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！

不好意思，但是为了隐藏几行代码，这似乎是非常复杂的语法。

为什么不这样呢:

/**

  Read line from a CSV file

  @param[in] fp file pointer to open file
  @param[in] vls reference to vector of strings to hold next line

  */
void readCSV( FILE *fp, std::vector<std::string>& vls )
{
    vls.clear();
    if( ! fp )
        return;
    char buf[10000];
    if( ! fgets( buf,999,fp) )
        return;
    std::string s = buf;
    int p,q;
    q = -1;
    // loop over columns
    while( 1 ) {
        p = q;
        q = s.find_first_of(",\n",p+1);
        if( q == -1 ) 
            break;
        vls.push_back( s.substr(p+1,q-p-1) );
    }
}

int _tmain(int argc, _TCHAR* argv[])
{
    std::vector<std::string> vls;
    FILE * fp = fopen( argv[1], "r" );
    if( ! fp )
        return 1;
    readCSV( fp, vls );
    readCSV( fp, vls );
    readCSV( fp, vls );
    std::cout << "row 3, col 4 is " << vls[3].c_str() << "\n";

    return 0;
}

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;
    }
}

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!

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);
}

如果可以的话，这是我简单快速的贡献。 没有提高。

接受分隔符和分隔符中的分隔符，只要成对或远离分隔符即可。

#include <iostream>
#include <vector>
#include <fstream>

std::vector<std::string> SplitCSV(const std::string &data, char separator, char delimiter)
{
  std::vector<std::string> Values;
  std::string Val = "";
  bool VDel = false; // Is within delimiter?
  size_t CDel = 0; // Delimiters counter within delimiters.
  const char *C = data.c_str();
  size_t P = 0;
  do
  {
    if ((Val.length() == 0) && (C[P] == delimiter))
    {
      VDel = !VDel;
      CDel = 0;
      P++;
      continue;
    }
    if (VDel)
    {
      if (C[P] == delimiter)
      {
        if (((CDel % 2) == 0) && ( (C[P+1] == separator) || (C[P+1] == 0) || (C[P+1] == '\n') || (C[P+1] == '\r') ))
        {
          VDel = false;
          CDel = 0;
          P++;
          continue;
        }
        else
          CDel++;
      }
    }
    else
    {
      if (C[P] == separator)
      {
        Values.push_back(Val);
        Val = "";
        P++;
        continue;
      }
      if ((C[P] == 0) || (C[P] == '\n') || (C[P] == '\r'))
        break;
    }
    Val += C[P];
    P++;
  } while(P < data.length());
  Values.push_back(Val);
  return Values;
}

bool ReadCsv(const std::string &fname, std::vector<std::vector<std::string>> &data,
  char separator = ',', char delimiter = '\"')
{
  bool Ret = false;
  std::ifstream FCsv(fname);
  if (FCsv)
  {
    FCsv.seekg(0, FCsv.end);
    size_t Siz = FCsv.tellg();
    if (Siz > 0)
    {
      FCsv.seekg(0);
      data.clear();
      std::string Line;
      while (getline(FCsv, Line, '\n'))
        data.push_back(SplitCSV(Line, separator, delimiter));
      Ret = true;
    }
    FCsv.close();
  }
  return Ret;
}

int main(int argc, char *argv[])
{
  std::vector<std::vector<std::string>> Data;
  ReadCsv("fsample.csv", Data);
  return 0;
}