mirror of
https://github.com/explosion/spaCy.git
synced 2025-05-02 23:03:41 +03:00
Move English tokenizer tests to directory /en
This commit is contained in:
parent
8b45363b4d
commit
c5f2dc15de
0
spacy/tests/en/__init__.py
Normal file
0
spacy/tests/en/__init__.py
Normal file
0
spacy/tests/en/tokenizer/__init__.py
Normal file
0
spacy/tests/en/tokenizer/__init__.py
Normal file
|
@ -6,12 +6,13 @@ from __future__ import unicode_literals
|
||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
|
|
||||||
from ... import util
|
from ....util import compile_prefix_regex
|
||||||
from ...language_data import TOKENIZER_PREFIXES
|
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_OPEN = ['(', '[', '{', '*']
|
||||||
PUNCT_CLOSE = [')', ']', '}', '*']
|
PUNCT_CLOSE = [')', ']', '}', '*']
|
||||||
PUNCT_PAIRED = [('(', ')'), ('[', ']'), ('{', '}'), ('*', '*')]
|
PUNCT_PAIRED = [('(', ')'), ('[', ']'), ('{', '}'), ('*', '*')]
|
|
@ -4,7 +4,7 @@ from os import path
|
||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
|
|
||||||
from spacy.util import utf8open
|
from ....util import utf8open
|
||||||
|
|
||||||
|
|
||||||
def test_tokenizer_handles_no_word(en_tokenizer):
|
def test_tokenizer_handles_no_word(en_tokenizer):
|
Loading…
Reference in New Issue
Block a user