'''
Created on Jun 29, 2017

@author: David
'''
import codecs
import pickle

list_file = "f:/parll data/data/suffix_tfidf.dist"
outfile_name = "f:/parll data/data/suffixes.pickle"

elems = []

with codecs.open(list_file, "r", encoding="utf-8") as f:
    for l in f:
        elems.append(l.split("\t")[0])
        
pickle.dump(elems, open(outfile_name, "wb"))