当你使用boost::spirit这样漂亮的东西时，你应该感到自豪

这里我的一个解析器的尝试(几乎)符合这个链接的CSV规范(我不需要在字段中换行)。逗号周围的空格也被省略了)。

在你克服了编译这段代码需要等待10秒的令人震惊的经历之后:)，你就可以坐下来享受了。

// csvparser.cpp
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix_operator.hpp>

#include <iostream>
#include <string>

namespace qi = boost::spirit::qi;
namespace bascii = boost::spirit::ascii;

template <typename Iterator>
struct csv_parser : qi::grammar<Iterator, std::vector<std::string>(), 
    bascii::space_type>
{
    qi::rule<Iterator, char()                                           > COMMA;
    qi::rule<Iterator, char()                                           > DDQUOTE;
    qi::rule<Iterator, std::string(),               bascii::space_type  > non_escaped;
    qi::rule<Iterator, std::string(),               bascii::space_type  > escaped;
    qi::rule<Iterator, std::string(),               bascii::space_type  > field;
    qi::rule<Iterator, std::vector<std::string>(),  bascii::space_type  > start;

    csv_parser() : csv_parser::base_type(start)
    {
        using namespace qi;
        using qi::lit;
        using qi::lexeme;
        using bascii::char_;

        start       = field % ',';
        field       = escaped | non_escaped;
        escaped     = lexeme['"' >> *( char_ -(char_('"') | ',') | COMMA | DDQUOTE)  >> '"'];
        non_escaped = lexeme[       *( char_ -(char_('"') | ',')                  )        ];
        DDQUOTE     = lit("\"\"")       [_val = '"'];
        COMMA       = lit(",")          [_val = ','];
    }

};

int main()
{
    std::cout << "Enter CSV lines [empty] to quit\n";

    using bascii::space;
    typedef std::string::const_iterator iterator_type;
    typedef csv_parser<iterator_type> csv_parser;

    csv_parser grammar;
    std::string str;
    int fid;
    while (getline(std::cin, str))
    {
        fid = 0;

        if (str.empty())
            break;

        std::vector<std::string> csv;
        std::string::const_iterator it_beg = str.begin();
        std::string::const_iterator it_end = str.end();
        bool r = phrase_parse(it_beg, it_end, grammar, space, csv);

        if (r && it_beg == it_end)
        {
            std::cout << "Parsing succeeded\n";
            for (auto& field: csv)
            {
                std::cout << "field " << ++fid << ": " << field << std::endl;
            }
        }
        else
        {
            std::cout << "Parsing failed\n";
        }
    }

    return 0;
}

编译:

make csvparser

测试(例子摘自维基百科):

./csvparser
Enter CSV lines [empty] to quit

1999,Chevy,"Venture ""Extended Edition, Very Large""",,5000.00
Parsing succeeded
field 1: 1999
field 2: Chevy
field 3: Venture "Extended Edition, Very Large"
field 4: 
field 5: 5000.00

1999,Chevy,"Venture ""Extended Edition, Very Large""",,5000.00"
Parsing failed

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!

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;
    }
}

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);
}

下面是Unicode CSV解析器的另一个实现(使用wchar_t)。我写了一部分，乔纳森·莱弗勒写了剩下的部分。

注意:此解析器旨在尽可能地复制Excel的行为，特别是在导入损坏或格式错误的CSV文件时。

这是最初的问题-用多行字段和转义双引号解析CSV文件

这是作为SSCCE(简短，自包含，正确示例)的代码。

#include <stdbool.h>
#include <wchar.h>
#include <wctype.h>

extern const wchar_t *nextCsvField(const wchar_t *p, wchar_t sep, bool *newline);

// Returns a pointer to the start of the next field,
// or zero if this is the last field in the CSV
// p is the start position of the field
// sep is the separator used, i.e. comma or semicolon
// newline says whether the field ends with a newline or with a comma
const wchar_t *nextCsvField(const wchar_t *p, wchar_t sep, bool *newline)
{
    // Parse quoted sequences
    if ('"' == p[0]) {
        p++;
        while (1) {
            // Find next double-quote
            p = wcschr(p, L'"');
            // If we don't find it or it's the last symbol
            // then this is the last field
            if (!p || !p[1])
                return 0;
            // Check for "", it is an escaped double-quote
            if (p[1] != '"')
                break;
            // Skip the escaped double-quote
            p += 2;
        }
    }

    // Find next newline or comma.
    wchar_t newline_or_sep[4] = L"\n\r ";
    newline_or_sep[2] = sep;
    p = wcspbrk(p, newline_or_sep);

    // If no newline or separator, this is the last field.
    if (!p)
        return 0;

    // Check if we had newline.
    *newline = (p[0] == '\r' || p[0] == '\n');

