mandos.entries.common_args.CommonArgs.parse_taxon_id_or_name() - Code Metrics - Inspection of "build(deps): bump pyarrow from 3.0.0 to 4.0.1" - dmyersturnbull/mandos - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — dependabot/pip/pyarrow-4.0.1 ( ca09ce...b2836e )

unknown

created 2021-07-05 18:49 UTC

CommonArgs.parse_taxon_id_or_name() A

↳ Parent: mandos.entries.common_args

Complexity

Conditions

Size

Total Lines	7
Code Lines	7

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	4
eloc	7
nop	1
dl	0
loc	7
rs	10
c	0
b	0
f	0

"""
Common argument processing and arguments for Typer.
"""
import enum
import os
from inspect import cleandoc
from pathlib import Path
from typing import Any, Callable, Iterable, Mapping, Optional, Sequence, TypeVar, Union

import typer


from mandos.model import CleverEnum

from mandos.model.settings import MANDOS_SETTINGS

T = TypeVar("T", covariant=True)



class _Args:
    @staticmethod
    def _arg(doc: str, *names, default: Optional[T] = None, req: bool = False, **kwargs):
        kwargs = dict(
            help=cleandoc(doc),
            **kwargs,
            allow_dash=True,
        )
        return typer.Argument(default, **kwargs) if req else typer.Option(default, *names, **kwargs)

    @staticmethod
    def _path(
        doc: str, *names, default: Optional[str], f: bool, d: bool, out: bool, req: bool, **kwargs

    ):
        # if it's None, we're going to have a special default set afterward, so we'll explain it in the doc

        if out and default is None:
            kwargs = dict(show_default=True, **kwargs)
        kwargs = {
            **dict(
                exists=not out,
                dir_okay=d,
                file_okay=f,
                readable=out,
                writable=not out,
            ),
            **kwargs,
        }
        return _Args._arg(doc, *names, default=default, req=req, **kwargs)


class Arg(_Args):

    @staticmethod
    def out_file(doc: str, *names, default: Optional[str] = None, **kwargs):

        return _Args._path(
            doc, *names, default=default, f=True, d=False, out=True, req=True, **kwargs
        )

    @staticmethod
    def out_dir(doc: str, *names, default: Optional[str] = None, **kwargs):

        return _Args._path(
            doc, *names, default=default, f=True, d=True, out=True, req=True, **kwargs
        )

    @staticmethod
    def out_path(doc: str, *names, default: Optional[str] = None, **kwargs):

        return _Args._path(
            doc, *names, default=default, f=True, d=True, out=False, req=True, **kwargs
        )

    @staticmethod
    def in_file(doc: str, *names, default: Optional[str] = None, **kwargs):

        return _Args._path(
            doc, *names, default=default, f=True, d=False, out=False, req=True, **kwargs
        )

    @staticmethod
    def in_dir(doc: str, *names, default: Optional[str] = None, **kwargs):

        return _Args._path(
            doc, *names, default=default, f=False, d=True, out=False, req=True, **kwargs
        )

    @staticmethod
    def in_path(doc: str, *names, default: Optional[str] = None, **kwargs):

        return _Args._path(
            doc, *names, default=default, f=True, d=True, out=False, req=True, **kwargs
        )

    @staticmethod
    def x(doc: str, *names, default: Optional[T] = None, **kwargs):

        return _Args._arg(doc, *names, default=default, req=True, **kwargs)


class Opt(_Args):

    @staticmethod
    def out_file(doc: str, *names, default: Optional[str] = None, **kwargs):

        return _Args._path(
            doc, *names, default=default, f=True, d=False, out=True, req=False, **kwargs
        )

    @staticmethod
    def out_dir(doc: str, *names, default: Optional[str] = None, **kwargs):

        return _Args._path(
            doc, *names, default=default, f=True, d=True, out=True, req=False, **kwargs
        )

    @staticmethod
    def out_path(doc: str, *names, default: Optional[str] = None, **kwargs):

        return _Args._path(
            doc,
            *names,
            default=default,
            f=True,
            d=True,
            out=False,
            req=False,
            exists=False,
            **kwargs,
        )

    @staticmethod
    def in_file(doc: str, *names, default: Optional[str] = None, **kwargs):

        return _Args._path(
            doc, *names, default=default, f=True, d=False, out=False, req=False, **kwargs
        )

    @staticmethod
    def in_dir(doc: str, *names, default: Optional[str] = None, **kwargs):

        return _Args._path(
            doc, *names, default=default, f=False, d=True, out=False, req=False, **kwargs
        )

    @staticmethod
    def in_path(doc: str, *names, default: Optional[str] = None, **kwargs):

        return _Args._path(
            doc,
            *names,
            default=default,
            f=True,
            d=True,
            out=False,
            req=False,
            exists=False,
            **kwargs,
        )

    @staticmethod
    def val(doc: str, *names, default: Optional[T] = None, **kwargs):

        return _Args._arg(doc, *names, default=default, req=False, **kwargs)

