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
            }
        }
    }

其他回答

使用流解析CSV文件行

我写了一个解析CSV文件行的小例子,如果需要,它可以用for和while循环来开发:

#include <iostream>
#include <fstream>
#include <string.h>

using namespace std;

int main() {


ifstream fin("Infile.csv");
ofstream fout("OutFile.csv");
string strline, strremain, strCol1 , strout;

string delimeter =";";

int d1;

继续到文件的末尾:

while (!fin.eof()){ 

从InFile获取第一行:

    getline(fin,strline,'\n');      

在直线上找到度距仪的位置:

    d1 = strline.find(';');

然后解析第一列:

    strCol1 = strline.substr(0,d1); // parse first Column
    d1++;
    strremain = strline.substr(d1); // remaining line

创建CSV格式输出行:

    strout.append(strCol1);
    strout.append(delimeter);

写行到输出文件:

    fout << strout << endl; //out file line

} 

fin.close();
fout.close();

return(0);
}

代码已编译并运行。好运!

当你使用boost::spirit这样漂亮的东西时,你应该感到自豪

这里我的一个解析器的尝试(几乎)符合这个链接的CSV规范(我不需要在字段中换行)。逗号周围的空格也被省略了)。

在你克服了编译这段代码需要等待10秒的令人震惊的经历之后:),你就可以坐下来享受了。

// csvparser.cpp
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix_operator.hpp>

#include <iostream>
#include <string>

namespace qi = boost::spirit::qi;
namespace bascii = boost::spirit::ascii;

template <typename Iterator>
struct csv_parser : qi::grammar<Iterator, std::vector<std::string>(), 
    bascii::space_type>
{
    qi::rule<Iterator, char()                                           > COMMA;
    qi::rule<Iterator, char()                                           > DDQUOTE;
    qi::rule<Iterator, std::string(),               bascii::space_type  > non_escaped;
    qi::rule<Iterator, std::string(),               bascii::space_type  > escaped;
    qi::rule<Iterator, std::string(),               bascii::space_type  > field;
    qi::rule<Iterator, std::vector<std::string>(),  bascii::space_type  > start;

    csv_parser() : csv_parser::base_type(start)
    {
        using namespace qi;
        using qi::lit;
        using qi::lexeme;
        using bascii::char_;

        start       = field % ',';
        field       = escaped | non_escaped;
        escaped     = lexeme['"' >> *( char_ -(char_('"') | ',') | COMMA | DDQUOTE)  >> '"'];
        non_escaped = lexeme[       *( char_ -(char_('"') | ',')                  )        ];
        DDQUOTE     = lit("\"\"")       [_val = '"'];
        COMMA       = lit(",")          [_val = ','];
    }

};

int main()
{
    std::cout << "Enter CSV lines [empty] to quit\n";

    using bascii::space;
    typedef std::string::const_iterator iterator_type;
    typedef csv_parser<iterator_type> csv_parser;

    csv_parser grammar;
    std::string str;
    int fid;
    while (getline(std::cin, str))
    {
        fid = 0;

        if (str.empty())
            break;

        std::vector<std::string> csv;
        std::string::const_iterator it_beg = str.begin();
        std::string::const_iterator it_end = str.end();
        bool r = phrase_parse(it_beg, it_end, grammar, space, csv);

        if (r && it_beg == it_end)
        {
            std::cout << "Parsing succeeded\n";
            for (auto& field: csv)
            {
                std::cout << "field " << ++fid << ": " << field << std::endl;
            }
        }
        else
        {
            std::cout << "Parsing failed\n";
        }
    }

    return 0;
}

编译:

make csvparser

测试(例子摘自维基百科):

./csvparser
Enter CSV lines [empty] to quit

1999,Chevy,"Venture ""Extended Edition, Very Large""",,5000.00
Parsing succeeded
field 1: 1999
field 2: Chevy
field 3: Venture "Extended Edition, Very Large"
field 4: 
field 5: 5000.00

1999,Chevy,"Venture ""Extended Edition, Very Large""",,5000.00"
Parsing failed

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

使用Spirit来解析csv并不过分。Spirit非常适合微解析任务。例如,使用Spirit 2.1,它就像:

bool r = phrase_parse(first, last,

    //  Begin grammar
    (
        double_ % ','
    )
    ,
    //  End grammar

    space, v);

向量v被值填满了。在刚刚与Boost 1.41一起发布的新的Spirit 2.1文档中,有一系列教程涉及到这一点。

本教程从简单到复杂。CSV解析器呈现在中间的某个位置,并涉及使用Spirit的各种技术。生成的代码与手写代码一样紧凑。检查生成的汇编程序!

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;
}