Related
I am trying to model a parser for a subset of the C language, for a school project. However, I seem stuck in the process of generating recursive parsing rules for Boost.Spirit, as my rules either overflow the stack or simply do not pick up anything.
For example, I want to model the following syntax:
a ::= ... | A[a] | a1 op a2 | ...
There are some other subsets of syntax for this expression rule, but those are working without problems. For example, if I were to parse A[3*4], it should be read as a recursive parsing where A[...] (A[a] in the syntax) is the array accessor and 3*4 (a1 op a2 in the syntax) is the index.
I've tried defining the following rule objects in the grammar struct:
qi::rule<Iterator, Type(), Skipper> expr_arr;
qi::rule<Iterator, Type(), Skipper> expr_binary_arith;
qi::rule<Iterator, Type(), Skipper> expr_a;
And giving them the following grammar:
expr_arr %= qi::lexeme[identifier >> qi::omit['[']] >> expr_a >> qi::lexeme[qi::omit[']']];
expr_binary_arith %= expr_a >> op_binary_arith >> expr_a;
expr_a %= (expr_binary_arith | expr_arr);
where "op_binary_arith" is a qi::symbol<> object with the allowed operator symbols.
This compiles fine, but upon execution enters a supposedly endless loop, and the stack overflows. I've tried looking at the answer by Sehe in the following question: How to set max recursion in boost spirit.
However, I have been unsuccessful in setting a max recursion depth. Firstly, I failed to make it compile without errors for almost any of my attempts, but on the last attempt it built successfully, albeit with very unexpected results.
Can someone guide me in the right direction, as to how I should go about implementing this grammar correctly?
PEG grammars do not handle left-recursion well. In general you have to split out helper rules to write without left-recursion.
In your particular case, the goal production
a ::= ... | A[a] | a1 op a2 | ...
Seems a little off. This would allows foo[bar] or foo + bar but not foo + bar[qux].
Usually, the choice between array element reference or plain identifier is at a lower level of precedence (often "simple expression").
Here's a tiny elaboration:
literal = number_literal | string_literal; // TODO exapnd?
expr_arr = identifier >> '[' >> (expr_a % ',') >> ']';
simple_expression = literal | expr_arr | identifier;
expr_binary_arith = simple_expression >> op_binary_arith >> expr_a;
expr_a = expr_binary_arith | simple_expression;
Now you can parse e.g.:
for (std::string const& input : {
"A[3*4]",
"A[F[3]]",
"A[8 + F[0x31]]",
"3 * \"foo\"",
})
{
std::cout << std::quoted(input) << " -> ";
It f=begin(input), l=end(input);
AST::Expr e;
if (parse(f,l,g,e)) {
std::cout << "Parsed: " << e << "\n";
} else {
std::cout << "Failed\n";
}
if (f!=l) {
std::cout << "Remaining: " << std::quoted(std::string(f,l)) << "\b";
}
}
Which prints Live On Coliru
"A[3*4]" -> Parsed: A[3*4]
"A[F[3]]" -> Parsed: A[F[3]]
"A[8 + F[0x31]]" -> Parsed: A[8+F[49]]
"3 * \"foo\"" -> Parsed: 3*"foo"
NOTE I deliberately left efficiency and operator precedence out of the picture for now.
These are talked about in detail in other answers:
Boost::Spirit Expression Parser
Implementing operator precedence with boost spirit
Boost::Spirit : Optimizing an expression parser
And many more
Full Demo Listing
Live On Coliru
//#define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/qi.hpp>
#include <iomanip>
#include <experimental/iterator>
namespace qi = boost::spirit::qi;
namespace AST {
using Var = std::string;
struct String : std::string {
using std::string::string;
};
using Literal = boost::variant<String, intmax_t, double>;
enum class ArithOp {
addition, subtraction, division, multplication
};
struct IndexExpr;
struct BinOpExpr;
using Expr = boost::variant<
Literal,
Var,
boost::recursive_wrapper<IndexExpr>,
boost::recursive_wrapper<BinOpExpr>
>;
struct IndexExpr {
Expr expr;
std::vector<Expr> indices;
};
struct BinOpExpr {
Expr lhs, rhs;
ArithOp op;
};
std::ostream& operator<<(std::ostream& os, Literal const& lit) {
struct {
std::ostream& os;
void operator()(String const& s) const { os << std::quoted(s); }
void operator()(double d) const { os << d; }
void operator()(intmax_t i) const { os << i; }
} vis {os};
boost::apply_visitor(vis, lit);
return os;
}
std::ostream& operator<<(std::ostream& os, ArithOp const& op) {
switch(op) {
case ArithOp::addition: return os << '+';
case ArithOp::subtraction: return os << '-';
case ArithOp::division: return os << '/';
case ArithOp::multplication: return os << '*';
}
return os << '?';
}
std::ostream& operator<<(std::ostream& os, BinOpExpr const& e) {
return os << e.lhs << e.op << e.rhs;
}
std::ostream& operator<<(std::ostream& os, IndexExpr const& e) {
std::copy(
begin(e.indices),
end(e.indices),
std::experimental::make_ostream_joiner(os << e.expr << '[', ","));
return os << ']';
}
}
BOOST_FUSION_ADAPT_STRUCT(AST::IndexExpr, expr, indices)
BOOST_FUSION_ADAPT_STRUCT(AST::BinOpExpr, lhs, op, rhs)
template <typename Iterator, typename Skipper = qi::space_type>
struct G : qi::grammar<Iterator, AST::Expr()> {
G() : G::base_type(start) {
using namespace qi;
identifier = alpha >> *alnum;
number_literal =
qi::real_parser<double, qi::strict_real_policies<double> >{}
| "0x" >> qi::uint_parser<intmax_t, 16> {}
| qi::int_parser<intmax_t, 10> {}
;
string_literal = '"' >> *('\\' >> char_escape | ~char_('"')) >> '"';
literal = number_literal | string_literal; // TODO exapnd?
expr_arr = identifier >> '[' >> (expr_a % ',') >> ']';
simple_expression = literal | expr_arr | identifier;
expr_binary_arith = simple_expression >> op_binary_arith >> expr_a;
expr_a = expr_binary_arith | simple_expression;
start = skip(space) [expr_a];
BOOST_SPIRIT_DEBUG_NODES(
(start)
(expr_a)(expr_binary_arith)(simple_expression)(expr_a)
(literal)(number_literal)(string_literal)
(identifier))
}
private:
struct escape_sym : qi::symbols<char, char> {
escape_sym() {
this->add
("b", '\b')
("f", '\f')
("r", '\r')
("n", '\n')
("t", '\t')
("\\", '\\')
;
}
} char_escape;
struct op_binary_arith_sym : qi::symbols<char, AST::ArithOp> {
op_binary_arith_sym() {
this->add
("+", AST::ArithOp::addition)
("-", AST::ArithOp::subtraction)
("/", AST::ArithOp::division)
("*", AST::ArithOp::multplication)
;
}
} op_binary_arith;
qi::rule<Iterator, AST::Expr()> start;
qi::rule<Iterator, AST::IndexExpr(), Skipper> expr_arr;
qi::rule<Iterator, AST::BinOpExpr(), Skipper> expr_binary_arith;
qi::rule<Iterator, AST::Expr(), Skipper> simple_expression, expr_a;
// implicit lexemes
qi::rule<Iterator, AST::Literal()> literal, string_literal, number_literal;
qi::rule<Iterator, AST::Var()> identifier;
};
int main() {
using It = std::string::const_iterator;
G<It> const g;
for (std::string const& input : {
"A[3*4]",
"A[F[3]]",
"A[8 + F[0x31]]",
"3 * \"foo\"",
})
{
std::cout << std::quoted(input) << " -> ";
It f=begin(input), l=end(input);
AST::Expr e;
if (parse(f,l,g,e)) {
std::cout << "Parsed: " << e << "\n";
} else {
std::cout << "Failed\n";
}
if (f!=l) {
std::cout << "Remaining: " << std::quoted(std::string(f,l)) << "\b";
}
}
}
We try parse simple number/text(in text present numbers, so we must split input sequence, into 2 elements type(TEXT and NUMBER) vector) grammar where number can be in follow format:
+10.90
10.90
10
+10
-10
So we write grammar:
struct CMyTag
{
TagTypes tagName;
std::string tagData;
std::vector<CMyTag> tagChild;
};
BOOST_FUSION_ADAPT_STRUCT(::CMyTag, (TagTypes, tagName) (std::string, tagData) (std::vector<CMyTag>, tagChild))
template <typename Iterator>
struct TextWithNumbers_grammar : qi::grammar<Iterator, std::vector<CMyTag>()>
{
TextWithNumbers_grammar() :
TextWithNumbers_grammar::base_type(line)
{
line = +(numbertag | texttag);
number = qi::lexeme[-(qi::lit('+') | '-') >> +qi::digit >> *(qi::char_('.') >> +qi::digit)];
numbertag = qi::attr(NUMBER) >> number;
text = +(~qi::digit - (qi::char_("+-") >> qi::digit));
texttag = qi::attr(TEXT) >> text;
}
qi::rule<Iterator, std::string()> number, text;
qi::rule<Iterator, CMyTag()> numbertag, texttag;
qi::rule<Iterator, std::vector<CMyTag>()> line;
};
Everything work fine, but if we try to parse this line:
wernwl kjwnwenrlwe +10.90+ klwnfkwenwf
We got 3 elements vector as expected, but last element in this vector will be with text(CMyTag.tagData):
++ klwnfkwenwf
Additional symbol "+" added.
We also try to rewrite grammar to simple skip number rule:
text = qi::skip(number)[+~qi::digit];
But parser died with segmentation fault exception
Attribute values are not rolled back on backtracking. In practice this is only visible with container attributes (such as vector<> or string).
In this case, the numbertag rule is parsed first and parses the + sign. Then, the number rule fails, and the already-matched + is left in the input.
I don't know exactly what you're trying to do, but it looks like you just want:
line = +(numbertag | texttag);
numbertag = attr(NUMBER) >> raw[double_];
texttag = attr(TEXT) >> raw[+(char_ - double_)];
For the input "wernwl kjwnwenrlwe +10.90e3++ klwnfkwenwf" it prints
Parse success: 5 elements
TEXT 'wernwl kjwnwenrlwe '
NUMBER '+10.90'
TEXT 'e'
NUMBER '3'
TEXT '++ klwnfkwenwf'
Live Demo
Live On Coliru
#include <boost/spirit/include/qi.hpp>
namespace qi = boost::spirit::qi;
enum TagTypes { NUMBER, TEXT, };
struct CMyTag {
TagTypes tagName;
std::string tagData;
};
BOOST_FUSION_ADAPT_STRUCT(::CMyTag, (TagTypes, tagName) (std::string, tagData))
template <typename Iterator>
struct TextWithNumbers_grammar : qi::grammar<Iterator, std::vector<CMyTag>()>
{
TextWithNumbers_grammar() : TextWithNumbers_grammar::base_type(line)
{
using namespace qi;
line = +(numbertag | texttag);
numbertag = attr(NUMBER) >> raw[number];
texttag = attr(TEXT) >> raw[+(char_ - number)];
}
private:
template <typename T>
struct simple_real_policies : boost::spirit::qi::real_policies<T>
{
template <typename It> // No exponent
static bool parse_exp(It&, It const&) { return false; }
template <typename It, typename Attribute> // No exponent
static bool parse_exp_n(It&, It const&, Attribute&) { return false; }
};
qi::real_parser<double, simple_real_policies<double> > number;
qi::rule<Iterator, CMyTag()> numbertag, texttag;
qi::rule<Iterator, std::vector<CMyTag>()> line;
};
int main() {
std::string const input = "wernwl kjwnwenrlwe +10.90e3++ klwnfkwenwf";
using It = std::string::const_iterator;
It f = input.begin(), l = input.end();
std::vector<CMyTag> data;
TextWithNumbers_grammar<It> g;
if (qi::parse(f, l, g, data)) {
std::cout << "Parse success: " << data.size() << " elements\n";
for (auto& s : data) {
std::cout << (s.tagName == NUMBER?"NUMBER":"TEXT")
<< "\t'" << s.tagData << "'\n";
}
} else {
std::cout << "Parse failed\n";
}
if (f!=l)
std::cout << "Remaining unparsed: '" << std::string(f,l) << "'\n";
}
I have a working boost spirit parser and was thinking if it is possible to do iterative update of an abstract syntax tree with boost spirit?
I have a struct similar to:
struct ast;
typedef boost::variant< boost::recursive_wrapper<ast> > node;
struct ast
{
std::vector<int> value;
std::vector<node> children;
};
Which is being parsed by use of:
bool r = phrase_parse(begin, end, grammar, space, ast);
Would it be possible to do iterative update of abstract syntax tree with boost spirit? I have not found any documentation on this, but I was thinking if the parsers semantic actions could push_back on an already existing AST. Has anyone tried this?
This would allow for parsing like this:
bool r = phrase_parse(begin, end, grammar, space, ast); //initial parsing
//the second parse will be called at a later state given some event/timer/io/something
bool r = phrase_parse(begin, end, grammar, space, ast); //additional parsing which will update the already existing AST
How would you know which nodes to merge? Or would you always add ("graft") at the root level? In that case, why don't you just parse another and merge moving the elements into the existing ast?
ast& operator+=(ast&& other) {
std::move(other.value.begin(), other.value.end(), back_inserter(value));
std::move(other.children.begin(), other.children.end(), back_inserter(children));
return *this;
}
Demo Time
Let's devise the simplest grammar I can think of for this AST:
start = '{' >> -(int_ % ',') >> ';' >> -(start % ',') >> '}';
Note I didn't even make the ; optional. Oh well. Samples. Exercises for readers. ☡ You know the drill.
We implement the trivial function ast parse(It f, It l), and then we can simply merge the asts:
int main() {
ast merged;
for(std::string const& input : {
"{1 ,2 ,3 ;{4 ;{9 , 8 ;}},{5 ,6 ;}}",
"{10,20,30;{40;{90, 80;}},{50,60;}}",
})
{
merged += parse(input.begin(), input.end());
std::cout << "merged + " << input << " --> " << merged << "\n";
}
}
Live On Coliru
//#define BOOST_SPIRIT_DEBUG
#include <boost/fusion/adapted/struct.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/karma.hpp>
namespace qi = boost::spirit::qi;
namespace karma = boost::spirit::karma;
struct ast;
//typedef boost::make_recursive_variant<boost::recursive_wrapper<ast> >::type node;
typedef boost::variant<boost::recursive_wrapper<ast> > node;
struct ast {
std::vector<int> value;
std::vector<node> children;
ast& operator+=(ast&& other) {
std::move(other.value.begin(), other.value.end(), back_inserter(value));
std::move(other.children.begin(), other.children.end(), back_inserter(children));
return *this;
}
};
BOOST_FUSION_ADAPT_STRUCT(ast,
(std::vector<int>,value)
(std::vector<node>,children)
)
template <typename It, typename Skipper = qi::space_type>
struct grammar : qi::grammar<It, ast(), Skipper>
{
grammar() : grammar::base_type(start) {
using namespace qi;
start = '{' >> -(int_ % ',') >> ';' >> -(start % ',') >> '}';
BOOST_SPIRIT_DEBUG_NODES((start));
}
private:
qi::rule<It, ast(), Skipper> start;
};
// for output:
static inline std::ostream& operator<<(std::ostream& os, ast const& v) {
using namespace karma;
rule<boost::spirit::ostream_iterator, ast()> r;
r = '{' << -(int_ % ',') << ';' << -((r|eps) % ',') << '}';
return os << format(r, v);
}
template <typename It> ast parse(It f, It l)
{
ast parsed;
static grammar<It> g;
bool ok = qi::phrase_parse(f,l,g,qi::space,parsed);
if (!ok || (f!=l)) {
std::cout << "Parse failure\n";
std::cout << "Remaining unparsed: '" << std::string(f,l) << "'\n";
exit(255);
}
return parsed;
}
int main() {
ast merged;
for(std::string const& input : {
"{1 ,2 ,3 ;{4 ;{9 , 8 ;}},{5 ,6 ;}}",
"{10,20,30;{40;{90, 80;}},{50,60;}}",
})
{
merged += parse(input.begin(), input.end());
std::cout << "merged + " << input << " --> " << merged << "\n";
}
}
Of course, it prints:
merged + {1 ,2 ,3 ;{4 ;{9 , 8 ;}},{5 ,6 ;}} --> {1,2,3;{4;{9,8;}},{5,6;}}
merged + {10,20,30;{40;{90, 80;}},{50,60;}} --> {1,2,3,10,20,30;{4;{9,8;}},{5,6;},{40;{90,80;}},{50,60;}}
UPDATE
In this - trivial - example, you can just bind the collections to the attributes in the parse call. The same thing will happen without the operator+= call needed to move the elements, because the rules are written to automatically append to the bound container attribute.
CAVEAT: A distinct disadvantage of modifying the target value in-place is what happens if parsing fails. In the version the merged value will then be "undefined" (has received partial information from the failed parse).
So if you want to parse inputs "atomically", the first, more explicit approach is a better fit.
So the following is a slightly shorter way to write the same:
Live On Coliru
// #define BOOST_SPIRIT_DEBUG
#include <boost/fusion/adapted/struct.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/karma.hpp>
namespace qi = boost::spirit::qi;
namespace karma = boost::spirit::karma;
struct ast;
//typedef boost::make_recursive_variant<boost::recursive_wrapper<ast> >::type node;
typedef boost::variant<boost::recursive_wrapper<ast> > node;
struct ast {
std::vector<int> value;
std::vector<node> children;
};
BOOST_FUSION_ADAPT_STRUCT(ast,
(std::vector<int>,value)
(std::vector<node>,children)
)
template <typename It, typename Skipper = qi::space_type>
struct grammar : qi::grammar<It, ast(), Skipper>
{
grammar() : grammar::base_type(start) {
using namespace qi;
start = '{' >> -(int_ % ',') >> ';' >> -(start % ',') >> '}';
BOOST_SPIRIT_DEBUG_NODES((start));
}
private:
qi::rule<It, ast(), Skipper> start;
};
// for output:
static inline std::ostream& operator<<(std::ostream& os, ast const& v) {
using namespace karma;
rule<boost::spirit::ostream_iterator, ast()> r;
r = '{' << -(int_ % ',') << ';' << -((r|eps) % ',') << '}';
return os << format(r, v);
}
template <typename It> void parse(It f, It l, ast& into)
{
static grammar<It> g;
bool ok = qi::phrase_parse(f,l,g,qi::space,into);
if (!ok || (f!=l)) {
std::cout << "Parse failure\n";
std::cout << "Remaining unparsed: '" << std::string(f,l) << "'\n";
exit(255);
}
}
int main() {
ast merged;
for(std::string const& input : {
"{1 ,2 ,3 ;{4 ;{9 , 8 ;}},{5 ,6 ;}}",
"{10,20,30;{40;{90, 80;}},{50,60;}}",
})
{
parse(input.begin(), input.end(), merged);
std::cout << "merged + " << input << " --> " << merged << "\n";
}
}
Still prints
Lets say I have code like this (line numbers for reference):
1:
2:function FuncName_1 {
3: var Var_1 = 3;
4: var Var_2 = 4;
5: ...
I want to write a grammar that parses such text, puts all indentifiers (function and variable names) infos into a tree (utree?).
Each node should preserve: line_num, column_num and symbol value. example:
root: FuncName_1 (line:2,col:10)
children[0]: Var_1 (line:3, col:8)
children[1]: Var_1 (line:4, col:9)
I want to put it into the tree because I plan to traverse through that tree and for each node I must know the 'context': (all parent nodes of current nodes).
E.g, while processing node with Var_1, I must know that this is a name for local variable for function FuncName_1 (that is currently being processed as node, but one level earlier)
I cannot figure out few things
Can this be done in Spirit with semantic actions and utree's ? Or should I use variant<> trees ?
How to pass to the node those three informations (column,line,symbol_name) at the same time ? I know I must use pos_iterator as iterator type for grammar but how to access those information in sematic action ?
I'm a newbie in Boost so I read the Spirit documentaiton over and over, I try to google my problems but I somehow cannot put all the pieces together ot find the solution. Seems like there was no one me with such use case like mine before (or I'm just not able to find it)
Looks like the only solutions with position iterator are the ones with parsing error handling, but this is not the case I'm interested in.
The code that only parses the code I was taking about is below but I dont know how to move forward with it.
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/support_line_pos_iterator.hpp>
namespace qi = boost::spirit::qi;
typedef boost::spirit::line_pos_iterator<std::string::const_iterator> pos_iterator_t;
template<typename Iterator=pos_iterator_t, typename Skipper=qi::space_type>
struct ParseGrammar: public qi::grammar<Iterator, Skipper>
{
ParseGrammar():ParseGrammar::base_type(SourceCode)
{
using namespace qi;
KeywordFunction = lit("function");
KeywordVar = lit("var");
SemiColon = lit(';');
Identifier = lexeme [alpha >> *(alnum | '_')];
VarAssignemnt = KeywordVar >> Identifier >> char_('=') >> int_ >> SemiColon;
SourceCode = KeywordFunction >> Identifier >> '{' >> *VarAssignemnt >> '}';
}
qi::rule<Iterator, Skipper> SourceCode;
qi::rule<Iterator > KeywordFunction;
qi::rule<Iterator, Skipper> VarAssignemnt;
qi::rule<Iterator> KeywordVar;
qi::rule<Iterator> SemiColon;
qi::rule<Iterator > Identifier;
};
int main()
{
std::string const content = "function FuncName_1 {\n var Var_1 = 3;\n var Var_2 = 4; }";
pos_iterator_t first(content.begin()), iter = first, last(content.end());
ParseGrammar<pos_iterator_t> resolver; // Our parser
bool ok = phrase_parse(iter,
last,
resolver,
qi::space);
std::cout << std::boolalpha;
std::cout << "\nok : " << ok << std::endl;
std::cout << "full : " << (iter == last) << std::endl;
if(ok && iter == last)
{
std::cout << "OK: Parsing fully succeeded\n\n";
}
else
{
int line = get_line(iter);
int column = get_column(first, iter);
std::cout << "-------------------------\n";
std::cout << "ERROR: Parsing failed or not complete\n";
std::cout << "stopped at: " << line << ":" << column << "\n";
std::cout << "remaining: '" << std::string(iter, last) << "'\n";
std::cout << "-------------------------\n";
}
return 0;
}
This has been a fun exercise, where I finally put together a working demo of on_success[1] to annotate AST nodes.
Let's assume we want an AST like:
namespace ast
{
struct LocationInfo {
unsigned line, column, length;
};
struct Identifier : LocationInfo {
std::string name;
};
struct VarAssignment : LocationInfo {
Identifier id;
int value;
};
struct SourceCode : LocationInfo {
Identifier function;
std::vector<VarAssignment> assignments;
};
}
I know, 'location information' is probably overkill for the SourceCode node, but you know... Anyways, to make it easy to assign attributes to these nodes without requiring semantic actions or lots of specifically crafted constructors:
#include <boost/fusion/adapted/struct.hpp>
BOOST_FUSION_ADAPT_STRUCT(ast::Identifier, (std::string, name))
BOOST_FUSION_ADAPT_STRUCT(ast::VarAssignment, (ast::Identifier, id)(int, value))
BOOST_FUSION_ADAPT_STRUCT(ast::SourceCode, (ast::Identifier, function)(std::vector<ast::VarAssignment>, assignments))
There. Now we can declare the rules to expose these attributes:
qi::rule<Iterator, ast::SourceCode(), Skipper> SourceCode;
qi::rule<Iterator, ast::VarAssignment(), Skipper> VarAssignment;
qi::rule<Iterator, ast::Identifier()> Identifier;
// no skipper, no attributes:
qi::rule<Iterator> KeywordFunction, KeywordVar, SemiColon;
We don't (essentially) modify the grammar, at all: attribute propagation is "just automatic"[2] :
KeywordFunction = lit("function");
KeywordVar = lit("var");
SemiColon = lit(';');
Identifier = as_string [ alpha >> *(alnum | char_("_")) ];
VarAssignment = KeywordVar >> Identifier >> '=' >> int_ >> SemiColon;
SourceCode = KeywordFunction >> Identifier >> '{' >> *VarAssignment >> '}';
The magic
How do we get the source location information attached to our nodes?
auto set_location_info = annotate(_val, _1, _3);
on_success(Identifier, set_location_info);
on_success(VarAssignment, set_location_info);
on_success(SourceCode, set_location_info);
Now, annotate is just a lazy version of a calleable that is defined as:
template<typename It>
struct annotation_f {
typedef void result_type;
annotation_f(It first) : first(first) {}
It const first;
template<typename Val, typename First, typename Last>
void operator()(Val& v, First f, Last l) const {
do_annotate(v, f, l, first);
}
private:
void static do_annotate(ast::LocationInfo& li, It f, It l, It first) {
using std::distance;
li.line = get_line(f);
li.column = get_column(first, f);
li.length = distance(f, l);
}
static void do_annotate(...) { }
};
Due to way in which get_column works, the functor is stateful (as it remembers the start iterator)[3]. As you can see do_annotate just accepts anything that derives from LocationInfo.
Now, the proof of the pudding:
std::string const content = "function FuncName_1 {\n var Var_1 = 3;\n var Var_2 = 4; }";
pos_iterator_t first(content.begin()), iter = first, last(content.end());
ParseGrammar<pos_iterator_t> resolver(first); // Our parser
ast::SourceCode program;
bool ok = phrase_parse(iter,
last,
resolver,
qi::space,
program);
std::cout << std::boolalpha;
std::cout << "ok : " << ok << std::endl;
std::cout << "full: " << (iter == last) << std::endl;
if(ok && iter == last)
{
std::cout << "OK: Parsing fully succeeded\n\n";
std::cout << "Function name: " << program.function.name << " (see L" << program.printLoc() << ")\n";
for (auto const& va : program.assignments)
std::cout << "variable " << va.id.name << " assigned value " << va.value << " at L" << va.printLoc() << "\n";
}
else
{
int line = get_line(iter);
int column = get_column(first, iter);
std::cout << "-------------------------\n";
std::cout << "ERROR: Parsing failed or not complete\n";
std::cout << "stopped at: " << line << ":" << column << "\n";
std::cout << "remaining: '" << std::string(iter, last) << "'\n";
std::cout << "-------------------------\n";
}
This prints:
ok : true
full: true
OK: Parsing fully succeeded
Function name: FuncName_1 (see L1:1:56)
variable Var_1 assigned value 3 at L2:3:14
variable Var_2 assigned value 4 at L3:3:15
Full Demo Program
See it Live On Coliru
Also showing:
error handling, e.g.:
Error: expecting "=" in line 3:
var Var_2 - 4; }
^---- here
ok : false
full: false
-------------------------
ERROR: Parsing failed or not complete
stopped at: 1:1
remaining: 'function FuncName_1 {
var Var_1 = 3;
var Var_2 - 4; }'
-------------------------
BOOST_SPIRIT_DEBUG macros
A bit of a hacky way to conveniently stream the LocationInfo part of any AST node, sorry :)
//#define BOOST_SPIRIT_DEBUG
#define BOOST_SPIRIT_USE_PHOENIX_V3
#include <boost/fusion/adapted/struct.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <boost/spirit/include/support_line_pos_iterator.hpp>
#include <iomanip>
namespace qi = boost::spirit::qi;
namespace phx= boost::phoenix;
typedef boost::spirit::line_pos_iterator<std::string::const_iterator> pos_iterator_t;
namespace ast
{
namespace manip { struct LocationInfoPrinter; }
struct LocationInfo {
unsigned line, column, length;
manip::LocationInfoPrinter printLoc() const;
};
struct Identifier : LocationInfo {
std::string name;
};
struct VarAssignment : LocationInfo {
Identifier id;
int value;
};
struct SourceCode : LocationInfo {
Identifier function;
std::vector<VarAssignment> assignments;
};
///////////////////////////////////////////////////////////////////////////
// Completely unnecessary tweak to get a "poor man's" io manipulator going
// so we can do `std::cout << x.printLoc()` on types of `x` deriving from
// LocationInfo
namespace manip {
struct LocationInfoPrinter {
LocationInfoPrinter(LocationInfo const& ref) : ref(ref) {}
LocationInfo const& ref;
friend std::ostream& operator<<(std::ostream& os, LocationInfoPrinter const& lip) {
return os << lip.ref.line << ':' << lip.ref.column << ':' << lip.ref.length;
}
};
}
manip::LocationInfoPrinter LocationInfo::printLoc() const { return { *this }; }
// feel free to disregard this hack
///////////////////////////////////////////////////////////////////////////
}
BOOST_FUSION_ADAPT_STRUCT(ast::Identifier, (std::string, name))
BOOST_FUSION_ADAPT_STRUCT(ast::VarAssignment, (ast::Identifier, id)(int, value))
BOOST_FUSION_ADAPT_STRUCT(ast::SourceCode, (ast::Identifier, function)(std::vector<ast::VarAssignment>, assignments))
struct error_handler_f {
typedef qi::error_handler_result result_type;
template<typename T1, typename T2, typename T3, typename T4>
qi::error_handler_result operator()(T1 b, T2 e, T3 where, T4 const& what) const {
std::cerr << "Error: expecting " << what << " in line " << get_line(where) << ": \n"
<< std::string(b,e) << "\n"
<< std::setw(std::distance(b, where)) << '^' << "---- here\n";
return qi::fail;
}
};
template<typename It>
struct annotation_f {
typedef void result_type;
annotation_f(It first) : first(first) {}
It const first;
template<typename Val, typename First, typename Last>
void operator()(Val& v, First f, Last l) const {
do_annotate(v, f, l, first);
}
private:
void static do_annotate(ast::LocationInfo& li, It f, It l, It first) {
using std::distance;
li.line = get_line(f);
li.column = get_column(first, f);
li.length = distance(f, l);
}
static void do_annotate(...) {}
};
template<typename Iterator=pos_iterator_t, typename Skipper=qi::space_type>
struct ParseGrammar: public qi::grammar<Iterator, ast::SourceCode(), Skipper>
{
ParseGrammar(Iterator first) :
ParseGrammar::base_type(SourceCode),
annotate(first)
{
using namespace qi;
KeywordFunction = lit("function");
KeywordVar = lit("var");
SemiColon = lit(';');
Identifier = as_string [ alpha >> *(alnum | char_("_")) ];
VarAssignment = KeywordVar > Identifier > '=' > int_ > SemiColon; // note: expectation points
SourceCode = KeywordFunction >> Identifier >> '{' >> *VarAssignment >> '}';
on_error<fail>(VarAssignment, handler(_1, _2, _3, _4));
on_error<fail>(SourceCode, handler(_1, _2, _3, _4));
auto set_location_info = annotate(_val, _1, _3);
on_success(Identifier, set_location_info);
on_success(VarAssignment, set_location_info);
on_success(SourceCode, set_location_info);
BOOST_SPIRIT_DEBUG_NODES((KeywordFunction)(KeywordVar)(SemiColon)(Identifier)(VarAssignment)(SourceCode))
}
phx::function<error_handler_f> handler;
phx::function<annotation_f<Iterator>> annotate;
qi::rule<Iterator, ast::SourceCode(), Skipper> SourceCode;
qi::rule<Iterator, ast::VarAssignment(), Skipper> VarAssignment;
qi::rule<Iterator, ast::Identifier()> Identifier;
// no skipper, no attributes:
qi::rule<Iterator> KeywordFunction, KeywordVar, SemiColon;
};
int main()
{
std::string const content = "function FuncName_1 {\n var Var_1 = 3;\n var Var_2 - 4; }";
pos_iterator_t first(content.begin()), iter = first, last(content.end());
ParseGrammar<pos_iterator_t> resolver(first); // Our parser
ast::SourceCode program;
bool ok = phrase_parse(iter,
last,
resolver,
qi::space,
program);
std::cout << std::boolalpha;
std::cout << "ok : " << ok << std::endl;
std::cout << "full: " << (iter == last) << std::endl;
if(ok && iter == last)
{
std::cout << "OK: Parsing fully succeeded\n\n";
std::cout << "Function name: " << program.function.name << " (see L" << program.printLoc() << ")\n";
for (auto const& va : program.assignments)
std::cout << "variable " << va.id.name << " assigned value " << va.value << " at L" << va.printLoc() << "\n";
}
else
{
int line = get_line(iter);
int column = get_column(first, iter);
std::cout << "-------------------------\n";
std::cout << "ERROR: Parsing failed or not complete\n";
std::cout << "stopped at: " << line << ":" << column << "\n";
std::cout << "remaining: '" << std::string(iter, last) << "'\n";
std::cout << "-------------------------\n";
}
return 0;
}
[1] sadly un(der)documented, except for the conjure sample(s)
[2] well, I used as_string to get proper assignment to Identifier without too much work
[3] There could be smarter ways about this in terms of performance, but for now, let's keep it simple
I want to use boost spirit to parse an expression like
function1(arg1, arg2, function2(arg1, arg2, arg3),
function3(arg1,arg2))
and call corresponding c++ functions. What should be the grammar to parse above expression and call the corresponding c++ function by phoneix::bind()?
I have 2 types of functions to call
1) string functions;
wstring GetSubString(wstring stringToCut, int position, int length);
wstring GetStringToken(wstring stringToTokenize, wstring seperators,
int tokenNumber );
2) Functions that return integer;
int GetCount();
int GetId(wstring srcId, wstring srcType);
Second Answer (more pragmatic)
Here's a second take, for comparison:
Just in case you really didn't want to parse into an abstract syntax tree representation, but rather evaluate the functions on-the-fly during parsing, you can simplify the grammar.
It comes in at 92 lines as opposed to 209 lines in the first answer. It really depends on what you're implementing which approach is more suitable.
This shorter approach has some downsides:
less flexible (not reusable)
less robust (if functions have side effects, they will happen even if parsing fails halfway)
less extensible (the supported functions are hardwired into the grammar1)
Full code:
//#define BOOST_SPIRIT_DEBUG
#define BOOST_SPIRIT_USE_PHOENIX_V3
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <boost/phoenix/function.hpp>
namespace qi = boost::spirit::qi;
namespace phx = boost::phoenix;
typedef boost::variant<int, std::string> value;
//////////////////////////////////////////////////
// Demo functions:
value AnswerToLTUAE() {
return 42;
}
value ReverseString(value const& input) {
auto& as_string = boost::get<std::string>(input);
return std::string(as_string.rbegin(), as_string.rend());
}
value Concatenate(value const& a, value const& b) {
std::ostringstream oss;
oss << a << b;
return oss.str();
}
BOOST_PHOENIX_ADAPT_FUNCTION_NULLARY(value, AnswerToLTUAE_, AnswerToLTUAE)
BOOST_PHOENIX_ADAPT_FUNCTION(value, ReverseString_, ReverseString, 1)
BOOST_PHOENIX_ADAPT_FUNCTION(value, Concatenate_, Concatenate, 2)
//////////////////////////////////////////////////
// Parser grammar
template <typename It, typename Skipper = qi::space_type>
struct parser : qi::grammar<It, value(), Skipper>
{
parser() : parser::base_type(expr_)
{
using namespace qi;
function_call_ =
(lit("AnswerToLTUAE") > '(' > ')')
[ _val = AnswerToLTUAE_() ]
| (lit("ReverseString") > '(' > expr_ > ')')
[ _val = ReverseString_(_1) ]
| (lit("Concatenate") > '(' > expr_ > ',' > expr_ > ')')
[ _val = Concatenate_(_1, _2) ]
;
string_ = as_string [
lexeme [ "'" >> *~char_("'") >> "'" ]
];
value_ = int_ | string_;
expr_ = function_call_ | value_;
on_error<fail> ( expr_, std::cout
<< phx::val("Error! Expecting ") << _4 << phx::val(" here: \"")
<< phx::construct<std::string>(_3, _2) << phx::val("\"\n"));
BOOST_SPIRIT_DEBUG_NODES((expr_)(function_call_)(value_)(string_))
}
private:
qi::rule<It, value(), Skipper> value_, function_call_, expr_, string_;
};
int main()
{
for (const std::string input: std::vector<std::string> {
"-99",
"'string'",
"AnswerToLTUAE()",
"ReverseString('string')",
"Concatenate('string', 987)",
"Concatenate('The Answer Is ', AnswerToLTUAE())",
})
{
auto f(std::begin(input)), l(std::end(input));
const static parser<decltype(f)> p;
value direct_eval;
bool ok = qi::phrase_parse(f,l,p,qi::space,direct_eval);
if (!ok)
std::cout << "invalid input\n";
else
{
std::cout << "input:\t" << input << "\n";
std::cout << "eval:\t" << direct_eval << "\n\n";
}
if (f!=l) std::cout << "unparsed: '" << std::string(f,l) << "'\n";
}
}
Note how, instead of using BOOST_PHOENIX_ADAPT_FUNCTION* we could have directly used boost::phoenix::bind.
The output is still the same:
input: -99
eval: -99
input: 'string'
eval: string
input: AnswerToLTUAE()
eval: 42
input: ReverseString('string')
eval: gnirts
input: Concatenate('string', 987)
eval: string987
input: Concatenate('The Answer Is ', AnswerToLTUAE())
eval: The Answer Is 42
1 This last downside is easily remedied by using the 'Nabialek Trick'
First Answer (complete)
I've gone and implemented a simple recursive expression grammar for functions having up-to-three parameters:
for (const std::string input: std::vector<std::string> {
"-99",
"'string'",
"AnswerToLTUAE()",
"ReverseString('string')",
"Concatenate('string', 987)",
"Concatenate('The Answer Is ', AnswerToLTUAE())",
})
{
auto f(std::begin(input)), l(std::end(input));
const static parser<decltype(f)> p;
expr parsed_script;
bool ok = qi::phrase_parse(f,l,p,qi::space,parsed_script);
if (!ok)
std::cout << "invalid input\n";
else
{
const static generator<boost::spirit::ostream_iterator> g;
std::cout << "input:\t" << input << "\n";
std::cout << "tree:\t" << karma::format(g, parsed_script) << "\n";
std::cout << "eval:\t" << evaluate(parsed_script) << "\n";
}
if (f!=l) std::cout << "unparsed: '" << std::string(f,l) << "'\n";
}
Which prints:
input: -99
tree: -99
eval: -99
input: 'string'
tree: 'string'
eval: string
input: AnswerToLTUAE()
tree: nullary_function_call()
eval: 42
input: ReverseString('string')
tree: unary_function_call('string')
eval: gnirts
input: Concatenate('string', 987)
tree: binary_function_call('string',987)
eval: string987
input: Concatenate('The Answer Is ', AnswerToLTUAE())
tree: binary_function_call('The Answer Is ',nullary_function_call())
eval: The Answer Is 42
Some notes:
I separated parsing from execution (which is always a good idea IMO)
I implemented function evaluation for zero, one or two parameters (this should be easy to extend)
Values are assumed to be integers or strings (should be easy to extend)
I added a karma generator to display the parsed expression (with a TODO marked in the comment)
I hope this helps:
//#define BOOST_SPIRIT_DEBUG
#include <boost/fusion/adapted/struct.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <boost/spirit/include/karma.hpp>
#include <boost/variant/recursive_wrapper.hpp>
namespace qi = boost::spirit::qi;
namespace karma = boost::spirit::karma;
namespace phx = boost::phoenix;
typedef boost::variant<int, std::string> value;
typedef boost::variant<value, boost::recursive_wrapper<struct function_call> > expr;
typedef std::function<value() > nullary_function_impl;
typedef std::function<value(value const&) > unary_function_impl;
typedef std::function<value(value const&, value const&)> binary_function_impl;
typedef boost::variant<nullary_function_impl, unary_function_impl, binary_function_impl> function_impl;
typedef qi::symbols<char, function_impl> function_table;
struct function_call
{
typedef std::vector<expr> arguments_t;
function_call() = default;
function_call(function_impl f, arguments_t const& arguments)
: f(f), arguments(arguments) { }
function_impl f;
arguments_t arguments;
};
BOOST_FUSION_ADAPT_STRUCT(function_call, (function_impl, f)(function_call::arguments_t, arguments))
#ifdef BOOST_SPIRIT_DEBUG
namespace std
{
static inline std::ostream& operator<<(std::ostream& os, nullary_function_impl const& f) { return os << "<nullary_function_impl>"; }
static inline std::ostream& operator<<(std::ostream& os, unary_function_impl const& f) { return os << "<unary_function_impl>"; }
static inline std::ostream& operator<<(std::ostream& os, binary_function_impl const& f) { return os << "<binary_function_impl>"; }
}
static inline std::ostream& operator<<(std::ostream& os, function_call const& call) { return os << call.f << "(" << call.arguments.size() << ")"; }
#endif
//////////////////////////////////////////////////
// Evaluation
value evaluate(const expr& e);
struct eval : boost::static_visitor<value>
{
eval() {}
value operator()(const value& v) const
{
return v;
}
value operator()(const function_call& call) const
{
return boost::apply_visitor(invoke(call.arguments), call.f);
}
private:
struct invoke : boost::static_visitor<value>
{
function_call::arguments_t const& _args;
invoke(function_call::arguments_t const& args) : _args(args) {}
value operator()(nullary_function_impl const& f) const {
return f();
}
value operator()(unary_function_impl const& f) const {
auto a = evaluate(_args.at(0));
return f(a);
}
value operator()(binary_function_impl const& f) const {
auto a = evaluate(_args.at(0));
auto b = evaluate(_args.at(1));
return f(a, b);
}
};
};
value evaluate(const expr& e)
{
return boost::apply_visitor(eval(), e);
}
//////////////////////////////////////////////////
// Demo functions:
value AnswerToLTUAE() {
return 42;
}
value ReverseString(value const& input) {
auto& as_string = boost::get<std::string>(input);
return std::string(as_string.rbegin(), as_string.rend());
}
value Concatenate(value const& a, value const& b) {
std::ostringstream oss;
oss << a << b;
return oss.str();
}
//////////////////////////////////////////////////
// Parser grammar
template <typename It, typename Skipper = qi::space_type>
struct parser : qi::grammar<It, expr(), Skipper>
{
parser() : parser::base_type(expr_)
{
using namespace qi;
n_ary_ops.add
("AnswerToLTUAE", nullary_function_impl{ &::AnswerToLTUAE })
("ReverseString", unary_function_impl { &::ReverseString })
("Concatenate" , binary_function_impl { &::Concatenate });
function_call_ = n_ary_ops > '(' > expr_list > ')';
string_ = qi::lexeme [ "'" >> *~qi::char_("'") >> "'" ];
value_ = qi::int_ | string_;
expr_list = -expr_ % ',';
expr_ = function_call_ | value_;
on_error<fail> ( expr_, std::cout
<< phx::val("Error! Expecting ") << _4 << phx::val(" here: \"")
<< phx::construct<std::string>(_3, _2) << phx::val("\"\n"));
BOOST_SPIRIT_DEBUG_NODES((expr_)(expr_list)(function_call_)(value_)(string_))
}
private:
function_table n_ary_ops;
template <typename Attr> using Rule = qi::rule<It, Attr(), Skipper>;
Rule<std::string> string_;
Rule<value> value_;
Rule<function_call> function_call_;
Rule<std::vector<expr>> expr_list;
Rule<expr> expr_;
};
//////////////////////////////////////////////////
// Output generator
template <typename It>
struct generator : karma::grammar<It, expr()>
{
generator() : generator::base_type(expr_)
{
using namespace karma;
nullary_ = eps << "nullary_function_call"; // TODO reverse lookup :)
unary_ = eps << "unary_function_call";
binary_ = eps << "binary_function_call";
function_ = nullary_ | unary_ | binary_;
function_call_ = function_ << expr_list;
expr_list = '(' << -(expr_ % ',') << ')';
value_ = karma::int_ | ("'" << karma::string << "'");
expr_ = function_call_ | value_;
}
private:
template <typename Attr> using Rule = karma::rule<It, Attr()>;
Rule<nullary_function_impl> nullary_;
Rule<unary_function_impl> unary_;
Rule<binary_function_impl> binary_;
Rule<function_impl> function_;
Rule<function_call> function_call_;
Rule<value> value_;
Rule<std::vector<expr>> expr_list;
Rule<expr> expr_;
};
int main()
{
for (const std::string input: std::vector<std::string> {
"-99",
"'string'",
"AnswerToLTUAE()",
"ReverseString('string')",
"Concatenate('string', 987)",
"Concatenate('The Answer Is ', AnswerToLTUAE())",
})
{
auto f(std::begin(input)), l(std::end(input));
const static parser<decltype(f)> p;
expr parsed_script;
bool ok = qi::phrase_parse(f,l,p,qi::space,parsed_script);
if (!ok)
std::cout << "invalid input\n";
else
{
const static generator<boost::spirit::ostream_iterator> g;
std::cout << "input:\t" << input << "\n";
std::cout << "tree:\t" << karma::format(g, parsed_script) << "\n";
std::cout << "eval:\t" << evaluate(parsed_script) << "\n\n";
}
if (f!=l) std::cout << "unparsed: '" << std::string(f,l) << "'\n";
}
}