我需要在c++中加载和使用CSV文件数据。在这一点上,它实际上只是一个以逗号分隔的解析器(即不用担心转义新行和逗号)。主要需要的是逐行解析器,它将在每次调用方法时为下一行返回一个向量。

我发现这篇文章看起来很有前途: http://www.boost.org/doc/libs/1_35_0/libs/spirit/example/fundamental/list_parser.cpp

我从未使用过Boost's Spirit,但我愿意尝试一下。但前提是我忽略了一个更直接的解决方案。


当前回答

可以使用std::regex。

根据文件大小和可用内存,可以逐行读取,也可以完全在std::string中读取。

读取文件可以使用:

std::ifstream t("file.txt");
std::string sin((std::istreambuf_iterator<char>(t)),
                 std::istreambuf_iterator<char>());

然后你可以和这个相匹配,它实际上是根据你的需要定制的。

std::regex word_regex(",\\s]+");
auto what = 
    std::sregex_iterator(sin.begin(), sin.end(), word_regex);
auto wend = std::sregex_iterator();

std::vector<std::string> v;
for (;what!=wend ; wend) {
    std::smatch match = *what;
    v.push_back(match.str());
}

其他回答

另一个CSV I/O库可以在这里找到:

http://code.google.com/p/fast-cpp-csv-parser/

#include "csv.h"

int main(){
  io::CSVReader<3> in("ram.csv");
  in.read_header(io::ignore_extra_column, "vendor", "size", "speed");
  std::string vendor; int size; double speed;
  while(in.read_row(vendor, size, speed)){
    // do stuff with the data
  }
}

另一个类似于Loki Astari的答案的解决方案,在c++ 11中。这里的行是给定类型的std::元组。代码扫描一行,然后扫描到每个分隔符,然后将值直接转换并转储到元组中(使用一些模板代码)。

for (auto row : csv<std::string, int, float>(file, ',')) {
    std::cout << "first col: " << std::get<0>(row) << std::endl;
}

优势:

非常干净,使用简单,只有c++ 11。 自动类型转换为std::tuple<t1,…>通过算子>>。

缺少什么:

转义和引用 没有错误处理的情况下畸形的CSV。

主要代码:

#include <iterator>
#include <sstream>
#include <string>

namespace csvtools {
    /// Read the last element of the tuple without calling recursively
    template <std::size_t idx, class... fields>
    typename std::enable_if<idx >= std::tuple_size<std::tuple<fields...>>::value - 1>::type
    read_tuple(std::istream &in, std::tuple<fields...> &out, const char delimiter) {
        std::string cell;
        std::getline(in, cell, delimiter);
        std::stringstream cell_stream(cell);
        cell_stream >> std::get<idx>(out);
    }

    /// Read the @p idx-th element of the tuple and then calls itself with @p idx + 1 to
    /// read the next element of the tuple. Automatically falls in the previous case when
    /// reaches the last element of the tuple thanks to enable_if
    template <std::size_t idx, class... fields>
    typename std::enable_if<idx < std::tuple_size<std::tuple<fields...>>::value - 1>::type
    read_tuple(std::istream &in, std::tuple<fields...> &out, const char delimiter) {
        std::string cell;
        std::getline(in, cell, delimiter);
        std::stringstream cell_stream(cell);
        cell_stream >> std::get<idx>(out);
        read_tuple<idx + 1, fields...>(in, out, delimiter);
    }
}

/// Iterable csv wrapper around a stream. @p fields the list of types that form up a row.
template <class... fields>
class csv {
    std::istream &_in;
    const char _delim;
public:
    typedef std::tuple<fields...> value_type;
    class iterator;

    /// Construct from a stream.
    inline csv(std::istream &in, const char delim) : _in(in), _delim(delim) {}

    /// Status of the underlying stream
    /// @{
    inline bool good() const {
        return _in.good();
    }
    inline const std::istream &underlying_stream() const {
        return _in;
    }
    /// @}

    inline iterator begin();
    inline iterator end();
private:

    /// Reads a line into a stringstream, and then reads the line into a tuple, that is returned
    inline value_type read_row() {
        std::string line;
        std::getline(_in, line);
        std::stringstream line_stream(line);
        std::tuple<fields...> retval;
        csvtools::read_tuple<0, fields...>(line_stream, retval, _delim);
        return retval;
    }
};

