[kovidgoyal]

Since I'm on a roll here's one for HTML it might need a little adjustment

import re
from hyphenate import hyphenate_word as hyphenate

def process_text(match):
    src = match.group(1)
    return re.sub('\S+', lambda match : u'\u00ad'.join(hyphenate(match.group())), src)

src = open('file', 'rb').read()
result = re.sub(r'>([^><]+)<', process_text, src)