diff --git a/utf8/utf8.h b/utf8/utf8.h new file mode 100755 index 0000000..73fe8d0 --- /dev/null +++ b/utf8/utf8.h @@ -0,0 +1,111 @@ +/* + * This file is a part of EZC -- Easy templating in C++ + * and is distributed under the (new) BSD licence. + * Author: Tomasz Sowa + */ + +/* + * Copyright (c) 2010-2011, Tomasz Sowa + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * * Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * + * * Neither the name Tomasz Sowa nor the names of contributors to this + * project may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF + * THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef headerfile_ezc_utf8 +#define headerfile_ezc_utf8 + +#include +#include + + +namespace Ezc +{ + +/*! + UTF-8, a transformation format of ISO 10646 + http://tools.ietf.org/html/rfc3629 + + when wchar_t is 4 bytes length we use UTF-32 + when wchar_t is 2 bytes length we use UTF-16 (with surrogate pairs) + + UTF-16 + http://www.ietf.org/rfc/rfc2781.txt +*/ + + + +/*! + returns true if 'c' is a correct unicode character +*/ +bool UTF8_CheckRange(int c); + + + +/*! + converting one character from UTF-8 to an int +*/ +size_t UTF8ToInt(const char * utf8, size_t utf8_len, int & res, bool & correct); +size_t UTF8ToInt(const char * utf8, int & res, bool & correct); +size_t UTF8ToInt(const std::string & utf8, int & res, bool & correct); +size_t UTF8ToInt(std::istream & utf8, int & res, bool & correct); + + +/*! + converting UTF-8 string to a wide string +*/ +bool UTF8ToWide(const char * utf8, size_t utf8_len, std::wstring & res, bool clear = true, int mode = 1); +bool UTF8ToWide(const char * utf8, std::wstring & res, bool clear = true, int mode = 1); +bool UTF8ToWide(const std::string & utf8, std::wstring & res, bool clear = true, int mode = 1); +bool UTF8ToWide(std::istream & utf8, std::wstring & res, bool clear = true, int mode = 1); + + +/*! + converting one int character to UTF-8 +*/ +size_t IntToUTF8(int z, char * utf8, size_t utf8_max_len); +size_t IntToUTF8(int z, std::string & utf8, bool clear = true ); +size_t IntToUTF8(int z, std::ostream & utf8); + + +/*! + converting a wide string to UTF-8 string +*/ +bool WideToUTF8(const wchar_t * wide_string, size_t string_len, std::string & utf8, bool clear = true, int mode = 1); +bool WideToUTF8(const wchar_t * wide_string, std::string & utf8, bool clear = true, int mode = 1); +bool WideToUTF8(const std::wstring & wide_string, std::string & utf8, bool clear = true, int mode = 1); +bool WideToUTF8(const wchar_t * wide_string, size_t string_len, std::ostream & utf8, int mode = 1); +bool WideToUTF8(const wchar_t * wide_string, std::ostream & utf8, int mode = 1); +bool WideToUTF8(const std::wstring & wide_string, std::ostream & utf8, int mode = 1); + + + + +} // namespace Ezc + + +#endif +