提升精神解析器 Lex->qi：让"undocumented" on_success机制发挥作用

查看头文件，我认为占位符的含义是：

_1 = Iterator position when the rule was tried.
_2 = Iterator to the end of the input.
_3 = Iterator position right after the rule has been successfully matched.

(由于我不确定上面的行是否可以理解，这里有一个包含您输入的小示例(

                                 rule being tried
                        _________________________________
                       ´                                 `
[EVENT][1][:][sihan][{][OPTIONAL][123][:][hassan][int4][;][OPTIONAL][321][:][hassan2][int4][;][}]
                           _1                                 _3                                 _2

正如 GManNickG 在注释中提到的，这些是词法分析器迭代器，您无法使用它们轻松访问原始字符串。该conjure2 example结合了词法分析器和on_error/on_success的使用。为此，它使用了一种特殊的令牌，position_token .此令牌始终可以访问与自身关联的原始字符串的迭代器对(当您使用 lex::omit 时，普通令牌会丢失此信息(。 position_token有几种有趣的方法。 matched()返回一个iterator_range<OriginalIterator>，begin()和end()返回相应的迭代器。

在下面的代码中，我选择创建一个phoenix::function，该接受两个词法分析器迭代器(使用 _1 和 _3 调用(并返回一个覆盖它们之间距离的字符串(使用 std::string(begin_iter->begin(), end_iter->begin()) (。

我发现的一个问题是，空格处于不同状态的事实导致position_token返回的迭代器无效。我所做的解决这个问题是将所有内容置于相同的状态，然后简单地将lex::_pass = lex::pass_flags::pass_ignore与空格一起使用。

最后一个(次要(问题是，如果要使用std::cout << _val则需要为您感兴趣的类型定义operator<<。

PS：我总是使用BOOST_SPIRIT_USE_PHOENIX_V3，这要求每个精神/凤凰都来自boost/spirit/include/...。如果出于任何原因，您需要/想要使用 V2，则需要更改 phoenix：：函数。我也无法使用旧的循环样式，所以如果你不能使用 c++11，你将不得不更改运算符的定义<<for event_descriptor。

#define BOOST_SPIRIT_USE_PHOENIX_V3
// #define BOOST_SPIRIT_DEBUG
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix_core.hpp>
#include <boost/spirit/include/phoenix_bind.hpp> //CHANGED
#include <boost/spirit/include/lex_lexertl.hpp>
#include <boost/spirit/include/lex_lexertl_position_token.hpp> //ADDED
#include <boost/none.hpp>
#include <boost/cstdint.hpp>
#include <boost/fusion/include/adapt_struct.hpp>
#include <string>
#include <exception>
#include <vector>
namespace lex = boost::spirit::lex;
namespace px = boost::phoenix;
namespace qi = boost::spirit::qi;
namespace ascii = boost::spirit::ascii;

template <typename Lexer>
struct tokens : lex::lexer<Lexer>
{
    tokens()
        : left_curly(""{""),
        right_curly(""}""),
        left_paren(""(""),
        right_paren("")""),
        colon(":"),
        scolon(";"),
        namespace_("(?i:namespace)"),
        event("(?i:event)"),
        optional("(?i:optional)"),
        required("(?i:required)"),
        repeated("(?i:repeated)"),
        t_int_4("(?i:int4)"),
        t_int_8("(?i:int8)"),
        t_string("(?i:string)"),
        ordinal("\d+"),
        identifier("\w+")
    {
        using boost::spirit::lex::_val;
        this->self
            = 
              left_curly    //[ std::cout << px::val("lpar") << std::endl]
            | right_curly   //[ std::cout << px::val("rpar") << std::endl]
            | left_paren
            | right_paren
            | colon               //[ std::cout << px::val("colon") << std::endl]
            | scolon
            | namespace_         // [ std::cout << px::val("kw namesapce") << std::endl]
            | event              // [ std::cout << px::val("kw event") << std::endl]
            | optional            //[ std::cout << px::val("optional ")  << "-->" << _val << "<--" << std::endl]
            | required            //[ std::cout << px::val("required") << std::endl]
            | repeated
            | t_int_4
            | t_int_8
            | t_string
            | ordinal             //[ std::cout << px::val("val ordinal (") << _val << ")" << std::endl]
            | identifier          //[std::cout << px::val("val identifier(") << _val << ")" << std::endl]
            | lex::token_def<>("[ \t\n]+")   [lex::_pass = lex::pass_flags::pass_ignore] //CHANGED
            ;
    }

