我尝试用出色的 mustache 解析器.html" rel="nofollow">Boost.XPressive 来自杰出的 Eric Niebler.但由于这是我的第一个解析器，我不熟悉编译器编写者的正常"方法和行话，并且在经过几天的反复试验后感到有点迷茫.所以我来到这里，希望有人能告诉我我的愚蠢方式是多么愚蠢；)
I have tried to write a mustache parser with the excellent Boost.XPressive from the brilliant Eric Niebler. But since this is my first parser I am not familiar with the "normal" approach and lingo of compiler writers and feel a bit lost after a few days of trial&error. So I come here and hope someone can tell me the foolishness of my n00bish ways ;)
这是我想提取的带有胡子模板的 HTML 代码 (http://mustache.github.io/):现在<bold>是{{#time}}gugus {{zeit}} oder nicht{{/time}} <i>为所有好人</i>来{007}帮助他们的</bold>{{国家}}.结果:{{#Res1}}零<b>est</b>mundi{{/Res1}}
This is the HTML code with the mustache templates that I want to extract (http://mustache.github.io/):
Now <bold>is the {{#time}}gugus {{zeit}} oder nicht{{/time}} <i>for all good men</i> to come to the {007} aid of their</bold> {{country}}. Result: {{#Res1}}Nullum <b>est</b> mundi{{/Res1}}
smatch what; 变量一样访问它们.该文档仅显示如何使用what"查找第一次出现或如何使用迭代器"输出所有出现.smatch what; variable. The doc only shows how to find the first occurrence with "what" or how to output all the occurrences with the "iterator".
#include <boost/xpressive/xpressive_static.hpp>
#include <boost/xpressive/match_results.hpp>
typedef std::string::const_iterator It;
using namespace boost::xpressive;
std::string str = "Now <bold>is the {{#time}}gugus {{zeit}} oder nicht{{/time}} <i>for all good men</i> to come to the {007} aid of their</bold> {{country}}. Result: {{#Res1}}Nullum <b>est</b> mundi{{/Res1}}";
// Parser setup --------------------------------------------------------
mark_tag mtag (1), cond_mtag (2), user_str (3);
sregex brackets = "{{"
>> keep ( mtag = repeat<1, 20> (_w) )
>> "}}"
;
sregex cond_brackets = "{{#"
>> keep (cond_mtag = repeat<1, 20> (_w) )
>> "}}"
>> * (
keep (user_str = + (*_s >> +alnum >> *_s) ) |
by_ref (brackets) |
by_ref (cond_brackets)
)
>> "{{/"
>> cond_mtag
>> "}}"
;
sregex mexpression = *( by_ref (cond_brackets) | by_ref (brackets) );
// Looping + catching the results --------------------------------------
smatch what2;
std::cout << "
regex_search:
" << str << '
';
It strBegin = str.begin(), strEnd = str.end();
int ic = 0;
do
{
if ( !regex_search ( strBegin, strEnd, what2, mexpression ) )
{
std::cout << " >> Breakout of this life...! Exit after " << ic << " loop(s)." << std::endl;
break;
}
else
{
std::cout << "**Loop Nr: " << ic << '
';
std::cout << " what2[0] " << what2[0] << '
'; // whole match
std::cout << " what2[mtag] " << what2[mtag] << '
';
std::cout << " what2[cond_mtag] " << what2[cond_mtag] << '
';
std::cout << " what2[user_str] " << what2[user_str] << '
';
// display the nested results
std::for_each (
what2.nested_results().begin(),
what2.nested_results().end(),
output_nested_results() // <--identical function from E.Nieblers documentation
);
strBegin = what2[0].second;
}
++ic;
}
while (ic < 6 || strBegin != str.end() );
这是来自@sehe 的正确完整代码，现在可以在 GCC >4.8 和 Linux 和 Windows 下的 CLANG 下工作.再次非常感谢伙伴提供的这个很棒的帮助，尽管这意味着我可以埋葬 XPressive :D
Here is the correct full code from @sehe that now works under GCC >4.8 and CLANG under Linux and Windows. Again many thanks mate for this awesome help, even though this means that I can bury XPressive :D
以下几行已更改或添加:
The following lines have changed or been added:
// --
#define BOOST_RESULT_OF_USE_DECLTYPE
// --
struct to_string_f {
template <typename T>
std::string operator()(T const& v) const { return v.to_string(); }};
// --
section %= "{{" >> sense >> reference [ section_id = to_string(_1) ] >> "}}"
>> sequence // contents
> ("{{" >> ('/' >> lexeme [ lit(section_id) ]) >> "}}");
// --
phx::function<to_string_f> to_string;
//#define BOOST_SPIRIT_DEBUG
#define BOOST_RESULT_OF_USE_DECLTYPE
#define BOOST_SPIRIT_USE_PHOENIX_V3
#include <boost/fusion/adapted/struct.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/include/phoenix.hpp>
#include <boost/utility/string_ref.hpp>
#include <functional>
#include <map>
namespace mustache {
// any atom refers directly to source iterators for efficiency
using boost::string_ref;
template <typename Kind> struct atom {
string_ref value;
atom() { }
atom(string_ref const& value) : value(value) { }
friend std::ostream& operator<<(std::ostream& os, atom const& v) { return os << typeid(v).name() << "[" << v.value << "]"; }
};
// the atoms
using verbatim = atom<struct verbatim_tag>;
using variable = atom<struct variable_tag>;
using partial = atom<struct partial_tag>;
// the template elements (any atom or a section)
struct section;
using melement = boost::variant<
verbatim,
variable,
partial, // TODO comments and set-separators
boost::recursive_wrapper<section>
>;
// the template: sequences of elements
using sequence = std::vector<melement>;
// section: recursively define to contain a template sequence
struct section {
bool sense; // positive or negative
string_ref control;
sequence content;
};
}
