def test_nonbreaking_prefixes_manual(self):
nonbreaking_prefixes = corpus.NonbreakingPrefixes()
self.assertListEqual(
list(nonbreaking_prefixes.words('en'))[:10],
[u'A', u'B', u'C', u'D', u'E', u'F', u'G', u'H', u'I', u'J'])
self.assertListEqual(
list(nonbreaking_prefixes.words('ta'))[:5],
[u'\u0b85', u'\u0b86', u'\u0b87', u'\u0b88', u'\u0b89'])
def test_nonbreaking_prefixes_manual(self):
nonbreaking_prefixes = corpus.NonbreakingPrefixes()
self.assertListEqual(
list(nonbreaking_prefixes.words("en"))[:10],
[u"A", u"B", u"C", u"D", u"E", u"F", u"G", u"H", u"I", u"J"],
)
self.assertListEqual(
list(nonbreaking_prefixes.words("ta"))[:5],
[u"\u0b85", u"\u0b86", u"\u0b87", u"\u0b88", u"\u0b89"],
)
def test_nonbreaking_prefixes_manual(self):
nonbreaking_prefixes = corpus.NonbreakingPrefixes()
self.assertListEqual(
list(nonbreaking_prefixes.words("en"))[:10],
[u"A", u"B", u"C", u"D", u"E", u"F", u"G", u"H", u"I", u"J"],
)
self.assertListEqual(
list(nonbreaking_prefixes.words("ta"))[:5],
[
"\u0bb0", "\u0bc2", "\u0ba4\u0bbf\u0bb0\u0bc1", "\u0b8f",
"\u0baa\u0bc0"
],
)
def test_nonbreaking_prefixes_sanity_check(self):
nonbreaking_prefixes = corpus.NonbreakingPrefixes()
for language in nonbreaking_prefixes.available_langs.values():
if sys.version_info[0] >= 3: # Python 3
with self.subTest(language=language):
count = 0
for word in nonbreaking_prefixes.words(lang=language):
self.assertIsInstance(word, str)
count += 1
self.assertGreater(count, 0)
else:
self.assertEqual(
all(
isinstance(word, text_type)
for word in nonbreaking_prefixes.words(lang=language)),
True)