396 lines
8.5 KiB
C++
396 lines
8.5 KiB
C++
/*
|
|
* 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_templates
|
|
#define headerfile_picotools_utf8_utf8_templates
|
|
|
|
// this file is included at the end of utf8.h
|
|
|
|
#include "utf8_private.h"
|
|
|
|
|
|
namespace pt
|
|
{
|
|
|
|
|
|
template<typename StreamType>
|
|
void int_to_wide(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);
|
|
}
|
|
}
|
|
|
|
|
|
|
|
/*!
|
|
converting UTF-8 string to a TextStreamBase<wchar_t,...> stream
|
|
(need to be tested)
|
|
*/
|
|
// need to be tested
|
|
template<typename StreamType>
|
|
bool utf8_to_wide(const char * utf8, size_t utf8_len, StreamType & res, bool clear, int mode)
|
|
{
|
|
if( clear )
|
|
res.clear();
|
|
|
|
bool status = private_namespace::utf8_to_wide_generic(utf8, utf8_len, mode, [&res](int c) {
|
|
int_to_wide(c, res);
|
|
});
|
|
|
|
return status;
|
|
}
|
|
|
|
|
|
|
|
|
|
template<typename StreamType>
|
|
bool utf8_to_wide(const char * utf8, StreamType & res, bool clear, int mode)
|
|
{
|
|
size_t utf8_len = 0;
|
|
|
|
while( utf8[utf8_len] != 0 )
|
|
utf8_len += 1;
|
|
|
|
return utf8_to_wide(utf8, utf8_len, res, clear, mode);
|
|
}
|
|
|
|
|
|
|
|
template<typename StreamType>
|
|
bool utf8_to_wide(const std::string & utf8, StreamType & res, bool clear, int mode)
|
|
{
|
|
return utf8_to_wide(utf8.c_str(), utf8.size(), res, clear, mode);
|
|
}
|
|
|
|
|
|
|
|
// need to be tested
|
|
template<typename StreamType>
|
|
bool utf8_to_wide(std::istream & utf8, StreamType & res, bool clear, int mode)
|
|
{
|
|
int z;
|
|
bool correct, was_error = false;
|
|
|
|
if( clear )
|
|
res.clear();
|
|
|
|
while( utf8_to_int(utf8, z, correct) > 0 )
|
|
{
|
|
if( !correct )
|
|
{
|
|
if( mode == 1 )
|
|
res << 0xFFFD; // U+FFFD "replacement character"
|
|
|
|
was_error = true;
|
|
}
|
|
else
|
|
{
|
|
int_to_wide(z, res);
|
|
}
|
|
}
|
|
|
|
return !was_error;
|
|
}
|
|
|
|
|
|
/*
|
|
this function converts a UTF-8 stream into wide stream
|
|
|
|
input:
|
|
stream - a UTF-8 stream for converting
|
|
mode - what to do with errors when converting
|
|
0: skip an invalid character
|
|
1: put U+FFFD "replacement character" istead of the invalid character (default)
|
|
|
|
output:
|
|
res - a wide stream for the output sequence
|
|
|
|
this function returns false if there were some errors when converting
|
|
*/
|
|
template<typename StreamType>
|
|
bool utf8_to_wide(const Stream & stream, StreamType & res, bool clear, int mode)
|
|
{
|
|
size_t len;
|
|
bool correct;
|
|
int z;
|
|
size_t index = 0;
|
|
bool was_error = false;
|
|
|
|
if( clear )
|
|
res.clear();
|
|
|
|
// CHECKME test me when sizeof(wchar_t) is 2
|
|
|
|
do
|
|
{
|
|
len = utf8_to_int(stream, index, z, correct);
|
|
|
|
if( len > 0 )
|
|
{
|
|
if( !correct )
|
|
{
|
|
if( mode == 1 )
|
|
res << 0xFFFD; // U+FFFD "replacement character"
|
|
|
|
was_error = true;
|
|
}
|
|
else
|
|
{
|
|
int_to_wide(z, res);
|
|
}
|
|
|
|
index += len;
|
|
}
|
|
}
|
|
while( len > 0 );
|
|
|
|
return !was_error;
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*!
|
|
this function converts one wide character into UTF-8 stream
|
|
|
|
input:
|
|
z - wide character
|
|
|
|
output:
|
|
utf8 - a UTF-8 stream for the output sequence
|
|
|
|
the function returns how many characters have been written to the utf8 stream,
|
|
zero means that 'z' is an incorrect unicode character
|
|
*/
|
|
template<typename StreamType>
|
|
size_t int_to_utf8(int z, StreamType & utf8)
|
|
{
|
|
char buf[10];
|
|
|
|
size_t len = int_to_utf8(z, buf, sizeof(buf)/sizeof(char));
|
|
|
|
if( len > 0 )
|
|
utf8.write(buf, len);
|
|
|
|
return len;
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*!
