Created
April 3, 2013 23:40
-
-
Save gamblore/5306465 to your computer and use it in GitHub Desktop.
Find folder based on filename. Needs Season Episode stripping.
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 os, sys | |
import re, collections | |
from operator import itemgetter | |
PATH = "/TV" | |
DICTIONARY = os.listdir(PATH) | |
def damerau_levenshtein_distance(s1, s2): | |
d = {} | |
lenstr1 = len(s1) | |
lenstr2 = len(s2) | |
for i in xrange(-1,lenstr1+1): | |
d[(i,-1)] = i+1 | |
for j in xrange(-1,lenstr2+1): | |
d[(-1,j)] = j+1 | |
for i in xrange(lenstr1): | |
for j in xrange(lenstr2): | |
if s1[i] == s2[j]: | |
cost = 0 | |
else: | |
cost = 1 | |
d[(i,j)] = min( | |
d[(i-1,j)] + 1, # deletion | |
d[(i,j-1)] + 1, # insertion | |
d[(i-1,j-1)] + cost, # substitution | |
) | |
if i and j and s1[i]==s2[j-1] and s1[i-1] == s2[j]: | |
d[(i,j)] = min (d[(i,j)], d[i-2,j-2] + cost) # transposition | |
return d[lenstr1-1,lenstr2-1] | |
def find_match(filename): | |
distances = map(lambda x: (x, damerau_levenshtein_distance(x, filename)), DICTIONARY) | |
sorted_distances = sorted(distances, key=itemgetter(1)) | |
print sorted_distances[0][0] | |
def main(): | |
if len(sys.argv) < 2: | |
print "Need a parameter" | |
sys.exit(0) | |
find_match(sys.argv[1]) | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment