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

如果您所需要的只是加载一个双精度数据文件(没有整数,没有文本),那么这里有一个随时可用的函数。

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

using namespace std;

/**
 * Parse a CSV data file and fill the 2d STL vector "data".
 * Limits: only "pure datas" of doubles, not encapsulated by " and without \n inside.
 * Further no formatting in the data (e.g. scientific notation)
 * It however handles both dots and commas as decimal separators and removes thousand separator.
 * 
 * returnCodes[0]: file access 0-> ok 1-> not able to read; 2-> decimal separator equal to comma separator
 * returnCodes[1]: number of records
 * returnCodes[2]: number of fields. -1 If rows have different field size
 * 
 */
vector<int>
readCsvData (vector <vector <double>>& data, const string& filename, const string& delimiter, const string& decseparator){

 int vv[3] = { 0,0,0 };
 vector<int> returnCodes(&vv[0], &vv[0]+3);

 string rowstring, stringtoken;
 double doubletoken;
 int rowcount=0;
 int fieldcount=0;
 data.clear();

 ifstream iFile(filename, ios_base::in);
 if (!iFile.is_open()){
   returnCodes[0] = 1;
   return returnCodes;
 }
 while (getline(iFile, rowstring)) {
    if (rowstring=="") continue; // empty line
    rowcount ++; //let's start with 1
    if(delimiter == decseparator){
      returnCodes[0] = 2;
      return returnCodes;
    }
    if(decseparator != "."){
     // remove dots (used as thousand separators)
     string::iterator end_pos = remove(rowstring.begin(), rowstring.end(), '.');
     rowstring.erase(end_pos, rowstring.end());
     // replace decimal separator with dots.
     replace(rowstring.begin(), rowstring.end(),decseparator.c_str()[0], '.'); 
    } else {
     // remove commas (used as thousand separators)
     string::iterator end_pos = remove(rowstring.begin(), rowstring.end(), ',');
     rowstring.erase(end_pos, rowstring.end());
    }
    // tokenize..
    vector<double> tokens;
    // Skip delimiters at beginning.
    string::size_type lastPos = rowstring.find_first_not_of(delimiter, 0);
    // Find first "non-delimiter".
    string::size_type pos     = rowstring.find_first_of(delimiter, lastPos);
    while (string::npos != pos || string::npos != lastPos){
        // Found a token, convert it to double add it to the vector.
        stringtoken = rowstring.substr(lastPos, pos - lastPos);
        if (stringtoken == "") {
      tokens.push_back(0.0);
    } else {
          istringstream totalSString(stringtoken);
      totalSString >> doubletoken;
      tokens.push_back(doubletoken);
    }     
        // Skip delimiters.  Note the "not_of"
        lastPos = rowstring.find_first_not_of(delimiter, pos);
        // Find next "non-delimiter"
        pos = rowstring.find_first_of(delimiter, lastPos);
    }
    if(rowcount == 1){
      fieldcount = tokens.size();
      returnCodes[2] = tokens.size();
    } else {
      if ( tokens.size() != fieldcount){
    returnCodes[2] = -1;
      }
    }
    data.push_back(tokens);
 }
 iFile.close();
 returnCodes[1] = rowcount;
 return returnCodes;
}

其他回答

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;
    }
}

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);
}

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
  }
}

CSV文件是由行组成的文本文件,每一行都由逗号分隔的令牌组成。虽然在解析时你应该知道一些事情:

(0)文件用“CP_ACP”编码页编码。您应该使用相同的编码页来解码文件内容。

(1) CSV丢失了“复合单元格”信息(比如rowspan > 1),所以当它被读回excel时,复合单元格信息丢失。

(2)单元格文本可以在头部和尾部用""" "进行引用,文字引用char将变成双引号。因此,结束匹配的引号字符必须是一个引号字符,而不是后面跟着另一个引号字符。例如,如果一个单元格有逗号,它必须在csv中被引用,因为逗号在csv中有意义。

(3)当单元格内容有多行时,它将在CSV中被引用,在这种情况下,解析器必须继续读取CSV文件中的下几行,直到获得与第一个引用字符匹配的结束引号字符,确保当前逻辑行读取完成后再解析该行的令牌。

例如:在CSV文件中,以下3个物理行是由3个令牌组成的逻辑行:

    --+----------
    1 |a,"b-first part
    2 |b-second part
    3 |b-third part",c
    --+----------