如何结合boost :: spirit :: lex和boost :: spirit :: qi？

Question

I have a lexer and based on that lexer I now want to create a grammar that used the tokens generated by this lexer. I tried adapting some examples that I found and now I have something that compiles and works at least a little bit, but one of my tests that should fail does not. Now I want to know why and I also want to know what I'm actually doing there (I want to understand - I just copied some code from some examples but that doesn't really improve the understanding much).

Lexer:

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

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;
};

Grammar:

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

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

    template< typename TokenDef >
    custom_grammar(const TokenDef& tok) : custom_grammar::base_type(ges)
    {
        ges = qi::token(ID_INTEGER) | qi::token(ID_FLOAT);
        BOOST_SPIRIT_DEBUG_NODE(ges);
        debug(ges);
    }
    qi::rule<Iterator, qi::in_state_skipper<Lexer>> ges;
};

And example:

BOOST_AUTO_TEST_CASE(BasicGrammar)
{
    namespace lex = boost::spirit::lex;
    namespace qi = boost::spirit::qi;

    std::string test("1234 56");

    typedef lex::lexertl::token<char const*, lex::omit, boost::mpl::true_> token_type;
    typedef lex::lexertl::lexer<token_type> lexer_type;

    typedef custom_lexer<lexer_type>::iterator_type iterator_type;

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

    char const* first = test.c_str();
    char const* last = &first[test.size()];

    lexer_type::iterator_type iter = my_lexer.begin(first, last);
    lexer_type::iterator_type end = my_lexer.end();

    bool r = qi::phrase_parse(iter,end,my_grammar, qi::in_state( "WS" )[ my_lexer.self ]);

    BOOST_CHECK(r);
}

My assumption is that this returns true because the whitespace is skipped - because auf qi::in_state("WS"). Is that true? Additionally, I know how I can output additional tokens for whitespace - but then I don't know what to put at the location where the qi::in_stat is now - without it it isn't working.

Any ideas what I can improve regarding the structure? Why is the debug output so funny?

<ges>
  <try>[]</try>
  <success></success>
  <attributes>[]</attributes>
</ges>

Thank you for your help.

Regards

Tobias

Answer 1

You parser isn't failing, but no it isn't 'silently' skipping the whitespace either (it parses only one non-whitespace token, anyway).

In fact, a property of *phrase_parse family of Spirit APIs is that it may not match the full input. In fact, this is why it takes the first iterator by reference: after parsing the iterator will indicate where parsing stopped.

I have changed a few bits around so you can easily access the source iterator, by using lex::tokenize_and_phrase_parse instead of qi::phrase_parse on lexer_tokens:

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";

The output is:

Remaining unparsed: '56'

Here is a full working example (note I also changed the second parameter of the grammar class to be the Skipper directly, which is more typical for Spirit grammars):

#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_INTEGER) | qi::token(ID_FLOAT);
        BOOST_SPIRIT_DEBUG_NODE(ges);
    }
    qi::rule<Iterator, Skipper > ges;
};

int main()
{
    std::string test("1234 56");

    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";
}