（待扩展）读取一个文件统计词频

#include<iostream>
#include<fstream>
#include<string>
#include<map>
#include<set>
using namespace std;

int main()
{
    map<string,int>word_count;
  //  set<string>exclude={"the","a","but","an","and","or",
  //                         "The","A","An","But","And","Or"};
    string buff;
    string filename;
    cout<<"Input file name: "<<endl;
    cin>>filename;
    ifstream fin(filename.c_str());

    while(fin>>buff)
    {
      //  if(exclude.find(word)==exclude.end())
            word_count[buff]++;
    }
    fin.close();
    map<string,int>::iterator iter;

    for(iter=word_count.begin();iter!=word_count.end();iter++)
        cout<<(*iter).first<<" occurs"<<(*iter).second<<(((*iter).second>1)?" times":" time")<<endl;
    return 0;

}

待扩展：
1.忽略大小写
2.词根提取，也就是忽略不同时态等差别
3.按出现次数排序
4.可识别中文