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
def eligible(self, character: str) -> bool:
return is_latin(character)
def eligible(self, character: str) -> bool:
return character.isalpha() and is_latin(character)