X3 newbie here. Two questions:
<attributes>[[1, 9, 2, ., 1, 6, 8, ., 1, 1, 1, ., 1, 1, 1], [8, 0]]</attributes>, when I expect something like this <attributes>[[1, 9, 2, ., 1, 6, 8, ., 1, ., 1], [8, 0]]</attributes>x3::repeat(1)[x3::digit], but this seems wrong and probably causes errors of first question. (x3::repeat(1)[x3::digit] is used because it seems I can'not just use x3::digit instead, because it would fail rule collapsing ?)#include <iostream>
#include <string>
#define BOOST_SPIRIT_X3_DEBUG
#include <boost/spirit/home/x3.hpp>
#include <boost/fusion/include/adapt_struct.hpp>
namespace x3 = boost::spirit::x3;
namespace ast
{
struct ip_port
{
std::string host;
boost::optional<std::string> port;
};
}
BOOST_FUSION_ADAPT_STRUCT(ast::ip_port, host, port)
namespace parser
{
template <typename T> auto as = [](auto name, auto p) { return x3::rule<struct _, T> {name} = p; };
const auto dec_octet = as<std::string>("dec_octet",
(
x3::char_('2') >> x3::char_('5') >> x3::char_('0', '5')
| x3::char_('2') >> x3::char_('0', '4') >> x3::digit
| x3::char_('1') >> x3::digit >> x3::digit
| x3::char_('1', '9') >> x3::digit
| x3::repeat(1)[x3::digit] // awkward way to force sequence from single char, but can't use x3::digit
)
);
const auto ipv4address = as<std::string>("ipv4address",
dec_octet >> x3::char_('.') >> dec_octet >> x3::char_('.') >> dec_octet >> x3::char_('.') >> dec_octet
);
const auto ip = as<std::string>("host", ipv4address);
const auto port = as<std::string>("port", +x3::digit);
const auto ip_port = as<ast::ip_port>("ip_port", ip >> -((':') >> port));
}
template <typename T, typename Parser>
bool parse(const std::string& in, const Parser& p)
{
T parsed;
auto iter = in.begin();
auto end_iter = in.end();
bool res = x3::parse(iter, end_iter, p, parsed);
return res && (iter == end_iter);
}
int main()
{
std::cerr << std::boolalpha << parse<ast::ip_port>(std::string{"192.168.1.1:80"}, parser::ip_port) << '\n';
return EXIT_SUCCESS;
}
Debug output:
<ip_port>
<try>192.168.1.1:80</try>
<host>
<try>192.168.1.1:80</try>
<ipv4address>
<try>192.168.1.1:80</try>
<dec_octet>
<try>192.168.1.1:80</try>
<success>.168.1.1:80</success>
<attributes>[1, 9, 2]</attributes>
</dec_octet>
<dec_octet>
<try>168.1.1:80</try>
<success>.1.1:80</success>
<attributes>[1, 6, 8]</attributes>
</dec_octet>
<dec_octet>
<try>1.1:80</try>
<success>.1:80</success>
<attributes>[1, 1, 1]</attributes>
</dec_octet>
<dec_octet>
<try>1:80</try>
<success>:80</success>
<attributes>[1, 1, 1]</attributes>
</dec_octet>
<success>:80</success>
<attributes>[1, 9, 2, ., 1, 6, 8, ., 1, 1, 1, ., 1, 1, 1]</attributes>
</ipv4address>
<success>:80</success>
<attributes>[1, 9, 2, ., 1, 6, 8, ., 1, 1, 1, ., 1, 1, 1]</attributes>
</host>
<port>
<try>80</try>
<success></success>
<attributes>[8, 0]</attributes>
</port>
<success></success>
<attributes>[[1, 9, 2, ., 1, 6, 8, ., 1, 1, 1, ., 1, 1, 1], [8, 0]]</attributes>
</ip_port>
true
Thanks.
Q. 1. Why the result contains repeated "1,1,1"s, like so: [[1, 9, 2, ., 1, 6, 8, ., 1, 1, 1, ., 1, 1, 1], [8, 0]], when I expect something like this [[1, 9, 2, ., 1, 6, 8, ., 1, ., 1], [8, 0]]
It's been 7 days since the last time people ran into this pitfall:
It's the age-old "container attributes aren't atomic" pitfall:
- boost::spirit::qi duplicate parsing on the output
- Understanding Boost.spirit's string parser
- Parsing with Boost::Spirit (V2.4) into container
You can paper over it using
qi::hold. Or you can revise your strategy.
Like in that case, I'd advise to use raw to get the underlying source sequence instead.
Q. 2. [...] not so awkward [...]
The intermediate step would be
const auto dec_octet = x3::raw [ x3::uint_parser<uint8_t>{} ];
Boom. Use the fact that X3 is a highlevel parser generator. Don't do the nitty gritty, error prone work. In fact, you could simply
const x3::uint_parser<std::uint8_t> dec_octet{};
Which defers the "stringification" to the point where it's needed:
const x3::uint_parser<std::uint8_t> dec_octet{};
const x3::uint_parser<std::uint16_t> port{};
const auto ipv4address = x3::raw [
dec_octet >> '.' >> dec_octet >> '.' >> dec_octet >> '.' >> dec_octet ];
const auto ip_port = as<ast::ip_port>("ip_port", ipv4address >> -(':' >> port));
Note the use of uint16_t for the port, x3::eoi to expect full parse, removal of explicit rule/conversions:
#include <iostream>
#include <string>
#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/fusion/include/io.hpp>
#include <boost/optional/optional_io.hpp>
#include <boost/spirit/home/x3.hpp>
namespace x3 = boost::spirit::x3;
namespace ast {
struct ip_port {
std::string host;
boost::optional<uint16_t> port;
};
using boost::fusion::operator<<;
}
BOOST_FUSION_ADAPT_STRUCT(ast::ip_port, host, port)
namespace parser {
const x3::uint_parser<uint8_t> dec_octet {};
const x3::uint_parser<uint16_t> port {};
const auto ipv4address = x3::raw[dec_octet >> '.' >> dec_octet >> '.'
>> dec_octet >> '.' >> dec_octet];
const auto ip_port = ipv4address >> -(':' >> port) >> x3::eoi;
}
template <typename Parser, typename Attr>
static inline bool parse(std::string_view in, Parser const& p, Attr& result)
{
return x3::parse(in.begin(), in.end(), p, result);
}
auto parse_ipport(std::string_view in)
{
ast::ip_port result;
if (!parse(in, parser::ip_port, result))
throw std::invalid_argument("ipv4address");
return result;
}
int main()
{
for (auto input : { "192.168.1.1:80", "1.1.1.1", ":" }) {
std::cerr << parse_ipport(input) << std::endl;
}
}
Prints
(192.168.1.1 80)
(1.1.1.1 --)
terminate called after throwing an instance of 'std::invalid_argument'
what(): ipv4address
Aborted (core dumped)
Simplifying the code some more by removing the optional:
(192.168.1.1 80)
(1.1.1.1 0)
terminate called after throwing an instance of 'std::invalid_argument'
what(): ipv4address
Note: your grammar doesn't match all RFC compliant ip v4 addresses. E.g.
127.1 is valid for 127.0.0.1.0177.1 or 0x7f.1Either fix it for real or don't re-invent the wheel, using boost::asio::ip::address_v4::from_string or even boost::asio::ip::address::from_string and getting IPv6 support for free.