/// Iterator; just calls recursively @ref csv::read_row and stores the result.
template <class... fields>
class csv<fields...>::iterator {
    csv::value_type _row;
    csv *_parent;
public:
    typedef std::input_iterator_tag iterator_category;
    typedef csv::value_type         value_type;
    typedef std::size_t             difference_type;
    typedef csv::value_type *       pointer;
    typedef csv::value_type &       reference;

    /// Construct an empty/end iterator
    inline iterator() : _parent(nullptr) {}
    /// Construct an iterator at the beginning of the @p parent csv object.
    inline iterator(csv &parent) : _parent(parent.good() ? &parent : nullptr) {
        ++(*this);
    }

    /// Read one row, if possible. Set to end if parent is not good anymore.
    inline iterator &operator++() {
        if (_parent != nullptr) {
            _row = _parent->read_row();
            if (!_parent->good()) {
                _parent = nullptr;
            }
        }
        return *this;
    }

    inline iterator operator++(int) {
        iterator copy = *this;
        ++(*this);
        return copy;
    }

    inline csv::value_type const &operator*() const {
        return _row;
    }

    inline csv::value_type const *operator->() const {
        return &_row;
    }

    bool operator==(iterator const &other) {
        return (this == &other) or (_parent == nullptr and other._parent == nullptr);
    }
    bool operator!=(iterator const &other) {
        return not (*this == other);
    }
};

template <class... fields>
typename csv<fields...>::iterator csv<fields...>::begin() {
    return iterator(*this);
}

template <class... fields>
typename csv<fields...>::iterator csv<fields...>::end() {
    return iterator();
}

我在GitHub上放了一个小的工作示例;我一直用它来解析一些数值数据,它达到了它的目的。

您需要做的第一件事是确保文件存在。来完成 这你只需要尝试打开文件流的路径。在你 打开文件流使用stream.fail()查看它是否如预期的那样工作, 与否。

bool fileExists(string fileName)
{

ifstream test;

test.open(fileName.c_str());

if (test.fail())
{
    test.close();
    return false;
}
else
{
    test.close();
    return true;
}
}

您还必须验证所提供的文件是正确的文件类型。 要做到这一点,您需要查看提供的文件路径直到 您可以找到文件扩展名。一旦你有了文件扩展名,请确保 它是一个。csv文件。

bool verifyExtension(string filename)
{
int period = 0;

for (unsigned int i = 0; i < filename.length(); i++)
{
    if (filename[i] == '.')
        period = i;
}

string extension;

for (unsigned int i = period; i < filename.length(); i++)
    extension += filename[i];

if (extension == ".csv")
    return true;
else
    return false;
}

此函数将返回稍后在错误消息中使用的文件扩展名。

string getExtension(string filename)
{
int period = 0;

for (unsigned int i = 0; i < filename.length(); i++)
{
    if (filename[i] == '.')
        period = i;
}

string extension;

if (period != 0)
{
    for (unsigned int i = period; i < filename.length(); i++)
        extension += filename[i];
}
else
    extension = "NO FILE";

return extension;
}

这个函数实际上会调用上面创建的错误检查,然后解析文件。

void parseFile(string fileName)
{
    if (fileExists(fileName) && verifyExtension(fileName))
    {
        ifstream fs;
        fs.open(fileName.c_str());
        string fileCommand;

        while (fs.good())
        {
            string temp;

            getline(fs, fileCommand, '\n');

            for (unsigned int i = 0; i < fileCommand.length(); i++)
            {
                if (fileCommand[i] != ',')
                    temp += fileCommand[i];
                else
                    temp += " ";
            }

            if (temp != "\0")
            {
                // Place your code here to run the file.
            }
        }
        fs.close();
    }
    else if (!fileExists(fileName))
    {
        cout << "Error: The provided file does not exist: " << fileName << endl;

        if (!verifyExtension(fileName))
        {
            if (getExtension(fileName) != "NO FILE")
                cout << "\tCheck the file extension." << endl;
            else
                cout << "\tThere is no file in the provided path." << endl;
        }
    }
    else if (!verifyExtension(fileName)) 
    {
        if (getExtension(fileName) != "NO FILE")
            cout << "Incorrect file extension provided: " << getExtension(fileName) << endl;
        else
            cout << "There is no file in the following path: " << fileName << endl;
    }
}

