- >>> ngrams(sanitise('the quick brown fox'), 2)
- [('t', 'h'), ('h', 'e'), ('e', 'q'), ('q', 'u'), ('u', 'i'), ('i', 'c'), ('c', 'k'), ('k', 'b'), ('b', 'r'), ('r', 'o'), ('o', 'w'), ('w', 'n'), ('n', 'f'), ('f', 'o'), ('o', 'x')]
- >>> ngrams(sanitise('the quick brown fox'), 4)
- [('t', 'h', 'e', 'q'), ('h', 'e', 'q', 'u'), ('e', 'q', 'u', 'i'), ('q', 'u', 'i', 'c'), ('u', 'i', 'c', 'k'), ('i', 'c', 'k', 'b'), ('c', 'k', 'b', 'r'), ('k', 'b', 'r', 'o'), ('b', 'r', 'o', 'w'), ('r', 'o', 'w', 'n'), ('o', 'w', 'n', 'f'), ('w', 'n', 'f', 'o'), ('n', 'f', 'o', 'x')]
+ >>> 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)]
+
+def every_nth(text, n, fillvalue=''):
+ """Returns n strings, each of which consists of every nth character,
+ starting with the 0th, 1st, 2nd, ... (n-1)th character
+
+ >>> every_nth(string.ascii_lowercase, 5)
+ ['afkpuz', 'bglqv', 'chmrw', 'dinsx', 'ejoty']
+ >>> every_nth(string.ascii_lowercase, 1)
+ ['abcdefghijklmnopqrstuvwxyz']
+ >>> every_nth(string.ascii_lowercase, 26) # doctest: +NORMALIZE_WHITESPACE
+ ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n',
+ 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z']
+ >>> every_nth(string.ascii_lowercase, 5, fillvalue='!')
+ ['afkpuz', 'bglqv!', 'chmrw!', 'dinsx!', 'ejoty!']
+ """
+ split_text = [text[i:i+n] for i in range(0, len(text), n)]
+ return [''.join(l) for l in zip_longest(*split_text, fillvalue=fillvalue)]
+
+def combine_every_nth(split_text):
+ """Reforms a text split into every_nth strings
+
+ >>> combine_every_nth(every_nth(string.ascii_lowercase, 5))
+ 'abcdefghijklmnopqrstuvwxyz'
+ >>> combine_every_nth(every_nth(string.ascii_lowercase, 1))
+ 'abcdefghijklmnopqrstuvwxyz'
+ >>> combine_every_nth(every_nth(string.ascii_lowercase, 26))
+ 'abcdefghijklmnopqrstuvwxyz'
+ """
+ return ''.join([''.join(l)
+ for l in zip_longest(*split_text, fillvalue='')])
+
+def transpose(items, transposition):
+ """Moves items around according to the given transposition
+
+ >>> transpose(['a', 'b', 'c', 'd'], [0,1,2,3])
+ ['a', 'b', 'c', 'd']
+ >>> transpose(['a', 'b', 'c', 'd'], [3,1,2,0])
+ ['d', 'b', 'c', 'a']
+ >>> transpose([10,11,12,13,14,15], [3,2,4,1,5,0])
+ [13, 12, 14, 11, 15, 10]
+ """
+ transposed = list(repeat('', len(transposition)))
+ for p, t in enumerate(transposition):
+ transposed[p] = items[t]
+ return transposed
+
+def untranspose(items, transposition):
+ """Undoes a transpose
+
+ >>> untranspose(['a', 'b', 'c', 'd'], [0,1,2,3])
+ ['a', 'b', 'c', 'd']
+ >>> untranspose(['d', 'b', 'c', 'a'], [3,1,2,0])
+ ['a', 'b', 'c', 'd']
+ >>> untranspose([13, 12, 14, 11, 15, 10], [3,2,4,1,5,0])
+ [10, 11, 12, 13, 14, 15]