c++ - spirit 解析器输出中的附加符号

Question

我们尝试解析简单的数字/文本(在文本中呈现数字，因此我们必须将输入序列拆分为 2 个元素类型(TEXT 和 NUMBER) vector )语法，其中数字可以采用以下格式:

+10.90
10.90
10
+10
-10

所以我们写语法:

struct CMyTag
{
    TagTypes tagName;
    std::string tagData;
    std::vector<CMyTag> tagChild;
};
BOOST_FUSION_ADAPT_STRUCT(::CMyTag, (TagTypes, tagName) (std::string, tagData) (std::vector<CMyTag>, tagChild))

template <typename Iterator>
struct TextWithNumbers_grammar : qi::grammar<Iterator, std::vector<CMyTag>()>
{
    TextWithNumbers_grammar() :
        TextWithNumbers_grammar::base_type(line)
    {
        line = +(numbertag | texttag);

        number = qi::lexeme[-(qi::lit('+') | '-') >> +qi::digit >> *(qi::char_('.') >> +qi::digit)];
        numbertag = qi::attr(NUMBER) >> number;

        text = +(~qi::digit - (qi::char_("+-") >> qi::digit));
        texttag = qi::attr(TEXT) >> text;
    }

    qi::rule<Iterator, std::string()> number, text;
    qi::rule<Iterator, CMyTag()> numbertag, texttag;
    qi::rule<Iterator, std::vector<CMyTag>()> line;
};

一切正常，但如果我们尝试解析这一行:

wernwl kjwnwenrlwe +10.90+ klwnfkwenwf

我们按预期获得了 3 个元素 vector ，但此 vector 中的最后一个元素将带有文本 (CMyTag.tagData):

++ klwnfkwenwf

添加了附加符号“+”。 我们还尝试将语法重写为简单的跳过数字规则:

text = qi::skip(number)[+~qi::digit];

但是解析器死于段错误异常

Answer 1

回溯时不会回滚属性值。实际上，这仅在容器属性(例如 vector<> 或 string )中可见。

在这种情况下，首先解析 numbertag 规则并解析 +符号。然后，数字规则失败，并且已经匹配的 +留在输入中。

我确切地不知道您要做什么，但看起来您只是想要:

line      = +(numbertag | texttag);

numbertag = attr(NUMBER) >> raw[double_];
texttag   = attr(TEXT)   >> raw[+(char_ - double_)];

对于输入"wernwl kjwnwenrlwe +10.90e3++ klwnfkwenwf"它打印

Parse success: 5 elements
TEXT    'wernwl kjwnwenrlwe '
NUMBER  '+10.90'
TEXT    'e'
NUMBER  '3'
TEXT    '++ klwnfkwenwf'

现场演示

Live On Coliru

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

enum TagTypes { NUMBER, TEXT, };

struct CMyTag {
    TagTypes tagName;
    std::string tagData;
};
BOOST_FUSION_ADAPT_STRUCT(::CMyTag, (TagTypes, tagName) (std::string, tagData))

template <typename Iterator>
struct TextWithNumbers_grammar : qi::grammar<Iterator, std::vector<CMyTag>()>
{
    TextWithNumbers_grammar() : TextWithNumbers_grammar::base_type(line)
    {
        using namespace qi;
        line      = +(numbertag | texttag);

        numbertag = attr(NUMBER) >> raw[number];
        texttag   = attr(TEXT)   >> raw[+(char_ - number)];
    }

  private:
    template <typename T>
        struct simple_real_policies : boost::spirit::qi::real_policies<T>
    {
        template <typename It> //  No exponent
            static bool parse_exp(It&, It const&) { return false; }

        template <typename It, typename Attribute> //  No exponent
            static bool parse_exp_n(It&, It const&, Attribute&) { return false; }
    };

    qi::real_parser<double, simple_real_policies<double> > number;
    qi::rule<Iterator, CMyTag()> numbertag, texttag;
    qi::rule<Iterator, std::vector<CMyTag>()> line;
};

int main() {

    std::string const input = "wernwl kjwnwenrlwe +10.90e3++ klwnfkwenwf";
    using It = std::string::const_iterator;

    It f = input.begin(), l = input.end();

    std::vector<CMyTag> data;
    TextWithNumbers_grammar<It> g;

    if (qi::parse(f, l, g, data)) {
        std::cout << "Parse success: " << data.size() << " elements\n";
        for (auto& s : data) {
            std::cout << (s.tagName == NUMBER?"NUMBER":"TEXT")
                      << "\t'" << s.tagData << "'\n";
        }
    } else {
        std::cout << "Parse failed\n";
    }

    if (f!=l)
        std::cout << "Remaining unparsed: '" << std::string(f,l) << "'\n";
}