Line data    Source code

       1             : // Copyright (c) 2000-2022  Made to Order Software Corp.  All Rights Reserved
       2             : //
       3             : // https://snapwebsites.org/project/libutf8
       4             : // contact@m2osw.com
       5             : //
       6             : // This program is free software; you can redistribute it and/or modify
       7             : // it under the terms of the GNU General Public License as published by
       8             : // the Free Software Foundation; either version 2 of the License, or
       9             : // (at your option) any later version.
      10             : //
      11             : // This program is distributed in the hope that it will be useful,
      12             : // but WITHOUT ANY WARRANTY; without even the implied warranty of
      13             : // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
      14             : // GNU General Public License for more details.
      15             : //
      16             : // You should have received a copy of the GNU General Public License along
      17             : // with this program; if not, write to the Free Software Foundation, Inc.,
      18             : // 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA.
      19             : #pragma once
      20             : 
      21             : /** \file
      22             :  * \brief The declarations of the UTF-8 library.
      23             :  *
      24             :  * This file is the declarations of the UTF-8 library which are just a few
      25             :  * functions used to convert a string from one format to another.
      26             :  */
      27             : 
      28             : // C++
      29             : //
      30             : #include    <string>
      31             : 
      32             : 
      33             : 
      34             : namespace libutf8
      35             : {
      36             : 
      37             : 
      38             : enum class bom_t
      39             : {
      40             :     BOM_NONE,
      41             :     BOM_UTF8,
      42             :     BOM_UTF16_LE,
      43             :     BOM_UTF16_BE,
      44             :     BOM_UTF32_LE,
      45             :     BOM_UTF32_BE
      46             : };
      47             : 
      48             : 
      49             : enum class surrogate_t
      50             : {
      51             :     SURROGATE_NO,
      52             :     SURROGATE_HIGH,
      53             :     SURROGATE_LOW
      54             : };
      55             : 
      56             : 
      57             : constexpr char32_t const    BOM_CHAR = U'\U0000FEFF';
      58             : constexpr char32_t const    NOT_A_CHARACTER = static_cast<char32_t>(-1);
      59             : 
      60             : 
      61             : bool                is_valid_ascii(char c, bool ctrl = true);
      62             : bool                is_valid_ascii(char const * str, bool ctrl = true);
      63             : bool                is_valid_ascii(std::string const & str, bool ctrl = true);
      64             : bool                is_valid_utf8(char const * str);
      65             : bool                is_valid_utf8(std::string const & str);
      66             : bool                is_valid_unicode(char32_t const wc, bool ctrl = true);
      67             : bool                is_valid_unicode(char32_t const * str, bool ctrl = true);
      68             : bool                is_valid_unicode(std::u32string const & str, bool ctrl = true);
      69             : surrogate_t         is_surrogate(char32_t wc);
      70             : bom_t               start_with_bom(char const * str, size_t len);
      71             : std::string         to_u8string(std::u32string const & str);
      72             : std::string         to_u8string(std::u16string const & str);
      73             : std::string         to_u8string(std::wstring const & str);
      74             : std::string         to_u8string(wchar_t one, wchar_t two = L'\0');
      75             : std::string         to_u8string(char16_t one, char16_t two = u'\0');
      76             : std::string         to_u8string(char32_t wc);
      77             : std::u16string      to_u16string(std::string const & str);
      78             : std::u32string      to_u32string(std::string const & str);
      79             : size_t              u8length(std::string const & str);
      80             : int                 u8casecmp(std::string const & lhs, std::string const & rhs);
      81             : 
      82             : 
      83             : 
      84             : } // libutf8 namespace
      85             : 
      86             : 
      87             : template<typename CharT, typename Traits>
      88           0 : std::basic_ostream<CharT, Traits> & operator << (std::basic_ostream<CharT, Traits> & out, char32_t const & c)
      89             : {
      90           0 :     return out << libutf8::to_u8string(c);
      91             : }
      92             : 
      93             : 
      94             : // vim: ts=4 sw=4 et