Sign upLogin

BLKSerene/Wordless

View on GitHub
Star
wordless/wl_nlp/wl_texts.py
a508352c

Summary

Maintainability
C
7 hrs
Test Coverage

Function to_tokens has 9 arguments (exceeds 4 allowed). Consider refactoring.
Open

def to_tokens(
Severity: Major
Found in wordless/wl_nlp/wl_texts.py - About 1 hr to fix

    Function __init__ has 9 arguments (exceeds 4 allowed). Consider refactoring.
    Open

        def __init__(
    Severity: Major
    Found in wordless/wl_nlp/wl_texts.py - About 1 hr to fix

      Consider simplifying this complex logical expression.
      Open

                  if (
                self.tokenized
                and (css_para and css_sentence and css_word)
                and (soup.select_one(css_para) and soup.select_one(css_sentence) and soup.select_one(css_word))
            ):
      Severity: Major
      Found in wordless/wl_nlp/wl_texts.py - About 1 hr to fix

        Avoid deeply nested control flow statements.
        Open

                                if (para := para[tag_end:]):
                            tags_tokens = self.add_tags_splitting(para, tags_tokens)

            # Add empty tags for untagged files
            if not self.tagged:
        Severity: Major
        Found in wordless/wl_nlp/wl_texts.py - About 45 mins to fix

          Avoid deeply nested control flow statements.
          Open

                                  for tag in re.finditer(re_tags, para):
                            tags_tokens = self.add_tags_splitting(para[tag_end:tag.start()], tags_tokens)
                            tags_tokens[-1].append(tag.group())

                            tag_end = tag.end()
          Severity: Major
          Found in wordless/wl_nlp/wl_texts.py - About 45 mins to fix

            Avoid deeply nested control flow statements.
            Open

                                    for sentence in wl_sentence_tokenization.wl_sentence_split(self.main, text_no_tags):
                            self.tokens_multilevel[-1].append([])

                            for sentence_seg in wl_sentence_tokenization.wl_sentence_seg_split(self.main, sentence):
                                self.tokens_multilevel[-1][-1].append(sentence_seg.split())
            Severity: Major
            Found in wordless/wl_nlp/wl_texts.py - About 45 mins to fix

              Avoid deeply nested control flow statements.
              Open

                                      if i == 0 and re.match(re_tags_start, para):
                            # Check if the first paragraph is empty
                            if not self.tokens_multilevel[0]:
                                self.tokens_multilevel[0].append([[]])
              Severity: Major
              Found in wordless/wl_nlp/wl_texts.py - About 45 mins to fix

                Avoid deeply nested control flow statements.
                Open

                                        for sentence in wl_sentence_tokenization.wl_sentence_split(self.main, para):
                            self.tokens_multilevel[-1].append([])

                            for sentence_seg in wl_sentence_tokenization.wl_sentence_seg_split(self.main, sentence):
                                self.tokens_multilevel[-1][-1].append(sentence_seg.split())
                Severity: Major
                Found in wordless/wl_nlp/wl_texts.py - About 45 mins to fix

                  There are no issues that match your filters.

                  Category
                  Status