Last active
September 11, 2015 11:32
-
-
Save arktrin/b02959d5f0ce5f7406c0 to your computer and use it in GitHub Desktop.
find longest string coincidences in all possible combinations of two subtitles that are located in current folder
This file contains 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
import itertools, glob, os, re, difflib | |
import timeit as ti | |
# srts = os.listdir(os.path.dirname(os.path.abspath(__file__))) | |
srts = glob.glob(os.path.dirname(os.path.abspath(__file__))+'/*.srt') | |
srtsComb = list(itertools.combinations(srts, 2)) | |
print len(srtsComb) | |
i = 0 | |
repls = (',', ''),('</i>', ''),('<i>', ''),('\n', ''),('-', ''),(' ', ''),(':', ''),('#', '') | |
for comb in srtsComb: | |
in0 = open(comb[0], 'r').read() | |
in1 = open(comb[1], 'r').read() | |
in0 = re.sub(r'(?m)^\d.*\n?', '', in0).lower() | |
in0 = reduce(lambda a, kv: a.replace(*kv), repls, in0) | |
in1 = re.sub(r'(?m)^\d.*\n?', '', in1).lower() | |
in1 = reduce(lambda a, kv: a.replace(*kv), repls, in1) | |
s = difflib.SequenceMatcher(None, in0, in1) | |
longestMatch = s.find_longest_match(0,len(in0),0,len(in1)) | |
if longestMatch[2] > 8: | |
print comb[0][50:-4], comb[1][50:-4] | |
print longestMatch, in0[longestMatch[0]:longestMatch[0]+longestMatch[2]+1] | |
i += 1 | |
if i % 50 == 0: | |
print i | |
# break |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment