Avoid deeply nested control flow statements.

Open

                        if is_json:
                            list_of_boxes.append((text[0], text[1], text[2],
                                                  text[3], norm_text))
                        else:
                            drawboxes_text += (norm_text + sep)

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

Open

    def _extract_acts(self, text, prediction):
        """Extract and join words predicted to be part of an act.

        Args:
            text (list): List of words in the text of a DODF.

• Read up
  Read up

Avoid deeply nested control flow statements.

Open

                        if offset_sum != -1:
                            offset_prop = offset + offset_sum
                            child_annotation = self._annotate(prop_type,
                                                                value, offset_prop)
                            root_passage.append(child_annotation)

Avoid deeply nested control flow statements.

Open

              if re.search(r'(?:ADITIVO)', titulo) is None:
                if re.search(regex_titulo_contrato, titulo) is not None:
                  if 'termo aditivo ao contrato' not in section_3[orgao][documento][ato]['texto'].lower():
                    atos_contrato_convenio['numero_dodf'].append(file['json']['nu_numero'])
                    atos_contrato_convenio['titulo'].append(titulo)

Avoid deeply nested control flow statements.

Open

                        if cand.label_ == 'PER':
                            break

Avoid deeply nested control flow statements.

Open

                        if section and (title not in content_dict[section].keys()):
                            content_dict[section].update(
                                {normalized_title: []})
                    else:

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

Open

def extract_multiple(files, act_type, backend, txt_out=False, txt_path="./results"):
    """Extract Act from Multiple DODF to a single DataFrame.

    Note:
        This function might save data to disc in text format,

• Read up
  Read up

Function __init__ has 5 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, file, backend, debug=False, extra_search=True, pipeline = None):

Function extract_multiple has 5 arguments (exceeds 4 allowed). Consider refactoring.

Open

def extract_multiple(files, act_type, backend, txt_out=False, txt_path="./results"):

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

Open

    def _standard_props(self):
        act = {}

        file = self._file_name.split('/')[-1] if self._file_name else None
        match = re.search(r'(\d+\-\d+\-\d+)',file) if file else None

• Read up
  Read up

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

Open

    def _find_prop_value(self, rule, act):
        """Returns named group, or the whole match if no named groups
                are present on the match.
        Args:
            match: a re.Match object

• Read up
  Read up

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

Open

def get_files_path(path, file_type):
    """Get all files path inside a folder.

    Works with nested folders.

• Read up
  Read up

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

Open

def _extract_page_lines_content(page):
    """Extracts page lines.

    Args:
        page: fitz.fitz.Page object to have its bold content extracted.

• Read up
  Read up

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

Open

  def load(self):
    # Load model
    if self.pipeline is None:
      f_path = os.path.dirname(__file__)
      f_path += self.model_path

• Read up
  Read up

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

Open

def committee_classification(all_acts, path, types, backend):
    """Uses committee classification to find act types.

    Args:
        all_acts (DataFrame): Dataframe with acts text and regex type.

• Read up
  Read up

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

Open

    def _get_pdfs_list(cls, folder):
        """Get DODFs list from the path.

        Args:
            folder: The folder containing the PDFs to be extracted.

• Read up
  Read up

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

Open

    def extract_to_txt(cls, folder='./', norm='NFKD'):
        """Extract information from DODF to a .txt file.

        For each PDF file in data/DODFs, the method extracts information from the
        PDF and writes it to the .txt file.

• Read up
  Read up

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

Open

def get_downloads(year, month):
    if "_" in month:
        url2, dodfs = req2(req1(year), month)
        _links = {}

• Read up
  Read up

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

Open

def xml_multiple(path, backend):
    files = []
    if os.path.isfile(path):
        files = [path]
        path_ = './'

• Read up
  Read up