    // Handle "\r\n", otherwise just increment
    if (p[0] == '\r' && p[1] == '\n')
        p += 2;
    else
        p++;

    return p;
}

static wchar_t *csvFieldData(const wchar_t *fld_s, const wchar_t *fld_e, wchar_t *buffer, size_t buflen)
{
    wchar_t *dst = buffer;
    wchar_t *end = buffer + buflen - 1;
    const wchar_t *src = fld_s;

    if (*src == L'"')
    {
        const wchar_t *p = src + 1;
        while (p < fld_e && dst < end)
        {
            if (p[0] == L'"' && p+1 < fld_s && p[1] == L'"')
            {
                *dst++ = p[0];
                p += 2;
            }
            else if (p[0] == L'"')
            {
                p++;
                break;
            }
            else
                *dst++ = *p++;
        }
        src = p;
    }
    while (src < fld_e && dst < end)
        *dst++ = *src++;
    if (dst >= end)
        return 0;
    *dst = L'\0';
    return(buffer);
}

static void dissect(const wchar_t *line)
{
    const wchar_t *start = line;
    const wchar_t *next;
    bool     eol;
    wprintf(L"Input %3zd: [%.*ls]\n", wcslen(line), wcslen(line)-1, line);
    while ((next = nextCsvField(start, L',', &eol)) != 0)
    {
        wchar_t buffer[1024];
        wprintf(L"Raw Field: [%.*ls] (eol = %d)\n", (next - start - eol), start, eol);
        if (csvFieldData(start, next-1, buffer, sizeof(buffer)/sizeof(buffer[0])) != 0)
            wprintf(L"Field %3zd: [%ls]\n", wcslen(buffer), buffer);
        start = next;
    }
}

static const wchar_t multiline[] =
   L"First field of first row,\"This field is multiline\n"
    "\n"
    "but that's OK because it's enclosed in double quotes, and this\n"
    "is an escaped \"\" double quote\" but this one \"\" is not\n"
    "   \"This is second field of second row, but it is not multiline\n"
    "   because it doesn't start \n"
    "   with an immediate double quote\"\n"
    ;

int main(void)
{
    wchar_t line[1024];

    while (fgetws(line, sizeof(line)/sizeof(line[0]), stdin))
        dissect(line);
    dissect(multiline);

    return 0;
}

该解决方案检测这4种情况

完整的课程在

https://github.com/pedro-vicente/csv-parser

1,field 2,field 3,
1,field 2,"field 3 quoted, with separator",
1,field 2,"field 3
with newline",
1,field 2,"field 3
with newline and separator,",

它一个字符一个字符地读取文件，每次读取一行到一个向量(字符串)，因此适合于非常大的文件。

使用

迭代直到返回空行(文件结束)。行是一个向量，其中每个条目都是一个CSV列。

read_csv_t csv;
csv.open("../test.csv");
std::vector<std::string> row;
while (true)
{
  row = csv.read_row();
  if (row.size() == 0)
  {
    break;
  }
}

类声明

class read_csv_t
{
public:
  read_csv_t();
  int open(const std::string &file_name);
  std::vector<std::string> read_row();
private:
  std::ifstream m_ifs;
};

实现

std::vector<std::string> read_csv_t::read_row()
{
  bool quote_mode = false;
  std::vector<std::string> row;
  std::string column;
  char c;
  while (m_ifs.get(c))
  {
    switch (c)
    {
      /////////////////////////////////////////////////////////////////////////////////////////////////////
      //separator ',' detected. 
      //in quote mode add character to column
      //push column if not in quote mode
      /////////////////////////////////////////////////////////////////////////////////////////////////////

    case ',':
      if (quote_mode == true)
      {
        column += c;
      }
      else
      {
        row.push_back(column);
        column.clear();
      }
      break;

      /////////////////////////////////////////////////////////////////////////////////////////////////////
      //quote '"' detected. 
      //toggle quote mode
      /////////////////////////////////////////////////////////////////////////////////////////////////////

    case '"':
      quote_mode = !quote_mode;
      break;

      /////////////////////////////////////////////////////////////////////////////////////////////////////
      //line end detected
      //in quote mode add character to column
      //return row if not in quote mode
      /////////////////////////////////////////////////////////////////////////////////////////////////////

    case '\n':
    case '\r':
      if (quote_mode == true)
      {
        column += c;
      }
      else
      {
        return row;
      }
      break;

      /////////////////////////////////////////////////////////////////////////////////////////////////////
      //default, add character to column
      /////////////////////////////////////////////////////////////////////////////////////////////////////

    default:
      column += c;
      break;
    }
  }

  //return empty vector if end of file detected 
  m_ifs.close();
  std::vector<std::string> v;
  return v;
}