From 0aaa546435a261a03e27fee53a3c5f334cca6b66 Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Mon, 27 Feb 2017 11:20:47 +0100 Subject: [PATCH] Fix test after updating the French tokenizer stuff --- spacy/tests/regression/test_issue768.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/spacy/tests/regression/test_issue768.py b/spacy/tests/regression/test_issue768.py index d8c8be80b..a1701334b 100644 --- a/spacy/tests/regression/test_issue768.py +++ b/spacy/tests/regression/test_issue768.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals from ...language import Language from ...attrs import LANG -from ...fr.language_data import TOKENIZER_EXCEPTIONS, STOP_WORDS +from ...fr.language_data import get_tokenizer_exceptions, STOP_WORDS from ...language_data.punctuation import TOKENIZER_INFIXES, ALPHA import pytest @@ -20,7 +20,7 @@ def fr_tokenizer_w_infix(): class Defaults(Language.Defaults): lex_attr_getters = dict(Language.Defaults.lex_attr_getters) lex_attr_getters[LANG] = lambda text: 'fr' - tokenizer_exceptions = TOKENIZER_EXCEPTIONS + tokenizer_exceptions = get_tokenizer_exceptions() stop_words = STOP_WORDS infixes = TOKENIZER_INFIXES + [SPLIT_INFIX]