在没有船长的情况下提升精神解析

Question

考虑一个将读取原始文本的预处理器（没有明显的白色 space 或标记）。

有 3 条规则。

resolve_para_entry 应该解决调用中的参数。顶级文本作为字符串返回。
resolve_para 应该解析整个参数列表并将所有顶级参数放在字符串列表中。
resolve是条目

在跟踪迭代器并获取文本部分的过程中

样本：

sometext(para) → 在字符串列表中期望 para
sometext(para1,para2) → 在字符串列表

para1

para2

sometext(call(a)) → 在字符串列表中期望 call(a)
sometext(call(a,b)) ← 这里失败了；看起来“!lit(',')”不会让解析器走出去..

规则：

resolve_para_entry = +(  
     (iter_pos >> lit('(') >> (resolve_para_entry | eps) >> lit(')') >> iter_pos) [_val=  phoenix::bind(&appendString, _val, _1,_3)]
     | (!lit(',') >> !lit(')') >> !lit('(') >> (wide::char_ | wide::space))         [_val = phoenix::bind(&appendChar, _val, _1)]
    );

resolve_para = (lit('(') >> lit(')'))[_val = std::vector<std::wstring>()]  // empty para -> old style
    | (lit('(') >> resolve_para_entry >> *(lit(',') >> resolve_para_entry) > lit(')'))[_val = phoenix::bind(&appendStringList, _val, _1, _2)]
    | eps;
  ;

resolve = (iter_pos >> name_valid >> iter_pos >> resolve_para >> iter_pos);

最后好像不太优雅。也许有更好的方法可以在没有船长的情况下解析这些东西

Answer 1

确实这样应该简单很多。

首先，我不明白为什么船长缺席根本相关。

其次，最好使用 qi::raw[] 来公开原始输入，而不是使用 iter_pos 和笨拙的语义动作来完成。

在我看到的其他观察结果中：

negating a charset 是用 ~ 完成的，所以例如~char_(",()")
(p|eps) 最好写成 -p
(lit('(') >> lit(')'))可能只是"()"（毕竟没有船长吧）
p >> *(',' >> p) 等同于 p % ','

有了上面的内容，resolve_para 简化为：

resolve_para = '(' >> -(resolve_para_entry % ',') >> ')';

resolve_para_entry 对我来说似乎很奇怪。似乎任何嵌套的括号都被简单地吞没了。为什么不实际解析递归语法以便检测语法错误？

这是我的看法：

定义 AST

我更愿意将此作为第一步，因为它有助于我思考解析器产品：

namespace Ast {

    using ArgList = std::list<std::string>;

    struct Resolve {
        std::string name;
        ArgList arglist;
    };

    using Resolves = std::vector<Resolve>;
}

创建语法规则

qi::rule<It, Ast::Resolves()> start;
qi::rule<It, Ast::Resolve()>  resolve;
qi::rule<It, Ast::ArgList()>  arglist;
qi::rule<It, std::string()>   arg, identifier;

及其定义：

identifier = char_("a-zA-Z_") >> *char_("a-zA-Z0-9_");

arg        = raw [ +('(' >> -arg >> ')' | +~char_(",)(")) ];
arglist    = '(' >> -(arg % ',') >> ')';
resolve    = identifier >> arglist;

start      = *qr::seek[hold[resolve]];

备注：

不再有语义动作
没有了eps
没有了iter_pos
我选择将 arglist 设置为非可选。如果你真的想要那个，把它改回来：
```
resolve    = identifier >> -arglist;
```
但在我们的示例中，它会产生大量嘈杂的输出。
当然您的入口点 (start) 会有所不同。我只是做了可能可行的最简单的事情，使用 Spirit Repository 中的另一个方便的解析器指令（比如你已经在使用的 iter_pos）：seek[]
保留的原因是：boost::spirit::qi duplicate parsing on the output - 在您的实际解析器中可能不需要它。

Live On Coliru

#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/repository/include/qi_seek.hpp>

namespace Ast {

    using ArgList = std::list<std::string>;

    struct Resolve {
        std::string name;
        ArgList arglist;
    };

    using Resolves = std::vector<Resolve>;
}

BOOST_FUSION_ADAPT_STRUCT(Ast::Resolve, name, arglist)

namespace qi = boost::spirit::qi;
namespace qr = boost::spirit::repository::qi;

template <typename It>
struct Parser : qi::grammar<It, Ast::Resolves()>
{
    Parser() : Parser::base_type(start) {
        using namespace qi;

        identifier = char_("a-zA-Z_") >> *char_("a-zA-Z0-9_");

        arg        = raw [ +('(' >> -arg >> ')' | +~char_(",)(")) ];
        arglist    = '(' >> -(arg % ',') >> ')';
        resolve    = identifier >> arglist;

        start      = *qr::seek[hold[resolve]];
    }
  private:
    qi::rule<It, Ast::Resolves()> start;
    qi::rule<It, Ast::Resolve()>  resolve;
    qi::rule<It, Ast::ArgList()>  arglist;
    qi::rule<It, std::string()>   arg, identifier;
};

#include <iostream>

int main() {
    using It = std::string::const_iterator;
    std::string const samples = R"--(
Samples:

sometext(para)        → expect para in the string list
sometext(para1,para2) → expect para1 and para2 in string list
sometext(call(a))     → expect call(a) in the string list
sometext(call(a,b))   ← here it fails; it seams that the "!lit(',')" wont make the parser step outside
)--";
    It f = samples.begin(), l = samples.end();

