使用Boost Spirit X3解析HTML遇C1202编译错误求助

问题详情 #

使用Boost Spirit X3编写HTML解析器时触发编译错误：

fatal error C1202: recursive type or function dependency context too complex

已知错误源于html_element_与tag_block_解析器的互相递归引用，但官方Qi/X3示例无法覆盖当前复杂场景，原代码如下：

#include <boost/spirit/home/x3.hpp>
#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/spirit/home/x3/support/ast/position_tagged.hpp>
#include <boost/spirit/home/x3/support/ast/variant.hpp>
#include <iostream>
using namespace boost::spirit::x3;
struct tag_name{};
struct html_tag;
struct html_comment;
struct attribute_data : boost::spirit::x3::position_tagged {
  std::string name;
  boost::optional<std::string> value;
};


struct tag_header :  boost::spirit::x3::position_tagged {
  std::string name;
  std::vector<attribute_data> attributes;
};

struct self_tag: boost::spirit::x3::position_tagged {
  tag_header header;
};

struct html_element : boost::spirit::x3::position_tagged, boost::spirit::x3::variant< std::string, self_tag, boost::recursive_wrapper<html_tag>>{
  using base_type::base_type;
  using base_type::operator=;
};



struct html_tag: boost::spirit::x3::position_tagged {
  tag_header header;
  std::vector<html_element> children;
};

BOOST_FUSION_ADAPT_STRUCT(attribute_data, name, value);
BOOST_FUSION_ADAPT_STRUCT(tag_header, name, attributes);
BOOST_FUSION_ADAPT_STRUCT(self_tag, header);
BOOST_FUSION_ADAPT_STRUCT(html_tag,header,children);

// These are the attributes parser, seems fine
struct attribute_parser_id;
auto attribute_identifier_= rule<attribute_parser_id, std::string>{"AttributeIdentifier"} = lexeme[+(char_ - char_(" /=>"))];
auto attribute_value_= rule<attribute_parser_id, std::string>{"AttributeValue"} =
                           lexeme["\"" > +(char_ - char_("\"")) > "\""]|lexeme["'" > +(char_ - char_("'")) > "'"]|
                           lexeme[+(char_ - char_(" />"))];
auto single_attribute_ = rule<attribute_parser_id, attribute_data>{"SingleAttribute"} = attribute_identifier_ > -("=>"  attribute_value_);
auto attributes_ = rule<attribute_parser_id, std::vector<attribute_data>>{"Attributes"} = (*single_attribute_);


struct tag_parser_id;


auto tag_name_begin_func = [](auto &ctx){
  get<tag_name>(ctx) = _attr(ctx).name;
  //_val(ctx).header.name = _attr(ctx);
  std::cout << typeid(_val(ctx)).name() << std::endl;

};
auto tag_name_end_func = [](auto &ctx){
  _pass(ctx) = get<tag_name>(ctx) == _attr(ctx);
};

auto self_tag_name_action = [](auto &ctx){
  _val(ctx).header.name = _attr(ctx);
};
auto self_tag_attribute_action = [](auto &ctx){
  _val(ctx).header.attributes = _attr(ctx);
};

auto inner_text = lexeme[+(char_-'<')];
auto tag_name_ = rule<tag_parser_id, std::string>{"HtmlTagName"} = lexeme[*(char_ - char_(" />"))];
auto self_tag_ = rule<tag_parser_id, self_tag>{"HtmlSelfTag"} = '<' > tag_name_[self_tag_name_action] > attributes_[self_tag_attribute_action] > "/>";
auto tag_header_ = rule<tag_parser_id, tag_header>{"HtmlTagBlockHeader"} = '<' > tag_name_ > attributes_ > '>';

rule<tag_parser_id, html_tag> tag_block_;

rule<tag_parser_id, html_element> html_element_ = "HtmlElement";

auto tag_block__def = with<tag_name>(std::string())[tag_header_[tag_name_begin_func] > (*html_element_) > "</" > omit[tag_name_[tag_name_end_func]] > '>'];
auto html_element__def = inner_text | self_tag_ | tag_block_ ;

BOOST_SPIRIT_DEFINE(tag_block_, html_element_);
int main()
{
  std::string source = "<div data-src=\"https://www.google.com\" id='hello world'></div>";
   html_element result;
  auto const parser = html_element_;
  auto parse_result = phrase_parse(source.begin(), source.end(), parser, ascii::space, result);
}

解决方法 #

问题核心在于递归解析器规则的声明与初始化方式错误，X3处理递归规则时需确保规则仅先声明、后定义，避免编译器推导类型时陷入无限递归。具体修改点：

1. 调整递归规则声明：将html_element_的初始化改为默认构造，避免提前绑定字符串干扰类型推导：

   rule<tag_parser_id, html_element> html_element_; // 仅声明，不初始化
   

2. 优化规则定义顺序：确保所有依赖子规则声明完成后，再通过BOOST_SPIRIT_DEFINE绑定递归规则的定义。
3. 移除调试输出：暂时删除tag_name_begin_func中的std::cout，减少编译上下文复杂度。

