File archiver.py has 605 lines of code (exceeds 250 allowed). Consider refactoring.

Open

import json
import logging
import sys

import polling as polling

File converter.py has 426 lines of code (exceeds 250 allowed). Consider refactoring.

Open

import logging
import re

from flatten_json import flatten

IngestAPI has 27 functions (exceeds 20 allowed). Consider refactoring.

Open

class IngestAPI:
    def __init__(self, url=None):
        self.logger = logging.getLogger(__name__)
        self.headers = {
            'Content-type': 'application/json',

USIAPI has 24 functions (exceeds 20 allowed). Consider refactoring.

Open

class USIAPI:
    def __init__(self, url=None):
        self.logger = logging.getLogger(__name__)
        self.url = url if url else config.USI_API_URL
        self.logger.info(f'Using {self.url}')

Function rename_attributes has a Cognitive Complexity of 15 (exceeds 5 allowed). Consider refactoring.

Open

    def rename_attributes(self, converted_data, hca_data):
        new_attributes = {}
        attributes = converted_data.get('attributes')

        for field, value in attributes.items():

• Read up
  Read up

Function _convert has a Cognitive Complexity of 15 (exceeds 5 allowed). Consider refactoring.

Open

    def _convert(self, assay_bundle: AssayBundle):
        aggregator = ArchiveEntityAggregator(assay_bundle, alias_prefix=self.alias_prefix)

        entities = []
        for archive_entity_type in ["project", "study", "sample", "sequencingExperiment", "sequencingRun"]:

• Read up
  Read up

Function _flatten has a Cognitive Complexity of 14 (exceeds 5 allowed). Consider refactoring.

Open

    def _flatten(self, hca_data):
        input_data = dict(hca_data)

        for key in self.exclude_data:
            if key in input_data:

• Read up
  Read up

Function _build_output has a Cognitive Complexity of 13 (exceeds 5 allowed). Consider refactoring.

Open

    def _build_output(self, extracted_data, flattened_hca_data, hca_data=None):
        # TODO BioStudies minimum length
        title_len = len(extracted_data["title"])
        MIN_LEN = 25
        DELIM = ' , '

• Read up
  Read up

Function get_conversion_summary has a Cognitive Complexity of 10 (exceeds 5 allowed). Consider refactoring.

Open

    def get_conversion_summary(self):
        summary = {}
        for entities_dict in self.entities_dict_type.values():
            for entity in entities_dict.values():
                if entity.conversion and not entity.errors:

• Read up
  Read up

Function _extract_attributes has a Cognitive Complexity of 9 (exceeds 5 allowed). Consider refactoring.

Open

    def _extract_attributes(self, flattened_hca_data):
        attributes = {}
        prefix = "content__"
        ontology_keyword = "__ontology"
        ontology_text_keyword = "__text"

• Read up
  Read up

Function notify_file_archiver has a Cognitive Complexity of 9 (exceeds 5 allowed). Consider refactoring.

Open

    def notify_file_archiver(self, archive_submission: ArchiveSubmission):

        messages = []
        # TODO a bit redundant with converter, refactor this
        for entity in archive_submission.converted_entities:

• Read up
  Read up

Function _build_output has a Cognitive Complexity of 8 (exceeds 5 allowed). Consider refactoring.

Open

    def _build_output(self, extracted_data, flattened_hca_data, hca_data=None):
        extracted_data["studyRef"] = {}
        extracted_data["sampleUses"] = []

        if not extracted_data.get("attributes"):

• Read up
  Read up

Function _extract_fields has a Cognitive Complexity of 8 (exceeds 5 allowed). Consider refactoring.

Open

    def _extract_fields(self, flattened_hca_data, hca_data):
        extracted_data = {}

        for key, new_key in self.field_mapping.items():
            if key in flattened_hca_data:

• Read up
  Read up

Function __init__ has 6 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, ingest_api, usi_api, ontology_api, exclude_types=None, alias_prefix=None):

Function _get_all has a Cognitive Complexity of 8 (exceeds 5 allowed). Consider refactoring.

Open

    def _get_all(self, url, entity_type):
        r = self.session.get(url, headers=self.headers)
        r.raise_for_status()
        if "_embedded" in r.json():
            for entity in r.json()["_embedded"][entity_type]:

• Read up
  Read up

Function _get_all has a Cognitive Complexity of 8 (exceeds 5 allowed). Consider refactoring.

Open

    def _get_all(self, url, entity_type):
        r = self.session.get(url, headers=self.get_headers())
        r.raise_for_status()
        if "_embedded" in r.json():
            for entity in r.json()["_embedded"][entity_type]:

• Read up
  Read up

Function get_converted_entities has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def get_converted_entities(self):
        for entities_dict in self.entities_dict_type.values():
            for entity in entities_dict.values():
                if entity.conversion and not entity.errors:
                    yield entity

• Read up
  Read up

Function get_all_validation_errors has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.

Open

    def get_all_validation_errors(self):
        get_validation_results_url = self.usi_submission['_links']['validationResults']['href']
        validation_results = self.usi_api.get_validation_results(get_validation_results_url)

        errors = []

• Read up
  Read up

Function validate_and_submit has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.

Open

    def validate_and_submit(self):
        if not self.usi_submission:
            return self

        print("Waiting for the submission to be validated in USI...")

• Read up
  Read up

Function expand_curie has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.

Open

    def expand_curie(self, term):
        term = quote(term)
        params = f'q={term}&exact=true&groupField=true&queryFields=obo_id'
        query_url = f'{self.url}/api/search?{params}'

• Read up
  Read up