    Ast::Resolves data;
    if (parse(f, l, Parser<It>{}, data)) {
        std::cout << "Parsed " << data.size() << " resolves\n";

    } else {
        std::cout << "Parsing failed\n";
    }

    for (auto& resolve: data) {
        std::cout << " - " << resolve.name << "\n   (\n";
        for (auto& arg : resolve.arglist) {
            std::cout << "       " << arg << "\n";
        }
        std::cout << "   )\n";
    }
}

打印

Parsed 6 resolves
 - sometext
   (
       para
   )
 - sometext
   (
       para1
       para2
   )
 - sometext
   (
       call(a)
   )
 - call
   (
       a
   )
 - call
   (
       a
       b
   )
 - lit
   (
       '
       '
   )

奖金

使用 string_view 并显示所有提取单词的准确 line/column 信息的奖励版本。

注意它仍然不需要任何凤凰或语义动作。相反，它只是定义了从迭代器范围分配给 boost::string_view 的必要特征。

Live On Coliru

#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/repository/include/qi_seek.hpp>
#include <boost/utility/string_view.hpp>

namespace Ast {

    using Source  = boost::string_view;
    using ArgList = std::list<Source>;

    struct Resolve {
        Source name;
        ArgList arglist;
    };

    using Resolves = std::vector<Resolve>;
}

BOOST_FUSION_ADAPT_STRUCT(Ast::Resolve, name, arglist)

namespace boost { namespace spirit { namespace traits {
    template <typename It>
    struct assign_to_attribute_from_iterators<boost::string_view, It, void> {
        static void call(It f, It l, boost::string_view& attr) { 
            attr = boost::string_view { f.base(), size_t(std::distance(f.base(),l.base())) };
        }
    };
} } }

namespace qi = boost::spirit::qi;
namespace qr = boost::spirit::repository::qi;

template <typename It>
struct Parser : qi::grammar<It, Ast::Resolves()>
{
    Parser() : Parser::base_type(start) {
        using namespace qi;

        identifier = raw [ char_("a-zA-Z_") >> *char_("a-zA-Z0-9_") ];

        arg        = raw [ +('(' >> -arg >> ')' | +~char_(",)(")) ];
        arglist    = '(' >> -(arg % ',') >> ')';
        resolve    = identifier >> arglist;

        start      = *qr::seek[hold[resolve]];
    }
  private:
    qi::rule<It, Ast::Resolves()> start;
    qi::rule<It, Ast::Resolve()>  resolve;
    qi::rule<It, Ast::ArgList()>  arglist;
    qi::rule<It, Ast::Source()>   arg, identifier;
};

#include <iostream>

struct Annotator {
    using Ref = boost::string_view;

    struct Manip {
        Ref fragment, context;

        friend std::ostream& operator<<(std::ostream& os, Manip const& m) {
            return os << "[" << m.fragment << " at line:" << m.line() << " col:" << m.column() << "]";
        }

        size_t line() const {
            return 1 + std::count(context.begin(), fragment.begin(), '\n');
        }
        size_t column() const {
            return 1 + (fragment.begin() - start_of_line().begin());
        }
        Ref start_of_line() const {
            return context.substr(context.substr(0, fragment.begin()-context.begin()).find_last_of('\n') + 1);
        }
    };

    Ref context;
    Manip operator()(Ref what) const { return {what, context}; }
};

int main() {
    using It = std::string::const_iterator;
    std::string const samples = R"--(Samples:

sometext(para)        → expect para in the string list
sometext(para1,para2) → expect para1 and para2 in string list
sometext(call(a))     → expect call(a) in the string list
sometext(call(a,b))   ← here it fails; it seams that the "!lit(',')" wont make the parser step outside
)--";
    It f = samples.begin(), l = samples.end();

    Ast::Resolves data;
    if (parse(f, l, Parser<It>{}, data)) {
        std::cout << "Parsed " << data.size() << " resolves\n";

    } else {
        std::cout << "Parsing failed\n";
    }

    Annotator annotate{samples};

    for (auto& resolve: data) {
        std::cout << " - " << annotate(resolve.name) << "\n   (\n";
        for (auto& arg : resolve.arglist) {
            std::cout << "       " << annotate(arg) << "\n";
        }
        std::cout << "   )\n";
    }
}

打印

Parsed 6 resolves
 - [sometext at line:3 col:1]
   (
       [para at line:3 col:10]
   )
 - [sometext at line:4 col:1]
   (
       [para1 at line:4 col:10]
       [para2 at line:4 col:16]
   )
 - [sometext at line:5 col:1]
   (
       [call(a) at line:5 col:10]
   )
 - [call at line:5 col:34]
   (
       [a at line:5 col:39]
   )
 - [call at line:6 col:10]
   (
       [a at line:6 col:15]
       [b at line:6 col:17]
   )
 - [lit at line:6 col:62]
   (
       [' at line:6 col:66]
       [' at line:6 col:68]
   )

¹ Boost Spirit: "Semantic actions are evil"?

在没有船长的情况下提升精神解析

boost spirit parsing with no skipper

c++

preprocessor

boost-spirit

定义 AST

创建语法规则

更多想法

奖金