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

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

其他回答

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!

@sastanin的解决方案的一个小版本,以便它可以处理引号中的换行。

std::vector<std::vector<std::string>> readCSV(std::istream &in) {
    std::vector<std::vector<std::string>> table;

    while (!in.eof()) {
        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;
                        case '\n': // newline
                                  table.push_back(fields);
                                  state = CSVState::UnquotedField;
                                  fields = vector<string>{""};
                                  i = 0;
                        default:  // end of quote
                                  state = CSVState::UnquotedField;
                                  break; }
                    break;
            }
        }
    }
    return table;
}

就像每个人都把他的解决方案,这里是我的使用模板,lambda和tuple。

它可以将任何具有所需列的CSV转换为tuple的c++向量。

它通过在元组中定义每个CSV行元素类型来工作。

您还需要为每个元素定义std::string到类型转换Formatter lambda(例如使用std::atod)。

然后你就得到了这个结构的一个向量,对应于你的CSV数据。

您可以很容易地重用它来匹配任何CSV结构。

StringsHelpers.hpp

#include <string>
#include <fstream>
#include <vector>
#include <functional>

namespace StringHelpers
{
    template<typename Tuple>
    using Formatter = std::function<Tuple(const std::vector<std::string> &)>;

    std::vector<std::string> split(const std::string &string, const std::string &delimiter);

    template<typename Tuple>
    std::vector<Tuple> readCsv(const std::string &path, const std::string &delimiter, Formatter<Tuple> formatter);
};

StringsHelpers.cpp

#include "StringHelpers.hpp"

namespace StringHelpers
{
    /**
     * Split a string with the given delimiter into several strings
     *
     * @param string - The string to extract the substrings from
     * @param delimiter - The substrings delimiter
     *
     * @return The substrings
     */
    std::vector<std::string> split(const std::string &string, const std::string &delimiter)
    {
        std::vector<std::string> result;
        size_t                   last = 0,
                                 next = 0;

        while ((next = string.find(delimiter, last)) != std::string::npos) {
            result.emplace_back(string.substr(last, next - last));
            last = next + 1;
        }

        result.emplace_back(string.substr(last));

        return result;
    }

    /**
     * Read a CSV file and store its values into the given structure (Tuple with Formatter constructor)
     *
     * @tparam Tuple - The CSV line structure format
     *
     * @param path - The CSV file path
     * @param delimiter - The CSV values delimiter
     * @param formatter - The CSV values formatter that take a vector of strings in input and return a Tuple
     *
     * @return The CSV as vector of Tuple
     */
    template<typename Tuple>
    std::vector<Tuple> readCsv(const std::string &path, const std::string &delimiter, Formatter<Tuple> formatter)
    {
        std::ifstream      file(path, std::ifstream::in);
        std::string        line;
        std::vector<Tuple> result;

        if (file.fail()) {
            throw std::runtime_error("The file " + path + " could not be opened");
        }

        while (std::getline(file, line)) {
            result.emplace_back(formatter(split(line, delimiter)));
        }

        file.close();

        return result;
    }

    // Forward template declarations

    template std::vector<std::tuple<double, double, double>> readCsv<std::tuple<double, double, double>>(const std::string &, const std::string &, Formatter<std::tuple<double, double, double>>);
} // End of StringHelpers namespace

Main.cpp(一些用法)

#include "StringHelpers.hpp"

/**
 * Example of use with a CSV file which have (number,Red,Green,Blue) as line values. We do not want to use the 1st value
 * of the line.
 */
int main(int argc, char **argv)
{
    // Declare CSV line type, formatter and template type
    typedef std::tuple<double, double, double>                          CSV_format;
    typedef std::function<CSV_format(const std::vector<std::string> &)> formatterT;

    enum RGB { Red = 1, Green, Blue };

    const std::string COLOR_MAP_PATH = "/some/absolute/path";

    // Load the color map
    auto colorMap = StringHelpers::readCsv<CSV_format>(COLOR_MAP_PATH, ",", [](const std::vector<std::string> &values) {
        return CSV_format {
                // Here is the formatter lambda that convert each value from string to what you want
                std::strtod(values[Red].c_str(), nullptr),
                std::strtod(values[Green].c_str(), nullptr),
                std::strtod(values[Blue].c_str(), nullptr)
        };
    });

    // Use your colorMap as you  wish...
}

另一个CSV I/O库可以在这里找到:

http://code.google.com/p/fast-cpp-csv-parser/

#include "csv.h"

int main(){
  io::CSVReader<3> in("ram.csv");
  in.read_header(io::ignore_extra_column, "vendor", "size", "speed");
  std::string vendor; int size; double speed;
  while(in.read_row(vendor, size, speed)){
    // do stuff with the data
  }
}

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;
}