648 lines
14 KiB
C++
648 lines
14 KiB
C++
/*
|
|
* This file is a part of PikoTools
|
|
* and is distributed under the 2-Clause BSD licence.
|
|
* Author: Tomasz Sowa <t.sowa@ttmath.org>
|
|
*/
|
|
|
|
/*
|
|
* Copyright (c) 2021-2023, 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:
|
|
*
|
|
* 1. Redistributions of source code must retain the above copyright notice,
|
|
* this list of conditions and the following disclaimer.
|
|
*
|
|
* 2. 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.
|
|
*
|
|
* 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 HOLDER 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_pikotools_src_utf8_utf8_templates
|
|
#define headerfile_pikotools_src_utf8_utf8_templates
|
|
|
|
// this file is included at the end of utf8.h
|
|
|
|
#include "utf8_private.h"
|
|
|
|
|
|
namespace pt
|
|
{
|
|
|
|
|
|
|
|
template<typename StreamType>
|
|
bool int_to_wide(int c, StreamType & res)
|
|
{
|
|
wchar_t buf[2];
|
|
size_t used = int_to_wide(c, buf, sizeof(buf) / sizeof(wchar_t));
|
|
|
|
if( used == 1 )
|
|
{
|
|
res << buf[0];
|
|
}
|
|
else
|
|
if( used == 2 )
|
|
{
|
|
res << buf[0];
|
|
res << buf[1];
|
|
}
|
|
|
|
return used > 0;
|
|
}
|
|
|
|
|
|
/*!
|
|
this function converts one UTF-8 character into int
|
|
|
|
input:
|
|
iterator_in - an stream iterator for reading from (the stream can by any stream, we use *, ++ and == operators only)
|
|
iterator_end - an end iterator
|
|
|
|
output:
|
|
res - an output character
|
|
correct - true if it is a correct character
|
|
|
|
the function returns how many characters have been used from the input stream
|
|
*/
|
|
template<typename StreamIteratorType>
|
|
size_t utf8_to_int(StreamIteratorType & iterator_in, const StreamIteratorType & iterator_end, int & res, bool & correct)
|
|
{
|
|
size_t i, len;
|
|
unsigned char uz;
|
|
|
|
res = 0;
|
|
correct = false;
|
|
|
|
if( iterator_in == iterator_end )
|
|
return 0;
|
|
|
|
uz = *iterator_in;
|
|
++iterator_in;
|
|
|
|
if( !private_namespace::utf8_to_int_first_octet(uz, len, res) )
|
|
return 1;
|
|
|
|
for(i=1 ; i<len ; ++i)
|
|
{
|
|
if( iterator_in == iterator_end )
|
|
return i;
|
|
|
|
uz = *iterator_in;
|
|
++iterator_in;
|
|
|
|
if( !private_namespace::utf8_to_int_add_next_octet(uz, res) )
|
|
return i + 1;
|
|
}
|
|
|
|
if( utf8_check_range(res, len) )
|
|
correct = true;
|
|
|
|
return len;
|
|
}
|
|
|
|
|
|
|
|
/*!
|
|
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);
|
|
}
|
|
|
|
|
|
|
|
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 a wide stream or a wide string
|
|
|
|
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 or a wide string for the output sequence
|
|
|
|
this function returns false if there were some errors when converting
|
|
*/
|
|
template<typename StreamOrStringType>
|
|
bool utf8_to_wide(const Stream & stream, StreamOrStringType & 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 )
|
|
int_to_wide(0xFFFD, res); // U+FFFD "replacement character"
|
|
|
|
was_error = true;
|
|
}
|
|
else
|
|
{
|
|
int_to_wide(z, res);
|
|
}
|
|
|
|
index += len;
|
|
}
|
|
}
|
|
while( len > 0 );
|
|
|
|
return !was_error;
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*!