修改后的完整代码 #

#include <boost/spirit/home/x3.hpp>
#include <boost/fusion/include/adapt_struct.hpp>
#include <boost/spirit/home/x3/support/ast/position_tagged.hpp>
#include <boost/spirit/home/x3/support/ast/variant.hpp>
#include <iostream>
using namespace boost::spirit::x3;

struct tag_name{};
struct html_tag;
struct html_comment;

struct attribute_data : boost::spirit::x3::position_tagged {
    std::string name;
    boost::optional<std::string> value;
};

struct tag_header : boost::spirit::x3::position_tagged {
    std::string name;
    std::vector<attribute_data> attributes;
};

struct self_tag : boost::spirit::x3::position_tagged {
    tag_header header;
};

struct html_element : boost::spirit::x3::position_tagged, boost::spirit::x3::variant<std::string, self_tag, boost::recursive_wrapper<html_tag>> {
    using base_type::base_type;
    using base_type::operator=;
};

struct html_tag : boost::spirit::x3::position_tagged {
    tag_header header;
    std::vector<html_element> children;
};

BOOST_FUSION_ADAPT_STRUCT(attribute_data, name, value);
BOOST_FUSION_ADAPT_STRUCT(tag_header, name, attributes);
BOOST_FUSION_ADAPT_STRUCT(self_tag, header);
BOOST_FUSION_ADAPT_STRUCT(html_tag, header, children);

// 属性解析器部分
struct attribute_parser_id;
auto attribute_identifier_ = rule<attribute_parser_id, std::string>{"AttributeIdentifier"} = lexeme[+(char_ - char_(" /=>"))];
auto attribute_value_ = rule<attribute_parser_id, std::string>{"AttributeValue"} =
    lexeme["\"" > +(char_ - char_("\"")) > "\""] | lexeme["'" > +(char_ - char_("'")) > "'"] |
    lexeme[+(char_ - char_(" />"))];
auto single_attribute_ = rule<attribute_parser_id, attribute_data>{"SingleAttribute"} = attribute_identifier_ > -('=' > attribute_value_); // 修正HTML属性赋值符为'='而非"=>"
auto attributes_ = rule<attribute_parser_id, std::vector<attribute_data>>{"Attributes"} = *single_attribute_;

// 标签解析器部分
struct tag_parser_id;

auto tag_name_begin_func = [](auto &ctx) {
    get<tag_name>(ctx) = _attr(ctx).name;
};
auto tag_name_end_func = [](auto &ctx) {
    _pass(ctx) = get<tag_name>(ctx) == _attr(ctx);
};

auto self_tag_name_action = [](auto &ctx) {
    _val(ctx).header.name = _attr(ctx);
};
auto self_tag_attribute_action = [](auto &ctx) {
    _val(ctx).header.attributes = _attr(ctx);
};

auto inner_text = lexeme[+(char_ - '<')];
auto tag_name_ = rule<tag_parser_id, std::string>{"HtmlTagName"} = lexeme[+(char_ - char_(" />"))]; // 修正标签名解析规则，禁止空标签名
auto self_tag_ = rule<tag_parser_id, self_tag>{"HtmlSelfTag"} = '<' > tag_name_[self_tag_name_action] > attributes_[self_tag_attribute_action] > "/>";
auto tag_header_ = rule<tag_parser_id, tag_header>{"HtmlTagBlockHeader"} = '<' > tag_name_ > attributes_ > '>';

// 递归规则仅声明
rule<tag_parser_id, html_tag> tag_block_;
rule<tag_parser_id, html_element> html_element_;

// 定义递归规则
auto tag_block__def = with<tag_name>(std::string())[tag_header_[tag_name_begin_func] > (*html_element_) > "</" > omit[tag_name_[tag_name_end_func]] > '>'];
auto html_element__def = inner_text | self_tag_ | tag_block_;

BOOST_SPIRIT_DEFINE(tag_block_, html_element_)

int main() {
    std::string source = "<div data-src=\"https://www.google.com\" id='hello world'></div>";
    html_element result;
    auto const parser = html_element_;
    auto parse_result = phrase_parse(source.begin(), source.end(), parser, ascii::space, result);
    
    std::cout << (parse_result ? "解析成功" : "解析失败") << std::endl;
    return 0;
}

额外修复说明 #

除解决编译问题外，还修正了两处逻辑错误：

• 将属性赋值运算符从"=>"改为HTML标准的'='
• 标签名解析规则从*(char_ ...)改为+(char_ ...)，禁止空标签名

内容的提问来源于stack exchange，提问作者Hackman Lo