就像每个人都把他的解决方案,这里是我的使用模板,lambda和tuple。

它可以将任何具有所需列的CSV转换为tuple的c++向量。

它通过在元组中定义每个CSV行元素类型来工作。

您还需要为每个元素定义std::string到类型转换Formatter lambda(例如使用std::atod)。

然后你就得到了这个结构的一个向量,对应于你的CSV数据。

您可以很容易地重用它来匹配任何CSV结构。

StringsHelpers.hpp

#include <string>
#include <fstream>
#include <vector>
#include <functional>

namespace StringHelpers
{
    template<typename Tuple>
    using Formatter = std::function<Tuple(const std::vector<std::string> &)>;

    std::vector<std::string> split(const std::string &string, const std::string &delimiter);

    template<typename Tuple>
    std::vector<Tuple> readCsv(const std::string &path, const std::string &delimiter, Formatter<Tuple> formatter);
};

StringsHelpers.cpp

#include "StringHelpers.hpp"

namespace StringHelpers
{
    /**
     * Split a string with the given delimiter into several strings
     *
     * @param string - The string to extract the substrings from
     * @param delimiter - The substrings delimiter
     *
     * @return The substrings
     */
    std::vector<std::string> split(const std::string &string, const std::string &delimiter)
    {
        std::vector<std::string> result;
        size_t                   last = 0,
                                 next = 0;

        while ((next = string.find(delimiter, last)) != std::string::npos) {
            result.emplace_back(string.substr(last, next - last));
            last = next + 1;
        }

        result.emplace_back(string.substr(last));

        return result;
    }

    /**
     * Read a CSV file and store its values into the given structure (Tuple with Formatter constructor)
     *
     * @tparam Tuple - The CSV line structure format
     *
     * @param path - The CSV file path
     * @param delimiter - The CSV values delimiter
     * @param formatter - The CSV values formatter that take a vector of strings in input and return a Tuple
     *
     * @return The CSV as vector of Tuple
     */
    template<typename Tuple>
    std::vector<Tuple> readCsv(const std::string &path, const std::string &delimiter, Formatter<Tuple> formatter)
    {
        std::ifstream      file(path, std::ifstream::in);
        std::string        line;
        std::vector<Tuple> result;

        if (file.fail()) {
            throw std::runtime_error("The file " + path + " could not be opened");
        }

        while (std::getline(file, line)) {
            result.emplace_back(formatter(split(line, delimiter)));
        }

        file.close();

        return result;
    }

    // Forward template declarations

    template std::vector<std::tuple<double, double, double>> readCsv<std::tuple<double, double, double>>(const std::string &, const std::string &, Formatter<std::tuple<double, double, double>>);
} // End of StringHelpers namespace

Main.cpp(一些用法)

#include "StringHelpers.hpp"

/**
 * Example of use with a CSV file which have (number,Red,Green,Blue) as line values. We do not want to use the 1st value
 * of the line.
 */
int main(int argc, char **argv)
{
    // Declare CSV line type, formatter and template type
    typedef std::tuple<double, double, double>                          CSV_format;
    typedef std::function<CSV_format(const std::vector<std::string> &)> formatterT;

    enum RGB { Red = 1, Green, Blue };

    const std::string COLOR_MAP_PATH = "/some/absolute/path";

    // Load the color map
    auto colorMap = StringHelpers::readCsv<CSV_format>(COLOR_MAP_PATH, ",", [](const std::vector<std::string> &values) {
        return CSV_format {
                // Here is the formatter lambda that convert each value from string to what you want
                std::strtod(values[Red].c_str(), nullptr),
                std::strtod(values[Green].c_str(), nullptr),
                std::strtod(values[Blue].c_str(), nullptr)
        };
    });

    // Use your colorMap as you  wish...
}

如果你确实关心正确解析CSV,这将做它…相对较慢,因为它一次只处理一个字符。

 void ParseCSV(const string& csvSource, vector<vector<string> >& lines)
    {
       bool inQuote(false);
       bool newLine(false);
       string field;
       lines.clear();
       vector<string> line;

       string::const_iterator aChar = csvSource.begin();
       while (aChar != csvSource.end())
       {
          switch (*aChar)
          {
          case '"':
             newLine = false;
             inQuote = !inQuote;
             break;

          case ',':
             newLine = false;
             if (inQuote == true)
             {
                field += *aChar;
             }
             else
             {
                line.push_back(field);
                field.clear();
             }
             break;

          case '\n':
          case '\r':
             if (inQuote == true)
             {
                field += *aChar;
             }
             else
             {
                if (newLine == false)
                {
                   line.push_back(field);
                   lines.push_back(line);
                   field.clear();
                   line.clear();
                   newLine = true;
                }
             }
             break;

          default:
             newLine = false;
             field.push_back(*aChar);
             break;
          }

          aChar++;
       }

       if (field.size())
          line.push_back(field);

       if (line.size())
          lines.push_back(line);
    }