r:xz") as tar:
                for member in tar.getmembers():
                    basename = os.path.basename(member.name)
                    if basename in ("ffmpeg", "ffprobe"):
                        member.name = basename
                        tar.extract(member, path=str(output_dir))
                        dest = output_dir / basename
                        dest.chmod(dest.stat().st_mode | stat.S_IEXEC)
        elif url.endswith(".zip"):
            with zipfile.ZipFile(str(tmp_path), "r") as zf:
                for name in zf.namelist():
                    basename = os.path.basename(name)
                    if basename in ("ffmpeg", "ffprobe", "ffmpeg.exe", "ffprobe.exe"):
                        data = zf.read(name)
                        dest = output_dir / basename
                        dest.write_bytes(data)
                        if sys.platform != "win32":
                            dest.chmod(dest.stat().st_mode | stat.S_IEXEC)
        print("[build] ffmpeg downloaded successfully")
    except Exception as e:
        print(f"[build] Warning: Failed to download ffmpeg: {e}")
    finally:
        if tmp_path.exists():
            tmp_path.unlink()


def rename_binary(output_dir: Path, target_triple: str) -> None:
    """Rename the main binary to include the target triple for Tauri."""
    if sys.platform == "win32":
        src = output_dir / "voice-to-notes-sidecar.exe"
        dst = output_dir / f"voice-to-notes-sidecar-{target_triple}.exe"
    else:
        src = output_dir / "voice-to-notes-sidecar"
        dst = output_dir / f"voice-to-notes-sidecar-{target_triple}"

    if src.exists():
        print(f"[build] Renaming {src.name} -> {dst.name}")
        src.rename(dst)
    else:
        print(f"[build] Warning: Expected binary not found at {src}")


def main() -> None:
    parser = argparse.ArgumentParser(description="Build the Voice to Notes sidecar binary")
    parser.add_argument(
        "--cpu-only",
        action="store_true",
        default=True,
        help="Install CPU-only PyTorch (default: True, avoids bundling CUDA)",
    )
    parser.add_argument(
        "--with-cuda",
        action="store_true",
        help="Install PyTorch with CUDA support",
    )
    args = parser.parse_args()
    cpu_only = not args.with_cuda

    target_triple = get_target_triple()
    print(f"[build] Target triple: {target_triple}")
    print(f"[build] CPU-only: {cpu_only}")

    python = create_venv_and_install(cpu_only)
    output_dir = run_pyinstaller(python)
    download_ffmpeg(output_dir)
    rename_binary(output_dir, target_triple)

    print(f"\n[build] Done! Sidecar built at: {output_dir}")
    print(f"[build] Copy contents to src-tauri/binaries/ for Tauri bundling")


if __name__ == "__main__":
    main()