from __future__ import annotations
import warnings
from collections import defaultdict
from emmet.core.molecules_jcesr import MoleculesDoc
from pymatgen.core.periodic_table import Element
from mp_api.client.core import BaseRester
from mp_api.client.core.exceptions import MPRestWarning
from mp_api.client.core.utils import validate_ids
[docs]
class JcesrMoleculesRester(BaseRester):
suffix = "molecules/jcesr"
document_model = MoleculesDoc # type: ignore
primary_key = "task_id"
[docs]
def __init__(self, **kwargs):
"""Throw deprecation warning when JCESR client is initialized."""
warnings.warn(
"NOTE: You are accessing the unmaintained legacy molecules data, "
"please use MPRester.molecules.summary.",
category=MPRestWarning,
stacklevel=2,
)
super().__init__(**kwargs)
[docs]
def search(
self,
task_ids: str | list[str] | None = None,
charge: tuple[float, float] | None = None,
elements: list[Element] | None = None,
EA: tuple[float, float] | None = None,
IE: tuple[float, float] | None = None,
nelements: tuple[float, float] | None = None,
pointgroup: str | None = None,
smiles: str | None = None,
num_chunks: int | None = None,
chunk_size: int = 1000,
all_fields: bool = True,
fields: list[str] | None = None,
_page: int | None = None,
_sort_fields: str | None = None,
):
"""Query legacy molecule docs using a variety of search criteria.
JCESR = Joint Center for Energy Storage Research
Arguments:
task_ids (str, List[str]): A single molecule task ID string or list of strings.
(e.g., mol-45004, [mol-45004, mol-45228]).
charge (Tuple[float,float]): Minimum and maximum value of the charge in +e to consider.
elements (List[Element]): A list of elements.
film_orientation (List[Elements]): List of elements that are in the molecule.
EA (Tuple[float,float]): Minimum and maximum value of the electron affinity in eV to consider.
IE (Tuple[float,float]): Minimum and maximum value of the ionization energy in eV to consider.
nelements (Tuple[float,float]): Minimum and maximum number of elements in the molecule to consider.
pointgroup (str): Point group of the molecule in Schoenflies notation.
smiles (str): The simplified molecular input line-entry system (SMILES) representation of the molecule.
num_chunks (int): Maximum number of chunks of data to yield. None will yield all possible.
chunk_size (int): Number of data entries per chunk.
all_fields (bool): Whether to return all fields in the document. Defaults to True.
fields (List[str]): List of fields in MoleculesDoc to return data for.
Default is the material_id only if all_fields is False.
_page (int or None) : Page of the results to skip to.
_sort_fields (str or None) : Field to sort on. Including a leading "-" sign will reverse sort order.
Returns:
([MoleculesDoc]) List of molecule documents
"""
query_params: dict = defaultdict(dict)
if task_ids:
if isinstance(task_ids, str):
task_ids = [task_ids]
query_params.update({"task_ids": ",".join(validate_ids(task_ids))})
if elements:
query_params.update({"elements": ",".join([str(ele) for ele in elements])})
_locals = locals()
for k in ("pointgroup", "smiles", "_page", "_sort_fields"):
if (v := _locals.get(k)) is not None:
query_params[k] = v
for k in ("nelements", "EA", "IE", "charge"):
if (vals := _locals.get(k)) is not None:
query_params.update({f"{k}_min": vals[0], f"{k}_max": vals[1]})
query_params = {
entry: query_params[entry]
for entry in query_params
if query_params[entry] is not None
}
return super()._search(
num_chunks=num_chunks,
chunk_size=chunk_size,
all_fields=all_fields,
fields=fields,
**query_params,
)
