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

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;
}

其他回答

如果您正在使用Visual Studio / MFC,下面的解决方案可能会使您的工作更轻松。它支持Unicode和MBCS,有注释,除了CString之外没有其他依赖项,对我来说工作得很好。它不支持在带引号的字符串中嵌入换行符,但我不在乎,只要它在这种情况下不崩溃,它不会崩溃。

总体策略是,将带引号的字符串和空字符串作为特殊情况处理,其余使用Tokenize。对于带引号的字符串,策略是找到真正的结束引号,跟踪是否遇到了连续的引号对。如果是,则使用Replace将成对转换为单个。毫无疑问,有更有效的方法,但在我的案例中,性能还不够重要,不足以证明进一步优化的合理性。

class CParseCSV {
public:
// Construction
    CParseCSV(const CString& sLine);

// Attributes
    bool    GetString(CString& sDest);

protected:
    CString m_sLine;    // line to extract tokens from
    int     m_nLen;     // line length in characters
    int     m_iPos;     // index of current position
};

CParseCSV::CParseCSV(const CString& sLine) : m_sLine(sLine)
{
    m_nLen = m_sLine.GetLength();
    m_iPos = 0;
}

bool CParseCSV::GetString(CString& sDest)
{
    if (m_iPos < 0 || m_iPos > m_nLen)  // if position out of range
        return false;
    if (m_iPos == m_nLen) { // if at end of string
        sDest.Empty();  // return empty token
        m_iPos = -1;    // really done now
        return true;
    }
    if (m_sLine[m_iPos] == '\"') {  // if current char is double quote
        m_iPos++;   // advance to next char
        int iTokenStart = m_iPos;
        bool    bHasEmbeddedQuotes = false;
        while (m_iPos < m_nLen) {   // while more chars to parse
            if (m_sLine[m_iPos] == '\"') {  // if current char is double quote
                // if next char exists and is also double quote
                if (m_iPos < m_nLen - 1 && m_sLine[m_iPos + 1] == '\"') {
                    // found pair of consecutive double quotes
                    bHasEmbeddedQuotes = true;  // request conversion
                    m_iPos++;   // skip first quote in pair
                } else  // next char doesn't exist or is normal
                    break;  // found closing quote; exit loop
            }
            m_iPos++;   // advance to next char
        }
        sDest = m_sLine.Mid(iTokenStart, m_iPos - iTokenStart);
        if (bHasEmbeddedQuotes) // if string contains embedded quote pairs
            sDest.Replace(_T("\"\""), _T("\""));    // convert pairs to singles
        m_iPos += 2;    // skip closing quote and trailing delimiter if any
    } else if (m_sLine[m_iPos] == ',') {    // else if char is comma
        sDest.Empty();  // return empty token
        m_iPos++;   // advance to next char
    } else {    // else get next comma-delimited token
        sDest = m_sLine.Tokenize(_T(","), m_iPos);
    }
    return true;
}

// calling code should look something like this:

    CStdioFile  fIn(pszPath, CFile::modeRead);
    CString sLine, sToken;
    while (fIn.ReadString(sLine)) { // for each line of input file
        if (!sLine.IsEmpty()) { // ignore blank lines
            CParseCSV   csv(sLine);
            while (csv.GetString(sToken)) {
                // do something with sToken here
            }
        }
    }

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);
}

@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;
}

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;
}

下面是读取矩阵的代码,注意你在matlab中也有一个csvwrite函数

void loadFromCSV( const std::string& filename )
{
    std::ifstream       file( filename.c_str() );
    std::vector< std::vector<std::string> >   matrix;
    std::vector<std::string>   row;
    std::string                line;
    std::string                cell;

    while( file )
    {
        std::getline(file,line);
        std::stringstream lineStream(line);
        row.clear();

        while( std::getline( lineStream, cell, ',' ) )
            row.push_back( cell );

        if( !row.empty() )
            matrix.push_back( row );
    }

    for( int i=0; i<int(matrix.size()); i++ )
    {
        for( int j=0; j<int(matrix[i].size()); j++ )
            std::cout << matrix[i][j] << " ";

        std::cout << std::endl;
    }
}