中文分词处理源代码C++备课讲稿.docVIP

中文分词处理源代码C++ 精品文档 精品文档 收集于网络，如有侵权请联系管理员删除 收集于网络，如有侵权请联系管理员删除 精品文档 收集于网络，如有侵权请联系管理员删除 #include fstream #include vector #include string #include iostream using namespace std; const int START1 = 0XB0,START2 = 0XA1, END1 = 0XF8,END2 = 0XFF; const int MAXWORDLEN = 48; ifstream fin(segdict.txt); ofstream out(out1.txt); //--------------------- 建树部分---------------------- struct Node3 { string S; bool IsWord; Node3 *L,*R; Node3(string s = ,bool isWord = 0, Node3 *l = 0, Node3 *r = 0): S(s),IsWord(isWord),L(l),R(r){} }; struct Node2 { string S; bool IsWord; Node3 *Child; Node2(string s =,bool isWord = 0, Node3* child =0): S(s),IsWord(isWord),Child(child){} }; struct Node { string S; vectorNode2v; }; vectorNodeDic; int HASH[END1 - START1][END2 - START2]; void Begin() //初始化 { for (int i = 0; i END1- START1; i++) for (int j = 0;j END2 - START2; j++) HASH[i][j] = -1; } void BuildTree(string s, Node3 *child) { int len = s.length(); string t = s.substr(0,2); Node3 *LAST = child; if (child == 0) LAST = child = new Node3(t, (len == 2),0,0); else { while (LAST-L != 0) LAST = LAST-L; if (LAST-S != t) { LAST-L = new Node3(t,(len == 2),0, 0); LAST = LAST-L; } } if (len 2) BuildTree(s.substr(2,MAXWORDLEN),LAST-R); } void Dictionary() //构造整个结构 { Begin(); string s; int N,k = 0; while(fin s) { Node n; n.S = s.substr(0,2); int m1 = (unsigned char)s[0] - START1; int m2 = (unsigned char)s[1] - START2; HASH[m1][m2] = k++; out s HASH[m1][m2] endl; fin N; out N endl; for (int i = 0; i N; i++) { fin s; out s endl; string t = s.substr(2,2); int LEN = s.length(); int SIZE = n.v.size(); int Len = s.length();