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
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();
}
其他回答
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)。
下面是读取矩阵的代码,注意你在matlab中也有一个csvwrite函数
void loadFromCSV( const std::string& filename )
{
std::ifstream file( filename.c_str() );
std::vector< std::vector<std::string> > matrix;
std::vector<std::string> row;
std::string line;
std::string cell;
while( file )
{
std::getline(file,line);
std::stringstream lineStream(line);
row.clear();
while( std::getline( lineStream, cell, ',' ) )
row.push_back( cell );
if( !row.empty() )
matrix.push_back( row );
}
for( int i=0; i<int(matrix.size()); i++ )
{
for( int j=0; j<int(matrix[i].size()); j++ )
std::cout << matrix[i][j] << " ";
std::cout << std::endl;
}
}
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;
}
CSV文件是由行组成的文本文件,每一行都由逗号分隔的令牌组成。虽然在解析时你应该知道一些事情:
(0)文件用“CP_ACP”编码页编码。您应该使用相同的编码页来解码文件内容。
(1) CSV丢失了“复合单元格”信息(比如rowspan > 1),所以当它被读回excel时,复合单元格信息丢失。
(2)单元格文本可以在头部和尾部用""" "进行引用,文字引用char将变成双引号。因此,结束匹配的引号字符必须是一个引号字符,而不是后面跟着另一个引号字符。例如,如果一个单元格有逗号,它必须在csv中被引用,因为逗号在csv中有意义。
(3)当单元格内容有多行时,它将在CSV中被引用,在这种情况下,解析器必须继续读取CSV文件中的下几行,直到获得与第一个引用字符匹配的结束引号字符,确保当前逻辑行读取完成后再解析该行的令牌。
例如:在CSV文件中,以下3个物理行是由3个令牌组成的逻辑行:
--+----------
1 |a,"b-first part
2 |b-second part
3 |b-third part",c
--+----------
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...
}