问题
I have a similar issue like How to use boost::spirit to parse UTF-8? and How to match unicode characters with boost::spirit? but none of these solve the issue i'm facing. I have a std::string with UTF-8 characters, i used the u8_to_u32_iterator to wrap the std::string and used unicode terminals like this:
BOOST_NETWORK_INLINE void parse_headers(std::string const & input, std::vector<request_header_narrow> & container) {
using namespace boost::spirit::qi;
u8_to_u32_iterator<std::string::const_iterator> begin(input.begin()), end(input.end());
std::vector<request_header_narrow_utf8_wrapper> wrapper_container;
parse(
begin, end,
*(
+(alnum|(punct-':'))
>> lit(": ")
>> +((unicode::alnum|space|punct) - '\r' - '\n')
>> lit("\r\n")
)
>> lit("\r\n")
, wrapper_container
);
BOOST_FOREACH(request_header_narrow_utf8_wrapper header_wrapper, wrapper_container)
{
request_header_narrow header;
u32_to_u8_iterator<request_header_narrow_utf8_wrapper::string_type::iterator> name_begin(header_wrapper.name.begin()),
name_end(header_wrapper.name.end()),
value_begin(header_wrapper.value.begin()),
value_end(header_wrapper.value.end());
for(; name_begin != name_end; ++name_begin)
header.name += *name_begin;
for(; value_begin != value_end; ++value_begin)
header.value += *value_begin;
container.push_back(header);
}
}
The request_header_narrow_utf8_wrapper is defined and mapped to Fusion like this (don't mind the missing namespace declarations):
struct request_header_narrow_utf8_wrapper
{
typedef std::basic_string<boost::uint32_t> string_type;
std::basic_string<boost::uint32_t> name, value;
};
BOOST_FUSION_ADAPT_STRUCT(
boost::network::http::request_header_narrow_utf8_wrapper,
(std::basic_string<boost::uint32_t>, name)
(std::basic_string<boost::uint32_t>, value)
)
This works fine, but i was wondering can i somehow manage to make the parser assing directly to a struct containing std::string members instead of doing the for-each loop with the u32_to_u8_iterator ? I was thinking that one way could be making a wrapper for std::string that would have an assignment operator with boost::uint32_t so that parser could assign directly, but are there other solutions?
EDIT
After reading some more i ended up with this:
namespace boost { namespace spirit { namespace traits {
typedef std::basic_string<uint32_t> u32_string;
/* template <>
struct is_string<u32_string> : mpl::true_ {};*/
template <> // <typename Attrib, typename T, typename Enable>
struct assign_to_container_from_value<std::string, u32_string, void>
{
static void call(u32_string const& val, std::string& attr) {
u32_to_u8_iterator<u32_string::const_iterator> begin(val.begin()), end(val.end());
for(; begin != end; ++begin)
attr += *begin;
}
};
} // namespace traits
} // namespace spirit
} // namespace boost
and this
BOOST_NETWORK_INLINE void parse_headers(std::string const & input, std::vector<request_header_narrow> & container) {
using namespace boost::spirit::qi;
u8_to_u32_iterator<std::string::const_iterator> begin(input.begin()), end(input.end());
parse(
begin, end,
*(
as<boost::spirit::traits::u32_string>()[+(alnum|(punct-':'))]
>> lit(": ")
>> as<boost::spirit::traits::u32_string>()[+((unicode::alnum|space|punct) - '\r' - '\n')]
>> lit("\r\n")
)
>> lit("\r\n")
, container
);
}
Any comments or advice if this is the best i can get?
回答1:
Another job for a attribute trait. I've simplified your datatypes for demonstration purposes:
typedef std::basic_string<uint32_t> u32_string;
struct Value
{
std::string value;
};
Now you can have the conversion happen "auto-magically" using:
namespace boost { namespace spirit { namespace traits {
template <> // <typename Attrib, typename T, typename Enable>
struct assign_to_attribute_from_value<Value, u32_string, void>
{
typedef u32_to_u8_iterator<u32_string::const_iterator> Conv;
static void call(u32_string const& val, Value& attr) {
attr.value.assign(Conv(val.begin()), Conv(val.end()));
}
};
}}}
Consider a sample parser that parses JSON-style strings in UTF-8, while also allowing Unicode escape sequences of 32-bit codepoints: \uXXXX. It is convenient to have the intermediate storage be a u32_string for this purpose:
///////////////////////////////////////////////////////////////
// Parser
///////////////////////////////////////////////////////////////
namespace qi = boost::spirit::qi;
namespace encoding = qi::standard_wide;
//namespace encoding = qi::unicode;
template <typename It, typename Skipper = encoding::space_type>
struct parser : qi::grammar<It, Value(), Skipper>
{
parser() : parser::base_type(start)
{
string = qi::lexeme [ L'"' >> *char_ >> L'"' ];
static qi::uint_parser<uint32_t, 16, 4, 4> _4HEXDIG;
char_ = +(
~encoding::char_(L"\"\\")) [ qi::_val += qi::_1 ] |
qi::lit(L"\x5C") >> ( // \ (reverse solidus)
qi::lit(L"\x22") [ qi::_val += L'"' ] | // " quotation mark U+0022
qi::lit(L"\x5C") [ qi::_val += L'\\' ] | // \ reverse solidus U+005C
qi::lit(L"\x2F") [ qi::_val += L'/' ] | // / solidus U+002F
qi::lit(L"\x62") [ qi::_val += L'\b' ] | // b backspace U+0008
qi::lit(L"\x66") [ qi::_val += L'\f' ] | // f form feed U+000C
qi::lit(L"\x6E") [ qi::_val += L'\n' ] | // n line feed U+000A
qi::lit(L"\x72") [ qi::_val += L'\r' ] | // r carriage return U+000D
qi::lit(L"\x74") [ qi::_val += L'\t' ] | // t tab U+0009
qi::lit(L"\x75") // uXXXX U+XXXX
>> _4HEXDIG [ qi::_val += qi::_1 ]
);
// entry point
start = string;
}
private:
qi::rule<It, Value(), Skipper> start;
qi::rule<It, u32_string()> string;
qi::rule<It, u32_string()> char_;
};
As you can see, the start rule simply assigns the attribute value to the Value struct - which implicitely invokes our assign_to_attribute_from_value trait!
A simple test program Live on Coliru to prove that it does work:
// input assumed to be utf8
Value parse(std::string const& input) {
auto first(begin(input)), last(end(input));
typedef boost::u8_to_u32_iterator<decltype(first)> Conv2Utf32;
Conv2Utf32 f(first), saved = f, l(last);
static const parser<Conv2Utf32, encoding::space_type> p;
Value parsed;
if (!qi::phrase_parse(f, l, p, encoding::space, parsed))
{
std::cerr << "whoops at position #" << std::distance(saved, f) << "\n";
}
return parsed;
}
#include <iostream>
int main()
{
Value parsed = parse("\"Footnote: ¹ serious busineş\\u1e61\n\"");
std::cout << parsed.value;
}
Now observe that the output is encoded in UTF8 again:
$ ./test | tee >(file -) >(xxd)
Footnote: ¹ serious busineşṡ
/dev/stdin: UTF-8 Unicode text
0000000: 466f 6f74 6e6f 7465 3a20 c2b9 2073 6572 Footnote: .. ser
0000010: 696f 7573 2062 7573 696e 65c5 9fe1 b9a1 ious busine.....
0000020: 0a
The U+1E61 code-point has been correctly encoded as [0xE1,0xB9,0xA1].
来源：https://stackoverflow.com/questions/19273882/handling-utf-8-in-boost-spirit-with-utf-32-parser