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
可以使用std::regex。
根据文件大小和可用内存,可以逐行读取,也可以完全在std::string中读取。
读取文件可以使用:
std::ifstream t("file.txt");
std::string sin((std::istreambuf_iterator<char>(t)),
std::istreambuf_iterator<char>());
然后你可以和这个相匹配,它实际上是根据你的需要定制的。
std::regex word_regex(",\\s]+");
auto what =
std::sregex_iterator(sin.begin(), sin.end(), word_regex);
auto wend = std::sregex_iterator();
std::vector<std::string> v;
for (;what!=wend ; wend) {
std::smatch match = *what;
v.push_back(match.str());
}
其他回答
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
}
}
如果你不关心转义逗号和换行符, 并且你不能在引号中嵌入逗号和换行符(如果你不能转义那么…) 那么它只有大约三行代码(好的14 ->,但它只有15读取整个文件)。
std::vector<std::string> getNextLineAndSplitIntoTokens(std::istream& str)
{
std::vector<std::string> result;
std::string line;
std::getline(str,line);
std::stringstream lineStream(line);
std::string cell;
while(std::getline(lineStream,cell, ','))
{
result.push_back(cell);
}
// This checks for a trailing comma with no data after it.
if (!lineStream && cell.empty())
{
// If there was a trailing comma then add an empty element.
result.push_back("");
}
return result;
}
我只需要创建一个表示一行的类。 然后流到该对象:
#include <iterator>
#include <iostream>
#include <fstream>
#include <sstream>
#include <vector>
#include <string>
class CSVRow
{
public:
std::string_view operator[](std::size_t index) const
{
return std::string_view(&m_line[m_data[index] + 1], m_data[index + 1] - (m_data[index] + 1));
}
std::size_t size() const
{
return m_data.size() - 1;
}
void readNextRow(std::istream& str)
{
std::getline(str, m_line);
m_data.clear();
m_data.emplace_back(-1);
std::string::size_type pos = 0;
while((pos = m_line.find(',', pos)) != std::string::npos)
{
m_data.emplace_back(pos);
++pos;
}
// This checks for a trailing comma with no data after it.
pos = m_line.size();
m_data.emplace_back(pos);
}
private:
std::string m_line;
std::vector<int> m_data;
};
std::istream& operator>>(std::istream& str, CSVRow& data)
{
data.readNextRow(str);
return str;
}
int main()
{
std::ifstream file("plop.csv");
CSVRow row;
while(file >> row)
{
std::cout << "4th Element(" << row[3] << ")\n";
}
}
但只要做一点工作,我们就可以在技术上创建一个迭代器:
class CSVIterator
{
public:
typedef std::input_iterator_tag iterator_category;
typedef CSVRow value_type;
typedef std::size_t difference_type;
typedef CSVRow* pointer;
typedef CSVRow& reference;
CSVIterator(std::istream& str) :m_str(str.good()?&str:nullptr) { ++(*this); }
CSVIterator() :m_str(nullptr) {}
// Pre Increment
CSVIterator& operator++() {if (m_str) { if (!((*m_str) >> m_row)){m_str = nullptr;}}return *this;}
// Post increment
CSVIterator operator++(int) {CSVIterator tmp(*this);++(*this);return tmp;}
CSVRow const& operator*() const {return m_row;}
CSVRow const* operator->() const {return &m_row;}
bool operator==(CSVIterator const& rhs) {return ((this == &rhs) || ((this->m_str == nullptr) && (rhs.m_str == nullptr)));}
bool operator!=(CSVIterator const& rhs) {return !((*this) == rhs);}
private:
std::istream* m_str;
CSVRow m_row;
};
int main()
{
std::ifstream file("plop.csv");
for(CSVIterator loop(file); loop != CSVIterator(); ++loop)
{
std::cout << "4th Element(" << (*loop)[3] << ")\n";
}
}
现在我们已经到了2020年,让我们添加一个CSVRange对象:
class CSVRange
{
std::istream& stream;
public:
CSVRange(std::istream& str)
: stream(str)
{}
CSVIterator begin() const {return CSVIterator{stream};}
CSVIterator end() const {return CSVIterator{};}
};
int main()
{
std::ifstream file("plop.csv");
for(auto& row: CSVRange(file))
{
std::cout << "4th Element(" << row[3] << ")\n";
}
}
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。
如果您所需要的只是加载一个双精度数据文件(没有整数,没有文本),那么这里有一个随时可用的函数。
#include <sstream>
#include <fstream>
#include <iterator>
#include <string>
#include <vector>
#include <algorithm>
using namespace std;
/**
* Parse a CSV data file and fill the 2d STL vector "data".
* Limits: only "pure datas" of doubles, not encapsulated by " and without \n inside.
* Further no formatting in the data (e.g. scientific notation)
* It however handles both dots and commas as decimal separators and removes thousand separator.
*
* returnCodes[0]: file access 0-> ok 1-> not able to read; 2-> decimal separator equal to comma separator
* returnCodes[1]: number of records
* returnCodes[2]: number of fields. -1 If rows have different field size
*
*/
vector<int>
readCsvData (vector <vector <double>>& data, const string& filename, const string& delimiter, const string& decseparator){
int vv[3] = { 0,0,0 };
vector<int> returnCodes(&vv[0], &vv[0]+3);
string rowstring, stringtoken;
double doubletoken;
int rowcount=0;
int fieldcount=0;
data.clear();
ifstream iFile(filename, ios_base::in);
if (!iFile.is_open()){
returnCodes[0] = 1;
return returnCodes;
}
while (getline(iFile, rowstring)) {
if (rowstring=="") continue; // empty line
rowcount ++; //let's start with 1
if(delimiter == decseparator){
returnCodes[0] = 2;
return returnCodes;
}
if(decseparator != "."){
// remove dots (used as thousand separators)
string::iterator end_pos = remove(rowstring.begin(), rowstring.end(), '.');
rowstring.erase(end_pos, rowstring.end());
// replace decimal separator with dots.
replace(rowstring.begin(), rowstring.end(),decseparator.c_str()[0], '.');
} else {
// remove commas (used as thousand separators)
string::iterator end_pos = remove(rowstring.begin(), rowstring.end(), ',');
rowstring.erase(end_pos, rowstring.end());
}
// tokenize..
vector<double> tokens;
// Skip delimiters at beginning.
string::size_type lastPos = rowstring.find_first_not_of(delimiter, 0);
// Find first "non-delimiter".
string::size_type pos = rowstring.find_first_of(delimiter, lastPos);
while (string::npos != pos || string::npos != lastPos){
// Found a token, convert it to double add it to the vector.
stringtoken = rowstring.substr(lastPos, pos - lastPos);
if (stringtoken == "") {
tokens.push_back(0.0);
} else {
istringstream totalSString(stringtoken);
totalSString >> doubletoken;
tokens.push_back(doubletoken);
}
// Skip delimiters. Note the "not_of"
lastPos = rowstring.find_first_not_of(delimiter, pos);
// Find next "non-delimiter"
pos = rowstring.find_first_of(delimiter, lastPos);
}
if(rowcount == 1){
fieldcount = tokens.size();
returnCodes[2] = tokens.size();
} else {
if ( tokens.size() != fieldcount){
returnCodes[2] = -1;
}
}
data.push_back(tokens);
}
iFile.close();
returnCodes[1] = rowcount;
return returnCodes;
}
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;
}