def split_zh_en (zh_en_str):
tokenizer = Tokenizer()
mark = {"en":1, "zh":2}
zh_en_group = []
zh_set = []
en_set = []
status = ""
en = ""
zh = ""
for c in zh_en_str:
if tokenizer.is_zh(c):
if status == 'en':
zh_en_group.append ([mark["en"], ''.join(en_set)])
en += ''.join(en_set)
en_set = []
zh_set.append(c)
status = 'zh'
else:
if status == 'zh':
zh_en_group.append ([mark["zh"], ''.join(zh_set)])
zh += ''.join(zh_set)
zh_set = []
en_set.append(c)
status = 'en'
if en_set:
zh_en_group.append ([mark["en"], ''.join(en_set)])
en += ''.join(en_set)
elif zh_set:
zh_en_group.append ([mark["zh"], ''.join(zh_set)])
zh += ''.join(zh_set)
if en == "":
print 'error'
return zh_en_group, en, zh
def split_zh_en(zh_en_str):
tokenizer = Tokenizer()
mark = {"en": 1, "zh": 2}
zh_en_group = []
zh_set = []
en_set = []
status = ""
en = ""
zh = ""
for c in zh_en_str:
if tokenizer.is_zh(c):
if status == 'en':
zh_en_group.append([mark["en"], ''.join(en_set)])
en += ''.join(en_set)
en_set = []
zh_set.append(c)
status = 'zh'
else:
if status == 'zh':
zh_en_group.append([mark["zh"], ''.join(zh_set)])
zh += ''.join(zh_set)
zh_set = []
en_set.append(c)
status = 'en'
if en_set:
zh_en_group.append([mark["en"], ''.join(en_set)])
en += ''.join(en_set)
elif zh_set:
zh_en_group.append([mark["zh"], ''.join(zh_set)])
zh += ''.join(zh_set)
if en == "":
print 'error'
return zh_en_group, en, zh
