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
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;
}
}
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)。
当你使用boost::spirit这样漂亮的东西时，你应该感到自豪
这里我的一个解析器的尝试(几乎)符合这个链接的CSV规范(我不需要在字段中换行)。逗号周围的空格也被省略了)。
在你克服了编译这段代码需要等待10秒的令人震惊的经历之后:)，你就可以坐下来享受了。
// csvparser.cpp
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix_operator.hpp>
#include <iostream>
#include <string>
namespace qi = boost::spirit::qi;
namespace bascii = boost::spirit::ascii;
template <typename Iterator>
struct csv_parser : qi::grammar<Iterator, std::vector<std::string>(),
bascii::space_type>
{
qi::rule<Iterator, char() > COMMA;
qi::rule<Iterator, char() > DDQUOTE;
qi::rule<Iterator, std::string(), bascii::space_type > non_escaped;
qi::rule<Iterator, std::string(), bascii::space_type > escaped;
qi::rule<Iterator, std::string(), bascii::space_type > field;
qi::rule<Iterator, std::vector<std::string>(), bascii::space_type > start;
csv_parser() : csv_parser::base_type(start)
{
using namespace qi;
using qi::lit;
using qi::lexeme;
using bascii::char_;
start = field % ',';
field = escaped | non_escaped;
escaped = lexeme['"' >> *( char_ -(char_('"') | ',') | COMMA | DDQUOTE) >> '"'];
non_escaped = lexeme[ *( char_ -(char_('"') | ',') ) ];
DDQUOTE = lit("\"\"") [_val = '"'];
COMMA = lit(",") [_val = ','];
}
};
int main()
{
std::cout << "Enter CSV lines [empty] to quit\n";
using bascii::space;
typedef std::string::const_iterator iterator_type;
typedef csv_parser<iterator_type> csv_parser;
csv_parser grammar;
std::string str;
int fid;
while (getline(std::cin, str))
{
fid = 0;
if (str.empty())
break;
std::vector<std::string> csv;
std::string::const_iterator it_beg = str.begin();
std::string::const_iterator it_end = str.end();
bool r = phrase_parse(it_beg, it_end, grammar, space, csv);
if (r && it_beg == it_end)
{
std::cout << "Parsing succeeded\n";
for (auto& field: csv)
{
std::cout << "field " << ++fid << ": " << field << std::endl;
}
}
else
{
std::cout << "Parsing failed\n";
}
}
return 0;
}
编译:
make csvparser
测试(例子摘自维基百科):
./csvparser
Enter CSV lines [empty] to quit
1999,Chevy,"Venture ""Extended Edition, Very Large""",,5000.00
Parsing succeeded
field 1: 1999
field 2: Chevy
field 3: Venture "Extended Edition, Very Large"
field 4:
field 5: 5000.00
1999,Chevy,"Venture ""Extended Edition, Very Large""",,5000.00"
Parsing failed
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();
}
我的版本只使用标准c++ 11库。它很好地处理Excel CSV引用:
spam eggs,"foo,bar","""fizz buzz"""
1.23,4.567,-8.00E+09
代码是作为有限状态机编写的，每次只消耗一个字符。我认为这更容易解释。
#include <istream>
#include <string>
#include <vector>
enum class CSVState {
UnquotedField,
QuotedField,
QuotedQuote
};
std::vector<std::string> readCSVRow(const std::string &row) {
CSVState state = CSVState::UnquotedField;
std::vector<std::string> fields {""};
size_t i = 0; // index of the current field
for (char c : row) {
switch (state) {
case CSVState::UnquotedField:
switch (c) {
case ',': // end of field
fields.push_back(""); i++;
break;
case '"': state = CSVState::QuotedField;
break;
default: fields[i].push_back(c);
break; }
break;
case CSVState::QuotedField:
switch (c) {
case '"': state = CSVState::QuotedQuote;
break;
default: fields[i].push_back(c);
break; }
break;
case CSVState::QuotedQuote:
switch (c) {
case ',': // , after closing quote
fields.push_back(""); i++;
state = CSVState::UnquotedField;
break;
case '"': // "" -> "
fields[i].push_back('"');
state = CSVState::QuotedField;
break;
default: // end of quote
state = CSVState::UnquotedField;
break; }
break;
}
}
return fields;
}
/// Read CSV file, Excel dialect. Accept "quoted fields ""with quotes"""
std::vector<std::vector<std::string>> readCSV(std::istream &in) {
std::vector<std::vector<std::string>> table;
std::string row;
while (!in.eof()) {
std::getline(in, row);
if (in.bad() || in.fail()) {
break;
}
auto fields = readCSVRow(row);
table.push_back(fields);
}
return table;
}
