pikotools/src/utf8/utf8_private.h

/*
 * This file is a part of PikoTools
 * and is distributed under the (new) BSD licence.
 * Author: Tomasz Sowa <t.sowa@ttmath.org>
 */

/*
 * Copyright (c) 2021, 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_picotools_utf8_utf8_private
#define headerfile_picotools_utf8_utf8_private

#include "textstream/textstream.h"


namespace pt
{

bool UTF8_CheckRange(int c);
size_t IntToUTF8(int z, char * utf8, size_t utf8_max_len);
size_t IntToUTF8(int z, std::string & utf8, bool clear);
size_t UTF8ToInt(const char * utf8, size_t utf8_len, int & res, bool & correct);


namespace private_namespace
{
bool UTF8ToInt_FirstOctet(unsigned char uz, size_t & len, int & res);
bool UTF8ToInt_AddNextOctet(unsigned char uz, int & res);

size_t WideToInt(const wchar_t * wide_string, size_t string_len, int & z, bool & correct);
size_t WideToInt(const wchar_t * wide_string, int & z, bool & correct);

size_t WideOneToUTF8(const wchar_t * wide_string, size_t string_len, char * utf8, size_t utf8_len,
							size_t & utf8_written, bool & was_utf8_buf_too_small, bool & was_error, int mode);

size_t WideOneToUTF8(const wchar_t * wide_string, size_t string_len, std::string & utf8, bool & was_error, int mode);

size_t WideOneToUTF8(const wchar_t * wide_string, std::string & utf8, bool & was_error, int mode);


/*!
	an auxiliary function for converting from wide characters to UTF-8

	returns how many wide characters were used
	if string_len is greater than 0 then the return value is always greater than zero too
*/
template<typename StreamType>
static size_t WideOneToUTF8(const wchar_t * wide_string, size_t string_len, StreamType & utf8, bool & was_error, int mode)
{
int z;
bool correct;
size_t chars;

	chars = WideToInt(wide_string, string_len, z, correct);

	if( correct )
		correct = IntToUTF8(z, utf8) != 0;

	if( !correct )
	{
		if( mode == 1 )
			IntToUTF8(0xFFFD, utf8); // U+FFFD "replacement character"

		was_error = true;
	}

return chars;
}


/*!
	an auxiliary function for converting from wide characters to UTF-8
*/
template<typename StreamType>
static size_t WideOneToUTF8(const wchar_t * wide_string, StreamType & utf8, bool & was_error, int mode)
{
	size_t min_str_len = 1;

	if( *wide_string == 0 )
		return 0;

	if( *(wide_string+1) != 0 )
		min_str_len = 2;

return WideOneToUTF8(wide_string, min_str_len, utf8, was_error, mode);
}



// declared in utf8.h, defined in utf8.cpp
size_t UTF8ToInt(const char * utf8, size_t utf8_len, int & res, bool & correct);



template<typename function_type>
bool UTF8ToWideGeneric(const char * utf8, size_t utf8_len, int mode, function_type convert_function)
{
int z;
size_t len;
bool correct, was_error = false;

	while( utf8_len > 0 )
	{
		if( (unsigned char)*utf8 <= 0x7f )
		{
			// small optimization
			len = 1;
			correct = true;
			z = static_cast<unsigned char>(*utf8);
		}
		else
		{
			len = pt::UTF8ToInt(utf8, utf8_len, z, correct); // the len will be different from zero
		}

		if( !correct )
		{
			if( mode == 1 )
				convert_function(0xFFFD); // U+FFFD "replacement character"

			was_error = true;
		}
		else
		{
			convert_function(z);
		}

		utf8     += len;
		utf8_len -= len;
	}

return !was_error;
}



template<typename StreamType>
void IntToWide(int c, StreamType & res)
{
	if( sizeof(wchar_t)==2 && c>0xffff )
	{
		// UTF16 surrogate pairs
		c -= 0x10000;
		res << static_cast<wchar_t>(((c >> 10) & 0x3FF) + 0xD800);
		res << static_cast<wchar_t>((c & 0x3FF) + 0xDC00);
	}
	else
	{
		res << static_cast<wchar_t>(c);
	}
}


// not tested
// FIX ME it is not using surrogate pairs from input stream
// and mode parameter
template<typename char_type, size_t stack_size, size_t heap_block_size, typename function_type>
void WideToUTF8Generic(TextStreamBase<char_type, stack_size, heap_block_size> & buffer, int mode, function_type write_function)
{
	char utf8_buffer[256];
	std::size_t buffer_len = sizeof(utf8_buffer) / sizeof(char);
	std::size_t utf8_sequence_max_length = 10;
	std::size_t index = 0;

	typename TextStreamBase<char_type, stack_size, heap_block_size>::const_iterator i = buffer.begin();

	while( i != buffer.end() )
	{
		if( index + utf8_sequence_max_length > buffer_len )
		{
			write_function(utf8_buffer, index);
			index = 0;
		}

		index += IntToUTF8(*i, utf8_buffer + index, buffer_len - index);
		++i;
	}

	if( index > 0 )
	{
		write_function(utf8_buffer, index);
	}
}




} // namespace private_namespace

} // namespace pt

#endif