fork download
  1. import sys
  2. from collections import Counter
  3.  
  4. accumulator = Counter()
  5. text = sys.stdin.read()
  6. for length in range(1,len(text)+1):
  7. for start in range(len(text) - length):
  8. accumulator[text[start:start+length]] += 1
  9.  
  10.  
  11. from pprint import pprint
  12. pprint(accumulator.most_common(100))
  13.  
Success #stdin #stdout 0.07s 10528KB
stdin
hello world this is hello world. hello world repeats three times in this string!
stdout
[(' ', 13),
 ('l', 9),
 ('e', 8),
 ('o', 6),
 ('h', 6),
 ('r', 6),
 ('s', 6),
 ('t', 6),
 ('i', 6),
 ('s ', 5),
 (' t', 4),
 ('ello ', 3),
 ('worl', 3),
 ('llo worl', 3),
 ('rl', 3),
 ('is ', 3),
 ('hello w', 3),
 (' wor', 3),
 ('wo', 3),
 ('lo wo', 3),
 ('is', 3),
 ('hello wor', 3),
 ('ello', 3),
 ('ell', 3),
 ('ello wor', 3),
 ('llo world', 3),
 ('lo w', 3),
 ('llo', 3),
 ('lo worl', 3),
 ('lo world', 3),
 ('el', 3),
 ('rld', 3),
 ('lo wor', 3),
 ('orl', 3),
 ('o worl', 3),
 ('llo ', 3),
 ('hello world', 3),
 ('llo wo', 3),
 ('world', 3),
 ('o ', 3),
 ('or', 3),
 ('hel', 3),
 ('lo ', 3),
 ('th', 3),
 ('llo wor', 3),
 ('o w', 3),
 ('hell', 3),
 ('w', 3),
 ('hello wo', 3),
 ('ello worl', 3),
 ('o world', 3),
 ('wor', 3),
 (' th', 3),
 ('hello ', 3),
 (' worl', 3),
 ('d', 3),
 ('orld', 3),
 ('llo w', 3),
 ('hello', 3),
 (' w', 3),
 ('ello wo', 3),
 ('ld', 3),
 ('lo', 3),
 ('ll', 3),
 (' world', 3),
 ('ello world', 3),
 ('he', 3),
 ('ello w', 3),
 (' wo', 3),
 ('o wor', 3),
 ('hello worl', 3),
 ('o wo', 3),
 ('d ', 2),
 (' this', 2),
 ('o world ', 2),
 ('n', 2),
 ('in', 2),
 (' hello world', 2),
 ('thi', 2),
 ('rld ', 2),
 (' hell', 2),
 (' hello wor', 2),
 ('orld ', 2),
 (' this ', 2),
 (' hel', 2),
 ('his ', 2),
 (' hello worl', 2),
 ('re', 2),
 (' hello wo', 2),
 (' hello ', 2),
 ('lo world ', 2),
 ('hello world ', 2),
 ('his', 2),
 (' world ', 2),
 ('ld ', 2),
 (' h', 2),
 (' i', 2),
 ('this', 2),
 ('llo world ', 2),
 ('ello world ', 2)]