PYTHON

python sentence splitter

# -*- coding: utf-8 -*-
import re
alphabets= "([A-Za-z])"
prefixes = "(Mr|St|Mrs|Ms|Dr)[.]"
suffixes = "(Inc|Ltd|Jr|Sr|Co)"
starters = "(Mr|Mrs|Ms|Dr|Hes|Shes|Its|Theys|Theirs|Ours|Wes|Buts|Howevers|Thats|Thiss|Wherever)"
acronyms = "([A-Z][.][A-Z][.](?:[A-Z][.])?)"
websites = "[.](com|net|org|io|gov)"

def split_into_sentences(text):
    text = " " + text + "  "
    text = text.replace("
"," ")
    text = re.sub(prefixes,"1<prd>",text)
    text = re.sub(websites,"<prd>1",text)
    if "Ph.D" in text: text = text.replace("Ph.D.","Ph<prd>D<prd>")
    text = re.sub("s" + alphabets + "[.] "," 1<prd> ",text)
    text = re.sub(acronyms+" "+starters,"1<stop> 2",text)
    text = re.sub(alphabets + "[.]" + alphabets + "[.]" + alphabets + "[.]","1<prd>2<prd>3<prd>",text)
    text = re.sub(alphabets + "[.]" + alphabets + "[.]","1<prd>2<prd>",text)
    text = re.sub(" "+suffixes+"[.] "+starters," 1<stop> 2",text)
    text = re.sub(" "+suffixes+"[.]"," 1<prd>",text)
    text = re.sub(" " + alphabets + "[.]"," 1<prd>",text)
    if "”" in text: text = text.replace(".”","”.")
    if """ in text: text = text.replace("."","".")
    if "!" in text: text = text.replace("!"",""!")
    if "?" in text: text = text.replace("?"",""?")
    text = text.replace(".",".<stop>")
    text = text.replace("?","?<stop>")
    text = text.replace("!","!<stop>")
    text = text.replace("<prd>",".")
    sentences = text.split("<stop>")
    sentences = sentences[:-1]
    sentences = [s.strip() for s in sentences]
    return sentences

python sentence splitter

>>> from nltk import tokenize
>>> p = "Good morning Dr. Adams. The patient is waiting for you in room number 3."

>>> tokenize.sent_tokenize(p)
['Good morning Dr. Adams.', 'The patient is waiting for you in room number 3.']