I'm writing a parser for PureData patches using Boost spirit and C++.
I have the following simple test of parsing canvas records:
#include <boost/spirit/include/qi.hpp>
#include <boost/fusion/adapted/adt/adapt_adt.hpp>
#include <boost/fusion/include/adapt_adt.hpp>
struct PdCanvas {
int topX;
int topY;
int wX;
int wY;
std::string name;
int openOnLoad;
};
BOOST_FUSION_ADAPT_STRUCT(
PdCanvas,
(int, topX)
(int, topY)
(int, wX)
(int, wY)
(std::string, name)
(int, openOnLoad));
template <typename Iterator>
struct PdCanvasGrammar : qi::grammar<Iterator, PdCanvas(), ascii::space_type> {
PdCanvasGrammar() : PdCanvasGrammar::base_type(canvasRule){
canvasRule = qi::lit("#N canvas") >> qi::int_ >> qi::int_ >> qi::int_ >> qi::int_ >> +(qi::char_ - qi::space) >> qi::int_ >> ";";
}
qi::rule<Iterator, PdCanvas(), ascii::space_type> canvasRule;
};
int main(int argc, char** argv)
{
if(argc != 2)
{
std::cout << "Usage: " <<argv[0] << " <PatchFile>" << std::endl;
exit(1);
}
std::ifstream inputFile(argv[1]);
std::string inputString(std::istreambuf_iterator<char>(inputFile), {});
PdCanvas root;
PdCanvasGrammar<std::string::iterator> parser;
std::cout << "Loaded file:\n " << inputString << std::endl;
bool success = qi::phrase_parse(inputString.begin(), inputString.end(), parser, boost::spirit::ascii::space, root);
std::cout << "Success: " << success << std::endl;
return 0;
}
As one can see, the format of a canvas record is
#N canvas <int> <int> <int> <int> <string> <int>;
And that's what the rule should expect, but when I try to parse the following:
#N canvas 0 0 400 300 moo 1;
qi::phrase_parse returns false, indicating an unsuccessful parse.
As an aside, there is another form of the canvas grammar in PD, specifically for the root, which is of the form:
#N canvas <int> <int> <int> <int> <int>;
Which I have successfully parsed using a different rule, so my assumption is the problem comes from attempting to parse the string in the middle of the integers.
So my question is thus: What is wrong with my qi::rule and how can I change it to properly parse?
Two things:
Note that PEG grammars are "greedy left-to-right", so you will want to make sure that the int_ >> ";" is not parsed into the name:
#include <boost/fusion/adapted.hpp>
#include <boost/spirit/include/qi.hpp>
#include <iomanip>
namespace qi = boost::spirit::qi;
struct PdCanvas { int topX, topY, wX, wY, openOnLoad; std::string name; };
BOOST_FUSION_ADAPT_STRUCT(PdCanvas, topX, topY, wX, wY, name, openOnLoad);
template <typename Iterator> struct PdCanvasGrammar : qi::grammar<Iterator, PdCanvas(), qi::space_type> {
PdCanvasGrammar() : PdCanvasGrammar::base_type(canvasRule) {
canvasRule = //
"#N canvas" >> qi::int_ >> qi::int_ //
>> qi::int_ >> qi::int_ //
>> *(qi::char_ - (qi::int_ >> ';')) //
>> qi::int_ >> ';' //
;
}
qi::rule<Iterator, PdCanvas(), qi::space_type> canvasRule;
};
int main() {
PdCanvasGrammar<std::string::const_iterator> const parser;
for (std::string const input :
{
"#N canvas 0 0 400 300 moo 1;",
"#N canvas -10 -10 390 290 42 answers LtUaE -9;",
R"(#N canvas -10 -10 390 290 To be, or not to be, that is the question:
Whether 'tis nobler in the mind to suffer
The slings and arrows of outrageous fortune,
Or to take Arms against a Sea of troubles,
-9;)",
}) //
{
// std::cout << "Input:\n " << quoted(input) << std::endl;
if (PdCanvas root; phrase_parse(input.begin(), input.end(), parser, qi::space, root))
std::cout << "Success -> " << boost::fusion::as_vector(root) << "\n";
else
std::cout << "Failed\n";
}
}
Prints:
Success -> (0 0 400 300 moo 1)
Success -> (-10 -10 390 290 42answersLtUaE -9)
Success -> (-10 -10 390 290 Tobe,ornottobe,thatisthequestion:Whether'tisnoblerinthemindtosufferTheslingsandarrowsofoutrageousfortune,OrtotakeArmsagainstaSeaoftroubles, -9)
I chose some outrageous "names" on purpose:
Your rule has a skipper: space_type. This - by definition - means that +(qi::char_ - qi::space) is equivalent to +qi::char_ because spaces aren't even seen by the expression.