|
|
this function converts a wide string into UTF-8 stream
|
|
|
|
input:
|
|
wide_string - a wide string for converting
|
|
string_len - size of the string
|
|
mode - what to do with errors when converting
|
|
0: skip an invalid character
|
|
1: put U+FFFD "replacement character" istead of the invalid character (default)
|
|
|
|
output:
|
|
utf8 - a UTF-8 stream for the output sequence
|
|
|
|
this function returns false if there were some errors when converting
|
|
*/
|
|
template<typename StreamType>
|
|
bool wide_to_utf8(const wchar_t * wide_string, size_t string_len, StreamType & utf8, int mode)
|
|
{
|
|
bool was_error = false;
|
|
size_t chars;
|
|
|
|
while( string_len > 0 )
|
|
{
|
|
chars = private_namespace::wide_one_to_utf8(wide_string, string_len, utf8, was_error, mode);
|
|
wide_string += chars;
|
|
string_len -= chars;
|
|
}
|
|
|
|
return !was_error;
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*!
|
|
this function converts a wide string into UTF-8 stream
|
|
|
|
input:
|
|
wide_string - a null terminated wide string for converting
|
|
mode - what to do with errors when converting
|
|
0: skip an invalid character
|
|
1: put U+FFFD "replacement character" istead of the invalid character (default)
|
|
|
|
output:
|
|
utf8 - a UTF-8 stream for the output sequence
|
|
|
|
this function returns false if there were some errors when converting
|
|
*/
|
|
template<typename StreamType>
|
|
bool wide_to_utf8(const wchar_t * wide_string, StreamType & utf8, int mode)
|
|
{
|
|
bool was_error = false;
|
|
|
|
while( *wide_string )
|
|
wide_string += private_namespace::wide_one_to_utf8(wide_string, utf8, was_error, mode);
|
|
|
|
return !was_error;
|
|
}
|
|
|
|
|
|
|
|
/*!
|
|
this function converts a wide string (std::wstring) into UTF-8 stream
|
|
|
|
input:
|
|
wide_string - a wide string for converting
|
|
mode - what to do with errors when converting
|
|
0: skip an invalid character
|
|
1: put U+FFFD "replacement character" istead of the invalid character (default)
|
|
|
|
output:
|
|
utf8 - a UTF-8 stream for the output sequence
|
|
|
|
this function returns false if there were some errors when converting
|
|
*/
|
|
template<typename StreamType>
|
|
bool wide_to_utf8(const std::wstring & wide_string, StreamType & utf8, int mode)
|
|
{
|
|
return wide_to_utf8(wide_string.c_str(), wide_string.size(), utf8, mode);
|
|
}
|
|
|
|
|
|
|
|
|
|
template<typename StreamType>
|
|
void wide_stream_to_utf8(StreamType & buffer, std::string & utf8, bool clear, int mode)
|
|
{
|
|
if( clear )
|
|
utf8.clear();
|
|
|
|
private_namespace::wide_to_utf8_generic(buffer, mode, [&utf8](const char * utf8_buffer, std::size_t buffer_len){
|
|
utf8.append(utf8_buffer, buffer_len);
|
|
});
|
|
}
|
|
|
|
|
|
|
|
template<typename StreamType>
|
|
bool wide_stream_to_utf8(const Stream & stream, StreamType & utf8, bool clear, int mode)
|
|
{
|
|
bool was_error = false;
|
|
|
|
if( clear )
|
|
utf8.clear();
|
|
|
|
for(size_t i=0 ; i < stream.size() ; ++i)
|
|
{
|
|
int c = static_cast<int>(stream.get_wchar(i));
|
|
bool is_correct = false;
|
|
|
|
if( utf8_check_range(c) )
|
|
{
|
|
// CHECKME test me when sizeof(wchar_t) == 2
|
|
if( is_first_surrogate_char(c) )
|
|
{
|
|
if( i + 1 < stream.size() )
|
|
{
|
|
wchar_t c1 = static_cast<wchar_t>(c);
|
|
wchar_t c2 = stream.get_wchar(++i);
|
|
|
|
if( surrogate_pair_to_int(c1, c2, c) )
|
|
{
|
|
is_correct = true;
|
|
}
|
|
}
|
|
}
|
|
else
|
|
{
|
|
is_correct = true;
|
|
}
|
|
}
|
|
|
|
if( is_correct )
|
|
{
|
|
int_to_utf8(c, utf8);
|
|
}
|
|
else
|
|
{
|
|
was_error = true;
|
|
|
|
if( mode == 1 )
|
|
int_to_utf8(0xFFFD, utf8); // U+FFFD "replacement character"
|
|
}
|
|
}
|
|
|
|
return !was_error;
|
|
}
|
|
|
|
|
|
// not tested
|
|
template<typename StreamTypeIn, typename StreamTypeOut>
|
|
void wide_stream_to_utf8(StreamTypeIn & buffer, StreamTypeOut & utf8, int mode)
|
|
{
|
|
private_namespace::wide_to_utf8_generic(buffer, mode, [&utf8](const char * utf8_buffer, std::size_t buffer_len){
|
|
utf8.write(utf8_buffer, buffer_len);
|
|
});
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
} // namespace pt
|
|
|
|
#endif
|
|
|
|
|
|
|