Created
May 13, 2015 17:36
-
-
Save sampsyo/852f11b840f902b35165 to your computer and use it in GitHub Desktop.
find the common n-grams between two documents
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 python3 | |
import sys | |
def words(fn): | |
with open(fn) as f: | |
for line in f: | |
for word in line.split(): | |
yield word.strip(".,?!'") | |
def ngrams(l, n): | |
return zip(*[l[i:] for i in range(n)]) | |
def common_ngrams(l1, l2, n): | |
ngrams1 = set(ngrams(l1, n)) | |
ngrams2 = set(ngrams(l2, n)) | |
return ngrams1.intersection(ngrams2) | |
def plagcheck(doc1, doc2): | |
words1 = list(words(doc1)) | |
words2 = list(words(doc2)) | |
for n in range(5, 10): | |
c = common_ngrams(words1, words2, n) | |
for phrase in c: | |
print(' '.join(phrase)) | |
if __name__ == '__main__': | |
plagcheck(*sys.argv[1:]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment