mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +03:00
Remove unused utf8open util and replace os.path with ensure_path
This commit is contained in:
parent
90cf6b9429
commit
0084466a66
|
@ -3,9 +3,8 @@ from __future__ import unicode_literals
|
||||||
|
|
||||||
from ...vocab import Vocab
|
from ...vocab import Vocab
|
||||||
from ...tokenizer import Tokenizer
|
from ...tokenizer import Tokenizer
|
||||||
from ...util import utf8open
|
from ... import util
|
||||||
|
|
||||||
from os import path
|
|
||||||
import pytest
|
import pytest
|
||||||
|
|
||||||
|
|
||||||
|
@ -75,8 +74,8 @@ Phasellus tincidunt, augue quis porta finibus, massa sapien consectetur augue, n
|
||||||
|
|
||||||
@pytest.mark.parametrize('file_name', ["sun.txt"])
|
@pytest.mark.parametrize('file_name', ["sun.txt"])
|
||||||
def test_tokenizer_handle_text_from_file(tokenizer, file_name):
|
def test_tokenizer_handle_text_from_file(tokenizer, file_name):
|
||||||
loc = path.join(path.dirname(__file__), file_name)
|
loc = util.ensure_path(__file__).parent / file_name
|
||||||
text = utf8open(loc).read()
|
text = loc.open('r', encoding='utf8').read()
|
||||||
assert len(text) != 0
|
assert len(text) != 0
|
||||||
tokens = tokenizer(text)
|
tokens = tokenizer(text)
|
||||||
assert len(tokens) > 100
|
assert len(tokens) > 100
|
||||||
|
|
|
@ -103,10 +103,6 @@ def normalize_slice(length, start, stop, step=None):
|
||||||
return start, stop
|
return start, stop
|
||||||
|
|
||||||
|
|
||||||
def utf8open(loc, mode='r'):
|
|
||||||
return io.open(loc, mode, encoding='utf8')
|
|
||||||
|
|
||||||
|
|
||||||
def check_renamed_kwargs(renamed, kwargs):
|
def check_renamed_kwargs(renamed, kwargs):
|
||||||
for old, new in renamed.items():
|
for old, new in renamed.items():
|
||||||
if old in kwargs:
|
if old in kwargs:
|
||||||
|
|
Loading…
Reference in New Issue
Block a user