使用 boost::spirit::x3 进行 URL 解析

Question

我正在尝试使用 boost::spirit::x3 将 URL 解析和分解为多个部分，如下所示：

#include <iostream>
#include <boost/fusion/adapted/std_tuple.hpp>
#include <boost/fusion/adapted/struct.hpp>
#include <boost/spirit/home/x3.hpp>

struct UrlParts { std::string prefix, host, suffix; };
BOOST_FUSION_ADAPT_STRUCT(UrlParts, prefix, host, suffix)

UrlParts parseSpirit(std::string_view input) {
    namespace x3 = boost::spirit::x3;

    static const auto scheme_    = (x3::raw[+x3::char_("a-zA-Z0-9+.-") >> "://"]);
    static const auto userinfo_  = (x3::raw[+~x3::char_("@") >> "@"]);
    static const auto prefix_    = (-scheme_ >> -userinfo_);
    static const auto port_      = (x3::raw[':' >> -x3::repeat(1, 5)[x3::digit] >> &(x3::char_("/?#") | x3::eoi)]);
    static const auto host_      = (+(x3::char_("a-fxXA-F0-9:.") - port_));
    static const auto path_      = (x3::char_("/?#") >> *x3::char_);    // to store path+query+fragment
    static const auto suffix_    = (-port_ >> -path_);

    //static const auto url = x3::rule<class url, UrlParts>() = -prefix_ >> ('[' >> host_ >> ']' | host_) >> -suffix_;
    static const auto url = -prefix_ >> ('[' >> host_ >> ']' | host_) >> -suffix_;    // prefix & suffix are optional but host is required

    // BOOST_SPIRIT_DEBUG_NODES((scheme_)(userinfo_)(host_)(port_)(path_)(url));

    // Parse the input
    auto iter = input.begin();
    auto end = input.end();
    UrlParts parts;
    auto attr = std::tie(parts.prefix, parts.host, parts.suffix);
    //parse(input.begin(), input.end(), x3::eps >> url >> x3::eoi, parts);
    bool ret = x3::parse(iter, end, url >> x3::eoi, attr);
    if (!ret) {
        std::cout << "Parsing failed" << std::endl;
    }
    return parts;
}

int main()
{
    for (auto input : {"http://usr:[email protected]:8080/file.php?abc=1#23",
                       "http://[::ffff:192.168.1.1]:8080/file.php?abc=1#23",
                       "http://::ffff:192.168.1.1/file.php?abc=1#23",
                       "::ffff:192.168.1.1"
                      }) {
        std::cout << "Input: " << input << std::endl;
        auto parts = parseSpirit("http://usr:[email protected]/file.php?abc=1");
        std::cout << "Output: Prefix: " << parts.prefix << ", Host: " << parts.host << ", Suffix: " << parts.suffix << std::endl;
        std::cout << "================" << std::endl;
    }
    return 0;
}

但是上面的代码无法编译并出现错误：

/usr/include/boost/spirit/home/x3/operator/detail/sequence.hpp:140:25: error: static assertion failed: Size of the passed attribute is less than expected.
  140 |             actual_size >= expected_size
      |             ~~~~~~~~~~~~^~~~~~~~~~~~~~~~
/usr/include/boost/spirit/home/x3/operator/detail/sequence.hpp:140:25: note: ‘(((int)boost::spirit::x3::detail::partition_attribute >, boost::spirit::x3::literal_string > > >, boost::spirit::x3::optional > >, boost::spirit::x3::literal_char > > > > >, boost::spirit::x3::alternative, boost::spirit::x3::plus, boost::spirit::x3::raw_directive, boost::spirit::x3::optional, boost::spirit::x3::detail::finite_count > > >, boost::spirit::x3::and_predicate, boost::spirit::x3::eoi_parser> > > > > > >, boost::spirit::x3::literal_char >, boost::spirit::x3::plus, boost::spirit::x3::raw_directive, boost::spirit::x3::optional, boost::spirit::x3::detail::finite_count > > >, boost::spirit::x3::and_predicate, boost::spirit::x3::eoi_parser> > > > > > > >, boost::spirit::x3::optional, boost::spirit::x3::optional, boost::spirit::x3::detail::finite_count > > >, boost::spirit::x3::and_predicate, boost::spirit::x3::eoi_parser> > > > >, boost::spirit::x3::optional, boost::spirit::x3::kleene > > > > >, std::tuple, std::allocator >&, std::__cxx11::basic_string, std::allocator >&, std::__cxx11::basic_string, std::allocator >&>, boost::spirit::x3::unused_type, void>::actual_size) >= ((int)boost::spirit::x3::detail::partition_attribute >, boost::spirit::x3::literal_string > > >, boost::spirit::x3::optional > >, boost::spirit::x3::literal_char > > > > >, boost::spirit::x3::alternative, boost::spirit::x3::plus, boost::spirit::x3::raw_directive, boost::spirit::x3::optional, boost::spirit::x3::detail::finite_count > > >, boost::spirit::x3::and_predicate, boost::spirit::x3::eoi_parser> > > > > > >, boost::spirit::x3::literal_char >, boost::spirit::x3::plus, boost::spirit::x3::raw_directive, boost::spirit::x3::optional, boost::spirit::x3::detail::finite_count > > >, boost::spirit::x3::and_predicate, boost::spirit::x3::eoi_parser> > > > > > > >, boost::spirit::x3::optional, boost::spirit::x3::optional, boost::spirit::x3::detail::finite_count > > >, boost::spirit::x3::and_predicate, boost::spirit::x3::eoi_parser> > > > >, boost::spirit::x3::optional, boost::spirit::x3::kleene > > > > >, std::tuple, std::allocator >&, std::__cxx11::basic_string, std::allocator >&, std::__cxx11::basic_string, std::allocator >&>, boost::spirit::x3::unused_type, void>::expected_size))’ evaluates to false

有什么问题的建议吗？与

boost::spirit::qi

类似的代码可以正常工作。
此外，我有兴趣了解是否有更有效的方法来执行此操作，例如：使用 string_view 而不是 string，因为所有 3 个部分都存在于输入视图中。
预先感谢！

Answer 1

这意味着属性未被检测为与解析器表达式兼容。看到它在 1.76 中被破坏了：

我看到的第一个问题是尝试从两个

prefix

指令合成单个字符串 (

raw[]

)。那是...行不通的。

好消息是它可以（再次？）从 1.77 开始，但总的来说，考虑对属性兼容性更明确一点，就像这个答案中的

as_type

理解 Boost.Spirit 中的列表运算符 (%) ，或许多其他https://stackoverflow.com/search?tab=newest&q=user%3a85371%20x3%20as_type&searchOn=3，甚至更多，如果你寻找我通常更喜欢的名字

as

...... https://stackoverflow.com/search?q=user%3A85371+x3+as+x3%3A%3Arule

也就是说，当我查看你的代码时，你绑定了一个手动绑定的元组AND不知何故仍然适应结构？那是多余的。我假设您只想手动绑定，所以放弃适应。

接下来，无论如何，不要使用解析器组合器库作为标记器。即，不要随机地将不相关的产品组合在一起（后缀确实不应包含端口规范）。

此外，使用整数解析器解析为真实的端口号。当然，如果您无论如何都要“迂腐”地严格限制允许的位数！请看这里： auto portnum_ = x3::uint_parser<uint16_t, 10, 1, 5>{}; auto portspec_ = ':' >> portnum_ >> &(x3::char_("/?#") | x3::eoi);

小心双重可选性。例如。由于

suffix_ = -port_ >> -path_

从字面上看只有可选元素，因此表达式

-suffix_

充其量与

suffix_

具有相同的含义。但是，在很多情况下（可选的重复结构），您将获得零长度匹配的无限循环。

我想

/

或

也应该结束用户信息的产生。

并非所有事情都需要

raw

。例如。我更愿意

auto userinfo_  = +~x3::char_("@/#") >> x3::char_("@");

用于用户信息。事实上，如果你这样做

auto authority_ = ('[' >> host_ >> ']' | host_) >> -portspec_;

您将正确获取解析后的主机，无需使用

[]

括号，该括号仅在 URI 语法中有意义。

您已注释掉输入结束验证，让我们重新启用它们。我们还返回更多丰富的信息（包括

valid

标志）和更多测试用例：

实时编译器资源管理器 #include <boost/fusion/adapted/std_tuple.hpp> #include <boost/spirit/home/x3.hpp> #include <iostream> struct UrlParts { std::string prefix, host, suffix; }; UrlParts parseSpirit(std::string_view input) { namespace x3 = boost::spirit::x3; auto scheme_ = x3::raw[+x3::char_("a-zA-Z0-9+.-") >> "://"]; auto userinfo_ = x3::raw[+~x3::char_("@") >> "@"]; auto prefix_ = scheme_ >> -userinfo_; auto port_ = x3::raw[':' >> -x3::repeat(1, 5)[x3::digit] >> &(x3::char_("/?#") | x3::eoi)]; auto host_ = +(x3::char_("a-fxXA-F0-9:.") - port_); auto path_ = x3::char_("/?#") >> *x3::char_; // to store path+query+fragment auto suffix_ = -port_ >> -path_; // static const auto url = = -prefix_ >> ('[' >> host_ >> ']' | host_) >> // -suffix_; auto url // //= x3::rule<class url, UrlParts>() // = -prefix_ // //>> ('[' >> host_ >> ']' | host_) >> // -suffix_ // prefix & suffix are optional but host is required ; // Parse the input auto iter = input.begin(); auto end = input.end(); UrlParts p; auto attr = std::tie(p.prefix/*, p.host, p.suffix*/); bool ret = x3::parse(iter, end, url >> x3::eoi, attr); if (!ret) { std::cout << "Parsing failed" << std::endl; } return p; } int main() { for (auto input : {"http://usr:[email protected]:8080/file.php?abc=1#23", "http://[::ffff:192.168.1.1]:8080/file.php?abc=1#23", "http://::ffff:192.168.1.1/file.php?abc=1#23", "::ffff:192.168.1.1"}) { std::cout << "Input: " << input << std::endl; auto parts = parseSpirit("http://usr:[email protected]/file.php?abc=1"); std::cout << "Output: Prefix: " << parts.prefix << ", Host: " << parts.host << ", Suffix: " << parts.suffix << std::endl; std::cout << "================" << std::endl; } }