BOOST_FUSION_ADAPT_STRUCT(mustache::section, (bool, sense)(boost::string_ref, control)(mustache::sequence, content))
namespace qi = boost::spirit::qi;
namespace phx= boost::phoenix;
struct to_string_f {
template <typename T>
std::string operator()(T const& v) const { return v.to_string(); }
};
template <typename Iterator>
struct mustache_grammar : qi::grammar<Iterator, mustache::sequence()>
{
mustache_grammar() : mustache_grammar::base_type(sequence)
{
using namespace qi;
static const _a_type section_id = {}; // local
using boost::phoenix::construct;
using boost::phoenix::begin;
using boost::phoenix::size;
sequence = *element;
element =
!(lit("{{") >> '/') >> // section-end ends the current sequence
(partial | section | variable | verbatim);
reference = raw [ lexeme [ +(graph - "}}") ] ]
[ _val = construct<boost::string_ref>(&*begin(_1), size(_1)) ];
partial = qi::lit("{{") >> "> " >> reference >> "}}";
sense = ('#' > attr(true))
| ('^' > attr(false));
section %= "{{" >> sense >> reference [ section_id = to_string(_1) ] >> "}}"
>> sequence // contents
> ("{{" >> ('/' >> lexeme [ lit(section_id) ]) >> "}}");
variable = "{{" >> reference >> "}}";
verbatim = raw [ lexeme [ +(char_ - "{{") ] ]
[ _val = construct<boost::string_ref>(&*begin(_1), size(_1)) ];
BOOST_SPIRIT_DEBUG_NODES(
(sequence)(element)(partial)(variable)(section)(verbatim)
(reference)(sense)
)
}
private:
phx::function<to_string_f> to_string;
qi::rule<Iterator, mustache::sequence()> sequence;
qi::rule<Iterator, mustache::melement()> element;
qi::rule<Iterator, mustache::partial()> partial;
qi::rule<Iterator, mustache::section(), qi::locals<std::string> > section;
qi::rule<Iterator, bool()> sense; // postive or negative
qi::rule<Iterator, mustache::variable()> variable;
qi::rule<Iterator, mustache::verbatim()> verbatim;
qi::rule<Iterator, boost::string_ref()> reference;
};
namespace Dumping {
struct dumper : boost::static_visitor<std::ostream&>
{
std::ostream& operator()(std::ostream& os, mustache::sequence const& v) const {
for(auto& element : v)
boost::apply_visitor(std::bind(dumper(), std::ref(os), std::placeholders::_1), element);
return os;
}
std::ostream& operator()(std::ostream& os, mustache::verbatim const& v) const {
return os << v.value;
}
std::ostream& operator()(std::ostream& os, mustache::variable const& v) const {
return os << "{{" << v.value << "}}";
}
std::ostream& operator()(std::ostream& os, mustache::partial const& v) const {
return os << "{{> " << v.value << "}}";
}
std::ostream& operator()(std::ostream& os, mustache::section const& v) const {
os << "{{" << (v.sense?'#':'^') << v.control << "}}";
(*this)(os, v.content);
return os << "{{/" << v.control << "}}";
}
};
}
namespace ContextExpander {
struct Nil { };
using Value = boost::make_recursive_variant<
Nil,
double,
std::string,
std::map<std::string, boost::recursive_variant_>,
std::vector<boost::recursive_variant_>
>::type;
using Dict = std::map<std::string, Value>;
using Array = std::vector<Value>;
static inline std::ostream& operator<<(std::ostream& os, Nil const&) { return os << "#NIL#"; }
static inline std::ostream& operator<<(std::ostream& os, Dict const& v) { return os << "#DICT(" << v.size() << ")#"; }
static inline std::ostream& operator<<(std::ostream& os, Array const& v) { return os << "#ARRAY(" << v.size() << ")#"; }
struct expander : boost::static_visitor<std::ostream&>
{
std::ostream& operator()(std::ostream& os, Value const& ctx, mustache::sequence const& v) const {
for(auto& element : v)
boost::apply_visitor(std::bind(expander(), std::ref(os), std::placeholders::_1, std::placeholders::_2), ctx, element);
return os;
}
template <typename Ctx>
std::ostream& operator()(std::ostream& os, Ctx const&/*ignored*/, mustache::verbatim const& v) const {
return os << v.value;
}
std::ostream& operator()(std::ostream& os, Dict const& ctx, mustache::variable const& v) const {
auto it = ctx.find(v.value.to_string());
if (it != ctx.end())
os << it->second;
return os;
}
template <typename Ctx>
std::ostream& operator()(std::ostream& os, Ctx const&, mustache::variable const&) const {
return os;
}
std::ostream& operator()(std::ostream& os, Dict const& ctx, mustache::partial const& v) const {
auto it = ctx.find(v.value.to_string());
if (it != ctx.end())
{
static const mustache_grammar<std::string::const_iterator> p;
auto const& subtemplate = boost::get<std::string>(it->second);
std::string::const_iterator first = subtemplate.begin(), last = subtemplate.end();
mustache::sequence dynamic_template;
if (qi::parse(first, last, p, dynamic_template))
return (*this)(os, Value{ctx}, dynamic_template);
}
return os << "#ERROR#";
}
std::ostream& operator()(std::ostream& os, Dict const& ctx, mustache::section const& v) const {
auto it = ctx.find(v.control.to_string());
if (it != ctx.end())
boost::apply_visitor(std::bind(do_section(), std::ref(os), std::placeholders::_1, std::cref(v)), it->second);
else if (!v.sense)
(*this)(os, Value{/*Nil*