explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-28 04:43:42 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix import and tokenizer exceptions

Browse Source
This commit is contained in:
ines 2017-05-08 16:20:14 +02:00
parent 2324788970
commit be5541bd16
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/tests/regression/test_issue768.py
View File

@ -3,8 +3,10 @@ from __future__ import unicode_literals
from ...language import Language from ...language import Language
from ...attrs import LANG from ...attrs import LANG
from ...fr.language_data import get_tokenizer_exceptions, STOP_WORDS from ...fr.stop_words import STOP_WORDS
from ...fr.tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from ...language_data.punctuation import TOKENIZER_INFIXES, ALPHA from ...language_data.punctuation import TOKENIZER_INFIXES, ALPHA
from ...util import update_exc
import pytest import pytest
@ -20,7 +22,7 @@ def fr_tokenizer_w_infix():
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: 'fr' lex_attr_getters[LANG] = lambda text: 'fr'
tokenizer_exceptions = get_tokenizer_exceptions() tokenizer_exceptions = update_exc(TOKENIZER_EXCEPTIONS)
stop_words = STOP_WORDS stop_words = STOP_WORDS
infixes = TOKENIZER_INFIXES + [SPLIT_INFIX] infixes = TOKENIZER_INFIXES + [SPLIT_INFIX]