一个库的基本方法可以写在以库名为名字的文件夹下的init.py里
比如,只要import jieba
就可以用init.py里的cut方法
用法是:
a = jieba.cut("")
def cut(self, sentence, cut_all=False, HMM=True):
'''
The main function that segments an entire sentence that contains
Chinese characters into seperated words.
Parameter:
- sentence: The str(unicode) to be segmented.
- cut_all: Model type. True for full pattern, False for accurate pattern.
- HMM: Whether to use the Hidden Markov Model.
'''
sentence = strdecode(sentence)
if cut_all:
re_han = re_han_cut_all
re_skip = re_skip_cut_all
else:
re_han = re_han_default
re_skip = re_skip_default
if cut_all:
cut_block = self.__cut_all
elif HMM:
cut_block = self.__cut_DAG
else:
cut_block = self.__cut_DAG_NO_HMM
blocks = re_han.split(sentence)
for blk in blocks:
if not blk:
continue
if re_han.match(blk):
for word in cut_block(blk):
yield word
else:
tmp = re_skip.split(blk)
for x in tmp:
if re_skip.match(x):
yield x
elif not cut_all:
for xx in x:
yield xx
else:
yield x