file_utils.py

"""File path helpers, ZIP operations, and CSV export."""

import re
import tempfile
import zipfile
from pathlib import Path

import pandas as pd


def _get_file_path(f):
    if isinstance(f, str):
        return Path(f)
    if hasattr(f, "path"):
        return Path(f.path)
    if isinstance(f, dict) and "path" in f:
        return Path(f["path"])
    return Path(str(f))


def _sanitize_download_stem(stem: str) -> str:
    sanitized = re.sub(r"[^A-Za-z0-9._-]+", "_", stem).strip("._-")
    return sanitized or "caliby"


def _make_named_download_path(stem: str, suffix: str) -> str:
    download_dir = Path(tempfile.mkdtemp(prefix="caliby_download_"))
    return str(download_dir / f"{_sanitize_download_stem(stem)}{suffix}")


def _get_results_stem(df: pd.DataFrame) -> str:
    if "Sample" not in df.columns:
        return "caliby"
    sample_name = str(df.iloc[0]["Sample"])
    return _sanitize_download_stem(re.sub(r"_sample\d+$", "", sample_name))


def _copy_uploaded_files(pdb_files: list, tmpdir: Path) -> list[str]:
    pdb_paths = []
    for f in pdb_files:
        src = _get_file_path(f)
        path = tmpdir / src.name
        path.write_bytes(src.read_bytes())
        pdb_paths.append(str(path))
    return pdb_paths


def _write_zip_from_paths(paths: list[str], download_stem: str, suffix: str) -> str | None:
    if not paths:
        return None

    zip_path = _make_named_download_path(download_stem, suffix)
    with zipfile.ZipFile(zip_path, "w", zipfile.ZIP_DEFLATED) as zf:
        for path in paths:
            zf.write(path, Path(path).name)
    return zip_path


def _write_zip_from_dir(directory: Path, download_stem: str, suffix: str) -> str:
    zip_path = _make_named_download_path(download_stem, suffix)
    with zipfile.ZipFile(zip_path, "w", zipfile.ZIP_DEFLATED) as zf:
        for path in directory.rglob("*"):
            if path.is_file():
                zf.write(path, path.relative_to(directory))
    return zip_path


def _df_to_csv(df: pd.DataFrame | None) -> str | None:
    if df is None or df.empty:
        return None
    path = _make_named_download_path(_get_results_stem(df), "_results.csv")
    df.to_csv(path, index=False)
    return path