// unicode.hh // This file is part of libpbe; see http://anyterm.org/ // (C) 2008 Philip Endecott // Distributed under the Boost Software License, Version 1.0: // // Permission is hereby granted, free of charge, to any person or organization // obtaining a copy of the software and accompanying documentation covered by // this license (the "Software") to use, reproduce, display, distribute, // execute, and transmit the Software, and to prepare derivative works of the // Software, and to permit third-parties to whom the Software is furnished to // do so, all subject to the following: // // The copyright notices in the Software and this entire statement, including // the above license grant, this restriction and the following disclaimer, // must be included in all copies of the Software, in whole or in part, and // all derivative works of the Software, unless such copies or derivative // works are solely in the form of machine-executable object code generated by // a source language processor. // // THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR // IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, // FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT // SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE // FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, // ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER // DEALINGS IN THE SOFTWARE. #ifndef libpbe_charset_conv_unicode_hh #define libpbe_charset_conv_unicode_hh #include "charset/charset_t.hh" #include "charset/char_conv.hh" #include "charset/char_t.hh" namespace pbe { // Unicode character conversion // ---------------------------- // // This file provides specialisation of char_conv for the Unicode // character types. // Note that UTF-8 and UTF-16 characters are 32-bit characters here, // not groups of units. // Everything is trivial except conversion to ucs2. // UTF16 has not been implemented yet. IDENTITY_CHAR_CONV(cs::ucs2,cs::ucs4) IDENTITY_CHAR_CONV(cs::ucs2,cs::utf8) //IDENTITY_CHAR_CONV(cs::ucs2,cs::utf16) IDENTITY_CHAR_CONV(cs::ucs4,cs::utf8) //IDENTITY_CHAR_CONV(cs::ucs4,cs::utf16) IDENTITY_CHAR_CONV(cs::utf8,cs::ucs4) //IDENTITY_CHAR_CONV(cs::utf8,cs::utf16) //IDENTITY_CHAR_CONV(cs::utf16,cs::ucs4) //IDENTITY_CHAR_CONV(cs::utf16,cs::utf8) #define CONV_TO_UCS2(FROM_CS) \ template \ struct char_conv { \ char16_t \ operator() ( charset_traits::char_t c, \ charset_traits::state_t&, \ charset_traits::state_t& ) { \ if (c>0xffff) { \ return error_policy::no_equivalent(); \ } \ return c; \ } \ }; CONV_TO_UCS2(cs::ucs4) CONV_TO_UCS2(cs::utf8) //CONV_TO_UCS2(cs::utf16) #undef CONV_TO_UCS2 }; #endif