def test_add_empty_to_nonempty():
gold = ['alpha', 'bravo', 'charlie']
words = WordStore()
for word in gold:
words.add(word)
words += WordStore()
assert len(list(words.iter_words())) == len(gold)
def test_add():
words = WordStore()
words.add('albatross')
assert len(list(words.iter_words())) == 1
assert 'albatross' in words.iter_words()
words.add('ganet')
assert len(list(words.iter_words())) == 2
assert 'albatross' in words.iter_words()
assert 'ganet' in words.iter_words()
def test_add_duplicate():
gold = ['left', 'center', 'right']
more_gold = ['surround', 'center']
words = WordStore()
for word in gold:
words.add(word)
more_words = WordStore()
for word in more_gold:
words.add(word)
words += more_words
assert len(list(words.iter_words())) == len(frozenset(gold + more_gold))
for word in words.iter_words():
assert word in gold or word in more_gold
def test_add_nonempty_to_nonempty():
gold = ['left', 'center', 'right']
more_gold = ['surround']
words = WordStore()
for word in gold:
words.add(word)
more_words = WordStore()
for word in more_gold:
words.add(word)
words += more_words
assert len(list(words.iter_words())) == len(gold) + len(more_gold)
for word in words.iter_words():
assert word in gold or word in more_gold
def scrape_html(html: str) -> WordStore:
"""Scrape HTML of its text.
Args:
html:
Returns:
words in HTML.
"""
words = WordStore()
soup = BeautifulSoup(html, 'html.parser')
try:
for s in soup.body.strings:
for word in s.split():
words.add(word)
except AttributeError:
_logger.info('HTML has no body.')
return words
def build_store(words):
store = WordStore()
for word in words:
store.add(word)
return store