def _get_sentence_tokenizer(self, language):
try:
path = to_string("tokenizers/punkt/%s.pickle") % to_string(
language)
return nltk.data.load(path)
except (LookupError, zipfile.BadZipfile):
raise LookupError(
"NLTK tokenizers are missing. Download them by following command: "
'''python -c "import nltk; nltk.download('punkt')"''')
def __repr__(self):
return to_string("<%s: %s>") % ("Heading" if self._is_heading else
"Sentence", self.__str__())
def expand_resource_path(path):
directory = dirname(sys.modules["sumy"].__file__)
directory = abspath(directory)
return join(directory, to_string("data"), to_string(path))
def __repr__(self):
return to_string("<ItemsCount: %r>" % self._value)