def feed()

in mlops-template-gitlab/lambda_functions/lambda-gitlab-pipeline-trigger/charset_normalizer/md.py [0:0]

• 42 lines of code
• 23 McCabe index (conditional complexity)

    def feed(self, character: str) -> None:
        if character.isalpha():
            self._buffer = "".join([self._buffer, character])
            if is_accentuated(character):
                self._buffer_accent_count += 1
            if (
                self._foreign_long_watch is False
                and is_latin(character) is False
                and is_cjk(character) is False
                and is_hangul(character) is False
                and is_katakana(character) is False
                and is_hiragana(character) is False
                and is_thai(character) is False
            ):
                self._foreign_long_watch = True
            return
        if not self._buffer:
            return
        if (
            character.isspace() or is_punctuation(character) or is_separator(character)
        ) and self._buffer:
            self._word_count += 1
            buffer_length = len(self._buffer)  # type: int

            self._character_count += buffer_length

            if buffer_length >= 4 and self._buffer_accent_count / buffer_length >= 0.3:
                self._is_current_word_bad = True
            if buffer_length >= 24 and self._foreign_long_watch:
                self._is_current_word_bad = True

            if self._is_current_word_bad:
                self._bad_word_count += 1
                self._bad_character_count += len(self._buffer)
                self._is_current_word_bad = False

            self._foreign_long_watch = False
            self._buffer = ""
            self._buffer_accent_count = 0
        elif (
            character not in {"<", ">", "-", "="}
            and character.isdigit() is False
            and is_symbol(character)
        ):
            self._is_current_word_bad = True
            self._buffer += character