I am new to Boost Spirit and is struggling to create a proper expression to parse the following input (actually a result of a stdout of some command):
^+ line-17532.dyn.kponet.fi 2 7 377 1 +1503us[+9103us] +/- 55ms
Which I need to parse into a set of strings and integers and recorded in variables. Most of the line should be just parsed into a variable of appropriate type (string or int). So in the end, I get:
string: "^+", "line-17532.dyn.kponet.fi", "+1503us", "+9103us", "55ms"
int : 2, 7, 377, 1
The pair
+1503us[+9103us]
can also be with space
+503us[ +103us]
and I need stuff before square brackets and in square brackets to be placed in separate strings.
additionally, time designations can be expressed as
ns, ms, us, s
I appreciate examples about how to deal with it, because the available documentation is quite sparse and not cohesive.
Large piece of the log, along with headings describing the individual fields:
MS Name/IP address Stratum Poll Reach LastRx Last sample
===============================================================================
^+ ns2.sdi.fi 2 9 377 381 -1476us[-1688us] +/- 72ms
^+ line-17532.dyn.kponet.fi 2 10 377 309 +302us[ +302us] +/- 59ms
^* heh.fi 2 10 377 319 -1171us[-1387us] +/- 50ms
^+ stara.mulimuli.fi 3 10 377 705 -1253us[-1446us] +/- 73ms
As always I start with sketching a useful AST:
namespace AST {
using clock = std::chrono::high_resolution_clock;
struct TimeSample {
enum Direction { up, down } direction; // + or -
clock::duration value;
};
struct Record {
std::string prefix; // "^+"
std::string fqdn; // "line-17532.dyn.kponet.fi"
int a, b, c, d; // 2, 7, 377, 1
TimeSample primary, braced;
clock::duration tolerance;
};
}
Now that we know what we want to parse, we mostly just mimick the AST with rules, for a bit:
using namespace qi;
start = skip(blank) [record_];
record_ = prefix_ >> fqdn_ >> int_ >> int_ >> int_ >> int_ >> sample_ >> '[' >> sample_ >> ']' >> tolerance_;
prefix_ = string("^+"); // or whatever you need to match here
fqdn_ = +graph; // or whatever additional constraints you have
sample_ = direction_ >> duration_;
duration_ = (long_ >> units_) [ _val = _1 * _2 ];
tolerance_= "+/-" >> duration_;
Of course, the interesting bits are the units and the direction:
struct directions : qi::symbols<char, AST::TimeSample::Direction> {
directions() { add("+", AST::TimeSample::up)("-", AST::TimeSample::down); }
} direction_;
struct units : qi::symbols<char, AST::clock::duration> {
units() {
using namespace std::literals::chrono_literals;
add("s", 1s)("ms", 1ms)("us", 1us)("µs", 1us)("ns", 1ns);
}
} units_;
The white-space acceptance is governed by a skipper; I chose qi::blank_type for the non-lexeme rules:
using Skipper = qi::blank_type;
qi::rule<It, AST::Record()> start;
qi::rule<It, AST::Record(), Skipper> record_;
qi::rule<It, AST::TimeSample(), Skipper> sample_;
qi::rule<It, AST::clock::duration(), Skipper> duration_, tolerance_;
// lexemes:
qi::rule<It, std::string()> prefix_;
qi::rule<It, std::string()> fqdn_;
Putting it all together, use it:
int main() {
std::istringstream iss(R"(^+ line-17532.dyn.kponet.fi 2 7 377 1 +1503us[+9103us] +/- 55ms
)");
std::string line;
while (getline(iss, line)) {
auto f = line.cbegin(), l = line.cend();
AST::Record record;
if (parse(f, l, parser<>{}, record))
std::cout << "parsed: " << boost::fusion::as_vector(record) << "\n";
else
std::cout << "parse error\n";
if (f!=l)
std::cout << "remaining unparsed input: '" << std::string(f,l) << "'\n";
}
}
Which prints: Live On Coliru
parsed: (^+ line-17532.dyn.kponet.fi 2 7 377 1 +0.001503s +0.009103s 0.055s)
(debug output below)
#define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <boost/fusion/adapted.hpp>
#include <sstream>
#include <chrono>
namespace std { namespace chrono {
// for debug
std::ostream& operator<<(std::ostream& os, duration<double> d) { return os << d.count() << "s"; }
} }
namespace AST {
using clock = std::chrono::high_resolution_clock;
struct TimeSample {
enum Direction { up, down } direction; // + or -
clock::duration value;
// for debug:
friend std::ostream& operator<<(std::ostream& os, Direction d) {
char const* signs[] = {"+","-"};
return os << signs[d];
}
friend std::ostream& operator<<(std::ostream& os, TimeSample const& sample) {
return os << sample.direction << std::chrono::duration<double>(sample.value).count() << "s";
}
};
struct Record {
std::string prefix; // "^+"
std::string fqdn; // "line-17532.dyn.kponet.fi"
int a, b, c, d; // 2, 7, 377, 1
TimeSample primary, braced;
clock::duration tolerance;
};
}
BOOST_FUSION_ADAPT_STRUCT(AST::Record, prefix, fqdn, a, b, c, d, primary, braced, tolerance)
BOOST_FUSION_ADAPT_STRUCT(AST::TimeSample, direction, value)
namespace qi = boost::spirit::qi;
template <typename It = std::string::const_iterator>
struct parser : qi::grammar<It, AST::Record()> {
parser() : parser::base_type(start) {
using namespace qi;
start = skip(blank) [record_];
record_ = prefix_ >> fqdn_ >> int_ >> int_ >> int_ >> int_ >> sample_ >> '[' >> sample_ >> ']' >> tolerance_;
prefix_ = string("^+"); // or whatever you need to match here
fqdn_ = +graph; // or whatever additional constraints you have
sample_ = direction_ >> duration_;
duration_ = (long_ >> units_) [ _val = _1 * _2 ];
tolerance_= "+/-" >> duration_;
BOOST_SPIRIT_DEBUG_NODES(
(start)(record_)
(prefix_)(fqdn_)(sample_)(duration_)(tolerance_)
)
}
private:
struct directions : qi::symbols<char, AST::TimeSample::Direction> {
directions() { add("+", AST::TimeSample::up)("-", AST::TimeSample::down); }
} direction_;
struct units : qi::symbols<char, AST::clock::duration> {
units() {
using namespace std::literals::chrono_literals;
add("s", 1s)("ms", 1ms)("us", 1us)("µs", 1us)("ns", 1ns);
}
} units_;
using Skipper = qi::blank_type;
qi::rule<It, AST::Record()> start;
qi::rule<It, AST::Record(), Skipper> record_;
qi::rule<It, AST::TimeSample(), Skipper> sample_;
qi::rule<It, AST::clock::duration(), Skipper> duration_, tolerance_;
// lexemes:
qi::rule<It, std::string()> prefix_;
qi::rule<It, std::string()> fqdn_;
};
int main() {
std::istringstream iss(R"(^+ line-17532.dyn.kponet.fi 2 7 377 1 +1503us[+9103us] +/- 55ms
)");
std::string line;
while (getline(iss, line)) {
auto f = line.cbegin(), l = line.cend();
AST::Record record;
if (parse(f, l, parser<>{}, record))
std::cout << "parsed: " << boost::fusion::as_vector(record) << "\n";
else
std::cout << "parse error\n";
if (f!=l)
std::cout << "remaining unparsed input: '" << std::string(f,l) << "'\n";
}
}
<start>
<try>^+ line-17532.dyn.kp</try>
<record_>
<try>^+ line-17532.dyn.kp</try>
<prefix_>
<try>^+ line-17532.dyn.kp</try>
<success> line-17532.dyn.kpon</success>
<attributes>[[^, +]]</attributes>
</prefix_>
<fqdn_>
<try>line-17532.dyn.kpone</try>
<success> 2 7 377 </success>
<attributes>[[l, i, n, e, -, 1, 7, 5, 3, 2, ., d, y, n, ., k, p, o, n, e, t, ., f, i]]</attributes>
</fqdn_>
<sample_>
<try> +1503us[+9103us] </try>
<duration_>
<try>1503us[+9103us] +/- </try>
<success>[+9103us] +/- 55ms</success>
<attributes>[0.001503s]</attributes>
</duration_>
<success>[+9103us] +/- 55ms</success>
<attributes>[[+, 0.001503s]]</attributes>
</sample_>
<sample_>
<try>+9103us] +/- 55ms</try>
<duration_>
<try>9103us] +/- 55ms</try>
<success>] +/- 55ms</success>
<attributes>[0.009103s]</attributes>
</duration_>
<success>] +/- 55ms</success>
<attributes>[[+, 0.009103s]]</attributes>
</sample_>
<tolerance_>
<try> +/- 55ms</try>
<duration_>
<try> 55ms</try>
<success></success>
<attributes>[0.055s]</attributes>
</duration_>
<success></success>
<attributes>[0.055s]</attributes>
</tolerance_>
<success></success>
<attributes>[[[^, +], [l, i, n, e, -, 1, 7, 5, 3, 2, ., d, y, n, ., k, p, o, n, e, t, ., f, i], 2, 7, 377, 1, [+, 0.001503s], [+, 0.009103s], 0.055s]]</attributes>
</record_>
<success></success>
<attributes>[[[^, +], [l, i, n, e, -, 1, 7, 5, 3, 2, ., d, y, n, ., k, p, o, n, e, t, ., f, i], 2, 7, 377, 1, [+, 0.001503s], [+, 0.009103s], 0.055s]]</attributes>
</start>