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！

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

不管怎样，下面是我的实现。它处理wstring输入，但是可以很容易地调整为string。它不处理字段中的换行符(因为我的应用程序也不这样做，但添加它的支持并不太难)，它不符合RFC中的“\r\n”行尾(假设您使用std::getline)，但它确实正确地处理空格修剪和双引号(希望如此)。

using namespace std;

// trim whitespaces around field or double-quotes, remove double-quotes and replace escaped double-quotes (double double-quotes)
wstring trimquote(const wstring& str, const wstring& whitespace, const wchar_t quotChar)
{
    wstring ws;
    wstring::size_type strBegin = str.find_first_not_of(whitespace);
    if (strBegin == wstring::npos)
        return L"";

    wstring::size_type strEnd = str.find_last_not_of(whitespace);
    wstring::size_type strRange = strEnd - strBegin + 1;

    if((str[strBegin] == quotChar) && (str[strEnd] == quotChar))
    {
        ws = str.substr(strBegin+1, strRange-2);
        strBegin = 0;
        while((strEnd = ws.find(quotChar, strBegin)) != wstring::npos)
        {
            ws.erase(strEnd, 1);
            strBegin = strEnd+1;
        }

    }
    else
        ws = str.substr(strBegin, strRange);
    return ws;
}

pair<unsigned, unsigned> nextCSVQuotePair(const wstring& line, const wchar_t quotChar, unsigned ofs = 0)
{
    pair<unsigned, unsigned> r;
    r.first = line.find(quotChar, ofs);
    r.second = wstring::npos;
    if(r.first != wstring::npos)
    {
        r.second = r.first;
        while(((r.second = line.find(quotChar, r.second+1)) != wstring::npos)
            && (line[r.second+1] == quotChar)) // WARNING: assumes null-terminated string such that line[r.second+1] always exist
            r.second++;

    }
    return r;
}

unsigned parseLine(vector<wstring>& fields, const wstring& line)
{
    unsigned ofs, ofs0, np;
    const wchar_t delim = L',';
    const wstring whitespace = L" \t\xa0\x3000\x2000\x2001\x2002\x2003\x2004\x2005\x2006\x2007\x2008\x2009\x200a\x202f\x205f";
    const wchar_t quotChar = L'\"';
    pair<unsigned, unsigned> quot;

    fields.clear();

    ofs = ofs0 = 0;
    quot = nextCSVQuotePair(line, quotChar);
    while((np = line.find(delim, ofs)) != wstring::npos)
    {
        if((np > quot.first) && (np < quot.second))
        { // skip delimiter inside quoted field
            ofs = quot.second+1;
            quot = nextCSVQuotePair(line, quotChar, ofs);
            continue;
        }
        fields.push_back( trimquote(line.substr(ofs0, np-ofs0), whitespace, quotChar) );
        ofs = ofs0 = np+1;
    }
    fields.push_back( trimquote(line.substr(ofs0), whitespace, quotChar) );

    return fields.size();
}

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;
}

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!

由于所有CSV问题似乎都被重定向到这里，我想我应该在这里发布我的答案。这个回答并没有直接回答提问者的问题。我希望能够读取已知的CSV格式的流，而且每个字段的类型都已经知道。当然，可以使用下面的方法将每个字段处理为字符串类型。

作为我希望能够使用CSV输入流的一个例子，考虑以下输入(取自维基百科的CSV页面):

const char input[] =
"Year,Make,Model,Description,Price\n"
"1997,Ford,E350,\"ac, abs, moon\",3000.00\n"
"1999,Chevy,\"Venture \"\"Extended Edition\"\"\",\"\",4900.00\n"
"1999,Chevy,\"Venture \"\"Extended Edition, Very Large\"\"\",\"\",5000.00\n"
"1996,Jeep,Grand Cherokee,\"MUST SELL!\n\
air, moon roof, loaded\",4799.00\n"
;

然后，我希望能够像这样读取数据:

std::istringstream ss(input);
std::string title[5];
int year;
std::string make, model, desc;
float price;
csv_istream(ss)
    >> title[0] >> title[1] >> title[2] >> title[3] >> title[4];
while (csv_istream(ss)
       >> year >> make >> model >> desc >> price) {
    //...do something with the record...
}

这就是我最后得到的解。

struct csv_istream {
    std::istream &is_;
    csv_istream (std::istream &is) : is_(is) {}
    void scan_ws () const {
        while (is_.good()) {
            int c = is_.peek();
            if (c != ' ' && c != '\t') break;
            is_.get();
        }
    }
    void scan (std::string *s = 0) const {
        std::string ws;
        int c = is_.get();
        if (is_.good()) {
            do {
                if (c == ',' || c == '\n') break;
                if (s) {
                    ws += c;
                    if (c != ' ' && c != '\t') {
                        *s += ws;
                        ws.clear();
                    }
                }
                c = is_.get();
            } while (is_.good());
            if (is_.eof()) is_.clear();
        }
    }
    template <typename T, bool> struct set_value {
        void operator () (std::string in, T &v) const {
            std::istringstream(in) >> v;
        }
    };
    template <typename T> struct set_value<T, true> {
        template <bool SIGNED> void convert (std::string in, T &v) const {
            if (SIGNED) v = ::strtoll(in.c_str(), 0, 0);
            else v = ::strtoull(in.c_str(), 0, 0);
        }
        void operator () (std::string in, T &v) const {
            convert<is_signed_int<T>::val>(in, v);
        }
    };
    template <typename T> const csv_istream & operator >> (T &v) const {
        std::string tmp;
        scan(&tmp);
        set_value<T, is_int<T>::val>()(tmp, v);
        return *this;
    }
    const csv_istream & operator >> (std::string &v) const {
        v.clear();
        scan_ws();
        if (is_.peek() != '"') scan(&v);
        else {
            std::string tmp;
            is_.get();
            std::getline(is_, tmp, '"');
            while (is_.peek() == '"') {
                v += tmp;
                v += is_.get();
                std::getline(is_, tmp, '"');
            }
            v += tmp;
            scan();
        }
        return *this;
    }
    template <typename T>
    const csv_istream & operator >> (T &(*manip)(T &)) const {
        is_ >> manip;
        return *this;
    }
    operator bool () const { return !is_.fail(); }
};

使用以下helper，可以通过c++ 11中的新积分特征模板进行简化:

template <typename T> struct is_signed_int { enum { val = false }; };
template <> struct is_signed_int<short> { enum { val = true}; };
template <> struct is_signed_int<int> { enum { val = true}; };
template <> struct is_signed_int<long> { enum { val = true}; };
template <> struct is_signed_int<long long> { enum { val = true}; };

template <typename T> struct is_unsigned_int { enum { val = false }; };
template <> struct is_unsigned_int<unsigned short> { enum { val = true}; };
template <> struct is_unsigned_int<unsigned int> { enum { val = true}; };
template <> struct is_unsigned_int<unsigned long> { enum { val = true}; };
template <> struct is_unsigned_int<unsigned long long> { enum { val = true}; };

template <typename T> struct is_int {
    enum { val = (is_signed_int<T>::val || is_unsigned_int<T>::val) };
};

在网上试试!