Created
December 7, 2012 21:02
-
-
Save enigmaticape/4236500 to your computer and use it in GitHub Desktop.
Really awful code to count ngrams
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import collections | |
import sys | |
nums = sys.argv[1:] | |
def factors_of( x ): | |
factors = [] | |
n = x-1 | |
while n > 1: | |
if x % n == 0: | |
factors.append( n ) | |
n = n - 1 | |
return factors | |
counts = collections.Counter() | |
for x in nums: | |
factors = factors_of( int(x) ) | |
print x, factors | |
counts += collections.Counter( factors ) | |
print "Common Factor : ",\ | |
sorted([n for n in counts if counts[n] == len(nums)]) | |
print "Most Common :",\ | |
[count for count in sorted( counts.items() ) if count[1] > 1] | |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import sys | |
#cipher = "hello there here is text jk kj" | |
cipher_in = open( sys.argv[ 1 ], 'rb') | |
cipher = cipher_in.read() | |
# remove all spaces | |
cipher_text = "".join( cipher.split() ) | |
matches = [] | |
reverses = [] | |
for n in range(2, (len(cipher_text) / 2) - 1 ): | |
p_found = [] | |
for p in range( 0, len( cipher_text ) ): | |
# get the digram | |
test_digram = cipher_text[ p:p+n ] | |
# get the ranges to the left and right that | |
# don't impinge on the current n-gram | |
for cand_range in [ range(0, p-n), range(p+n, len(cipher_text) ) ]: | |
for cand_p in [c for c in cand_range if c not in p_found]: | |
candidate_digram = cipher_text[ cand_p:cand_p + n ] | |
# print test_digram, candidate_digram | |
stride = cand_p - (p + n) + 1 | |
if candidate_digram == test_digram: | |
matches.append( "Matched : {} at {} is {} at {} stride {}".format( test_digram, p+1, candidate_digram, cand_p+1, stride ) ) | |
p_found.extend( [p, cand_p] ) | |
if candidate_digram[::-1] == test_digram: | |
reverses.append( "Reversed : {} at {} is {} at {} stride {}".format( test_digram, p+1, candidate_digram, cand_p+1, stride )) | |
p_found.extend( [p, cand_p] ) | |
print "\n".join( matches ) | |
#print "\n".join( reverses ) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment