TwitterHaikuBot/sentences.py at master · cannedtomatoes/TwitterHaikuBot · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
# This code by D Greenberg from https://stackoverflow.com/a/31505798
import re

caps = "([A-Z])"
prefixes = "(Mr|St|Mrs|Ms|Dr)[.]"
suffixes = "(Inc|Ltd|Jr|Sr|Co)"
starters = "(Mr|Mrs|Ms|Dr|He\s|She\s|It\s|They\s|Their\s|Our\s|We\s|But\s|However\s|That\s|This\s|Wherever)"
acronyms = "([A-Z][.][A-Z][.](?:[A-Z][.])?)"
websites = "[.](com|net|org|io|gov)"


def split_into_sentences(text):
	text = " " + text + "  "
	text = text.replace("\n", " ")
	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" + caps + "[.] ", " \\1<prd> ", text)
	text = re.sub(acronyms + " " + starters, "\\1<stop> \\2", text)
	text = re.sub(caps + "[.]" + caps + "[.]" + caps + "[.]", "\\1<prd>\\2<prd>\\3<prd>", text)
	text = re.sub(caps + "[.]" + caps + "[.]", "\\1<prd>\\2<prd>", text)
	text = re.sub(" " + suffixes + "[.] " + starters, " \\1<stop> \\2", text)
	text = re.sub(" " + suffixes + "[.]", " \\1<prd>", text)
	text = re.sub(" " + caps + "[.]", " \\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