Why does this boost::spirit::qi rule not match the input?

Question

I tried to continue to work on my previous example and expand the rules. My problem is, that rules that use ID_IDENTIFIER do not work - although I know that the lexer is working (using unit tests).

Here's the example:

#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/lex_lexertl.hpp>

namespace qi  = boost::spirit::qi;
namespace lex = boost::spirit::lex;

enum LexerIDs { ID_IDENTIFIER, ID_WHITESPACE, ID_INTEGER, ID_FLOAT, ID_PUNCTUATOR };

template <typename Lexer>
struct custom_lexer : lex::lexer<Lexer>
{
    custom_lexer()
        : identifier    ("[a-zA-Z_][a-zA-Z0-9_]*")
        , white_space   ("[ \\t\\n]+")
        , integer_value ("[1-9][0-9]*")
        , hex_value     ("0[xX][0-9a-fA-F]+")
        , float_value   ("[0-9]*\\.[0-9]+([eE][+-]?[0-9]+)?")
        , float_value2  ("[0-9]+\\.([eE][+-]?[0-9]+)?")
        , punctuator    ("\\[|\\]|\\(|\\)|\\.|&>|\\*\\*|\\*|\\+|-|~|!|\\/|%|<<|>>|<|>|<=|>=|==|!=|\\^|&|\\||\\^\\^|&&|\\|\\||\\?|:|,")// [ ] ( ) . &> ** * + - ~ ! / % << >> < > <= >= == != ^ & | ^^ && || ? : ,
    {
        using boost::spirit::lex::_start;
        using boost::spirit::lex::_end;

        this->self.add
            (identifier   , ID_IDENTIFIER)
            /*(white_space  , ID_WHITESPACE)*/
            (integer_value, ID_INTEGER)
            (hex_value    , ID_INTEGER)
            (float_value  , ID_FLOAT)
            (float_value2 , ID_FLOAT)
            (punctuator   , ID_PUNCTUATOR);

        this->self("WS") = white_space;
    }
    lex::token_def<std::string> identifier;
    lex::token_def<lex::omit>   white_space;
    lex::token_def<int>         integer_value;
    lex::token_def<int>         hex_value;
    lex::token_def<double>      float_value;
    lex::token_def<double>      float_value2;
    lex::token_def<>            punctuator;
};

template< typename Iterator, typename Skipper>
struct custom_grammar : qi::grammar<Iterator, Skipper>
{

    template< typename TokenDef >
    custom_grammar(const TokenDef& tok) : custom_grammar::base_type(ges)
    {
        ges = qi::token(ID_IDENTIFIER);
        BOOST_SPIRIT_DEBUG_NODE(ges);
    }
    qi::rule<Iterator, Skipper > ges;
};

int main(int argc, _TCHAR* argv[])
{
    std::string test("testidentifier");

    typedef char const* Iterator;
    typedef lex::lexertl::token<Iterator, lex::omit, boost::mpl::true_> token_type;
    typedef lex::lexertl::lexer<token_type> lexer_type;
    typedef qi::in_state_skipper<custom_lexer<lexer_type>::lexer_def> skipper_type;

    typedef custom_lexer<lexer_type>::iterator_type iterator_type;

    custom_lexer<lexer_type> my_lexer; 
    custom_grammar<iterator_type, skipper_type> my_grammar(my_lexer);

    Iterator first = test.c_str();
    Iterator last = &first[test.size()];

    bool r = lex::tokenize_and_phrase_parse(first,last,my_lexer,my_grammar,qi::in_state( "WS" )[ my_lexer.self ]);

    std::cout << std::boolalpha << r << "\n";
    std::cout << "Remaining unparsed: '" << std::string(first,last) << "'\n";
    return 0;
}

a similar rule with ID_INTEGER matches fine for "1234"

Answer 1

The problem lies in the way you define your token ids in your enumeration. If you do it this way ID_IDENTIFIER gets a value of 0 and that is not a valid lex token id. Fortunately Spirit.Lex defines a value boost::spirit::lex::min_token_id that you can use to make sure you get valid tokens. Using this your enum would be:

enum LexerIDs { ID_IDENTIFIER=boost::spirit::lex::min_token_id+1, ID_WHITESPACE, ID_INTEGER, ID_FLOAT, ID_PUNCTUATOR };