自顶向下学搜索引擎——北大天网搜索引擎TSE分析及完全注释[6]倒排索引的建立的程序分析(4)

自顶向下学搜索引擎——北大天网搜索引擎TSE分析及完全注释[6]倒排索引的建立的程序分析(4)

以下是根据正向索引建立倒排索引的注释

 

int main(int argc, char* argv[])    //./CrtInvertedIdx moon.fidx.sort > sun.iidx
{
    ifstream ifsImgInfo(argv[1]);
    if (!ifsImgInfo) 
    {
        cerr << "Cannot open " << argv[1] << " for input\n";
        return -1;
    }

    string strLine,strDocNum,tmp1="";
    int cnt = 0;
    while (getline(ifsImgInfo, strLine)) 
    {
        string::size_type idx;
        string tmp;

        idx = strLine.find("\t");
        tmp = strLine.substr(0,idx);

        if (tmp.size()<2 || tmp.size() > 8) continue;

        if (tmp1.empty()) tmp1=tmp;

        if (tmp == tmp1) 
        {
            strDocNum = strDocNum + " " + strLine.substr(idx+1);
        }
        else 
        {
            if ( strDocNum.empty() )
                strDocNum = strDocNum + " " + strLine.substr(idx+1);

            cout << tmp1 << "\t" << strDocNum << endl;
            tmp1 = tmp;
            strDocNum.clear();
            strDocNum = strDocNum + " " + strLine.substr(idx+1);
        }

        cnt++;
        //if (cnt==100) break;
    }
    cout << tmp1 << "\t" << strDocNum << endl;  //倒排索引中每个字典单词后的文档编号以table键为间隔

    return 0;
}