Created
June 22, 2016 07:50
-
-
Save Omrigan/5793d96ea0d322d884c28033136fd639 to your computer and use it in GitHub Desktop.
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 re | |
def get_sense(text): | |
tokens = text.split() | |
good_tokens = set() | |
prev_end = True | |
i = 0 | |
while i < len(tokens): | |
t = tokens[i] | |
if t[0].isupper() and not prev_end: | |
# prev_i = i | |
# while i < len(tokens) - 1 and tokens[i][0].isupper(): | |
# i += 1 | |
#good_tokens.add(" ".join(tokens[prev_i:i])) | |
good_tokens.add(t) | |
if t[0] in {'"', '\'', '«'}: | |
prev_i = i | |
end_char = t[0] | |
if end_char=='«': | |
end_char = '»' | |
while i<len(tokens)-1 and end_char not in tokens[i]: | |
i+=1 | |
if i-prev_i<5: | |
good_tokens.add(" ".join(tokens[prev_i:i+1])) | |
prev_end = False | |
if t[-1] in {'.', '!', '?', '-', '—'}: | |
prev_end = True | |
i+=1 | |
good_tokens = {re.sub('[,!\\.\\?\\)\\(\\[\\]]', '', _) for _ in good_tokens} | |
return good_tokens | |
print(get_sense(open('testtext.txt').read())) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment