Advertisement
Guest User

Untitled

a guest
Jan 26th, 2015
241
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 0.66 KB | None | 0 0
  1. def splite_sentence(text):
  2. long_sep = u'。!?;!?;'
  3. short_sep = u',, '
  4. long_sents = []
  5. offset_begin = 0
  6. short_sents = []
  7. for i, e in enumerate(text):
  8. if e in short_sep:
  9. short_sents.append(text[offset_begin: i+1])
  10. offset_begin = i+1
  11. elif e in long_sep:
  12. short_sents.append(text[offset_begin: i+1])
  13. long_sents.append(short_sents)
  14. short_sents = []
  15. offset_begin = i+1
  16. else:
  17. pass
  18. if offset_begin != len(text):
  19. short_sents.append(text[offset_begin:])
  20. if short_sents:
  21. long_sents.append(short_sents)
  22. return long_sents
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement