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

@sastanin的解决方案的一个小版本,以便它可以处理引号中的换行。

std::vector<std::vector<std::string>> readCSV(std::istream &in) {
    std::vector<std::vector<std::string>> table;

    while (!in.eof()) {
        CSVState state = CSVState::UnquotedField;
        std::vector<std::string> fields {""};
        size_t i = 0; // index of the current field
        for (char c : row) {
            switch (state) {
                case CSVState::UnquotedField:
                    switch (c) {
                        case ',': // end of field
                                  fields.push_back(""); i++;
                                  break;
                        case '"': state = CSVState::QuotedField;
                                  break;
                        default:  fields[i].push_back(c);
                                  break; }
                    break;
                case CSVState::QuotedField:
                    switch (c) {
                        case '"': state = CSVState::QuotedQuote;
                                  break;
                        default:  fields[i].push_back(c);
                                  break; }
                    break;
                case CSVState::QuotedQuote:
                    switch (c) {
                        case ',': // , after closing quote
                                  fields.push_back(""); i++;
                                  state = CSVState::UnquotedField;
                                  break;
                        case '"': // "" -> "
                                  fields[i].push_back('"');
                                  state = CSVState::QuotedField;
                                  break;
                        case '\n': // newline
                                  table.push_back(fields);
                                  state = CSVState::UnquotedField;
                                  fields = vector<string>{""};
                                  i = 0;
                        default:  // end of quote
                                  state = CSVState::UnquotedField;
                                  break; }
                    break;
            }
        }
    }
    return table;
}

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
  }
}

如果你不关心转义逗号和换行符, 并且你不能在引号中嵌入逗号和换行符(如果你不能转义那么…) 那么它只有大约三行代码(好的14 ->,但它只有15读取整个文件)。

std::vector<std::string> getNextLineAndSplitIntoTokens(std::istream& str)
{
    std::vector<std::string>   result;
    std::string                line;
    std::getline(str,line);

    std::stringstream          lineStream(line);
    std::string                cell;

    while(std::getline(lineStream,cell, ','))
    {
        result.push_back(cell);
    }
    // This checks for a trailing comma with no data after it.
    if (!lineStream && cell.empty())
    {
        // If there was a trailing comma then add an empty element.
        result.push_back("");
    }
    return result;
}

我只需要创建一个表示一行的类。 然后流到该对象:

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

class CSVRow
{
    public:
        std::string_view operator[](std::size_t index) const
        {
            return std::string_view(&m_line[m_data[index] + 1], m_data[index + 1] -  (m_data[index] + 1));
        }
        std::size_t size() const
        {
            return m_data.size() - 1;
        }
        void readNextRow(std::istream& str)
        {
            std::getline(str, m_line);

            m_data.clear();
            m_data.emplace_back(-1);
            std::string::size_type pos = 0;
            while((pos = m_line.find(',', pos)) != std::string::npos)
            {
                m_data.emplace_back(pos);
                ++pos;
            }
            // This checks for a trailing comma with no data after it.
            pos   = m_line.size();
            m_data.emplace_back(pos);
        }
    private:
        std::string         m_line;
        std::vector<int>    m_data;
};

std::istream& operator>>(std::istream& str, CSVRow& data)
{
    data.readNextRow(str);
    return str;
}   
int main()
{
    std::ifstream       file("plop.csv");

    CSVRow              row;
    while(file >> row)
    {
        std::cout << "4th Element(" << row[3] << ")\n";
    }
}

但只要做一点工作,我们就可以在技术上创建一个迭代器:

class CSVIterator
{   
    public:
        typedef std::input_iterator_tag     iterator_category;
        typedef CSVRow                      value_type;
        typedef std::size_t                 difference_type;
        typedef CSVRow*                     pointer;
        typedef CSVRow&                     reference;

        CSVIterator(std::istream& str)  :m_str(str.good()?&str:nullptr) { ++(*this); }
        CSVIterator()                   :m_str(nullptr) {}

        // Pre Increment
        CSVIterator& operator++()               {if (m_str) { if (!((*m_str) >> m_row)){m_str = nullptr;}}return *this;}
        // Post increment
        CSVIterator operator++(int)             {CSVIterator    tmp(*this);++(*this);return tmp;}
        CSVRow const& operator*()   const       {return m_row;}
        CSVRow const* operator->()  const       {return &m_row;}

        bool operator==(CSVIterator const& rhs) {return ((this == &rhs) || ((this->m_str == nullptr) && (rhs.m_str == nullptr)));}
        bool operator!=(CSVIterator const& rhs) {return !((*this) == rhs);}
    private:
        std::istream*       m_str;
        CSVRow              m_row;
};


int main()
{
    std::ifstream       file("plop.csv");

    for(CSVIterator loop(file); loop != CSVIterator(); ++loop)
    {
        std::cout << "4th Element(" << (*loop)[3] << ")\n";
    }
}

现在我们已经到了2020年,让我们添加一个CSVRange对象:

class CSVRange
{
    std::istream&   stream;
    public:
        CSVRange(std::istream& str)
            : stream(str)
        {}
        CSVIterator begin() const {return CSVIterator{stream};}
        CSVIterator end()   const {return CSVIterator{};}
};

int main()
{
    std::ifstream       file("plop.csv");

    for(auto& row: CSVRange(file))
    {
        std::cout << "4th Element(" << row[3] << ")\n";
    }
}

我的版本只使用标准c++ 11库。它很好地处理Excel CSV引用:

spam eggs,"foo,bar","""fizz buzz"""
1.23,4.567,-8.00E+09

代码是作为有限状态机编写的,每次只消耗一个字符。我认为这更容易解释。

#include <istream>
#include <string>
#include <vector>

enum class CSVState {
    UnquotedField,
    QuotedField,
    QuotedQuote
};

std::vector<std::string> readCSVRow(const std::string &row) {
    CSVState state = CSVState::UnquotedField;
    std::vector<std::string> fields {""};
    size_t i = 0; // index of the current field
    for (char c : row) {
        switch (state) {
            case CSVState::UnquotedField:
                switch (c) {
                    case ',': // end of field
                              fields.push_back(""); i++;
                              break;
                    case '"': state = CSVState::QuotedField;
                              break;
                    default:  fields[i].push_back(c);
                              break; }
                break;
            case CSVState::QuotedField:
                switch (c) {
                    case '"': state = CSVState::QuotedQuote;
                              break;
                    default:  fields[i].push_back(c);
                              break; }
                break;
            case CSVState::QuotedQuote:
                switch (c) {
                    case ',': // , after closing quote
                              fields.push_back(""); i++;
                              state = CSVState::UnquotedField;
                              break;
                    case '"': // "" -> "
                              fields[i].push_back('"');
                              state = CSVState::QuotedField;
                              break;
                    default:  // end of quote
                              state = CSVState::UnquotedField;
                              break; }
                break;
        }
    }
    return fields;
}

/// Read CSV file, Excel dialect. Accept "quoted fields ""with quotes"""
std::vector<std::vector<std::string>> readCSV(std::istream &in) {
    std::vector<std::vector<std::string>> table;
    std::string row;
    while (!in.eof()) {
        std::getline(in, row);
        if (in.bad() || in.fail()) {
            break;
        }
        auto fields = readCSVRow(row);
        table.push_back(fields);
    }
    return table;
}

使用Boost Tokenizer的解决方案:

std::vector<std::string> vec;
using namespace boost;
tokenizer<escaped_list_separator<char> > tk(
   line, escaped_list_separator<char>('\\', ',', '\"'));
for (tokenizer<escaped_list_separator<char> >::iterator i(tk.begin());
   i!=tk.end();++i) 
{
   vec.push_back(*i);
}

c++ String工具箱库(StrTk)有一个令牌网格类,它允许你从文本文件、字符串或字符缓冲区加载数据,并以行-列的方式解析/处理它们。

您可以指定行分隔符和列分隔符,或者只使用默认值。

void foo()
{
   std::string data = "1,2,3,4,5\n"
                      "0,2,4,6,8\n"
                      "1,3,5,7,9\n";

   strtk::token_grid grid(data,data.size(),",");

   for(std::size_t i = 0; i < grid.row_count(); ++i)
   {
      strtk::token_grid::row_type r = grid.row(i);
      for(std::size_t j = 0; j < r.size(); ++j)
      {
         std::cout << r.get<int>(j) << "\t";
      }
      std::cout << std::endl;
   }
   std::cout << std::endl;
}

更多的例子可以在这里找到