"""Create a portable source ZIP without environments, builds, or local credentials."""

import argparse
from datetime import datetime
import hashlib
import os
from pathlib import Path
import zipfile


EXCLUDED_DIRS = {
    ".git",
    ".venv",
    "venv",
    "env",
    "node_modules",
    "__pycache__",
    "__pypackages__",
    ".angular",
    ".gradle",
    ".pytest_cache",
    ".ruff_cache",
    ".mypy_cache",
    ".cache",
    ".tox",
    ".nox",
    ".hypothesis",
    ".eggs",
    ".idea",
    ".vscode",
    ".vs",
    ".codex",
    ".claude",
    ".gemini",
    ".cursor",
    ".ipynb_checkpoints",
    "build",
    "dist",
    "out",
    "coverage",
    "htmlcov",
    "artifacts",
    "traces",
    "scratch",
    "outputs",
    "trace_output",
}
EXCLUDED_SUFFIXES = {
    ".pyc",
    ".pyo",
    ".pyd",
    ".so",
    ".dll",
    ".exe",
    ".o",
    ".obj",
    ".a",
    ".lib",
    ".class",
    ".jar",
    ".apk",
    ".aab",
    ".wasm",
    ".map",
    ".tsbuildinfo",
    ".egg",
    ".whl",
    ".zip",
    ".7z",
    ".tar",
    ".gz",
    ".log",
    ".db",
    ".sqlite",
    ".sqlite3",
    ".pem",
    ".key",
    ".keystore",
    ".p12",
    ".pfx",
    ".swp",
    ".swo",
}


def excluded(path: Path) -> bool:
    parts = tuple(part.lower() for part in path.parts)
    name = parts[-1]
    if any(part in EXCLUDED_DIRS or part.endswith(".egg-info") for part in parts):
        return True
    # This tracked directory also contains generated Angular bundles.
    if parts[:3] == ("artemis", "resources", "showcase_ui"):
        return True
    if (name == ".env" or name.startswith(".env.")) and name != ".env.example":
        return True
    if name.startswith((".artemis_", ".jetski_", ".coverage")):
        return True
    if name in {".ds_store", "thumbs.db", ".ipc_port", ".ls_address", ".npmrc", ".pypirc"}:
        return True
    return path.suffix.lower() in EXCLUDED_SUFFIXES or name.endswith((".db-wal", ".db-shm", "~"))


def source_files(root: Path):
    for directory, dirs, files in os.walk(root, followlinks=False):
        current = Path(directory)
        dirs[:] = sorted(
            name
            for name in dirs
            if not (current / name).is_symlink()
            and not excluded((current / name).relative_to(root))
        )
        for name in sorted(files):
            path = current / name
            if not path.is_symlink() and not excluded(path.relative_to(root)):
                yield path


def package_source(root: Path, output: Path) -> tuple[int, str]:
    root = root.resolve()
    output = output.resolve()
    output.parent.mkdir(parents=True, exist_ok=True)
    temporary = output.with_suffix(".zip.tmp")
    files = [p for p in source_files(root) if p.resolve() not in {output, temporary}]
    try:
        with zipfile.ZipFile(temporary, "w", zipfile.ZIP_DEFLATED, compresslevel=6) as archive:
            for path in files:
                archive.write(path, Path("artemis") / path.relative_to(root))
        with zipfile.ZipFile(temporary) as archive:
            bad_file = archive.testzip()
            if bad_file:
                raise RuntimeError(f"ZIP integrity check failed: {bad_file}")
            if any(excluded(Path(name).relative_to("artemis")) for name in archive.namelist()):
                raise RuntimeError("An excluded file was found in the source archive")
        temporary.replace(output)
    finally:
        temporary.unlink(missing_ok=True)
    with output.open("rb") as stream:
        digest = hashlib.file_digest(stream, "sha256").hexdigest()
    return len(files), digest


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--root", type=Path, default=Path(__file__).resolve().parents[1])
    parser.add_argument("--output", type=Path)
    args = parser.parse_args()
    output = (
        args.output
        or args.root / "artifacts" / f"artemis-source-{datetime.now():%Y%m%d-%H%M%S}.zip"
    )
    count, digest = package_source(args.root, output)
    print(f"Archive: {output.resolve()}")
    print(f"Files: {count}; size: {output.stat().st_size / (1024 * 1024):.2f} MiB")
    print(f"SHA256: {digest}")