To alleviate the issue make sure that the space-sensitive expression does not execute under the skipper, see Boost spirit skipper issues.
Using lexeme[] here is the quickest solution:
canvasRule = //
"#N canvas" >> qi::int_ >> qi::int_ //
>> qi::int_ >> qi::int_ //
>> qi::lexeme[*(qi::char_ - (qi::int_ >> ';'))] //
>> qi::int_ >> ';' //
;
Prints Live:
Success -> (0 0 400 300 moo 1)
Success -> (-10 -10 390 290 42 answers LtUaE -9)
Success -> (-10 -10 390 290 To be, or not to be, that is the question:
Whether 'tis nobler in the mind to suffer
The slings and arrows of outrageous fortune,
Or to take Arms against a Sea of troubles,
-9)
To also disallow space in the name, use qi::graph instead of qi::char_:
Prints Live:
Success -> (0 0 400 300 moo 1)
Failed
Failed
To make things easier to maintain, debug (!!) and also express intent, I'd
qi::eoi)// #define BOOST_SPIRIT_DEBUG
#include <boost/fusion/adapted.hpp>
#include <boost/spirit/include/qi.hpp>
#include <iomanip>
namespace qi = boost::spirit::qi;
struct PdCanvas { int topX, topY, wX, wY, openOnLoad; std::string name; };
BOOST_FUSION_ADAPT_STRUCT(PdCanvas, topX, topY, wX, wY, name, openOnLoad);
template <typename Iterator> struct PdCanvasGrammar : qi::grammar<Iterator, PdCanvas()> {
PdCanvasGrammar() : PdCanvasGrammar::base_type(start) {
using namespace qi;
start = skip(space)[canvasRule >> eoi];
name = +graph;
canvasRule = "#N canvas" >> int_ >> int_ >> int_ >> int_ >> name >> int_ >> ';';
BOOST_SPIRIT_DEBUG_NODES((start)(canvasRule)(name))
}
private:
qi::rule<Iterator, PdCanvas()> start;
qi::rule<Iterator, PdCanvas(), qi::space_type> canvasRule;
qi::rule<Iterator, std::string()> name;
};
int main() {
PdCanvasGrammar<std::string::const_iterator> const parser;
for (std::string const input :
{
"#N canvas 0 0 400 300 foo 1;",
"#N canvas 0 0 400 300 bar 1;",
"#N canvas 0 0 400 300 qux1 1;",
"#N canvas 0 0 400 300 qux23 1;",
"#N canvas 0 0 400 300 qux23;funky 1;",
"#N canvas 0 0 400 300 trailing 1; junk",
}) //
{
std::cout << "Input: " << quoted(input) << std::endl;
if (PdCanvas root; parse(input.begin(), input.end(), parser, root))
std::cout << " Success -> " << boost::fusion::as_vector(root) << "\n";
else
std::cout << " Failed\n";
}
}
Prints
Input: "#N canvas 0 0 400 300 foo 1;"
Success -> (0 0 400 300 foo 1)
Input: "#N canvas 0 0 400 300 bar 1;"
Success -> (0 0 400 300 bar 1)
Input: "#N canvas 0 0 400 300 qux1 1;"
Success -> (0 0 400 300 qux1 1)
Input: "#N canvas 0 0 400 300 qux23 1;"
Success -> (0 0 400 300 qux23 1)
Input: "#N canvas 0 0 400 300 qux23;funky 1;"
Success -> (0 0 400 300 qux23;funky 1)
Input: "#N canvas 0 0 400 300 trailing 1; junk"
Failed
Or, with debug enabled, e.g.
Input: "#N canvas 0 0 400 300 foo 1;"
<start>
<try>#N canvas 0 0 400 30</try>
<canvasRule>
<try>#N canvas 0 0 400 30</try>
<name>
<try>foo 1;</try>
<success> 1;</success>
<attributes>[[f, o, o]]</attributes>
</name>
<success></success>
<attributes>[[0, 0, 400, 300, [f, o, o], 1]]</attributes>
</canvasRule>
<success></success>
<attributes>[[0, 0, 400, 300, [f, o, o], 1]]</attributes>
</start>
Success -> (0 0 400 300 foo 1)