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

如果你不关心转义逗号和换行符, 并且你不能在引号中嵌入逗号和换行符(如果你不能转义那么…) 那么它只有大约三行代码(好的14 ->,但它只有15读取整个文件)。

std::vector<std::string> getNextLineAndSplitIntoTokens(std::istream& str)
{
    std::vector<std::string>   result;
    std::string                line;
    std::getline(str,line);

    std::stringstream          lineStream(line);
    std::string                cell;

    while(std::getline(lineStream,cell, ','))
    {
        result.push_back(cell);
    }
    // This checks for a trailing comma with no data after it.
    if (!lineStream && cell.empty())
    {
        // If there was a trailing comma then add an empty element.
        result.push_back("");
    }
    return result;
}

我只需要创建一个表示一行的类。 然后流到该对象:

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

class CSVRow
{
    public:
        std::string_view operator[](std::size_t index) const
        {
            return std::string_view(&m_line[m_data[index] + 1], m_data[index + 1] -  (m_data[index] + 1));
        }
        std::size_t size() const
        {
            return m_data.size() - 1;
        }
        void readNextRow(std::istream& str)
        {
            std::getline(str, m_line);

            m_data.clear();
            m_data.emplace_back(-1);
            std::string::size_type pos = 0;
            while((pos = m_line.find(',', pos)) != std::string::npos)
            {
                m_data.emplace_back(pos);
                ++pos;
            }
            // This checks for a trailing comma with no data after it.
            pos   = m_line.size();
            m_data.emplace_back(pos);
        }
    private:
        std::string         m_line;
        std::vector<int>    m_data;
};

std::istream& operator>>(std::istream& str, CSVRow& data)
{
    data.readNextRow(str);
    return str;
}   
int main()
{
    std::ifstream       file("plop.csv");

    CSVRow              row;
    while(file >> row)
    {
        std::cout << "4th Element(" << row[3] << ")\n";
    }
}

但只要做一点工作,我们就可以在技术上创建一个迭代器:

class CSVIterator
{   
    public:
        typedef std::input_iterator_tag     iterator_category;
        typedef CSVRow                      value_type;
        typedef std::size_t                 difference_type;
        typedef CSVRow*                     pointer;
        typedef CSVRow&                     reference;

        CSVIterator(std::istream& str)  :m_str(str.good()?&str:nullptr) { ++(*this); }
        CSVIterator()                   :m_str(nullptr) {}

        // Pre Increment
        CSVIterator& operator++()               {if (m_str) { if (!((*m_str) >> m_row)){m_str = nullptr;}}return *this;}
        // Post increment
        CSVIterator operator++(int)             {CSVIterator    tmp(*this);++(*this);return tmp;}
        CSVRow const& operator*()   const       {return m_row;}
        CSVRow const* operator->()  const       {return &m_row;}

        bool operator==(CSVIterator const& rhs) {return ((this == &rhs) || ((this->m_str == nullptr) && (rhs.m_str == nullptr)));}
        bool operator!=(CSVIterator const& rhs) {return !((*this) == rhs);}
    private:
        std::istream*       m_str;
        CSVRow              m_row;
};


int main()
{
    std::ifstream       file("plop.csv");

    for(CSVIterator loop(file); loop != CSVIterator(); ++loop)
    {
        std::cout << "4th Element(" << (*loop)[3] << ")\n";
    }
}

现在我们已经到了2020年,让我们添加一个CSVRange对象:

class CSVRange
{
    std::istream&   stream;
    public:
        CSVRange(std::istream& str)
            : stream(str)
        {}
        CSVIterator begin() const {return CSVIterator{stream};}
        CSVIterator end()   const {return CSVIterator{};}
};

int main()
{
    std::ifstream       file("plop.csv");

    for(auto& row: CSVRange(file))
    {
        std::cout << "4th Element(" << row[3] << ")\n";
    }
}

其他回答

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!

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;
    }
}

如果你不关心转义逗号和换行符, 并且你不能在引号中嵌入逗号和换行符(如果你不能转义那么…) 那么它只有大约三行代码(好的14 ->,但它只有15读取整个文件)。

std::vector<std::string> getNextLineAndSplitIntoTokens(std::istream& str)
{
    std::vector<std::string>   result;
    std::string                line;
    std::getline(str,line);

    std::stringstream          lineStream(line);
    std::string                cell;

    while(std::getline(lineStream,cell, ','))
    {
        result.push_back(cell);
    }
    // This checks for a trailing comma with no data after it.
    if (!lineStream && cell.empty())
    {
        // If there was a trailing comma then add an empty element.
        result.push_back("");
    }
    return result;
}

我只需要创建一个表示一行的类。 然后流到该对象:

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

class CSVRow
{
    public:
        std::string_view operator[](std::size_t index) const
        {
            return std::string_view(&m_line[m_data[index] + 1], m_data[index + 1] -  (m_data[index] + 1));
        }
        std::size_t size() const
        {
            return m_data.size() - 1;
        }
        void readNextRow(std::istream& str)
        {
            std::getline(str, m_line);

            m_data.clear();
            m_data.emplace_back(-1);
            std::string::size_type pos = 0;
            while((pos = m_line.find(',', pos)) != std::string::npos)
            {
                m_data.emplace_back(pos);
                ++pos;
            }
            // This checks for a trailing comma with no data after it.
            pos   = m_line.size();
            m_data.emplace_back(pos);
        }
    private:
        std::string         m_line;
        std::vector<int>    m_data;
};

std::istream& operator>>(std::istream& str, CSVRow& data)
{
    data.readNextRow(str);
    return str;
}   
int main()
{
    std::ifstream       file("plop.csv");

    CSVRow              row;
    while(file >> row)
    {
        std::cout << "4th Element(" << row[3] << ")\n";
    }
}

但只要做一点工作,我们就可以在技术上创建一个迭代器:

class CSVIterator
{   
    public:
        typedef std::input_iterator_tag     iterator_category;
        typedef CSVRow                      value_type;
        typedef std::size_t                 difference_type;
        typedef CSVRow*                     pointer;
        typedef CSVRow&                     reference;

        CSVIterator(std::istream& str)  :m_str(str.good()?&str:nullptr) { ++(*this); }
        CSVIterator()                   :m_str(nullptr) {}

        // Pre Increment
        CSVIterator& operator++()               {if (m_str) { if (!((*m_str) >> m_row)){m_str = nullptr;}}return *this;}
        // Post increment
        CSVIterator operator++(int)             {CSVIterator    tmp(*this);++(*this);return tmp;}
        CSVRow const& operator*()   const       {return m_row;}
        CSVRow const* operator->()  const       {return &m_row;}

        bool operator==(CSVIterator const& rhs) {return ((this == &rhs) || ((this->m_str == nullptr) && (rhs.m_str == nullptr)));}
        bool operator!=(CSVIterator const& rhs) {return !((*this) == rhs);}
    private:
        std::istream*       m_str;
        CSVRow              m_row;
};


int main()
{
    std::ifstream       file("plop.csv");

    for(CSVIterator loop(file); loop != CSVIterator(); ++loop)
    {
        std::cout << "4th Element(" << (*loop)[3] << ")\n";
    }
}

现在我们已经到了2020年,让我们添加一个CSVRange对象:

class CSVRange
{
    std::istream&   stream;
    public:
        CSVRange(std::istream& str)
            : stream(str)
        {}
        CSVIterator begin() const {return CSVIterator{stream};}
        CSVIterator end()   const {return CSVIterator{};}
};

int main()
{
    std::ifstream       file("plop.csv");

    for(auto& row: CSVRange(file))
    {
        std::cout << "4th Element(" << row[3] << ")\n";
    }
}

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;
}

该解决方案检测这4种情况

完整的课程在

https://github.com/pedro-vicente/csv-parser

1,field 2,field 3,
1,field 2,"field 3 quoted, with separator",
1,field 2,"field 3
with newline",
1,field 2,"field 3
with newline and separator,",

它一个字符一个字符地读取文件,每次读取一行到一个向量(字符串),因此适合于非常大的文件。

使用

迭代直到返回空行(文件结束)。行是一个向量,其中每个条目都是一个CSV列。

read_csv_t csv;
csv.open("../test.csv");
std::vector<std::string> row;
while (true)
{
  row = csv.read_row();
  if (row.size() == 0)
  {
    break;
  }
}

类声明

class read_csv_t
{
public:
  read_csv_t();
  int open(const std::string &file_name);
  std::vector<std::string> read_row();
private:
  std::ifstream m_ifs;
};

实现

std::vector<std::string> read_csv_t::read_row()
{
  bool quote_mode = false;
  std::vector<std::string> row;
  std::string column;
  char c;
  while (m_ifs.get(c))
  {
    switch (c)
    {
      /////////////////////////////////////////////////////////////////////////////////////////////////////
      //separator ',' detected. 
      //in quote mode add character to column
      //push column if not in quote mode
      /////////////////////////////////////////////////////////////////////////////////////////////////////

    case ',':
      if (quote_mode == true)
      {
        column += c;
      }
      else
      {
        row.push_back(column);
        column.clear();
      }
      break;

      /////////////////////////////////////////////////////////////////////////////////////////////////////
      //quote '"' detected. 
      //toggle quote mode
      /////////////////////////////////////////////////////////////////////////////////////////////////////

    case '"':
      quote_mode = !quote_mode;
      break;

      /////////////////////////////////////////////////////////////////////////////////////////////////////
      //line end detected
      //in quote mode add character to column
      //return row if not in quote mode
      /////////////////////////////////////////////////////////////////////////////////////////////////////

    case '\n':
    case '\r':
      if (quote_mode == true)
      {
        column += c;
      }
      else
      {
        return row;
      }
      break;

      /////////////////////////////////////////////////////////////////////////////////////////////////////
      //default, add character to column
      /////////////////////////////////////////////////////////////////////////////////////////////////////

    default:
      column += c;
      break;
    }
  }

  //return empty vector if end of file detected 
  m_ifs.close();
  std::vector<std::string> v;
  return v;
}