spaCy/spacy/lang/fr/__init__.py

40 lines
1.2 KiB
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
2017-05-08 16:49:05 +03:00
from __future__ import unicode_literals
2017-05-08 16:49:05 +03:00
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
2017-11-05 01:32:51 +03:00
from .tag_map import TAG_MAP
2017-05-08 16:49:05 +03:00
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
2017-05-08 16:49:05 +03:00
from .lemmatizer import LOOKUP
from .syntax_iterators import SYNTAX_ITERATORS
2016-12-08 22:07:14 +03:00
2017-05-08 23:29:04 +03:00
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
2017-05-08 23:29:04 +03:00
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
class FrenchDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters.update(LEX_ATTRS)
lex_attr_getters[LANG] = lambda text: 'fr'
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
2017-11-05 01:32:51 +03:00
tag_map = TAG_MAP
stop_words = STOP_WORDS
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
token_match = TOKEN_MATCH
syntax_iterators = SYNTAX_ITERATORS
lemma_lookup = LOOKUP
2017-05-08 16:49:05 +03:00
class French(Language):
lang = 'fr'
Defaults = FrenchDefaults
2017-05-03 12:01:42 +03:00
2017-05-08 16:49:05 +03:00
__all__ = ['French']