clean text (needs homogenize)

clean.py

def clean(sentence):
  stopchars = ['.', ',', '?', '!', '"', '-']
	gain = []
	sentence = sentence.lower()
	for char in stopchars:
		sentence = sentence.replace(char,' ')

	words = sentence.split(' ')
	for word in words:
		if word <> '':
			gain.append(homogenize(word.decode('utf-8')))
	return gain