#pragma once // Copyright Digital Mars 2003 - 2009. // Authors: Walter Bright, Sean Kelly // Boost Software License - Version 1.0 - August 17th, 2003 // 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. #include #include /******************************* * Test if c is a valid UTF-32 character. * * \uFFFE and \uFFFF are considered valid by this function, * as they are permitted for internal use by an application, * but they are not allowed for interchange by the Unicode standard. * * Returns: true if it is, false if not. */ inline bool isValidChar32(char32_t c) BOOST_NOEXCEPT { /* Note: FFFE and FFFF are specifically permitted by the * Unicode standard for application internal use, but are not * allowed for interchange. * (thanks to Arcane Jill) */ return c < 0xD800 || (c > 0xDFFF && c <= 0x10FFFF /*&& c != 0xFFFE && c != 0xFFFF*/); } /*************** * Decodes and returns character starting at s[idx]. idx is advanced past the * decoded character. If the character is not well formed, an exception is * thrown and idx remains unchanged. */ char32_t decodeUtf8(const char* s, size_t len, size_t& idx);