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

您可以使用仅头文件的Csv::Parser库。

它完全支持RFC 4180,包括字段值中的引号、转义引号和换行。 它只需要标准的c++ (c++ 17)。 它支持在编译时从std::string_view读取CSV数据。 它使用Catch2进行了广泛的测试。

其他回答

这是一个旧线程,但它仍然在搜索结果的顶部,所以我添加我的解决方案使用std::stringstream和一个简单的字符串替换方法由Yves Baumes我在这里找到。

下面的例子将逐行读取文件,忽略以//开头的注释行,并将其他行解析为字符串、int和double的组合。Stringstream进行解析,但希望字段由空格分隔,因此我使用stringreplace首先将逗号转换为空格。它可以处理制表符,但不处理带引号的字符串。

坏的或丢失的输入被简单地忽略,这可能是好事,也可能不是好事,这取决于您的情况。

#include <string>
#include <sstream>
#include <fstream>

void StringReplace(std::string& str, const std::string& oldStr, const std::string& newStr)
// code by  Yves Baumes
// http://stackoverflow.com/questions/1494399/how-do-i-search-find-and-replace-in-a-standard-string
{
  size_t pos = 0;
  while((pos = str.find(oldStr, pos)) != std::string::npos)
  {
     str.replace(pos, oldStr.length(), newStr);
     pos += newStr.length();
  }
}

void LoadCSV(std::string &filename) {
   std::ifstream stream(filename);
   std::string in_line;
   std::string Field;
   std::string Chan;
   int ChanType;
   double Scale;
   int Import;
   while (std::getline(stream, in_line)) {
      StringReplace(in_line, ",", " ");
      std::stringstream line(in_line);
      line >> Field >> Chan >> ChanType >> Scale >> Import;
      if (Field.substr(0,2)!="//") {
         // do your stuff 
         // this is CBuilder code for demonstration, sorry
         ShowMessage((String)Field.c_str() + "\n" + Chan.c_str() + "\n" + IntToStr(ChanType) + "\n" +FloatToStr(Scale) + "\n" +IntToStr(Import));
      }
   }
}

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;
}

我需要一个易于使用的c++库来解析CSV文件,但找不到任何可用的库,所以我最终构建了一个。 Rapidcsv是一个c++ 11的纯头库,它可以直接访问已解析的列(或行),作为选择的数据类型的向量。例如:

#include <iostream>
#include <vector>
#include <rapidcsv.h>

int main()
{
  rapidcsv::Document doc("../tests/msft.csv");

  std::vector<float> close = doc.GetColumn<float>("Close");
  std::cout << "Read " << close.size() << " values." << std::endl;
}

另一种快速简单的方法是使用Boost。I / O:融合

#include <iostream>
#include <sstream>

#include <boost/fusion/adapted/boost_tuple.hpp>
#include <boost/fusion/sequence/io.hpp>

namespace fusion = boost::fusion;

struct CsvString
{
    std::string value;

    // Stop reading a string once a CSV delimeter is encountered.
    friend std::istream& operator>>(std::istream& s, CsvString& v) {
        v.value.clear();
        for(;;) {
            auto c = s.peek();
            if(std::istream::traits_type::eof() == c || ',' == c || '\n' == c)
                break;
            v.value.push_back(c);
            s.get();
        }
        return s;
    }

    friend std::ostream& operator<<(std::ostream& s, CsvString const& v) {
        return s << v.value;
    }
};

int main() {
    std::stringstream input("abc,123,true,3.14\n"
                            "def,456,false,2.718\n");

    typedef boost::tuple<CsvString, int, bool, double> CsvRow;

    using fusion::operator<<;
    std::cout << std::boolalpha;

    using fusion::operator>>;
    input >> std::boolalpha;
    input >> fusion::tuple_open("") >> fusion::tuple_close("\n") >> fusion::tuple_delimiter(',');

    for(CsvRow row; input >> row;)
        std::cout << row << '\n';
}

输出:

(abc 123 true 3.14)
(def 456 false 2.718)

我写了一个很好的解析CSV文件的方法,我认为我应该把它作为一个答案:

#include <algorithm>
#include <fstream>
#include <iostream>
#include <stdlib.h>
#include <stdio.h>

struct CSVDict
{
  std::vector< std::string > inputImages;
  std::vector< double > inputLabels;
};

/**
\brief Splits the string

\param str String to split
\param delim Delimiter on the basis of which splitting is to be done
\return results Output in the form of vector of strings
*/
std::vector<std::string> stringSplit( const std::string &str, const std::string &delim )
{
  std::vector<std::string> results;

  for (size_t i = 0; i < str.length(); i++)
  {
    std::string tempString = "";
    while ((str[i] != *delim.c_str()) && (i < str.length()))
    {
      tempString += str[i];
      i++;
    }
    results.push_back(tempString);
  }

  return results;
}

/**
\brief Parse the supplied CSV File and obtain Row and Column information. 

Assumptions:
1. Header information is in first row
2. Delimiters are only used to differentiate cell members

\param csvFileName The full path of the file to parse
\param inputColumns The string of input columns which contain the data to be used for further processing
\param inputLabels The string of input labels based on which further processing is to be done
\param delim The delimiters used in inputColumns and inputLabels
\return Vector of Vector of strings: Collection of rows and columns
*/
std::vector< CSVDict > parseCSVFile( const std::string &csvFileName, const std::string &inputColumns, const std::string &inputLabels, const std::string &delim )
{
  std::vector< CSVDict > return_CSVDict;
  std::vector< std::string > inputColumnsVec = stringSplit(inputColumns, delim), inputLabelsVec = stringSplit(inputLabels, delim);
  std::vector< std::vector< std::string > > returnVector;
  std::ifstream inFile(csvFileName.c_str());
  int row = 0;
  std::vector< size_t > inputColumnIndeces, inputLabelIndeces;
  for (std::string line; std::getline(inFile, line, '\n');)
  {
    CSVDict tempDict;
    std::vector< std::string > rowVec;
    line.erase(std::remove(line.begin(), line.end(), '"'), line.end());
    rowVec = stringSplit(line, delim);

    // for the first row, record the indeces of the inputColumns and inputLabels
    if (row == 0)
    {
      for (size_t i = 0; i < rowVec.size(); i++)
      {
        for (size_t j = 0; j < inputColumnsVec.size(); j++)
        {
          if (rowVec[i] == inputColumnsVec[j])
          {
            inputColumnIndeces.push_back(i);
          }
        }
        for (size_t j = 0; j < inputLabelsVec.size(); j++)
        {
          if (rowVec[i] == inputLabelsVec[j])
          {
            inputLabelIndeces.push_back(i);
          }
        }
      }
    }
    else
    {
      for (size_t i = 0; i < inputColumnIndeces.size(); i++)
      {
        tempDict.inputImages.push_back(rowVec[inputColumnIndeces[i]]);
      }
      for (size_t i = 0; i < inputLabelIndeces.size(); i++)
      {
        double test = std::atof(rowVec[inputLabelIndeces[i]].c_str());
        tempDict.inputLabels.push_back(std::atof(rowVec[inputLabelIndeces[i]].c_str()));
      }
      return_CSVDict.push_back(tempDict);
    }
    row++;
  }

  return return_CSVDict;
}