mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-13 13:17:06 +03:00
fa3b8512da
Bundle everything in language_data to keep it consistent with other languages and make TOKENIZER_EXCEPTIONS importable from there.
30 lines
778 B
Python
30 lines
778 B
Python
# encoding: utf8
|
|
from __future__ import unicode_literals, print_function
|
|
|
|
from ..language import Language, BaseDefaults
|
|
from ..attrs import LANG
|
|
|
|
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'
|
|
|
|
Defaults = FrenchDefaults
|