    @staticmethod
    def flag(doc: str, *names, **kwargs):

        return _Args._arg(doc, *names, default=False, req=False, **kwargs)


def _strip(s: str) -> str:

    return s.strip().strip("'").strip('"').strip()


class CommonArgs:

    @staticmethod
    def definition_bullets(dct: Mapping[Any, Any], colon: str = ": ", indent: int = 12) -> str:

        joiner = os.linesep * 2 + " " * indent
        jesus = [f" - {k}{colon}{v}" for k, v in dct.items()]
        return joiner.join(jesus)

    @staticmethod
    def definition_list(dct: Mapping[Any, Any], colon: str = ": ", sep: str = "; ") -> str:

        jesus = [f"{k}{colon}{v}" for k, v in dct.items()]
        return sep.join(jesus)

    @staticmethod
    def list(

        lst: Iterable[Any], attr: Union[None, str, Callable[[Any], Any]] = None, sep: str = "; "

    ) -> str:
        x = []

        for v in lst:

            if attr is None and isinstance(v, enum.Enum):
                x += [v.name]

            elif attr is None:
                x += [str(v)]

            elif isinstance(attr, str):
                x += [str(getattr(v, attr))]

            else:
                x += [str(attr(v))]

        return sep.join(x)

    @staticmethod
    def parse_taxon_id_or_name(taxon: Union[int, str]) -> Union[int, str]:

        if isinstance(taxon, str):

            return taxon
        elif isinstance(taxon, str) and taxon.isdigit():
            return int(taxon)
        raise ValueError(f"Taxon {taxon} must be an ID or name")

    @staticmethod
    def parse_taxon_id(taxon: Union[int, str]) -> int:

        try:
            return int(taxon)
        except ValueError:
            raise ValueError(f"Taxon {taxon} must be an exact ID") from None

    @staticmethod
    def parse_taxa(taxa: str) -> Sequence[Union[int, str]]:

        taxa = [_strip(t) for t in taxa.split(",")]
        return [CommonArgs.parse_taxon_id_or_name(t) for t in taxa]

    output_formats = r"""
        The filename extension must be one of: .feather; .snappy/.parquet;
        .csv, .tsv, .tab, .json (with optional .gz/.bz2/.zip/.xz);
        Feather (.feather) and Parquet (.snappy) are recommended.
        If only a filename suffix is provided, only sets the format and filename suffix.
        If no extension is provided, interprets that path as a directory and uses the default format (Feather).

        Will fail if the file exists, unless `--replace` is passed.
    """

    input_formats = r"""
        The filename extension must be one of: .feather; .snappy/.parquet;
        .csv, .tsv, .tab (with optional .gz/.bz2/.zip/.xz);
        Feather (.feather) and Parquet (.snappy) are recommended formats.
        (Some other formats, such as .json or .h5, may be permitted but are discouraged.)
    """

    file_input = Arg.in_file("The path to a file output by `:concat` or `:search`.", "input")

    compounds = Arg.in_file(
        """
        The path to the input file.
        One of:

          (A) *.txt, *.lines, or *.list (optionally with .gz/.zip/.xz/.bz2)), with one InChI Key per line;


          (B) A *.csv, *.tsv, *.tab file (or .gz/.zip/.xz/.bz2 variant) with a column called 'inchikey'; OR


          (C) An Arrow *.feather file or Parquet *.snappy file with a column called 'inchikey'
        """
    )

    input_dir = Arg.in_dir(
        rf"""
        The path to a directory containing files output from mandos search.

        {input_formats}
        Note that *all* matching files will be included.
        Provide ``--exclude`` if needed.
        """
    )

    to_single = Opt.out_file(
        rf"""
        The path to the output file.

        {output_formats}

        [default: <input-path>/{...}.{MANDOS_SETTINGS.default_table_suffix}]
        """,
        "--to",
    )

    out_dir = Opt.val(
        rf"""
        Choose the output directory.

        If ``--to`` is set to a relative path, this value is prepended to ``--to``.

        Examples:

        - ``--dir output --to abc.snappy`` yields ``output/abc.snappy`` (to sets filename+format)
        - ``--dir output --to .snappy`` yields ``output/<key>.snappy`` (to sets format)
        - ``--dir output --to my_dir`` yields ``output/my_dir`` (to sets dir)
        - ``--dir output --to /my/absolute/path`` will error
        - ``--dir output --to /my/absolute/path/abc.snappy`` will error

        {output_formats}

        [default: inferred from --to]
        """,
    )

    input_matrix: Path = Arg.in_file(
        rf"""
        The path to a similarity matrix file to write to.

        {input_formats}
        .txt/.txt.gz/etc. is assumed to be whitespace-delimited.
        TCompounds can be referenced by InChI Key or compound ID (matching what you provided for the search).

        The set of compounds here must exactly match the set of compounds in the input files.
        For Excel and text formats, the first row and the first column (header and index) indicate the compounds.


