-def letters(text):
- """Remove all non-alphabetic characters from a text
- >>> letters('The Quick')
- 'TheQuick'
- >>> letters('The Quick BROWN fox jumped! over... the (9lazy) DOG')
- 'TheQuickBROWNfoxjumpedoverthelazyDOG'
- """
- return ''.join([c for c in text if c in string.ascii_letters])
-
-def sanitise(text):
- """Remove all non-alphabetic characters and convert the text to lowercase
-
- >>> sanitise('The Quick')
- 'thequick'
- >>> sanitise('The Quick BROWN fox jumped! over... the (9lazy) DOG')
- 'thequickbrownfoxjumpedoverthelazydog'
- """
- # sanitised = [c.lower() for c in text if c in string.ascii_letters]
- # return ''.join(sanitised)
- return letters(text).lower()
-
-def ngrams(text, n):
- """Returns all n-grams of a text
-
- >>> ngrams(sanitise('the quick brown fox'), 2) # doctest: +NORMALIZE_WHITESPACE
- ['th', 'he', 'eq', 'qu', 'ui', 'ic', 'ck', 'kb', 'br', 'ro', 'ow', 'wn',
- 'nf', 'fo', 'ox']
- >>> ngrams(sanitise('the quick brown fox'), 4) # doctest: +NORMALIZE_WHITESPACE
- ['theq', 'hequ', 'equi', 'quic', 'uick', 'ickb', 'ckbr', 'kbro', 'brow',
- 'rown', 'ownf', 'wnfo', 'nfox']
- """
- return [text[i:i+n] for i in range(len(text)-n+1)]