strip_comments.input

Boost provides free peer-reviewed portable C++ source libraries. We emphasize libraries that work

//  Copyright (c) 2001-2007 Hartmut Kaiser
// 
//  Distributed under the Boost Software License, Version 1.0. (See accompanying 
//  file LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt)

//  This example is the equivalent to the following lex program:
//
//       %{
//       /* INITIAL is the default start state.  COMMENT is our new  */
//       /* state where we remove comments.                          */
//       %}
// 
//       %s COMMENT
//       %%
//       <INITIAL>"//".*    ;
//       <INITIAL>"/*"      BEGIN COMMENT; 
//       <INITIAL>.         ECHO;
//       <INITIAL>[\n]      ECHO;
//       <COMMENT>"*/"      BEGIN INITIAL;
//       <COMMENT>.         ;
//       <COMMENT>[\n]      ;
//       %%
// 
//       main() 
//       {
//         yylex();
//       }
//
//  Its purpose is to strip comments out of C code.

// #define BOOST_SPIRIT_LEXERTL_DEBUG

#include <boost/spirit/qi.hpp>
#include <boost/spirit/lex/lexer_lexertl.hpp>
#include <boost/spirit/phoenix/operator.hpp>
#include <boost/spirit/phoenix/container.hpp>

#include <iostream>
#include <string>

#include "example.hpp"

using namespace boost::spirit;
using namespace boost::spirit::qi;
using namespace boost::spirit::lex;
using namespace boost::spirit::arg_names;

///////////////////////////////////////////////////////////////////////////////
//  Token definition: We use the lexertl based lexer engine as the underlying 
//                    lexer type.
///////////////////////////////////////////////////////////////////////////////
enum {
    IDANY = lex::min_token_id + 10
};

template <typename BaseIterator>
struct strip_comments_tokens : lexer_def<lexertl_lexer<BaseIterator> >
{
    template <typename Self>
    void def (Self& self)
    {
        // define tokens and associate them with the lexer
        cppcomment = "//.*\n";
        ccomment = "/\\*";
        endcomment = "\\*/";
        
        self.add
            (cppcomment)
            (ccomment)
            (".", IDANY)
        ;
        
        self("COMMENT").add
            (endcomment)
            (".", IDANY)
        ;
    }
    
    token_def<> cppcomment, ccomment, endcomment;
};

///////////////////////////////////////////////////////////////////////////////
//  Grammar definition
///////////////////////////////////////////////////////////////////////////////
template <typename Iterator>
struct strip_comments_grammar : grammar_def<Iterator>
{
    template <typename TokenDef>
    strip_comments_grammar(TokenDef const& tok)
    {
        start =  *(   tok.ccomment 
                      >>  in_state("COMMENT") 
                          [ *token(IDANY) >> tok.endcomment ]
                  |   tok.cppcomment
                  |   token(IDANY)
                  )
              ;
    }

    rule<Iterator> start;
};

///////////////////////////////////////////////////////////////////////////////
int main(int argc, char* argv[])
{
    // iterator type used to expose the underlying input stream
    typedef std::string::const_iterator base_iterator_type;
    
    // iterator type exposed by the lexer 
    typedef 
        lexer_iterator<strip_comments_tokens<base_iterator_type> >::type 
    iterator_type;

    // now we use the types defined above to create the lexer and grammar
    // object instances needed to invoke the parsing process
    strip_comments_tokens<base_iterator_type> strip_comments;    // Our token definition
    strip_comments_grammar<iterator_type> def (strip_comments);  // Our grammar definition

    // Parsing is done based on the the token stream, not the character 
    // stream read from the input.
    std::string str (read_from_file(1 == argc ? "strip_comments.input" : argv[1]));
    base_iterator_type first = str.begin();
    base_iterator_type end = str.end();
    bool r = lex_and_parse(first, end, strip_comments, make_grammar(def));

    if (r) {
        std::cout << "-------------------------\n";
        std::cout << "Parsing succeeded\n";
        std::cout << "-------------------------\n";
    }
    else {
        std::string rest(first, end);
        std::cout << "-------------------------\n";
        std::cout << "Parsing failed\n";
        std::cout << "stopped at: \"" << rest << "\"\n";
        std::cout << "-------------------------\n";
    }

    std::cout << "Bye... :-) \n\n";
    return 0;
}