def test_download(self, tmpdir):
dataset = wikimedia.Wikipedia(data_dir=str(tmpdir))
dataset.download()
assert os.path.isfile(dataset.filepath)
def test_oserror(self, tmpdir):
dataset = wikimedia.Wikipedia(data_dir=str(tmpdir))
with pytest.raises(OSError):
_ = list(dataset.texts())
# -*- coding: utf-8 -*-
from __future__ import absolute_import, unicode_literals
import os
import re
import pytest
from textacy import compat
from textacy.datasets import wikimedia
WIKINEWS = wikimedia.Wikinews(lang="en", version="current")
WIKIPEDIA = wikimedia.Wikipedia(lang="en", version="current")
@pytest.mark.skipif(
WIKIPEDIA.filepath is None,
reason="Wikinews dataset must be downloaded before running tests",
)
class TestWikipedia(object):
@pytest.mark.skip("No need to download a new dataset every time")
def test_download(self, tmpdir):
dataset = wikimedia.Wikipedia(data_dir=str(tmpdir))
dataset.download()
assert os.path.isfile(dataset.filepath)
def test_oserror(self, tmpdir):
dataset = wikimedia.Wikipedia(data_dir=str(tmpdir))
with pytest.raises(OSError):