spaCy/spacy/lang/en/__init__.py

43 lines
1.3 KiB
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
from __future__ import unicode_literals
2015-07-07 15:00:07 +03:00
2017-05-08 16:47:25 +03:00
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .norm_exceptions import NORM_EXCEPTIONS
2017-05-08 16:47:25 +03:00
from .tag_map import TAG_MAP
from .stop_words import STOP_WORDS
2017-05-09 02:09:52 +03:00
from .lex_attrs import LEX_ATTRS
2017-05-08 16:47:25 +03:00
from .morph_rules import MORPH_RULES
from .lemmatizer import LEMMA_RULES, LEMMA_INDEX, LEMMA_EXC
from .syntax_iterators import SYNTAX_ITERATORS
2017-05-08 16:47:25 +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 EnglishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters.update(LEX_ATTRS)
lex_attr_getters[LANG] = lambda text: 'en'
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM],
BASE_NORMS, NORM_EXCEPTIONS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
tag_map = dict(TAG_MAP)
stop_words = set(STOP_WORDS)
morph_rules = dict(MORPH_RULES)
lemma_rules = dict(LEMMA_RULES)
lemma_index = dict(LEMMA_INDEX)
lemma_exc = dict(LEMMA_EXC)
2017-06-04 23:51:50 +03:00
syntax_iterators = dict(SYNTAX_ITERATORS)
2015-08-25 16:37:30 +03:00
class English(Language):
2015-12-28 18:54:03 +03:00
lang = 'en'
Defaults = EnglishDefaults
2017-05-28 01:57:59 +03:00
__all__ = ['English']