Move English tokenizer tests to directory /en

This commit is contained in:
Ines Montani 2017-01-05 16:25:04 +01:00
parent 8b45363b4d
commit c5f2dc15de
11 changed files with 5 additions and 4 deletions

View File

View File

View File

@ -6,12 +6,13 @@ from __future__ import unicode_literals
import pytest
from ... import util
from ...language_data import TOKENIZER_PREFIXES
from ....util import compile_prefix_regex
from ....language_data import TOKENIZER_PREFIXES
en_search_prefixes = util.compile_prefix_regex(TOKENIZER_PREFIXES).search
en_search_prefixes = compile_prefix_regex(TOKENIZER_PREFIXES).search
PUNCT_OPEN = ['(', '[', '{', '*']
PUNCT_CLOSE = [')', ']', '}', '*']
PUNCT_PAIRED = [('(', ')'), ('[', ']'), ('{', '}'), ('*', '*')]

View File

@ -4,7 +4,7 @@ from os import path
import pytest
from spacy.util import utf8open
from ....util import utf8open
def test_tokenizer_handles_no_word(en_tokenizer):