使用亚洲字符的FuzzyWuzzy搜索

Question

以下来自善良撒玛利亚人的代码-很好地使用英语，可以在大型文档中找到文本字符串，并对其匹配程度充满信心

但无法弄清楚如何使用泰语字符

#!/usr/bin/python

from difflib import SequenceMatcher as SM
from nltk.util import ngrams
import codecs


with open('mainEN.txt', 'r') as hay_file:
    hay = hay_file.read()

with open('searchEN.txt', 'r') as needle_file:
    needle = needle_file.read()

needle_length  = len(needle.split())
max_sim_val    = 0
max_sim_string = u""

for ngram in ngrams(hay.split(), needle_length + int(.2*needle_length)):
    hay_ngram = u" ".join(ngram)
    similarity = SM(None, hay_ngram, needle).ratio() 
    if similarity > max_sim_val:
        max_sim_val = similarity
        max_sim_string = hay_ngram

print max_sim_val, max_sim_string