Support Utf8 characters in the asynchronous connection http header name/value parser grammar

Author: Rudolfs Bundulis

boost/network/protocol/http/server/impl/parsers.ipp

@@ -1,6 +1,7 @@
 #ifndef SERVER_REQUEST_PARSERS_IMPL_UW3PM6V6
 #define SERVER_REQUEST_PARSERS_IMPL_UW3PM6V6
 
+#define BOOST_SPIRIT_UNICODE
 #include <boost/spirit/include/qi.hpp>
 
 // Copyright 2010 Dean Michael Berris. 
@@ -20,6 +21,26 @@
 #endif
 #include <vector>
 
+namespace boost { namespace spirit { namespace traits {
+
+    typedef std::basic_string<uint32_t> u32_string;
+
+    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
+
 namespace boost { namespace network { namespace http {
 
     BOOST_NETWORK_INLINE void parse_version(std::string const & partial_parsed, fusion::tuple<uint8_t,uint8_t> & version_pair) {
@@ -37,12 +58,13 @@ namespace boost { namespace network { namespace http {
 
     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(
-            input.begin(), input.end(),
+            begin, end,
             *(
-                +(alnum|(punct-':'))
+                as<boost::spirit::traits::u32_string>()[+(alnum|(punct-':'))]
                 >> lit(": ")
-                >> +((alnum|space|punct) - '\r' - '\n')
+                >> as<boost::spirit::traits::u32_string>()[+((unicode::alnum|space|punct) - '\r' - '\n')]
                 >> lit("\r\n")
             )
             >> lit("\r\n")

libs/network/test/http/CMakeLists.txt

@@ -62,6 +62,7 @@ if (Boost_FOUND)
     set ( SERVER_API_TESTS
         server_constructor_test
         server_async_run_stop_concurrency
+        server_header_parser_test
         )
     foreach ( test ${SERVER_API_TESTS} )
         add_executable(cpp-netlib-http-${test} ${test}.cpp)

libs/network/test/http/server_header_parser_test.cpp

@@ -0,0 +1,42 @@
+// Copyright 2010 Dean Michael Berris.
+// Distributed under the Boost Software License, Version 1.0.
+// (See accompanying file LICENSE_1_0.txt or copy at
+// http://www.boost.org/LICENSE_1_0.txt)
+
+#define BOOST_TEST_MODULE HTTP Server Header Parser Test
+#include <boost/network/protocol/http/server.hpp>
+#include <boost/config/warning_disable.hpp>
+#include <boost/test/unit_test.hpp>
+#include <string>
+#include <iostream>
+
+/** Synopsis
+*
+*  Test for Utf8 support in the asynchronous connection header parser
+*  --------------------------------------------
+*
+*  This test checks for Utf8 support in the header parser
+*  for asynchronous connection
+*
+*/
+
+namespace tags = boost::network::tags;
+namespace logic = boost::logic;
+namespace fusion = boost::fusion;
+using namespace boost::network::http;
+
+BOOST_AUTO_TEST_CASE(async_connection_parse_headers) {
+    request_header_narrow utf8_header = { "X-Utf8-Test-Header", "R\uc5abdolfs" };
+    std::string valid_http_request;
+    valid_http_request.append(utf8_header.name).append(": ").append(utf8_header.value).append("\r\n\r\n");
+    std::vector<request_header_narrow> headers;
+    parse_headers(valid_http_request, headers);
+    std::vector<request_header_narrow>::iterator utf8_header_iterator = std::find_if(headers.begin(), headers.end(), [&utf8_header, &utf8_header_iterator](request_header_narrow& header)
+    {
+        if (header.name == utf8_header.name && header.value == utf8_header.value)
+            return true;
+        return false;
+    });
+    BOOST_CHECK(utf8_header_iterator != headers.end());
+    std::cout << "utf8 header parsed, name: " << utf8_header_iterator->name << ", value: " << utf8_header_iterator->value << std::endl;
+}