spaCy/spacy/fr/__init__.py

30 lines
778 B
Python
Raw Normal View History

2016-12-17 11:25:44 +00:00
# encoding: utf8
from __future__ import unicode_literals, print_function
from ..language import Language, BaseDefaults
2016-12-08 19:07:14 +00:00
from ..attrs import LANG
2016-12-18 15:54:19 +00:00
from .language_data import *
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
class FrenchDefaults(BaseDefaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'fr'
stop_words = STOP_WORDS
infixes = tuple(TOKENIZER_INFIXES)
suffixes = tuple(TOKENIZER_SUFFIXES)
token_match = TOKEN_MATCH
@classmethod
def create_tokenizer(cls, nlp=None):
cls.tokenizer_exceptions = TOKENIZER_EXCEPTIONS
return super(FrenchDefaults, cls).create_tokenizer(nlp)
class French(Language):
lang = 'fr'
2016-12-08 19:07:14 +00:00
Defaults = FrenchDefaults