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

我的版本只使用标准c++ 11库。它很好地处理Excel CSV引用:

spam eggs,"foo,bar","""fizz buzz"""
1.23,4.567,-8.00E+09

代码是作为有限状态机编写的,每次只消耗一个字符。我认为这更容易解释。

#include <istream>
#include <string>
#include <vector>

enum class CSVState {
    UnquotedField,
    QuotedField,
    QuotedQuote
};

std::vector<std::string> readCSVRow(const std::string &row) {
    CSVState state = CSVState::UnquotedField;
    std::vector<std::string> fields {""};
    size_t i = 0; // index of the current field
    for (char c : row) {
        switch (state) {
            case CSVState::UnquotedField:
                switch (c) {
                    case ',': // end of field
                              fields.push_back(""); i++;
                              break;
                    case '"': state = CSVState::QuotedField;
                              break;
                    default:  fields[i].push_back(c);
                              break; }
                break;
            case CSVState::QuotedField:
                switch (c) {
                    case '"': state = CSVState::QuotedQuote;
                              break;
                    default:  fields[i].push_back(c);
                              break; }
                break;
            case CSVState::QuotedQuote:
                switch (c) {
                    case ',': // , after closing quote
                              fields.push_back(""); i++;
                              state = CSVState::UnquotedField;
                              break;
                    case '"': // "" -> "
                              fields[i].push_back('"');
                              state = CSVState::QuotedField;
                              break;
                    default:  // end of quote
                              state = CSVState::UnquotedField;
                              break; }
                break;
        }
    }
    return fields;
}

/// Read CSV file, Excel dialect. Accept "quoted fields ""with quotes"""
std::vector<std::vector<std::string>> readCSV(std::istream &in) {
    std::vector<std::vector<std::string>> table;
    std::string row;
    while (!in.eof()) {
        std::getline(in, row);
        if (in.bad() || in.fail()) {
            break;
        }
        auto fields = readCSVRow(row);
        table.push_back(fields);
    }
    return table;
}

其他回答

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();
}

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;
}

我需要一个易于使用的c++库来解析CSV文件,但找不到任何可用的库,所以我最终构建了一个。 Rapidcsv是一个c++ 11的纯头库,它可以直接访问已解析的列(或行),作为选择的数据类型的向量。例如:

#include <iostream>
#include <vector>
#include <rapidcsv.h>

int main()
{
  rapidcsv::Document doc("../tests/msft.csv");

  std::vector<float> close = doc.GetColumn<float>("Close");
  std::cout << "Read " << close.size() << " values." << std::endl;
}

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!

你可以在escaped_list_separator中使用Boost Tokenizer。

Escaped_list_separator解析csv的超集。Boost::记号赋予器

这只使用Boost标记器头文件,不需要链接到Boost库。

下面是一个例子,(详情请参阅c++中使用Boost Tokenizer解析CSV文件或Boost:: Tokenizer):

#include <iostream>     // cout, endl
#include <fstream>      // fstream
#include <vector>
#include <string>
#include <algorithm>    // copy
#include <iterator>     // ostream_operator
#include <boost/tokenizer.hpp>

int main()
{
    using namespace std;
    using namespace boost;
    string data("data.csv");

    ifstream in(data.c_str());
    if (!in.is_open()) return 1;

    typedef tokenizer< escaped_list_separator<char> > Tokenizer;
    vector< string > vec;
    string line;

    while (getline(in,line))
    {
        Tokenizer tok(line);
        vec.assign(tok.begin(),tok.end());

        // vector now contains strings from one row, output to cout here
        copy(vec.begin(), vec.end(), ostream_iterator<string>(cout, "|"));

        cout << "\n----------------------" << endl;
    }
}