explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add English norm exceptions to lex_attrs

Browse Source
This commit is contained in:
ines 2017-06-03 20:27:28 +02:00
parent 095eeeb12f
commit 746653880c
2 changed files with 1767 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
spacy/lang/en/__init__.py
View File

@ -2,6 +2,7 @@
from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .norm_exceptions import NORM_EXCEPTIONS
from .tag_map import TAG_MAP
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
@ -10,14 +11,17 @@ from .lemmatizer import LEMMA_RULES, LEMMA_INDEX, LEMMA_EXC
from .syntax_iterators import SYNTAX_ITERATORS
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...attrs import LANG
from ...util import update_exc
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[LANG] = lambda text: 'en'
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM],
BASE_NORMS, NORM_EXCEPTIONS)
lex_attr_getters.update(LEX_ATTRS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)

1761
spacy/lang/en/norm_exceptions.py Normal file
View File

File diff suppressed because it is too large Load Diff