|
|
this function converts UTF-8 stream into a wide stream or a wide string
|
|
|
|
input:
|
|
iterator_in - a stream iterator for reading from (the stream can by any stream, we use *, ++ and == operators only)
|
|
iterator_end - an end iterator
|
|
|
|
output:
|
|
out_stream - an output wide stream or wide string (the stream can by of any kind, we use only << operator for a stream and += for a string)
|
|
|
|
this function returns false if there were some errors when converting
|
|
*/
|
|
template<typename StreamIteratorType, typename StreamOrStringType>
|
|
bool utf8_to_wide(StreamIteratorType & iterator_in, const StreamIteratorType & iterator_end, StreamOrStringType & out_stream, bool clear_stream, int mode)
|
|
{
|
|
if( clear_stream )
|
|
out_stream.clear();
|
|
|
|
int res;
|
|
bool correct;
|
|
bool was_error = false;
|
|
|
|
while( iterator_in != iterator_end )
|
|
{
|
|
utf8_to_int(iterator_in, iterator_end, res, correct);
|
|
|
|
if( correct )
|
|
{
|
|
int_to_wide(res, out_stream);
|
|
}
|
|
else
|
|
{
|
|
if( mode == 1 )
|
|
int_to_wide(0xFFFD, out_stream); // U+FFFD "replacement character"
|
|
|
|
was_error = true;
|
|
}
|
|
}
|
|
|
|
return !was_error;
|
|
}
|
|
|
|
|
|
|
|
|
|
/*!
|
|
this function converts UTF-8 stream into a wide string
|
|
|
|
input:
|
|
iterator_in - a stream iterator for reading from (the stream can by any stream, we use *, ++ and == operators only)
|
|
iterator_end - an end iterator
|
|
|
|
output:
|
|
out_buffer - an output wide string
|
|
max_buffer_len - how many characters can be write (we write the terminating null character too)
|
|
was_buffer_sufficient_large - a pointer to a bool value - if provided it is set to true if the buffer was sufficient large
|
|
|
|
this function returns false if there were some errors when converting or if the output buffer was too short
|
|
*/
|
|
template<typename StreamIteratorType>
|
|
bool utf8_to_wide(StreamIteratorType & iterator_in, const StreamIteratorType & iterator_end, wchar_t * out_buffer, size_t max_buffer_len, int mode, bool * was_buffer_sufficient_large)
|
|
{
|
|
int res;
|
|
bool correct;
|
|
bool was_error = true;
|
|
bool was_buffer_ok = false;
|
|
|
|
if( max_buffer_len > 0 )
|
|
{
|
|
max_buffer_len -= 1; // for terminating null character
|
|
was_error = false;
|
|
was_buffer_ok = true;
|
|
|
|
while( iterator_in != iterator_end )
|
|
{
|
|
utf8_to_int(iterator_in, iterator_end, res, correct);
|
|
|
|
if( !correct )
|
|
{
|
|
was_error = true;
|
|
|
|
if( mode == 1 )
|
|
{
|
|
res = 0xFFFD; // U+FFFD "replacement character"
|
|
correct = true;
|
|
}
|
|
}
|
|
|
|
if( correct )
|
|
{
|
|
size_t len = int_to_wide(res, out_buffer, max_buffer_len);
|
|
// if len is zero then the output buffer is too short - the res input value was correct (it was returned from utf_to_int(...) beforehand)
|
|
|
|
if( len == 0 )
|
|
{
|
|
was_error = true;
|
|
was_buffer_ok = false;
|
|
break;
|
|
}
|
|
else
|
|
{
|
|
out_buffer += len;
|
|
max_buffer_len -= len;
|
|
}
|
|
}
|
|
}
|
|
|
|
*out_buffer = 0;
|
|
}
|
|
|
|
if( was_buffer_sufficient_large )
|
|
*was_buffer_sufficient_large = was_buffer_ok;
|
|
|
|
return !was_error;
|
|
}
|
|
|
|
|
|
|
|
/*!
