import jieba

import jieba.posseg as psg

from os import path

from collections import Counter

s=u'我想和女朋友一起去北京天安门闲逛。。'

cut = jieba.cut(s)

print('精确模式')

print(cut)

print(','.join(cut))

print ('全模式')

print(','.join(jieba.cut(s,cut_all = True)))

print('搜索引擎模式')

print(','.join(jieba.cut_for_search(s)))

print('词性')

print([(x.word,x.flag) for x in psg.cut(s)])

print([(x.word,x.flag) for x in psg.cut(s) if x.flag.startswith('n')])

print('--*--'*10)

seg_list = jieba.cut("我来到北京清华大学", cut_all=True)

print("Full Mode:", "/ ".join(seg_list)) # 全模式

seg_list = jieba.cut("我来到北京清华大学", cut_all=False)

print("Default Mode:", "/ ".join(seg_list))  # 精确模式

seg_list = jieba.cut("他来到了网易杭研大厦")  # 默认是精确模式

print(", ".join(seg_list))

seg_list = jieba.cut_for_search("小明硕士毕业于中国科学院计算所，后在日本京都大学深造")  # 搜索引擎模式

print(", ".join(seg_list))

d=path.dirname(__file__)

sanguo_text=open(path.join(d,"data//sanguo.txt"),encoding='utf-8').read()

print(len(sanguo_text))

sanguo_words = [x for x in jieba.cut(sanguo_text) if len(x) >= 2]

c = Counter(sanguo_words).most_common(20)

print(c)