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

另一个类似于Loki Astari的答案的解决方案,在c++ 11中。这里的行是给定类型的std::元组。代码扫描一行,然后扫描到每个分隔符,然后将值直接转换并转储到元组中(使用一些模板代码)。

for (auto row : csv<std::string, int, float>(file, ',')) {
    std::cout << "first col: " << std::get<0>(row) << std::endl;
}

优势:

非常干净,使用简单,只有c++ 11。 自动类型转换为std::tuple<t1,…>通过算子>>。

缺少什么:

转义和引用 没有错误处理的情况下畸形的CSV。

主要代码:

#include <iterator>
#include <sstream>
#include <string>

namespace csvtools {
    /// Read the last element of the tuple without calling recursively
    template <std::size_t idx, class... fields>
    typename std::enable_if<idx >= std::tuple_size<std::tuple<fields...>>::value - 1>::type
    read_tuple(std::istream &in, std::tuple<fields...> &out, const char delimiter) {
        std::string cell;
        std::getline(in, cell, delimiter);
        std::stringstream cell_stream(cell);
        cell_stream >> std::get<idx>(out);
    }

    /// Read the @p idx-th element of the tuple and then calls itself with @p idx + 1 to
    /// read the next element of the tuple. Automatically falls in the previous case when
    /// reaches the last element of the tuple thanks to enable_if
    template <std::size_t idx, class... fields>
    typename std::enable_if<idx < std::tuple_size<std::tuple<fields...>>::value - 1>::type
    read_tuple(std::istream &in, std::tuple<fields...> &out, const char delimiter) {
        std::string cell;
        std::getline(in, cell, delimiter);
        std::stringstream cell_stream(cell);
        cell_stream >> std::get<idx>(out);
        read_tuple<idx + 1, fields...>(in, out, delimiter);
    }
}

/// Iterable csv wrapper around a stream. @p fields the list of types that form up a row.
template <class... fields>
class csv {
    std::istream &_in;
    const char _delim;
public:
    typedef std::tuple<fields...> value_type;
    class iterator;

    /// Construct from a stream.
    inline csv(std::istream &in, const char delim) : _in(in), _delim(delim) {}

    /// Status of the underlying stream
    /// @{
    inline bool good() const {
        return _in.good();
    }
    inline const std::istream &underlying_stream() const {
        return _in;
    }
    /// @}

    inline iterator begin();
    inline iterator end();
private:

    /// Reads a line into a stringstream, and then reads the line into a tuple, that is returned
    inline value_type read_row() {
        std::string line;
        std::getline(_in, line);
        std::stringstream line_stream(line);
        std::tuple<fields...> retval;
        csvtools::read_tuple<0, fields...>(line_stream, retval, _delim);
        return retval;
    }
};

/// Iterator; just calls recursively @ref csv::read_row and stores the result.
template <class... fields>
class csv<fields...>::iterator {
    csv::value_type _row;
    csv *_parent;
public:
    typedef std::input_iterator_tag iterator_category;
    typedef csv::value_type         value_type;
    typedef std::size_t             difference_type;
    typedef csv::value_type *       pointer;
    typedef csv::value_type &       reference;

    /// Construct an empty/end iterator
    inline iterator() : _parent(nullptr) {}
    /// Construct an iterator at the beginning of the @p parent csv object.
    inline iterator(csv &parent) : _parent(parent.good() ? &parent : nullptr) {
        ++(*this);
    }

    /// Read one row, if possible. Set to end if parent is not good anymore.
    inline iterator &operator++() {
        if (_parent != nullptr) {
            _row = _parent->read_row();
            if (!_parent->good()) {
                _parent = nullptr;
            }
        }
        return *this;
    }

    inline iterator operator++(int) {
        iterator copy = *this;
        ++(*this);
        return copy;
    }

    inline csv::value_type const &operator*() const {
        return _row;
    }

    inline csv::value_type const *operator->() const {
        return &_row;
    }

    bool operator==(iterator const &other) {
        return (this == &other) or (_parent == nullptr and other._parent == nullptr);
    }
    bool operator!=(iterator const &other) {
        return not (*this == other);
    }
};

template <class... fields>
typename csv<fields...>::iterator csv<fields...>::begin() {
    return iterator(*this);
}

template <class... fields>
typename csv<fields...>::iterator csv<fields...>::end() {
    return iterator();
}

我在GitHub上放了一个小的工作示例;我一直用它来解析一些数值数据,它达到了它的目的。

其他回答

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);
}

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!

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...
}

如果你不想在你的项目中包含boost(如果你只打算使用它来进行CSV解析,它就相当大了……)

我在这里有幸使用CSV解析:

http://www.zedwood.com/article/112/cpp-csv-parser

它处理带引号的字段-但不处理内联\n字符(这可能对大多数用途都很好)。

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;
}