File template.py has 1001 lines of code (exceeds 250 allowed). Consider refactoring.

Open

# -*- coding: utf-8 -*-

"""The underlying data representation of an assay or shipping manifest template."""

import os

Function _convert_api_to_template has a Cognitive Complexity of 94 (exceeds 10 allowed). Consider refactoring.

Open

def _convert_api_to_template(name: str, schema: dict, assay_schema: dict):
    # import here to avoid circular dependence where prism imports Template
    from .prism.merger import InvalidMergeTargetException

    # so many different ways of writing it

• Read up
  Read up

File generate_docs.py has 702 lines of code (exceeds 250 allowed). Consider refactoring.

Open

#!/usr/bin/env python3
from collections import OrderedDict
from copy import deepcopy
import jinja2
import json

File pipelines.py has 685 lines of code (exceeds 250 allowed). Consider refactoring.

Open

"""Analysis pipeline configuration generators."""
from collections import defaultdict
from datetime import datetime
from io import BytesIO
import logging

Function _validate_worksheet has a Cognitive Complexity of 54 (exceeds 10 allowed). Consider refactoring.

Open

    def _validate_worksheet(self, worksheet_name: str, ws_schema: dict) -> List[str]:
        """Validate rows in a worksheet, returning a list of validation error messages."""
        self.visited_fields.clear()

        # If no worksheet is found, return only that error.

• Read up
  Read up

Function _first_in_context has a Cognitive Complexity of 53 (exceeds 10 allowed). Consider refactoring.

Open

def _first_in_context(path: list, context: dict):
    """
    For matching a file path to its nearest equivalent key in a schema context
    Recursive to try for more specific, more complex entries

• Read up
  Read up

Function parse_clinical has a Cognitive Complexity of 46 (exceeds 10 allowed). Consider refactoring.

Open

def parse_clinical(file: BinaryIO) -> dict:
    """
    Parses the given clinical file to extract a list of participant IDs.
    By convention the first column should be "cimac_part_id" for files containing
    clinical data keyed to a specific participant. All tabs in each XLSX need to be checked

• Read up
  Read up

File core.py has 403 lines of code (exceeds 250 allowed). Consider refactoring.

Open

"""Build metadata dictionaries from Excel files."""
import logging
import base64
import hmac
from typing import List, Tuple, Union

File template_writer.py has 383 lines of code (exceeds 250 allowed). Consider refactoring.

Open

# -*- coding: utf-8 -*-

"""Defines the `XlTemplateWriter` class for writing `Template`s to Excel templates."""

import logging

File json_validation.py has 380 lines of code (exceeds 250 allowed). Consider refactoring.

Open

# -*- encoding: utf-8 -*-

"""Tools for performing validations based on json schemas"""

import os

Function prismify has a Cognitive Complexity of 37 (exceeds 10 allowed). Consider refactoring.

Open

def prismify(
    xlsx: XlTemplateReader,
    template: Template,
    schema_root: str = SCHEMA_DIR,
    debug: bool = False,

• Read up
  Read up

Function _map_refs has a Cognitive Complexity of 34 (exceeds 10 allowed). Consider refactoring.

Open

def _map_refs(node: dict, on_refs: Callable[[str], dict]) -> dict:
    """
    Apply `on_refs` to all nodes with `$ref`, returning node with refs replaced
    with results of the function call.

• Read up
  Read up

Function _update_definition_from_merge_pointer has a Cognitive Complexity of 32 (exceeds 10 allowed). Consider refactoring.

Open

    def _update_definition_from_merge_pointer(
        self,
        context_pointer: str,
        definition: dict,
    ) -> dict:

• Read up
  Read up

File utils.py has 317 lines of code (exceeds 250 allowed). Consider refactoring.

Open

import os
import jsonschema
from typing import Any, Dict, Iterable, List, Set, Tuple

from cidc_schemas.constants import SCHEMA_DIR

Function parse_npx has a Cognitive Complexity of 29 (exceeds 10 allowed). Consider refactoring.

Open

def parse_npx(xlsx: BinaryIO) -> dict:
    """
    Parses the given NPX file from olink to extract a list of sample IDs.
    If the file is not valid NPX but still xlsx the function will
    return a dict containing an empty list. Sample IDs not conforming to the CIMAC ID

• Read up
  Read up

File migrations.py has 305 lines of code (exceeds 250 allowed). Consider refactoring.

Open

from copy import deepcopy
from typing import NamedTuple, Dict

from .prism.core import _ENCRYPTED_FIELD_LEN, _encrypt

Function upgrade has a Cognitive Complexity of 28 (exceeds 10 allowed). Consider refactoring.

Open

    def upgrade(cls, metadata: dict, *args, **kwargs) -> MigrationResult:
        # these are removal, so cannot downgrade later
        metadata.pop("collection_event_list", None)

        for partic in metadata.get("participants", []):

• Read up
  Read up

File unprism.py has 290 lines of code (exceeds 250 allowed). Consider refactoring.

Open

"""Tools from extracting information from trial metadata blobs."""
from io import StringIO, BytesIO
from typing import Callable, Dict, List, NamedTuple, Optional, Union

import pandas as pd

Function from_excel has a Cognitive Complexity of 25 (exceeds 10 allowed). Consider refactoring.

Open

    def from_excel(xlsx_path: Union[str, BinaryIO]):
        """
        Initialize an Excel template reader from an excel file.

        Arguments:

• Read up
  Read up

Function _pair_all_samples has a Cognitive Complexity of 25 (exceeds 10 allowed). Consider refactoring.

Open

    def _pair_all_samples(
        self, partic_map: Dict[str, Dict[str, Dict[str, str]]]
    ) -> List[_PairingEntry]:
        """
        (Semi)automated pairing of tumor and normal samples

• Read up
  Read up