spaCy/spacy/hu/language_data.py

29 lines
867 B
Python
Raw Normal View History

# encoding: utf8
from __future__ import unicode_literals
2016-12-08 14:06:36 +03:00
import six
2016-12-21 00:28:20 +03:00
from spacy.language_data import strings_to_exc, update_exc
from .punctuation import *
2016-12-21 00:28:20 +03:00
from .stop_words import STOP_WORDS
from .tokenizer_exceptions import ABBREVIATIONS
from .tokenizer_exceptions import OTHER_EXC
from .. import language_data as base
2016-12-21 00:28:20 +03:00
STOP_WORDS = set(STOP_WORDS)
2016-12-08 14:06:36 +03:00
TOKENIZER_EXCEPTIONS = strings_to_exc(base.EMOTICONS)
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS))
2016-12-21 00:28:20 +03:00
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(OTHER_EXC))
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(ABBREVIATIONS))
TOKENIZER_PREFIXES = base.TOKENIZER_PREFIXES
TOKENIZER_SUFFIXES = base.TOKENIZER_SUFFIXES + TOKENIZER_SUFFIXES
TOKENIZER_INFIXES = TOKENIZER_INFIXES
2016-12-21 00:28:20 +03:00
__all__ = ["TOKENIZER_EXCEPTIONS", "STOP_WORDS", "TOKENIZER_PREFIXES", "TOKENIZER_SUFFIXES", "TOKENIZER_INFIXES"]