我正在使用来自这个 kaggle 的干净数据集，用于一个学校项目，我必须用 c++ 编写代码来对数据进行排序，并允许我对数据进行统计分析。https://www.kaggle.com/dat...

我正在使用来自这个 kaggle 的干净数据集，用于一个学校项目，我必须用 c++ 编写代码来对数据进行排序并允许我对数据进行统计分析。

https://www.kaggle.com/datasets/elvinrustam/ebay-laptops-and-netbooks-sales/data

我尝试了很多次，但似乎还是搞不清楚如何使用 c++ 忽略数据中的逗号和随机引号。我尝试将每个标题的数据存储到一个向量中，以便之后可以对数据进行操作，但当我打印数据时，我发现数据集中混杂了其他数据，还有随机逗号、括号、长文本等。

#include <iostream>
#include <fstream>
#include <sstream>
#include <vector>
#include <string>
#include <set>

std::vector<std::string> parseCSVLine(const std::string& line) {
    std::vector<std::string> result;
    std::string cell;
    bool inQuotes = false;
    bool inBulletPoint = false; // New flag to track when we're within a bullet point
    for (auto it = line.begin(); it != line.end(); ++it) {
        const char nextChar = *it;

        // Check for bullet points
        if (!inQuotes && *it == '•') {
            inBulletPoint = true; // We're now inside a bullet point
            cell += nextChar; // Add the bullet point character to the cell
            continue;
        }

        // If we're in a bullet point, check for the end of the line or a comma (end of cell)
        if (inBulletPoint && (nextChar == ',' || it == line.end() - 1)) {
            inBulletPoint = false; // Exiting bullet point mode
            if (nextChar != ',') {
                cell += nextChar; // Ensure last character is included if not a comma
            }
            result.push_back(cell);
            cell.clear();
            continue;
        }
        else if (inBulletPoint) {
            // Simply add the character to the cell without interpreting it
            cell += nextChar;
            continue;
        }

        // Handle quotes (outside of bullet points)
        if (nextChar == '"') {
            if (inQuotes && (it + 1 != line.end()) && (*(it + 1) == '"')) {
                cell += nextChar; // Add a single quote to the cell value
                ++it; // Skip the next quote
            }
            else {
                inQuotes = !inQuotes;
            }
        }
        else if (nextChar == ',' && !inQuotes) {
            result.push_back(cell);
            cell.clear();
        }
        else {
            cell += nextChar;
        }
    }
    // Only check the last character if the line is not empty
    if (!cell.empty() || (!line.empty() && line.back() == ',')) {
        result.push_back(cell);
    }


    return result;
}

int main() {
    std::string filePath = "insert file path here";
    std::ifstream file(filePath);
    if (!file.is_open()) {
        std::cerr << "Failed to open file: " << filePath << std::endl;
        return 1;
    }

    std::string line;
    std::vector<std::string> headers;
    std::vector<std::vector<std::string>> columnData;

    if (getline(file, line)) {
        headers = parseCSVLine(line);
        columnData.resize(headers.size());
    }

    while (getline(file, line)) {
        auto data = parseCSVLine(line);
        for (size_t i = 0; i < data.size() && i < columnData.size(); ++i) {
            columnData[i].push_back(data[i]);
        }
    }

    file.close();

    //// Example output: Printing unique values for each heading for verification
    //for (size_t i = 0; i < headers.size(); ++i) {
    //    std::set<std::string> uniqueValues(columnData[i].begin(), columnData[i].end());
    //    std::cout << "Heading: " << headers[i] << " - Unique Values: " << uniqueValues.size() << std::endl;
    //    for (const auto& value : uniqueValues) {
    //        std::cout << value << std::endl;
    //    }
    //    std::cout << std::endl;
    //}


    // Make sure to define and fill 'columnData' and 'headers' as per your CSV parsing logic before this snippet

    // Here, the index is set to 2 since vector indices are 0-based and we want the third column (heading 3)
    size_t index = 2;

    // Check if the index is within the bounds of the 'columnData' vector
    if (index < columnData.size()) {
        std::cout << "Values under Heading 3 (" << headers[index] << "):" << std::endl;

        // Iterate over the vector at the given index and print each value
        for (const auto& value : columnData[index]) {
            std::cout << value << std::endl;
        }
    }
    else {
        std::cerr << "Index out of range. The columnData does not have a heading 3." << std::endl;
    }

    return 0;
}