最大匹配演算法

最大匹配法是最簡單的分詞方法，他完全使用詞典進行分詞，如果詞典好，則分詞的效果好

正向，即從左往右進行匹配

#maximum match method 最大匹配法

class mm:
def __init__(self):
self.window_size = 4
def cut(self,text):
result = 
index = 0
text_lenght = len(text)
#研究生命的起源
dic = ["研究","研究生","生命"]
while text_lenght >index:
#range(3,0,-1)
for size in range(min(self.window_size+index,text_lenght),index,-1):
piece = text[index:size]
print("size:", size,piece)
if piece in dic:
index = size-1
break
index = index+1 #第一次結束index = 3
print(result)
return result

逆向即從右往左進行匹配

#rmm:reverse maxmium match method 逆向最大匹配

class rmm:
def __init__(self):
self.window_size = 3
def cut(self,text):
result = 
index = len(text)
#研究生命的起源
dic = ["研究","研究生","生命"]
while index>0:
for size in range(max((index-self.window_size),0),index):
piece = text[size:index]
print("size:", size,piece)
if piece in dic:
index = size+1
print("index:", index)
break
print("index:",index)
index = index - 1
result.reverse()
print(result)
return result

同時根據正向和逆向的結果，進行匹配

class mcut():

def __init__(self):
self.mm = mm()
self.rmm = rmm()
def cut(self,sentence):
"""1. 詞語數量不相同，選擇分詞後詞語數量少的
2. 如果詞語數量相同，返回單字數量少的
"""mm_ret = self.mm.cut(sentence)
rmm_ret = self.rmm.cut(sentence)
if len(mm_ret)==len(rmm_ret):
mm_ret_signle_len = len([i for i in mm_ret if len(i)==1])
rmm_ret_signle_len = len([i for i in rmm_ret if len(i)==1])
return mm_ret if rmm_ret_signle_len>mm_ret_signle_len else rmm_ret
else:
return mm_ret if len(mm_ret)