Question

我是一名初学c ++学生，我正在尝试编写一个程序，该程序在文件中对单词进行索引并对其进行索引，仅列出每个单词一次，并显示每次单词出现时的行号。我试过使用地图，但我发现无法获得单词的行号。相反，我使用的结构向量具有整数向量和每个单词的字符串。我试图读取每个单词，将其放入stringstream，然后将其输出到struct中的字符串中。然后我将行号和push_back引入结构中的向量中。然后我将所有内容保存到结构的向量中，并尝试打印出与行号向量相关联的每个单词。我无处可去，希望得到一些帮助。非常感谢！这是我的源代码：

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



 struct words {
 vector<int> lineNumbers;
 string word;

};

int main() {
ifstream inFile, testStream;
ofstream outFile; 
string temp, choice, inFileName, outFileName, word, trash, word2, tempString; 
int idx = 0, count = 0, idxTwo = 0;
bool outputOpened = false;
//map <string,int> wordList;    
/map <string,int>::iterator wordIt;     
stringstream myStream(ios_base::in| ios_base::out); 

vector<words> myIndex; 
words data; 



for (;;) {  
    cout << "Options: "<< endl << "1. Index" << endl << "2. Quit" << endl 
    << "Please enter an option: ";
    getline(cin, temp);
    //cin >> temp;
    //cin.ignore(8192, '\n');
    choice.resize(temp.length());
    transform(temp.begin(), temp.end(), choice.begin(), ::toupper);
    if (choice.compare("INDEX") == 0 || choice.compare("1") == 0) {
        do {
            inFileName.clear();
            cout << "Index Program" << endl
            << "==============" << endl << endl;
            cout << "Input file name: ";
            getline(cin, inFileName);
            inFile.open(inFileName.c_str());
            if(inFile.fail()) {
                cout << "Can't open file" << endl;
                if(inFile.bad()) {
                    cout << "Bad" << endl;
                }
                inFile.clear();
            }
        }
        while (!inFile.is_open());
        do {
            cout << "Output file name: ";
            getline( cin, outFileName);
            testStream.clear();
            testStream.open(outFileName.c_str());
            if(testStream.good()) {
                cout << "That file already exists, try again" <<         endl;
                testStream.clear();
                testStream.close();
            }
            else {
                testStream.clear();
                testStream.close();
                outFile.open(outFileName.c_str());
                if (outFile.good()) {
                    outputOpened = true;
                }
            }
        }
        while (!outputOpened);

        while (getline(inFile, trash)){

            count++;
            myStream << trash; 
            //myStream >> tempString; 

            while(myStream >> data.word) {

                data.lineNumbers.push_back(count);
                myIndex.push_back(data);
            }
        }
        for (idx = 0; idx < myIndex.size(); idx++) {
            outFile << "Word: "<< " "<< myIndex[idx].word << ", ";
            for (idxTwo = 0; idxTwo < myIndex[idx].lineNumbers.size(); idxTwo++) {
                outFile << "Found on lines " << " " << myIndex[idx].lineNumbers[idxTwo];
            }
        }
        inFile.close();
        outFile.close();
    }
    else if (choice.compare("QUIT") == 0 || choice.compare("2") == 0) {
        return 0;
    }
    else {
        cout << temp << " is an unrecognized option, please try again" << endl;
    }
}
return 0;

}

Answer 1

对于这部分程序：

    while (getline(inFile, trash)){
        count++;
        myStream << trash; 
        //myStream >> tempString; 
        while(myStream >> data.word) {
            // 2.
            // data.lineNumbers.clear();
            data.lineNumbers.push_back(count);
            myIndex.push_back(data);
        }
        // 1. add:
        // myStream.clear();
    }

您正在使用全局myStream。但是，处理完每一行后，myStream的状态将处于不良状态，因为数据耗尽。国家已被清除，以便再次运作。
data也是全局的，它会将每个单词的行号保存在data.lineNumber中，而不仅仅是当前单词的行号。您可能希望在每次运行时清除它。

Answer 2

您的问题似乎是，您始终将每个单词附加到vector<words>。

你可能想要的是map<string, vector<int>>。使用.insert将单词插入到集合中，如果它已经存在，则只需将当前行号附加到该值。

Answer 3

以下是一些问题：

在myStream.clear();循环后添加while(myStream >> data.word)。

将“\ n”添加到以下行的末尾以在新行上打印：

outFile << "Found on lines " << " " << myIndex[idx].lineNumbers[idxTwo]<<"\n";

此外，以下嵌套循环不会给您正确的结果。它将随行号增长并继续打印“在线上找到”：

for (idx = 0; idx < myIndex.size(); idx++) {
outFile << "Word: "<< " "<< myIndex[idx].word << ", ";
  for (idxTwo = 0; idxTwo < myIndex[idx].lineNumbers.size(); idxTwo++) {
     outFile << "Found on lines " << " " << myIndex[idx].lineNumbers[idxTwo]<<"\n";
    }

矢量和字符串的结构不能正确打印

3 个答案: