It's totally possible and it works great once set-up. Unfortunately documentation about pure C++ Flex/Bison lexer parser is not so easy to find and follow.
I can expose you a barebone of a parser I wrote but it's just an example of how you could do it.
Mind that some of this code has been set-up by trial and error, since documentation is scarce, so therey could be superfluous operations or things that are not exactly correct but it works.
ypp file
%skeleton "lalr1.cc"
%require "3.0.2"
%defines
%define api.namespace {script}
%define parser_class_name {Parser}
%define api.token.constructor
%define api.value.type variant
%define parse.assert true
%code requires {
namespace script
{
class Compiler;
class Lexer;
}
}
%lex-param { script::Lexer &lexer }
%lex-param { script::Compiler &compiler }
%parse-param { script::Lexer &lexer }
%parse-param { script::Compiler &compiler }
%locations
%initial-action
{
@$.begin.filename = @$.end.filename = &compiler.file;
};
%define parse.trace
%define parse.error verbose
%code top {
#include "Compiler.h"
#include "MyLexer.h"
#include "MyParser.hpp"
static script::Parser::symbol_type yylex(script::Lexer &scanner, script::Compiler &compiler) {
return scanner.get_next_token();
}
using namespace script;
}
// tokens and grammar
void script::Parser::error(const location_type& l, const std::string& m)
{
compiler.error(l,m);
}
Here you can use C++ everywhere, for example
%type<std::list<Statement*>> statement_list for_statement
...
statement_list:
{ $$ = std::list<Statement*>(); }
| statement_list statement { $1.push_back($2); $$ = $1; }
;
l file
%{
#include "MyParser.hpp"
#include "MyLexer.h"
#include "Compiler.h"
#include <string>
typedef script::Parser::token token;
#define yyterminate() script::Parser::make_END(loc);
static script::location loc;
using namespace script;
%}
%x sstring
%x scomment
%option nodefault
%option noyywrap
%option c++
%option yyclass="Lexer"
%option prefix="My"
%{
# define YY_USER_ACTION loc.columns((int)yyleng);
%}
%%
%{
loc.step();
%}
Then you'll need a header file which defines your Lexer class which will inherit from yyFlexLexer that is how C++ Flex works, which is something like
#if ! defined(yyFlexLexerOnce)
#undef yyFlexLexer
#define yyFlexLexer NanoFlexLexer
#include <FlexLexer.h>
#endif
#undef YY_DECL
#define YY_DECL script::Parser::symbol_type script::Lexer::get_next_token()
#include "MyParser.hpp"
namespace script
{
class Compiler;
class Lexer : public yyFlexLexer
{
public:
Lexer(Compiler &compiler, std::istream *in) : yyFlexLexer(in), compiler(compiler) {}
virtual script::Parser::symbol_type get_next_token();
virtual ~Lexer() { }
private:
Compiler &compiler;
};
}
The last step is defining your Compiler class which will get called from the Bison grammar rules (that's what parse-param attributes in ypp file are for). Something like:
#include "parser/MyParser.hpp"
#include "parser/MyLexer.h"
#include "parser/location.hh"
#include "Symbols.h"
namespace script
{
class Compiler
{
public:
Compiler();
std::string file;
void error(const location& l, const std::string& m);
void error(const std::string& m);
vm::Script* compile(const std::string& text);
bool parseString(const std::string& text);
void setRoot(ASTRoot* root);
Node* getRoot() { return root.get(); }
};
}
Now you can execute parsing easily and totally passing by C++ code, eg:
bool Compiler::parseString(const std::string &text)
{
constexpr bool shouldGenerateTrace = false;
istringstream ss(text);
script::Lexer lexer = script::Lexer(*this, &ss);
script::Parser parser(lexer, *this);
parser.set_debug_level(shouldGenerateTrace);
return parser.parse() == 0;
}
The only thing you must take care is to invoke flex on the .l file with -c++ argument to make it produce a C++ lexer.
Actually with some careful operations I've been also able to have multiple independent and self-reentrant lexers/parsers in the same project.
