mandos.entries.searcher.SearcherUtils.dl()

Complexity

Conditions

8

Size

Total Lines	54
Code Lines	40

Duplication

Lines	0
Ratio	0 %

Importance

Changes

0

"""
    @classmethod
    def dl(

Either all return statements in a function should return an expression, or none of them should.

Missing function or method docstring

Method name "dl" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,|_[^\\WA-Z]*|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern)

        cls,

Wrong hanging indentation before block (add 4 spaces).

        inchikeys: Sequence[str],

Wrong hanging indentation before block (add 4 spaces).

        pubchem: bool = True,

Wrong hanging indentation before block (add 4 spaces).

        chembl: bool = True,

Wrong hanging indentation before block (add 4 spaces).

        hmdb: bool = True,

Wrong hanging indentation before block (add 4 spaces).

The argument hmdb seems to be unused.

    ) -> IdMatchFrame:
        # we actually cache the results, even though the underlying APIs cache
        # the reasons for this are a little obscure --
        # when running a Searcher, we want to run before the FIRST search
        # for the typer commands to be replicas of the ``Entry.run`` methods, Searcher fetches before running a search

This line is too long as per the coding-style (118/100).

        # but if we have multiple searches (as in ``mandos search --config``), we only want that at the beginning

This line is too long as per the coding-style (113/100).

        # the alternative was having ``mandos search`` dynamically subclass each ``Entry`` -- which was really hard

This line is too long as per the coding-style (115/100).

        # this is much cleaner, even though it's redundant
        # if the cached results under /pubchem and /chembl are deleted, we unfortunately won't cache the results

This line is too long as per the coding-style (112/100).

        # when running this command
        # to fix that, we need to delete the cached /match dataframes
        # now that I'm writing this down, I realize this is pretty bad
        # TODO

TODO and FIXME comments should generally be avoided.

        # noinspection PyPep8Naming
        Chembl, Pubchem = Apis.Chembl, Apis.Pubchem

Variable name "Chembl" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,|_[^\\WA-Z]*|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern)

Variable name "Pubchem" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,|_[^\\WA-Z]*|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern)

        logger.notice(f"Using {Chembl}, {Pubchem}")
        key = hash(",".join(inchikeys))
        cached_path = (MANDOS_SETTINGS.match_cache_path / str(key)).with_suffix(".feather")
        if cached_path.exists():
            logger.info(f"Found ID matching results at {cached_path}")
            return IdMatchFrame.read_feather(cached_path)
        found_chembl: Dict[str, str] = {}
        found_pubchem: Dict[str, str] = {}
        if pubchem:
            for inchikey in inchikeys:
                try:
                    cid = Pubchem.fetch_data(inchikey).cid
                    found_pubchem[inchikey] = str(cid)
                    logger.info(f"Found:      PubChem {inchikey} ({cid})")
                except CompoundNotFoundError:
                    logger.info(f"NOT FOUND: PubChem {inchikey}")
                    logger.debug(f"Did not find PubChem {inchikey}", exc_info=True)
        if chembl:
            for inchikey in inchikeys:
                try:
                    chid = ChemblUtils(Chembl).get_compound(inchikey).chid
                    found_chembl[inchikey] = chid
                    logger.info(f"Found:      ChEMBL {inchikey} ({chid})")
                except CompoundNotFoundError:
                    logger.info(f"NOT FOUND: ChEMBL {inchikey}")
                    logger.debug(f"Did not find ChEMBL {inchikey}", exc_info=True)
        df = pd.DataFrame([pd.Series(dict(inchikey=c)) for c in inchikeys])

Variable name "df" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,|_[^\\WA-Z]*|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern)

        df["chembl_id"] = df["inchikey"].map(found_chembl.get)
        df["pubchem_id"] = df["inchikey"].map(found_pubchem.get)
        df = IdMatchFrame(df)

Variable name "df" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,|_[^\\WA-Z]*|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern)

        df.to_feather(cached_path)
        logger.info(f"Wrote {cached_path}")