"
#chinese = "\n".join([item for item in jieba.cut(chinese) i"
#chinese = "\n".join([item for item in jieba.cut(chinese) if item not in stoplionary])
english = "Introduce the movie"
english = ' '.join([item for item in nltk.word_tokenize(english.lower()) if item not in stopwords])
print(chinese)
print(english)
test = ChineseToGermanChn(chinese.lower())
# test = GermanToChineseEng(test)
# class ChineseToChinese(BaseTransformer):
# def __init__(self):
# self.obj = self
# super().__init__()
#
# def fit(self, X, y=None):
# return self
#
# def transform(self, X):
# return X
# test = ChineseToChinese().fit_transform(test)
english = ' '.join([item for item in nltk.word_tokenize(english.lower()) if item not in stopwords])
print(len(test))
print(len(english.split(' ')))
gd = GermanToEnglish().fit_transform([test])
# print(gd)
# print([i for i in gd])
# print([i for i in gd[0]])
# print([j for j in gd[0][0]])
print(gd[0][0])
print(english)
# RichTextWidget(gd[0][0])
# sequence = Sequence(maxlen=10000)
# for i in range(len(gd)):
# for j in gd[i][0]:
# sequence.add(j)
# for i in english:
# sequence.add(i)
# sequence.save("data/input")
# sequence = Sequence().load("data/input")
#
# # token2idx, _, _ = sequence.vocb_parser()
# print(token2idx[','])
# print(token2idx[','])
# print(token2idx[','])
# print(token2idx['.'])
# print(token2idx['-'])
# print(len(token2idx.keys()))
# print(token2idx)
# print(gd[0][0])
# print(english)
# batch = sequence.tranform(gd[0][0], batchsize=2)
# print(batch)详情
