半岛权威十大直营(官方)网站

#include <stdio.h>
#include <string>
#include <set>
using namespace std;
set<string> g_setWordDictionary;

int construct()
{
g_setWordDictionary.insert("中国");
g_setWordDictionary.insert("中国人");
g_setWordDictionary.insert("纽约");
g_setWordDictionary.insert("北京");
}

bool match(string &word)
{
set<string>::iterator itor = g_setWordDictionary.find(word);
if (itor == g_setWordDictionary.end())
{
return false;
}

return true;
}

void forward_maximum_matching(string content, set<string> &keywords)    
{
#define MAX_LEN 12      //词库中最长词语(utf-8一个汉字3个字节)
#define MIN_LEN 3       //单字(原理同上)
int len = content.length();
int right_len = len;
int start_pos = 0;
bool ret = false;
string kw_value = "";
int kw_len = 0;
int kw_pos = 0;
//单字或空串
while (right_len > MIN_LEN)
{
//语句大于词库中最长词语
if (right_len >= MAX_LEN)
{
kw_value = content.substr(start_pos, MAX_LEN);
}
//语句小于词库中最长词语
else
{
kw_value = content.substr(start_pos, right_len);
}

//词库匹配
ret = match(kw_value);
kw_len = kw_value.length();
kw_pos = 0;
while (!ret && kw_len > 2*MIN_LEN)
{
//去掉候选词右边一个汉字
kw_len -= MIN_LEN;
kw_value = kw_value.substr(kw_pos, kw_len);
//继续匹配
ret = match(kw_value);
}

//匹配到词
if (ret)
{
keywords.insert(kw_value);
//从语句中去掉匹配到的词
start_pos += kw_len;
right_len = len - start_pos;
}
//未匹配到词，下移一个字
else
{
start_pos += MIN_LEN;
right_len = len - start_pos;
}
}//while (right_len > MIN_LEN)      
}

int main()
{
//构造词库
construct();

//切分词库
string content = "我是中国人，我是来自中国北京的中国人，在纽约工作";
set<string> keywords;
forward_maximum_matching(content, keywords);
set<string>::iterator itor;

//输出分词
for (itor=keywords.begin(); itor!=keywords.end(); ++itor)
{
printf("result: %s\n", (*itor).c_str());
}

return 0;
}