Source code for boltz_data.ccd._from_path

from collections.abc import Mapping
from pathlib import Path

from boltz_data import fs
from boltz_data.cif import read_cif_from_file, read_single_cif_from_file

from ._compressed_dictionary import CompressedChemicalComponentDictionary
from ._from_mmcif import read_chemical_component_dictionary_from_mmcif
from ._models import ChemicalComponent




def chemical_component_from_path(path: str | Path, /) -> ChemicalComponent:
    """
    Read a single chemical component from a CIF file.

    Args:
        path: Path to the CIF file containing exactly one chemical component.

    Returns:
        The chemical component.

    Raises:
        ValueError: If the file does not contain exactly one chemical component.

    """
    cif = read_single_cif_from_file(path)
    ccd = read_chemical_component_dictionary_from_mmcif(cif)
    if len(ccd) != 1:
        msg = f"Expected exactly one chemical component in file {path}, found {len(ccd)}"
        raise ValueError(msg)
    return next(iter(ccd.values()))





def chemical_component_dictionary_from_path(path: str | Path, /) -> Mapping[str, ChemicalComponent]:
    """
    Read a chemical component dictionary from a file.

    Supports both compressed pickle formats (.pkl.gz, .pkl) and CIF formats (.cif.gz, .cif).

    Args:
        path: Path to the file containing the chemical component dictionary.

    Returns:
        A mapping from component IDs to ChemicalComponent objects.

    Raises:
        ValueError: If the file format is not supported.

    """
    match fs.get_extension(path, ignore_compression=True):
        case ".pkl":
            return CompressedChemicalComponentDictionary.from_file(path)
        case ".cif":
            return read_chemical_component_dictionary_from_mmcif(read_cif_from_file(path))
        case _:
            msg = f"Cannot open CCD from path {path}"
            raise ValueError(msg)