印刷

192.168.1.1 {true, "", "", "192.168.1.1", "", unspecified} 192.168.1.1/ {true, "", "", "192.168.1.1", "/", unspecified} 192.168.1.1/file.php {true, "", "", "192.168.1.1", "/file.php", unspecified} 192.168.1.1/file.php?abc=1 {true, "", "", "192.168.1.1", "/file.php?abc=1", unspecified} 192.168.1.1:8888 {true, "", "", "192.168.1.1", "", 8888} 192.168.1.1:8888/ {true, "", "", "192.168.1.1", "/", 8888} 192.168.1.1:8888/file.php {true, "", "", "192.168.1.1", "/file.php", 8888} 192.168.1.1:8888/file.php?abc=1 {true, "", "", "192.168.1.1", "/file.php?abc=1", 8888} ::ffffff::192.168.1.1:9999/file.php?abc=1 {true, "", "", "::ffffff::192.168.1.1", "/file.php?abc=1", 9999} http://192.168.1.1 {true, "http://", "", "192.168.1.1", "", unspecified} http://192.168.1.1/ {true, "http://", "", "192.168.1.1", "/", unspecified} http://192.168.1.1/file.php {true, "http://", "", "192.168.1.1", "/file.php", unspecified} http://192.168.1.1/file.php?abc=1 {true, "http://", "", "192.168.1.1", "/file.php?abc=1", unspecified} http://192.168.1.1:8888 {true, "http://", "", "192.168.1.1", "", 8888} http://192.168.1.1:8888/ {true, "http://", "", "192.168.1.1", "/", 8888} http://192.168.1.1:8888/file.php {true, "http://", "", "192.168.1.1", "/file.php", 8888} http://192.168.1.1:8888/file.php?abc=1 {true, "http://", "", "192.168.1.1", "/file.php?abc=1", 8888} http://::ffffff::192.168.1.1:9999/file.php?abc=1 {true, "http://", "", "::ffffff::192.168.1.1", "/file.php?abc=1", 9999} http://[email protected] {true, "http://", "sehe@", "192.168.1.1", "", unspecified} http://[email protected]/ {true, "http://", "sehe@", "192.168.1.1", "/", unspecified} http://[email protected]/file.php {true, "http://", "sehe@", "192.168.1.1", "/file.php", unspecified} http://[email protected]:8888 {true, "http://", "sehe@", "192.168.1.1", "", 8888} http://[email protected]:8888/ {true, "http://", "sehe@", "192.168.1.1", "/", 8888} http://[email protected]:8888/file.php {true, "http://", "sehe@", "192.168.1.1", "/file.php", 8888} http://usr:[email protected]/file.php?abc=1 {true, "http://", "usr:pwd@", "192.168.1.1", "/file.php?abc=1", unspecified} [email protected] {true, "", "sehe@", "192.168.1.1", "", unspecified} [email protected]/ {true, "", "sehe@", "192.168.1.1", "/", unspecified} [email protected]/file.php {true, "", "sehe@", "192.168.1.1", "/file.php", unspecified} [email protected]:8888 {true, "", "sehe@", "192.168.1.1", "", 8888} [email protected]:8888/ {true, "", "sehe@", "192.168.1.1", "/", 8888} [email protected]:8888/file.php {true, "", "sehe@", "192.168.1.1", "/file.php", 8888} usr:[email protected]/file.php?abc=1 {true, "", "usr:pwd@", "192.168.1.1", "/file.php?abc=1", unspecified}

但是等等 - 问题是什么？

如果您必须使用旧的 Boost 版本，我们会看到

问题又回来了

... 因此，让我们通过在用户信息周围重新设置

raw[]

作为提示来解决这个问题。显然我宁愿升级 Boost:

auto userinfo_  = x3::raw[+~x3::char_("@/#") >> x3::char_("@")];

在 Boost 1.76 上查看它：

https://godbolt.org/z/6bc5Ycrcr

输出相同，md5 校验和：

c69881691195579e3184ef6024136356 1.76 c69881691195579e3184ef6024136356 1.84

使用 boost::spirit::x3 进行 URL 解析

问题描述投票：0回答：1

1个回答

如果您必须使用旧的 Boost 版本，我们会看到

最新问题

使用 boost::spirit::x3 进行 URL 解析

问题描述 投票：0回答：1

1个回答

如果您必须使用旧的 Boost 版本，我们会看到

最新问题

问题描述投票：0回答：1