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

由于我现在不习惯boost,我将建议一个更简单的解决方案。假设您的.csv文件有100行,每行有10个数字,用“,”分隔。你可以用下面的代码以数组的形式加载这个数据:

#include <iostream>
#include <fstream>
#include <sstream>
#include <string>
using namespace std;

int main()
{
    int A[100][10];
    ifstream ifs;
    ifs.open("name_of_file.csv");
    string s1;
    char c;
    for(int k=0; k<100; k++)
    {
        getline(ifs,s1);
        stringstream stream(s1);
        int j=0;
        while(1)
        {
            stream >>A[k][j];
            stream >> c;
            j++;
            if(!stream) {break;}
        }
    }


}

其他回答

可以使用std::regex。

根据文件大小和可用内存,可以逐行读取,也可以完全在std::string中读取。

读取文件可以使用:

std::ifstream t("file.txt");
std::string sin((std::istreambuf_iterator<char>(t)),
                 std::istreambuf_iterator<char>());

然后你可以和这个相匹配,它实际上是根据你的需要定制的。

std::regex word_regex(",\\s]+");
auto what = 
    std::sregex_iterator(sin.begin(), sin.end(), word_regex);
auto wend = std::sregex_iterator();

std::vector<std::string> v;
for (;what!=wend ; wend) {
    std::smatch match = *what;
    v.push_back(match.str());
}

您需要做的第一件事是确保文件存在。来完成 这你只需要尝试打开文件流的路径。在你 打开文件流使用stream.fail()查看它是否如预期的那样工作, 与否。

bool fileExists(string fileName)
{

ifstream test;

test.open(fileName.c_str());

if (test.fail())
{
    test.close();
    return false;
}
else
{
    test.close();
    return true;
}
}

您还必须验证所提供的文件是正确的文件类型。 要做到这一点,您需要查看提供的文件路径直到 您可以找到文件扩展名。一旦你有了文件扩展名,请确保 它是一个。csv文件。

bool verifyExtension(string filename)
{
int period = 0;

for (unsigned int i = 0; i < filename.length(); i++)
{
    if (filename[i] == '.')
        period = i;
}

string extension;

for (unsigned int i = period; i < filename.length(); i++)
    extension += filename[i];

if (extension == ".csv")
    return true;
else
    return false;
}

此函数将返回稍后在错误消息中使用的文件扩展名。

string getExtension(string filename)
{
int period = 0;

for (unsigned int i = 0; i < filename.length(); i++)
{
    if (filename[i] == '.')
        period = i;
}

string extension;

if (period != 0)
{
    for (unsigned int i = period; i < filename.length(); i++)
        extension += filename[i];
}
else
    extension = "NO FILE";

return extension;
}

这个函数实际上会调用上面创建的错误检查,然后解析文件。

void parseFile(string fileName)
{
    if (fileExists(fileName) && verifyExtension(fileName))
    {
        ifstream fs;
        fs.open(fileName.c_str());
        string fileCommand;

        while (fs.good())
        {
            string temp;

            getline(fs, fileCommand, '\n');

            for (unsigned int i = 0; i < fileCommand.length(); i++)
            {
                if (fileCommand[i] != ',')
                    temp += fileCommand[i];
                else
                    temp += " ";
            }

            if (temp != "\0")
            {
                // Place your code here to run the file.
            }
        }
        fs.close();
    }
    else if (!fileExists(fileName))
    {
        cout << "Error: The provided file does not exist: " << fileName << endl;

        if (!verifyExtension(fileName))
        {
            if (getExtension(fileName) != "NO FILE")
                cout << "\tCheck the file extension." << endl;
            else
                cout << "\tThere is no file in the provided path." << endl;
        }
    }
    else if (!verifyExtension(fileName)) 
    {
        if (getExtension(fileName) != "NO FILE")
            cout << "Incorrect file extension provided: " << getExtension(fileName) << endl;
        else
            cout << "There is no file in the following path: " << fileName << endl;
    }
}

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
            }
        }
    }

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";
    }
}