麻煩加精:: lex＆whitespace

Question

我嘗試學習使用boost :: spirit。要做到這一點，我想創建一個簡單的詞法分析器，將它們結合起來，然後使用spirit開始分析。我試着修改這個例子，但它沒有像預期的那樣運行（結果r不正確）。

這裏的詞法分析器：

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

namespace lex = boost::spirit::lex; 

template <typename Lexer> 
struct lexer_identifier : lex::lexer<Lexer> 
{ 
    lexer_identifier() 
     : identifier("[a-zA-Z_][a-zA-Z0-9_]*") 
     , white_space("[ \\t\\n]+") 
    { 
     using boost::spirit::lex::_start; 
     using boost::spirit::lex::_end; 

     this->self = identifier; 
     this->self("WS") = white_space; 
    } 
    lex::token_def<> identifier; 
    lex::token_def<> white_space; 
    std::string identifier_name; 
}; 

這是我嘗試運行的例子：因爲只有一個字符串中令牌

#include "stdafx.h" 

#include <boost/spirit/include/lex_lexertl.hpp> 
#include "my_Lexer.h" 

namespace lex = boost::spirit::lex; 

int _tmain(int argc, _TCHAR* argv[]) 
{ 
    typedef lex::lexertl::token<char const*,lex::omit, boost::mpl::false_> token_type; 
    typedef lex::lexertl::lexer<token_type> lexer_type; 

    typedef lexer_identifier<lexer_type>::iterator_type iterator_type; 

    lexer_identifier<lexer_type> my_lexer; 

    std::string test("adedvied das934adf dfklj_03245"); 

    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(); 

    while (iter != end && token_is_valid(*iter)) 
    { 
     ++iter; 
    } 

    bool r = (iter == end); 

    return 0; 
} 

r是隻要真實的。爲什麼會這樣？

問候 托比亞斯

Answer 1

您已經創建了第二個詞法分析器狀態，但永遠不會調用它。

簡化及利潤：

---

在大多數情況下，能有預期的效果最簡單的方法是使用單態樂星與pass_ignore標誌上的可跳過標記：

this->self += identifier 
       | white_space [ lex::_pass = lex::pass_flags::pass_ignore ]; 

請注意，這需要actor_lexer以允許語義操作：

typedef lex::lexertl::actor_lexer<token_type> lexer_type; 

全樣本：

#include <boost/spirit/include/lex_lexertl.hpp> 
#include <boost/spirit/include/lex_lexertl.hpp> 
namespace lex = boost::spirit::lex; 

template <typename Lexer> 
struct lexer_identifier : lex::lexer<Lexer> 
{ 
    lexer_identifier() 
     : identifier("[a-zA-Z_][a-zA-Z0-9_]*") 
     , white_space("[ \\t\\n]+") 
    { 
     using boost::spirit::lex::_start; 
     using boost::spirit::lex::_end; 

     this->self += identifier 
        | white_space [ lex::_pass = lex::pass_flags::pass_ignore ]; 
    } 
    lex::token_def<> identifier; 
    lex::token_def<> white_space; 
    std::string identifier_name; 
}; 

int main(int argc, const char *argv[]) 
{ 
    typedef lex::lexertl::token<char const*,lex::omit, boost::mpl::false_> token_type; 
    typedef lex::lexertl::actor_lexer<token_type> lexer_type; 

    typedef lexer_identifier<lexer_type>::iterator_type iterator_type; 

    lexer_identifier<lexer_type> my_lexer; 

    std::string test("adedvied das934adf dfklj_03245"); 

    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(); 

    while (iter != end && token_is_valid(*iter)) 
    { 
     ++iter; 
    } 

    bool r = (iter == end); 
    std::cout << std::boolalpha << r << "\n"; 
} 

打印

true 

「WS」 作爲船長狀態

---

也可能您在使用第二解析器狀態的樣本來船長（lex::tokenize_and_phrase_parse）。讓我花一分鐘或10分鐘爲此創建一個工作示例。

更新我花了一點時間超過10分鐘（waaaah）:)這裏有一個對比試驗，展示如何詞法分析器狀態互動，以及如何使用精神船長解析調用第二解析器的狀態：

#include <boost/spirit/include/qi.hpp> 
#include <boost/spirit/include/lex_lexertl.hpp> 
namespace lex = boost::spirit::lex; 
namespace qi = boost::spirit::qi; 

template <typename Lexer> 
struct lexer_identifier : lex::lexer<Lexer> 
{ 
    lexer_identifier() 
     : identifier("[a-zA-Z_][a-zA-Z0-9_]*") 
     , white_space("[ \\t\\n]+") 
    { 
     this->self  = identifier; 
     this->self("WS") = white_space; 
    } 
    lex::token_def<> identifier; 
    lex::token_def<lex::omit> white_space; 
}; 

int main() 
{ 
    typedef lex::lexertl::token<char const*, lex::omit, boost::mpl::true_> token_type; 
    typedef lex::lexertl::lexer<token_type> lexer_type; 

    typedef lexer_identifier<lexer_type>::iterator_type iterator_type; 

    lexer_identifier<lexer_type> my_lexer; 

    std::string test("adedvied das934adf dfklj_03245"); 

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

     // cannot lex in just default WS state: 
     bool ok = lex::tokenize(first, last, my_lexer, "WS"); 
     std::cout << "Starting state WS:\t" << std::boolalpha << ok << "\n"; 
    } 

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

     // cannot lex in just default state either: 
     bool ok = lex::tokenize(first, last, my_lexer, "INITIAL"); 
     std::cout << "Starting state INITIAL:\t" << std::boolalpha << ok << "\n"; 
    } 

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

     bool ok = lex::tokenize_and_phrase_parse(first, last, my_lexer, *my_lexer.self, qi::in_state("WS")[my_lexer.self]); 
     ok = ok && (first == last); // verify full input consumed 
     std::cout << std::boolalpha << ok << "\n"; 
    } 
} 

輸出是

Starting state WS: false 
Starting state INITIAL: false 
true