import collections
import numpy as np
import pytest
import spacy
from spacy.tokens import Doc
from textacy import Corpus
from textacy import load_spacy_lang
from textacy.datasets.capitol_words import CapitolWords
DATASET = CapitolWords()
pytestmark = pytest.mark.skipif(
DATASET.filepath is None,
reason="CapitolWords dataset must be downloaded before running tests",
)
@pytest.fixture(scope="module")
def corpus():
return Corpus("en", data=DATASET.records(limit=5))
class TestCorpusInit:
def test_corpus_init_lang(self):
assert isinstance(Corpus("en"), Corpus)
assert isinstance(Corpus(load_spacy_lang("en")), Corpus)
for bad_lang in (b"en", None):
with pytest.raises(TypeError):
Corpus(bad_lang)
def test_ioerror(self):
dataset = CapitolWords(data_dir=self.tempdir)
with self.assertRaises(IOError):
_ = list(dataset.texts())
def test_download(self):
dataset = CapitolWords(data_dir=self.tempdir)
dataset.download()
self.assertTrue(os.path.exists(dataset.filename))
def test_ioerror(tmpdir):
dataset = CapitolWords(data_dir=str(tmpdir))
with pytest.raises(IOError):
_ = list(dataset.texts())
def test_download(tmpdir):
dataset = CapitolWords(data_dir=str(tempdir))
dataset.download()
assert os.path.exists(dataset.filename)
def test_download(tmpdir):
dataset = CapitolWords(data_dir=str(tmpdir))
dataset.download()
assert os.path.isfile(dataset._filepath)