tut01-lesson5-unicode.py

# -*- coding: utf-8 -*-
import re
import unicodedata

def normalize_unicode_to_ascii(data):
    normal = unicodedata.normalize('NFKD', data).encode('ASCII', 'ignore')
    val = normal.decode("utf-8")
    val = val.lower()
    # remove special characters
    val = re.sub('[^A-Za-z0-9 ]+', ' ', val)
    # remove multiple spaces
    val = re.sub(' +', ' ', val)
    return val

def sort_words(words):
    words = words.split(" ")
    words.sort()
    newSentence = " ".join(words)
    return newSentence