如何使用向量c ++迭代文件中单词的位置

Question

我必须阅读dictionary.txt和test.txt。然后，必须检查test.txt中的每个单词，如果它相等，那么这个单词将被添加到KnownWords容器中，剩下的将在UnknownWords容器中。我到目前为止所做的一切。但是，在功能DisplayKnownWordStats()我也必须显示单词的位置。我尝试了以下代码，但它没有给我正确的位置值。

有人可以帮助我从KnownWords获得test.txt的正确位置。

void WordStats::ReadTxtFile()
{
    std::ifstream ifile(Filename);
    if (!ifile)
    {
        std::cerr << "Error Opening file " << Filename << std::endl;
        exit(1);
    }
    for (std::string word; ifile >> word; )
    {
        transform(word.begin(), word.end(), word.begin(), ::tolower);
        WordMap & Words = (Dictionary.count(word) ? KnownWords : UnknownWords);
        Words[word].push_back(ifile.tellg());
    }
    std::cout << KnownWords.size() << " known words read." << std::endl;
    std::cout << UnknownWords.size() << " unknown words read." << std::endl;
}

// Displays stats of words in KnownWords
void WordStats::DisplayKnownWordStats()
{
    cout << "            ";
    cout << "    Word     Count      Position(s)\n";
    for (Paragraph = KnownWords.begin(); Paragraph != KnownWords.end(); ++Paragraph)
    {
        string word = (*Paragraph).first;
        vector<int> vect = (*Paragraph).second;
        int cnt = vect.size();
        cout << setw(15) << word << setw(10) << cnt << "   ";
        for (int i = 0; i<cnt; i++)
            cout << vect[i] << ' ';   // something wrong with this code
        cout << endl;
    }
}

Answer 1

void WordStats::ReadTxtFile(){

int pos=-1;
string word;

std::ifstream ifile(Filename);
if(!ifile)
{
    std::cerr << "Error Opening file " << Filename << std::endl;
    exit(1);
}
for (std::string word; ifile >> word;  )
{
    transform (word.begin(), word.end(), word.begin(), ::tolower);
    word.erase(std::remove_if(word.begin(), word.end(), [](char c)
    {
        return (c < 'a' || c > 'z') && c != '\'' ;

    }),  word.end());
    if (word == "") continue;
    pos++;
    if (Dictionary.find(word) != Dictionary.end())
    {
        Paragraph = KnownWords.find(word);            //adding word to the knownWords
        if (Paragraph != KnownWords.end())
        {
            Paragraph->second.push_back(pos);         //adding position of the word
        }         
        else 
        {
            KnownWords[word] = vector<int>(1, pos);   //adding record which is new
        }
    }
    else
    {
        Paragraph = UnknownWords.find(word);            //adding word to the knownWords
        if (Paragraph != UnknownWords.end())
        {
            Paragraph->second.push_back(pos);          //adding position of the word
        }         
        else 
        {
            UnknownWords[word] = vector<int>(1, pos);   //adding record which is new
        }
    }

}
cout << KnownWords.size() << " known words read." << endl;
cout << UnknownWords.size() << " unknown words read." << endl;
}


void WordStats::DisplayKnownWordsStats()
{
vector<int>::iterator v;
cout << "\n";
cout << setw(22) << "Word" << setw(12) << "Count" << setw(20) << "Position(s)"     << endl;
for (Paragraph = KnownWords.begin(); Paragraph != KnownWords.end(); Paragraph++) 
{
    string word = (*Paragraph).first;                   
    vector<int> vect = (*Paragraph).second;
    int count = vect.size();
    cout << setw(22) << word << setw(9) << count ;
    cout << "            ";
    for ( v = vect.begin(); v < vect.end(); v++)
    {
        cout << *v << " ";
    }   
    cout << endl;
}
cout << "\n";
}

Answer 2

Words[word].push_back(ifile.tellg());

以上ifile.tellg()在一个单词后面返回一个位置。例如，如果文件包含单词“word”，则从文件中读取第一个单词，然后ifile.tellg()返回4.看起来您希望位置0在那里。你应该像下面这样做：

Words[word].push_back(ifile.tellg() - word.size());