I have this csv line
std::string s = R"(1997,Ford,E350,"ac, abs, moon","some "rusty" parts",3000.00)";
I can parse it using boost::tokenizer
:
typedef boost::tokenizer< boost::escaped_list_separator<char> , std::string::const_iterator, std::string> Tokenizer;
boost::escaped_list_separator<char> seps('\\', ',', '\"');
Tokenizer tok(s, seps);
for (auto i : tok)
{
std::cout << i << std::endl;
}
It gets it right except token "rusty" should have double quotes which are getting stripped.
Here is my attempt to use boost::spirit
boost::spirit::classic::rule<> list_csv_item = !(boost::spirit::classic::confix_p('\"', *boost::spirit::classic::c_escape_ch_p, '\"') | boost::spirit::classic::longest_d[boost::spirit::classic::real_p | boost::spirit::classic::int_p]);
std::vector<std::string> vec_item;
std::vector<std::string> vec_list;
boost::spirit::classic::rule<> list_csv = boost::spirit::classic::list_p(list_csv_item[boost::spirit::classic::push_back_a(vec_item)],',')[boost::spirit::classic::push_back_a(vec_list)];
boost::spirit::classic::parse_info<> result = parse(s.c_str(), list_csv);
if (result.hit)
{
for (auto i : vec_item)
{
cout << i << endl;
}
}
Problems:
does not work, prints the first token only
why boost::spirit::classic? can't find examples using Spirit V2
the setup is brutal .. but I can live with this
** I really want to use boost::spirit
because it tends to be pretty fast
Expected output:
1997
Ford
E350
ac, abs, moon
some "rusty" parts
3000.00
For a background on parsing (optionally) quoted delimited fields, including different quoting characters (
'
,"
), see here:For a very, very, very complete example complete with support for partially quoted values and a
splitInto(input, output, ' ');
method that takes 'arbitrary' output containers and delimiter expressions, see here:
Addressing your exact question, assuming either quoted or unquoted fields (no partial quotes inside field values), using Spirit V2:
Let's take the simplest 'abstract datatype' that could possibly work:
using Column = std::string;
using Columns = std::vector<Column>;
using CsvLine = Columns;
using CsvFile = std::vector<CsvLine>;
And the repeated double-quote escapes a double-quote semantics (as I pointed out in the comment), you should be able to use something like:
static const char colsep = ',';
start = -line % eol;
line = column % colsep;
column = quoted | *~char_(colsep);
quoted = '"' >> *("\"\"" | ~char_('"')) >> '"';
The following complete test program prints
[1997][Ford][E350][ac, abs, moon][rusty][3001.00]
(Note the BOOST_SPIRIT_DEBUG define for easy debugging). See it Live on Coliru
//#define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/qi.hpp>
namespace qi = boost::spirit::qi;
using Column = std::string;
using Columns = std::vector<Column>;
using CsvLine = Columns;
using CsvFile = std::vector<CsvLine>;
template <typename It>
struct CsvGrammar : qi::grammar<It, CsvFile(), qi::blank_type>
{
CsvGrammar() : CsvGrammar::base_type(start)
{
using namespace qi;
static const char colsep = ',';
start = -line % eol;
line = column % colsep;
column = quoted | *~char_(colsep);
quoted = '"' >> *("\"\"" | ~char_('"')) >> '"';
BOOST_SPIRIT_DEBUG_NODES((start)(line)(column)(quoted));
}
private:
qi::rule<It, CsvFile(), qi::blank_type> start;
qi::rule<It, CsvLine(), qi::blank_type> line;
qi::rule<It, Column(), qi::blank_type> column;
qi::rule<It, std::string()> quoted;
};
int main()
{
const std::string s = R"(1997,Ford,E350,"ac, abs, moon","""rusty""",3001.00)";
auto f(begin(s)), l(end(s));
CsvGrammar<std::string::const_iterator> p;
CsvFile parsed;
bool ok = qi::phrase_parse(f,l,p,qi::blank,parsed);
if (ok)
{
for(auto& line : parsed) {
for(auto& col : line)
std::cout << '[' << col << ']';
std::cout << std::endl;
}
} else
{
std::cout << "Parse failed\n";
}
if (f!=l)
std::cout << "Remaining unparsed: '" << std::string(f,l) << "'\n";
}