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fopen,fscanf函数打开和读取.csv文件,但重要的是解析数据。使用分隔符解析数据的最简单方法。对于.csv,分隔符为','。

假设你的data1.csv文件如下所示:

A,45,76,01
B,77,67,02
C,63,76,03
D,65,44,04

您可以标记数据并存储在字符数组中,然后使用atoi()等函数进行适当的转换

FILE *fp;
char str1[10], str2[10], str3[10], str4[10];

fp = fopen("G:\\data1.csv", "r");
if(NULL == fp)
{
    printf("\nError in opening file.");
    return 0;
}
while(EOF != fscanf(fp, " %[^,], %[^,], %[^,], %s, %s, %s, %s ", str1, str2, str3, str4))
{
    printf("\n%s %s %s %s", str1, str2, str3, str4);
}
fclose(fp);

[^,], ^ -它颠倒了逻辑,意思是匹配任何不包含逗号的字符串,然后最后,表示匹配终止前一个字符串的逗号。

其他回答

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;
}

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)

如果可以的话,这是我简单快速的贡献。 没有提高。

接受分隔符和分隔符中的分隔符,只要成对或远离分隔符即可。

#include <iostream>
#include <vector>
#include <fstream>

std::vector<std::string> SplitCSV(const std::string &data, char separator, char delimiter)
{
  std::vector<std::string> Values;
  std::string Val = "";
  bool VDel = false; // Is within delimiter?
  size_t CDel = 0; // Delimiters counter within delimiters.
  const char *C = data.c_str();
  size_t P = 0;
  do
  {
    if ((Val.length() == 0) && (C[P] == delimiter))
    {
      VDel = !VDel;
      CDel = 0;
      P++;
      continue;
    }
    if (VDel)
    {
      if (C[P] == delimiter)
      {
        if (((CDel % 2) == 0) && ( (C[P+1] == separator) || (C[P+1] == 0) || (C[P+1] == '\n') || (C[P+1] == '\r') ))
        {
          VDel = false;
          CDel = 0;
          P++;
          continue;
        }
        else
          CDel++;
      }
    }
    else
    {
      if (C[P] == separator)
      {
        Values.push_back(Val);
        Val = "";
        P++;
        continue;
      }
      if ((C[P] == 0) || (C[P] == '\n') || (C[P] == '\r'))
        break;
    }
    Val += C[P];
    P++;
  } while(P < data.length());
  Values.push_back(Val);
  return Values;
}

bool ReadCsv(const std::string &fname, std::vector<std::vector<std::string>> &data,
  char separator = ',', char delimiter = '\"')
{
  bool Ret = false;
  std::ifstream FCsv(fname);
  if (FCsv)
  {
    FCsv.seekg(0, FCsv.end);
    size_t Siz = FCsv.tellg();
    if (Siz > 0)
    {
      FCsv.seekg(0);
      data.clear();
      std::string Line;
      while (getline(FCsv, Line, '\n'))
        data.push_back(SplitCSV(Line, separator, delimiter));
      Ret = true;
    }
    FCsv.close();
  }
  return Ret;
}

int main(int argc, char *argv[])
{
  std::vector<std::vector<std::string>> Data;
  ReadCsv("fsample.csv", Data);
  return 0;
}

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;
}

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;
}