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;
}

其他回答

我写了一个只有头文件的c++ 11 CSV解析器。它经过了良好的测试,快速,支持整个CSV规范(带引号的字段,引号中的分隔符/结束符,引号转义等),并且可以配置为不符合规范的CSV。

配置是通过一个流畅的接口完成的:

// constructor accepts any input stream
CsvParser parser = CsvParser(std::cin)
  .delimiter(';')    // delimited by ; instead of ,
  .quote('\'')       // quoted fields use ' instead of "
  .terminator('\0'); // terminated by \0 instead of by \r\n, \n, or \r

解析只是一个基于范围的for循环:

#include <iostream>
#include "../parser.hpp"

using namespace aria::csv;

int main() {
  std::ifstream f("some_file.csv");
  CsvParser parser(f);

  for (auto& row : parser) {
    for (auto& field : row) {
      std::cout << field << " | ";
    }
    std::cout << std::endl;
  }
}

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!

另一种快速简单的方法是使用Boost。I / O:融合

#include <iostream>
#include <sstream>

#include <boost/fusion/adapted/boost_tuple.hpp>
#include <boost/fusion/sequence/io.hpp>

namespace fusion = boost::fusion;

struct CsvString
{
    std::string value;

    // Stop reading a string once a CSV delimeter is encountered.
    friend std::istream& operator>>(std::istream& s, CsvString& v) {
        v.value.clear();
        for(;;) {
            auto c = s.peek();
            if(std::istream::traits_type::eof() == c || ',' == c || '\n' == c)
                break;
            v.value.push_back(c);
            s.get();
        }
        return s;
    }

    friend std::ostream& operator<<(std::ostream& s, CsvString const& v) {
        return s << v.value;
    }
};

int main() {
    std::stringstream input("abc,123,true,3.14\n"
                            "def,456,false,2.718\n");

    typedef boost::tuple<CsvString, int, bool, double> CsvRow;

    using fusion::operator<<;
    std::cout << std::boolalpha;

    using fusion::operator>>;
    input >> std::boolalpha;
    input >> fusion::tuple_open("") >> fusion::tuple_close("\n") >> fusion::tuple_delimiter(',');

    for(CsvRow row; input >> row;)
        std::cout << row << '\n';
}

输出:

(abc 123 true 3.14)
(def 456 false 2.718)

你可以使用这个库: https://github.com/vadamsky/csvworker

代码示例:

#include <iostream>
#include "csvworker.h"

using namespace std;

int main()
{
    //
    CsvWorker csv;
    csv.loadFromFile("example.csv");
    cout << csv.getRowsNumber() << "  " << csv.getColumnsNumber() << endl;

    csv.getFieldRef(0, 2) = "0";
    csv.getFieldRef(1, 1) = "0";
    csv.getFieldRef(1, 3) = "0";
    csv.getFieldRef(2, 0) = "0";
    csv.getFieldRef(2, 4) = "0";
    csv.getFieldRef(3, 1) = "0";
    csv.getFieldRef(3, 3) = "0";
    csv.getFieldRef(4, 2) = "0";

    for(unsigned int i=0;i<csv.getRowsNumber();++i)
    {
        //cout << csv.getRow(i) << endl;
        for(unsigned int j=0;j<csv.getColumnsNumber();++j)
        {
            cout << csv.getField(i, j) << ".";
        }
        cout << endl;
    }

    csv.saveToFile("test.csv");

    //
    CsvWorker csv2(4,4);

    csv2.getFieldRef(0, 0) = "a";
    csv2.getFieldRef(0, 1) = "b";
    csv2.getFieldRef(0, 2) = "r";
    csv2.getFieldRef(0, 3) = "a";
    csv2.getFieldRef(1, 0) = "c";
    csv2.getFieldRef(1, 1) = "a";
    csv2.getFieldRef(1, 2) = "d";
    csv2.getFieldRef(2, 0) = "a";
    csv2.getFieldRef(2, 1) = "b";
    csv2.getFieldRef(2, 2) = "r";
    csv2.getFieldRef(2, 3) = "a";

    csv2.saveToFile("test2.csv");

    return 0;
}

您还可以看看Qt库的功能。

它有正则表达式支持,QString类有很好的方法,例如split()返回QStringList,通过使用提供的分隔符分割原始字符串获得的字符串列表。应该足以为csv文件..

要获得具有给定标题名的列,我使用以下方法:c++继承Qt问题qstring