def get_text_paths():
with open(json_path, "r") as f:
texts = json.load(f)
for text in texts:
author = text["Author"]
title = text["Title"]
period = text["Period"]
url = text["URL"]
filename = format_filename(author, title)
yield filename, period
def distributions():
for period, texts in TEXTS_DISTRIBUTIONS.items():
for i, distribution in enumerate(texts):
title = "%s%d" % (period, i + 1)
filename = format_filename(author="test", title=title)
yield filename, distribution
def test_sources():
for author, title, period, url in trainer.json():
yield _test_exists, format_filename(author, title)