        Values must be floating-point.
        """
    )
    replace: bool = typer.Option(
        False, help="Replace output file(s) if they exist. See also: --skip"
    )

    taxa = Opt.val(
        r"""
        The IDs or names of UniProt taxa, comma-separated.
        Taxon names and common names can be used for vertebrate species (where available).

        This can have a significant effect on searches. See the docs for more info.

        [default: 7742] (Euteleostomi)
        """,
        "--taxa",
        "7742",
        show_default=False,
    )

    seed = Opt.val(r"A random seed (integer).", "--seed", default=0)

    n_samples = Opt.val(
        "Number of bootstrap samples (positive integer).",
        "--samples",
        min=1,
        default=2000,
    )

    exclude = Opt.val("A glob pattern matching input filenames to ignore.")

    verbose: bool = Opt.flag(
        r"Configure logger to output INFO (use ``--quiet`` for less info)",
        "-v",
        "--verbose",
    )

    quiet: bool = Opt.flag(
        r"Configure logger to output only ERROR (use ``--verbose`` for more info)",
        "-q",
        "--quiet",
    )

    in_cache: bool = Opt.flag(
        r"Do not download any data and fail if needed data is not cached.",
        hidden=True,
    )

    as_of: Optional[str] = Opt.val(
        f"""
        Restrict to data that was cached as of some date and time.
        This option can be useful for reproducibility.

        Note that this should imply that underlying data sources (such as of deposition or publication)

        are restricted by this datetime, but that is not checked.

        Examples:

            - --as-of 2021-10-11T14:12:13Z
            - --as-of 2021-10-11T14:12:13+14:00
            - --as-of 2021-10-11T14:12:13.496Z
            - --as-of "2021-10-11 14:12:13,496,915+14:00"
            - --as-of "2021-10-11 14:12:13-8:00 [America/Los_Angeles]"

        This is a subset of ISO 8601, represented as ``YYYY-mm-dd('T'|' '):hh:MM:ss(i)Z``.
        Precision must be nanosecond or less, and ``,`` and ``.`` are equivalent as a thousands separator.

        You can provide an IANA zone name in square brackets for context, but the offset is still required.

        """

    )

    log_path = Opt.out_path(
        r"""
        Also log to a file.
        The suffix can be .log, .log.gz, .log.zip, or .json, .json.gz, or .json.gz.
        You can prefix the path with :LEVEL: to control the level. For example, ``:INFO:out.log``
        """,
        "--log",
        show_default=True,
    )

    no_setup: bool = Opt.flag(
        r"Skip setup, such as configuring logging.",
        "--no-setup",
        hidden=True,
    )


cli = typer.Typer()


@cli.command()
def run(

    path: Path = CommonArgs.input_dir,

    x=CommonArgs.log_path,

):
    pass


if __name__ == "__main__":
    typer.run(run)


__all__ = ["CommonArgs", "Arg", "Opt"]


1			"""
2			Common argument processing and arguments for Typer.
3			"""
4			import enum
5			import os
6			from inspect import cleandoc
7			from pathlib import Path
8			from typing import Any, Callable, Iterable, Mapping, Optional, Sequence, TypeVar, Union
9
10			import typer
			0 ignored issues – show introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Unable to import 'typer' Loading history...
11
12			from mandos.model import CleverEnum
			0 ignored issues – show Unused Code introduced 2021-07-05 03:20 UTC by Report Bug Copy Issue Report Unused CleverEnum imported from mandos.model Loading history...
13			from mandos.model.settings import MANDOS_SETTINGS
14
15			T = TypeVar("T", covariant=True)
			0 ignored issues – show Coding Style Naming introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Class name "T" doesn't conform to PascalCase naming style ('[^\\W\\da-z][^\\W_]+$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
16
17
18			class _Args:
19			@staticmethod
20			def _arg(doc: str, names, default: Optional[T] = None, req: bool = False, *kwargs):
21			kwargs = dict(
22			help=cleandoc(doc),
23			**kwargs,
24			allow_dash=True,
25			)
26			return typer.Argument(default, *kwargs) if req else typer.Option(default, names, **kwargs)
27
28			@staticmethod
29			def _path(
30			doc: str, names, default: Optional[str], f: bool, d: bool, out: bool, req: bool, *kwargs
			0 ignored issues – show Coding Style Naming introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Variable name "d" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history... Coding Style Naming introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Variable name "f" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history... Coding Style introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
31			):
32			# if it's None, we're going to have a special default set afterward, so we'll explain it in the doc
			0 ignored issues – show Coding Style introduced 2021-06-30 04:51 UTC by Report Bug Copy Issue Report This line is too long as per the coding-style (107/100). This check looks for lines that are too long. You can specify the maximum line length. Loading history...
33			if out and default is None:
34			kwargs = dict(show_default=True, **kwargs)
35			kwargs = {

dmyersturnbull / mandos

Push — dependabot/pip/pyarrow-4.0.1 ( ca09ce...b2836e )

CommonArgs.parse_taxon_id_or_name() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like