I try to implement a Lexer for a little programming language with Boost Spirit.
I have to get the value of a token and I get a bad_get exception :
terminate called after throwing an instance of 'boost::bad_get'
what(): boost::bad_get: failed value get using boost::get Aborted
I obtain this exception when doing :
std::string contents = "void";
base_iterator_type first = contents.begin();
base_iterator_type last = contents.end();
SimpleLexer<lexer_type> lexer;
iter = lexer.begin(first, last);
end = lexer.end();
std::cout << "Value = " << boost::get<std::string>(iter->value()) << std::endl;
My lexer is defined like that :
typedef std::string::iterator base_iterator_type;
typedef boost::spirit::lex::lexertl::token<base_iterator_type, boost::mpl::vector<unsigned int, std::string>> Tok;
typedef lex::lexertl::actor_lexer<Tok> lexer_type;
template<typename L>
class SimpleLexer : public lex::lexer<L> {
private:
public:
SimpleLexer() {
keyword_for = "for";
keyword_while = "while";
keyword_if = "if";
keyword_else = "else";
keyword_false = "false";
keyword_true = "true";
keyword_from = "from";
keyword_to = "to";
keyword_foreach = "foreach";
word = "[a-zA-Z]+";
integer = "[0-9]+";
litteral = "...";
left_parenth = '(';
right_parenth = ')';
left_brace = '{';
right_brace = '}';
stop = ';';
comma = ',';
swap = "<>";
assign = '=';
addition = '+';
subtraction = '-';
multiplication = '*';
division = '/';
modulo = '%';
equals = "==";
not_equals = "!=";
greater = '>';
less = '<';
greater_equals = ">=";
less_equals = "<=";
whitespaces = "[ \\t\\n]+";
comments = "\\/\\*[^*]*\\*+([^/*][^*]*\\*+)*\\/";
//Add keywords
this->self += keyword_for | keyword_while | keyword_true | keyword_false | keyword_if | keyword_else | keyword_from | keyword_to | keyword_foreach;
this->self += integer | litteral | word;
this->self += equals | not_equals | greater_equals | less_equals | greater | less ;
this->self += left_parenth | right_parenth | left_brace | right_brace;
this->self += comma | stop;
this->self += assign | swap | addition | subtraction | multiplication | division | modulo;
//Ignore whitespaces and comments
this->self += whitespaces [lex::_pass = lex::pass_flags::pass_ignore];
this->self += comments [lex::_pass = lex::pass_flags::pass_ignore];
}
lex::token_def<std::string> word, litteral, integer;
lex::token_def<lex::omit> left_parenth, right_parenth, left_brace, right_brace;
lex::token_def<lex::omit> stop, comma;
lex::token_def<lex::omit> assign, swap, addition, subtraction, multiplication, division, modulo;
lex::token_def<lex::omit> equals, not_equals, greater, less, greater_equals, less_equals;
//Keywords
lex::token_def<lex::omit> keyword_if, keyword_else, keyword_for, keyword_while, keyword_from, keyword_to, keyword_foreach;
lex::token_def<lex::omit> keyword_true, keyword_false;
//Ignored tokens
lex::token_def<lex::omit> whitespaces;
lex::token_def<lex::omit> comments;
};
Is there an other way to get the value of a Token ?
You can always use the 'default' token data (which is iterator_range of the source iterator type).
After studying the test cases in the boost repository, I found out a number of things:
The cinch is that the token data is variant, which starts out as the raw input iterator range. Only after 'a' forced assignment, the converted attribute is cached in the variant. You can witness the transition:
As you can see, the attribute assignment is forced here, directly using the
assign_to
trait implementation.Full working demonstration: