FMM算法 分词

FMM算法的最简单思想是使用贪心算法向前找n个，如果这n个组成的词在词典中出现，就ok，如果没有出现，那么找n-1个...然后继续下去。假如n个词在词典中出现，那么从n+1位置继续找下去，知道句子结束。

标签：  Python

代码片段(3)

[代码] [Python]代码

01 import re
02 def PreProcess(sentence,edcode="utf-8"):
03     sentence = sentence.decode(edcode)
04     sentence=re.sub(u"[。，,！……!《》<>/"':：？/?、/|“”‘’；]"," ",sentence)
05     return sentence
06
07 def FMM(sentence,diction,result = [],maxwordLength = 4,edcode="utf-8"):
08     i = 0
09     sentence = PreProcess(sentence,edcode)
10     length = len(sentence)
11     while i < length:
12         # find the ascii word
13         tempi=i
14         tok=sentence[i:i+1]
15         while re.search("[0-9A-Za-z/-/+#@_/.]{1}",tok)<>None:
16             i= i+1
17             tok=sentence[i:i+1]
18         if i-tempi>0:
19             result.append(sentence[tempi:i].lower().encode(edcode))
20         # find chinese word
21         left = len(sentence[i:])
22         if left == 1:
23             """go to 4 step over the FMM"""
24             """should we add the last one? Yes, if not blank"""
25             if sentence[i:] <> " ":
26                 result.append(sentence[i:].encode(edcode))
27             return result
28         m = min(left,maxwordLength)
29
30         for j in xrange(m,0,-1):
31             leftword = sentence[i:j+i].encode(edcode)
32          #   print leftword.decode(edcode)
33             if LookUp(leftword,diction):
34                 # find the left word in dictionary
35                 # it's the right one
36                 i = j+i
37                 result.append(leftword)
38                 break
39             elif j == 1:
40                 """only one word, add into result, if not blank"""
41                 if leftword.decode(edcode) <> " ":
42                     result.append(leftword)
43                 i = i+1
44             else:
45                 continue
46     return result
47 def LookUp(word,dictionary):
48     if dictionary.has_key(word):
49         return True
50     return False
51 def ConvertGBKtoUTF(sentence):
52     return sentence.decode('gbk').encode('utf-8')

[代码] [Python]代码

01 dictions = {}
02 dictions["ab"] = 1
03 dictions["cd"] = 2
04 dictions["abc"] = 1
05 dictions["ss"] = 1
06 dictions[ConvertGBKtoUTF("好的")] = 1
07 dictions[ConvertGBKtoUTF("真的")] = 1
08 sentence = "asdfa好的是这样吗vasdiw呀真的daf dasfiw asid是吗？"
09 s = FMM(ConvertGBKtoUTF(sentence),dictions)
10 for i in s:
11     print i.decode("utf-8")

[代码] [Python]代码

1 test = open("test.txt","r")
2 for line in test:
3     s = FMM(CovertGBKtoUTF(line),dictions)
4     for i in s:
5         print i.decode("utf-8")