    lex::token_def<lex::omit> left_curly, right_curly, left_paren, right_paren, colon, scolon;
    lex::token_def<lex::omit> namespace_, event, optional, required, repeated, t_int_4, t_int_8, t_string;
    lex::token_def<boost::uint32_t> ordinal;
    lex::token_def<> identifier;
};
enum event_entry_qualifier
{
    ENTRY_OPTIONAL,
    ENTRY_REQUIRED,
    ENTRY_REPEATED
};
enum entry_type
{
    RBL_INT4,
    RBL_INT8,
    RBL_STRING,
    RBL_EVENT
};
struct oid
{
    boost::uint32_t   ordinal;
    std::string       name;
};
BOOST_FUSION_ADAPT_STRUCT
(
  oid,
  (boost::uint32_t, ordinal)
  (std::string, name)
)
std::ostream& operator<<(std::ostream& os, const oid& val) //ADDED
{
    return os << val.ordinal << "-" << val.name;
}
struct type_descriptor
{
    entry_type  type_id;
    std::string referenced_event;
};
BOOST_FUSION_ADAPT_STRUCT
(
  type_descriptor,
  (entry_type, type_id)
  (std::string, referenced_event)
)
std::ostream& operator<<(std::ostream& os, const type_descriptor& val)  //ADDED
{
    return os << val.type_id << "-" << val.referenced_event;
}
struct event_entry
{
    event_entry_qualifier  qualifier;
    oid                   identifier;
    type_descriptor       descriptor;
};

BOOST_FUSION_ADAPT_STRUCT
(
  event_entry,
  (event_entry_qualifier, qualifier)
  (oid, identifier)
  (type_descriptor, descriptor)
)
std::ostream& operator<<(std::ostream& os, const event_entry& val)  //ADDED
{
    return os << val.qualifier << "-" << val.identifier << "-" << val.descriptor;
}
struct event_descriptor
{
    oid                       identifier;
    std::vector<event_entry>  event_entries;
};

BOOST_FUSION_ADAPT_STRUCT
(
    event_descriptor,
    (oid, identifier)
    (std::vector<event_entry>, event_entries)
)
std::ostream& operator<<(std::ostream& os, const event_descriptor& val)  //ADDED
{
    os << val.identifier << "[";
    for(const auto& entry: val.event_entries)   //C++11
        os << entry;
    os << "]";
    return os;
}
struct build_string_impl        //ADDED
{
    template <typename Sig>
    struct result;
    template <typename This, typename Iter1, typename Iter2>
    struct result<This(Iter1,Iter2)>
    {
        typedef std::string type;
    };
    template <typename Iter1, typename Iter2>
    std::string operator()(Iter1 begin, Iter2 end) const
    {
        return std::string(begin->begin(),end->begin());
    }
};
px::function<build_string_impl> build_string;
template <typename Iterator, typename Lexer>
struct grammar : qi::grammar<Iterator,event_descriptor() >
{
    template <typename TokenDef>
    grammar(TokenDef const& tok)
      : grammar::base_type(event_descriptor_)
    {
      using qi::_val;
      //start = event;
      event_descriptor_ = tok.event >> oid_ >> tok.left_curly >> *(event_entry_) >> tok.right_curly;
      event_entry_ = event_qualifier >> oid_ >> type_descriptor_ >> tok.scolon;
      event_qualifier = tok.optional [ _val = ENTRY_OPTIONAL]  
                      | tok.required [ _val = ENTRY_REQUIRED]
                      | tok.repeated [ _val = ENTRY_REPEATED];
      oid_  = tok.ordinal 
            >> tok.colon 
            >> tok.identifier;
      type_descriptor_ 
          = (( atomic_type >> qi::attr("")) 
          | ( event_type >> tok.left_paren >> tok.identifier >> tok.right_paren));
      atomic_type = tok.t_int_4         [ _val = RBL_INT4]
              | tok.t_int_8             [ _val = RBL_INT8]
              | tok.t_string            [ _val = RBL_STRING];
      event_type = tok.event            [_val = RBL_EVENT];
      using namespace qi::labels;
      qi::on_success(event_entry_,std::cout << _val << " " << build_string(_1,_3) << std::endl); //CHANGED
      // BOOST_SPIRIT_DEBUG_NODES( (event_descriptor_)(event_entry_)(event_qualifier)(oid_)(type_descriptor_)(atomic_type)(event_type) );
    }
    qi::rule<Iterator> start;
    qi::rule<Iterator, event_descriptor()> event_descriptor_; 
    qi::rule<Iterator, event_entry()> event_entry_;
    qi::rule<Iterator, event_entry_qualifier()> event_qualifier;
    qi::rule<Iterator, entry_type()> atomic_type;
    qi::rule<Iterator, entry_type()> event_type;
    qi::rule<Iterator, type_descriptor()> type_descriptor_;
    qi::rule<Iterator, oid()> oid_;

};
std::string test = " EVENT 1:sihan { OPTIONAL 123:hassan int4; OPTIONAL 321:hassan2 int4; } ";
int main()
{
    typedef lex::lexertl::position_token<std::string::iterator, boost::mpl::vector<boost::uint32_t, std::string> > token_type; //CHANGED
    typedef lex::lexertl::actor_lexer<token_type> lexer_type;
    typedef tokens<lexer_type>::iterator_type iterator_type;
    tokens<lexer_type> token_lexer;
    grammar<iterator_type,tokens<lexer_type>::lexer_def> grammar(token_lexer);
    std::string::iterator it = test.begin();
    iterator_type first = token_lexer.begin(it, test.end());
    iterator_type last = token_lexer.end();
    bool r; 
    r = qi::parse(first, last, grammar); //CHANGED
    if(r)
        ;
    else
    {
        std::cout << "parsing failed" << std::endl;
    }
}