[Boost-commit] svn:boost r60260 - trunk/libs/spirit/example/qi/scheme

Subject: [Boost-commit] svn:boost r60260 - trunk/libs/spirit/example/qi/scheme
From: joel_at_[hidden]
Date: 2010-03-06 20:28:23

Author: djowel
Date: 2010-03-06 20:28:23 EST (Sat, 06 Mar 2010)
New Revision: 60260
URL: http://svn.boost.org/trac/boost/changeset/60260

Log:
s-expressions first shot (with proper unicode handling).
Added:
   trunk/libs/spirit/example/qi/scheme/
   trunk/libs/spirit/example/qi/scheme/sexpr.cpp   (contents, props changed)
   trunk/libs/spirit/example/qi/scheme/sexpr.hpp   (contents, props changed)

Added: trunk/libs/spirit/example/qi/scheme/sexpr.cpp
==============================================================================
--- (empty file)
+++ trunk/libs/spirit/example/qi/scheme/sexpr.cpp	2010-03-06 20:28:23 EST (Sat, 06 Mar 2010)
@@ -0,0 +1,28 @@
+/*=============================================================================
+    Copyright (c) 2001-2010 Joel de Guzman
+
+    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)
+=============================================================================*/
+#include "sexpr.hpp"
+
+int main()
+{
+    using namespace boost::spirit;
+    using namespace boost::spirit::qi;
+ 
+    char const* first = "\"this is a\\n hmmm... \\u20AC string\"";
+    char const* last  = first + std::strlen(first);
+ 
+    scheme::string<char const*> p;
+ 
+    std::string result;
+    if (parse(first, last, p, result))
+        std::cout << "success: '" << result << '\'' << std::endl;
+    else
+        std::cout << "parse error" << std::endl;
+ 
+    return 0;
+}
+
+

Added: trunk/libs/spirit/example/qi/scheme/sexpr.hpp
==============================================================================
--- (empty file)
+++ trunk/libs/spirit/example/qi/scheme/sexpr.hpp	2010-03-06 20:28:23 EST (Sat, 06 Mar 2010)
@@ -0,0 +1,118 @@
+/*=============================================================================
+    Copyright (c) 2001-2010 Joel de Guzman
+
+    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)
+=============================================================================*/
+#if !defined(BOOST_SPIRIT_SEXPR)
+#define BOOST_SPIRIT_SEXPR
+
+#include <string>
+
+#define BOOST_SPIRIT_UNICODE // We'll use unicode (UTF8) all throughout
+
+#include <boost/config/warning_disable.hpp>
+#include <boost/cstdint.hpp>
+#include <boost/spirit/include/qi.hpp>
+#include <boost/spirit/include/phoenix_core.hpp>
+#include <boost/spirit/include/phoenix_container.hpp>
+#include <boost/spirit/include/phoenix_statement.hpp>
+#include <boost/spirit/include/phoenix_operator.hpp>
+#include <boost/regex/pending/unicode_iterator.hpp>
+
+namespace scheme
+{
+    using boost::spirit::qi::grammar;
+    using boost::spirit::qi::rule;
+    using boost::spirit::unicode::char_;
+    using boost::spirit::unicode::space;
+    using boost::spirit::qi::eol;
+    using boost::spirit::qi::_val;
+    using boost::spirit::qi::_r1;
+    using boost::spirit::qi::_1;
+    using boost::spirit::qi::uint_parser;
+    using boost::phoenix::function;
+
+    typedef boost::spirit::char_encoding::unicode unicode;
+    typedef boost::uint32_t uchar; // a unicode code point
+
+    template <typename Iterator>
+    struct white_space : grammar<Iterator, unicode>
+    {
+        white_space() : white_space::base_type(start)
+        {
+            start =
+                    space                           // tab/space/cr/lf
+                |   ';' >> *(char_ - eol) >> eol    // comments
+                ;
+        }
+
+        rule<Iterator, unicode> start;
+    };
+
+    namespace detail
+    {
+        struct push_utf8
+        {
+            template <typename S, typename C>
+            struct result { typedef void type; };
+
+            void operator()(std::string& utf8, uchar code_point) const
+            {
+                typedef std::back_insert_iterator<std::string> insert_iter;
+                insert_iter out_iter(utf8);
+                boost::utf8_output_iterator<insert_iter> utf8_iter(out_iter);
+                *utf8_iter++ = code_point;
+            }
+        };
+
+        struct push_esc
+        {
+            template <typename S, typename C>
+            struct result { typedef void type; };
+
+            void operator()(std::string& utf8, uchar c) const
+            {
+                switch (c)
+                {
+                    case 'b': utf8 += '\b';     break;
+                    case 't': utf8 += '\t';     break;
+                    case 'n': utf8 += '\n';     break;
+                    case 'f': utf8 += '\f';     break;
+                    case 'r': utf8 += '\r';     break;
+                    case '"': utf8 += '"';      break;
+                    case '\\': utf8 += '\\';    break;
+                }
+            }
+        };
+    }
+
+    template <typename Iterator>
+    struct string : grammar<Iterator, unicode, std::string()>
+    {
+        string() : string::base_type(start)
+        {
+            uint_parser<uchar, 16> hex;
+            function<detail::push_utf8> push_utf8;
+            function<detail::push_esc> push_esc;
+
+            str_esc
+                =  '\\'
+                >>  (   ('u' >> hex)                [push_utf8(_r1, _1)]
+                    |   char_("btnfr\\\"'")         [push_esc(_r1, _1)]
+                    )
+                ;
+
+            start
+                = '"'
+                >> *(str_esc(_val) | (char_ - '"')  [push_utf8(_val, _1)])
+                >> '"'
+                ;
+        }
+
+        rule<Iterator, unicode, void(std::string&)> str_esc;
+        rule<Iterator, unicode, std::string()> start;
+    };
+}
+
+#endif