|
|
this function converts UTF-8 stream into a wide string
|
|
|
|
input:
|
|
stream - a stream for reading from
|
|
|
|
output:
|
|
out_buffer - an output wide string
|
|
max_buffer_len - how many characters can be write (we write the terminating null character too)
|
|
was_buffer_sufficient_large - a pointer to a bool value - if provided it is set to true if the buffer was sufficient large
|
|
|
|
this function returns false if there were some errors when converting or if the output buffer was too short
|
|
*/
|
|
template<typename StreamType>
|
|
bool utf8_to_wide(const StreamType & stream, wchar_t * out_buffer, size_t max_buffer_len, bool * was_buffer_sufficient_large, int mode)
|
|
{
|
|
typename StreamType::const_iterator stream_begin = stream.begin();
|
|
typename StreamType::const_iterator stream_end = stream.end();
|
|
|
|
return utf8_to_wide(stream_begin, stream_end, out_buffer, max_buffer_len, mode, was_buffer_sufficient_large);
|
|
}
|
|
|
|
|
|
|
|
/*!
|
|
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>
|
|
bool wide_stream_to_utf8(StreamType & buffer, std::string & utf8, bool clear, int mode)
|
|
{
|
|
if( clear )
|
|
utf8.clear();
|
|
|
|
return private_namespace::wide_to_utf8_generic(buffer, mode, [&utf8](const char * utf8_buffer, std::size_t buffer_len) -> bool {
|
|
utf8.append(utf8_buffer, buffer_len);
|
|
return true;
|
|
});
|
|
}
|
|
|
|
|
|
|
|
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;
|
|
}
|
|
|
|
|
|
template<typename StreamTypeIn, typename StreamTypeOut>
|
|
bool wide_stream_to_utf8(StreamTypeIn & buffer, StreamTypeOut & utf8, bool clear, int mode)
|
|
{
|
|
if( clear )
|
|
utf8.clear();
|
|
|
|
return private_namespace::wide_to_utf8_generic(buffer, mode, [&utf8](const char * utf8_buffer, std::size_t buffer_len) -> bool {
|
|
utf8.write(utf8_buffer, buffer_len);
|
|
return true;
|
|
});
|
|
}
|
|
|
|
|
|
|
|
/*!
|
|
this function converts a wide stream into a utf8 string
|
|
|
|
input:
|
|
buffer - a wide stream for reading from
|
|
|
|
output:
|
|
utf8 - an output utf8 string
|
|
max_buffer_len - how many characters can be write (we write the terminating null character too)
|
|
was_buffer_sufficient_large - a pointer to a bool value - if provided it is set to true if the buffer was sufficient large
|
|
|
|
this function returns false if there were some errors when converting or if the output buffer was too short
|
|
*/
|
|
template<typename StreamType>
|
|
bool wide_stream_to_utf8(StreamType & buffer, char * utf8, std::size_t max_buffer_size, bool * was_buffer_sufficient_large, int mode)
|
|
{
|
|
bool buffer_ok = false;
|
|
bool is_ok = false;
|
|
|
|
if( max_buffer_size > 0 )
|
|
{
|
|
buffer_ok = true;
|
|
max_buffer_size -= 1; // for terminating null character
|
|
|
|
is_ok = private_namespace::wide_to_utf8_generic(buffer, mode, [&utf8, &max_buffer_size, &buffer_ok](const char * utf8_buffer, std::size_t buffer_len) -> bool {
|
|
std::size_t i=0;
|
|
|
|
for( ; i < buffer_len ; ++i)
|
|
{
|
|
if( i < max_buffer_size )
|
|
{
|
|
*utf8 = utf8_buffer[i];
|
|
utf8 += 1;
|
|
}
|
|
else
|
|
{
|
|
buffer_ok = false;
|
|
break;
|
|
}
|
|
}
|
|
|
|
max_buffer_size -= i;
|
|
*utf8 = 0;
|
|
return buffer_ok;
|
|
});
|
|
}
|
|
|
|
if( was_buffer_sufficient_large )
|
|
*was_buffer_sufficient_large = buffer_ok;
|
|
|
|
return is_ok;
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
} // namespace pt
|
|
|
|
#endif
|
|
|
|
|
|
|