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 LEX_ATTRS

Browse Source
This commit is contained in:
ines 2017-05-12 15:37:45 +02:00
parent bca2ea9c72
commit c13b3fa052
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/lang/pt/__init__.py
View File

@ -3,6 +3,7 @@ from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .lemmatizer import LOOKUP from .lemmatizer import LOOKUP
from ..tokenizer_exceptions import BASE_EXCEPTIONS from ..tokenizer_exceptions import BASE_EXCEPTIONS
@ -18,6 +19,7 @@ class Portuguese(Language):
class Defaults(Language.Defaults): class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters) lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'pt' lex_attr_getters[LANG] = lambda text: 'pt'
lex_attr_getters.update(LEX_ATTRS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS) tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS) stop_words = set(STOP_WORDS)