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。
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;
}
}
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();
}
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...
}
如果可以的话,这是我简单快速的贡献。 没有提高。
接受分隔符和分隔符中的分隔符,只要成对或远离分隔符即可。
#include <iostream>
#include <vector>
#include <fstream>
std::vector<std::string> SplitCSV(const std::string &data, char separator, char delimiter)
{
std::vector<std::string> Values;
std::string Val = "";
bool VDel = false; // Is within delimiter?
size_t CDel = 0; // Delimiters counter within delimiters.
const char *C = data.c_str();
size_t P = 0;
do
{
if ((Val.length() == 0) && (C[P] == delimiter))
{
VDel = !VDel;
CDel = 0;
P++;
continue;
}
if (VDel)
{
if (C[P] == delimiter)
{
if (((CDel % 2) == 0) && ( (C[P+1] == separator) || (C[P+1] == 0) || (C[P+1] == '\n') || (C[P+1] == '\r') ))
{
VDel = false;
CDel = 0;
P++;
continue;
}
else
CDel++;
}
}
else
{
if (C[P] == separator)
{
Values.push_back(Val);
Val = "";
P++;
continue;
}
if ((C[P] == 0) || (C[P] == '\n') || (C[P] == '\r'))
break;
}
Val += C[P];
P++;
} while(P < data.length());
Values.push_back(Val);
return Values;
}
bool ReadCsv(const std::string &fname, std::vector<std::vector<std::string>> &data,
char separator = ',', char delimiter = '\"')
{
bool Ret = false;
std::ifstream FCsv(fname);
if (FCsv)
{
FCsv.seekg(0, FCsv.end);
size_t Siz = FCsv.tellg();
if (Siz > 0)
{
FCsv.seekg(0);
data.clear();
std::string Line;
while (getline(FCsv, Line, '\n'))
data.push_back(SplitCSV(Line, separator, delimiter));
Ret = true;
}
FCsv.close();
}
return Ret;
}
int main(int argc, char *argv[])
{
std::vector<std::vector<std::string>> Data;
ReadCsv("fsample.csv", Data);
return 0;
}
你可能想看看我的自由/开源软件项目CSVfix(更新链接),这是一个用c++编写的CSV流编辑器。CSV解析器不是什么好东西,但它完成了工作,整个包可以在不编写任何代码的情况下满足您的需要。
CSV解析器请参见alib/src/a_csv.cpp,使用示例请参见csvlib/src/csved_ioman.cpp (IOManager::ReadCSV)。
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。