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
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!
你可以使用这个库: https://github.com/vadamsky/csvworker
代码示例:
#include <iostream>
#include "csvworker.h"
using namespace std;
int main()
{
//
CsvWorker csv;
csv.loadFromFile("example.csv");
cout << csv.getRowsNumber() << " " << csv.getColumnsNumber() << endl;
csv.getFieldRef(0, 2) = "0";
csv.getFieldRef(1, 1) = "0";
csv.getFieldRef(1, 3) = "0";
csv.getFieldRef(2, 0) = "0";
csv.getFieldRef(2, 4) = "0";
csv.getFieldRef(3, 1) = "0";
csv.getFieldRef(3, 3) = "0";
csv.getFieldRef(4, 2) = "0";
for(unsigned int i=0;i<csv.getRowsNumber();++i)
{
//cout << csv.getRow(i) << endl;
for(unsigned int j=0;j<csv.getColumnsNumber();++j)
{
cout << csv.getField(i, j) << ".";
}
cout << endl;
}
csv.saveToFile("test.csv");
//
CsvWorker csv2(4,4);
csv2.getFieldRef(0, 0) = "a";
csv2.getFieldRef(0, 1) = "b";
csv2.getFieldRef(0, 2) = "r";
csv2.getFieldRef(0, 3) = "a";
csv2.getFieldRef(1, 0) = "c";
csv2.getFieldRef(1, 1) = "a";
csv2.getFieldRef(1, 2) = "d";
csv2.getFieldRef(2, 0) = "a";
csv2.getFieldRef(2, 1) = "b";
csv2.getFieldRef(2, 2) = "r";
csv2.getFieldRef(2, 3) = "a";
csv2.saveToFile("test2.csv");
return 0;
}
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;
}
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();
}
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);
}