281 lines
6.2 KiB
C++
281 lines
6.2 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, 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.
|
|
*
|
|
*/
|
|
|
|
#include "utf8_private.h"
|
|
|
|
|
|
namespace pt
|
|
{
|
|
|
|
namespace private_namespace
|
|
{
|
|
|
|
/*!
|
|
an auxiliary function for converting from UTF-8 string
|
|
*/
|
|
bool utf8_to_int_first_octet(unsigned char uz, size_t & len, int & res)
|
|
{
|
|
for(len=0 ; (uz & 0x80) != 0 ; ++len)
|
|
uz <<= 1;
|
|
|
|
if( len == 1 || len > 4 )
|
|
return false;
|
|
|
|
res = uz;
|
|
|
|
if( len > 0 )
|
|
res >>= len;
|
|
|
|
if( len == 0 )
|
|
len = 1;
|
|
|
|
return true;
|
|
}
|
|
|
|
|
|
|
|
/*!
|
|
an auxiliary function for converting from UTF-8 string
|
|
*/
|
|
bool utf8_to_int_add_next_octet(unsigned char uz, int & res)
|
|
{
|
|
if( (uz & 0xc0) != 0x80 )
|
|
return false;
|
|
|
|
res <<= 6;
|
|
res |= (uz & 0x3F);
|
|
|
|
return true;
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
an auxiliary function for converting from wide characters to UTF-8
|
|
converting a wide character into one int
|
|
|
|
returns how many wide characters were used
|
|
if string_len is greater than 0 then the return value is always greater than zero too
|
|
*/
|
|
size_t wide_to_int(const wchar_t * wide_string, size_t string_len, int & z, bool & correct)
|
|
{
|
|
if( string_len == 0 )
|
|
{
|
|
z = 0;
|
|
correct = false;
|
|
return 0;
|
|
}
|
|
|
|
z = static_cast<int>(*wide_string);
|
|
correct = true;
|
|
|
|
if( sizeof(wchar_t) == 2 && is_surrogate_char(z) )
|
|
{
|
|
if( is_first_surrogate_char(z) && string_len>1 )
|
|
{
|
|
int z2 = *(wide_string+1);
|
|
|
|
if( is_second_surrogate_char(z2) )
|
|
{
|
|
z = 0x10000 + (((z & 0x3FF) << 10) | (z2 & 0x3FF));
|
|
return 2;
|
|
}
|
|
else
|
|
{
|
|
correct = false;
|
|
return 2;
|
|
}
|
|
}
|
|
else
|
|
{
|
|
correct = false;
|
|
return 1;
|
|
}
|
|
}
|
|
else
|
|
{
|
|
correct = utf8_check_range(z);
|
|
return 1;
|
|
}
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
an auxiliary function for converting from wide characters to UTF-8
|
|
converting a wide character into one int
|
|
|
|
returns how many wide characters were used
|
|
if wide_string has at least one character then the return value is always greater than zero too
|
|
*/
|
|
size_t wide_to_int(const wchar_t * wide_string, int & z, bool & correct)
|
|
{
|
|
size_t min_str_len = 1;
|
|
|
|
if( *wide_string == 0 )
|
|
{
|
|
z = 0;
|
|
correct = false;
|
|
return 0;
|
|
}
|
|
|
|
if( *(wide_string+1) != 0 )
|
|
min_str_len = 2;
|
|
|
|
return wide_to_int(wide_string, min_str_len, z, correct);
|
|
}
|
|
|
|
|
|
|
|
/*!
|
|
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
|
|
|
|
utf8_written - how many characters were saved in the utf8 string (the string doesn't have
|
|
a null terminating character)
|
|
it can be equal to zero if the utf8 buffer is too small or there was an incorrect wide character read
|
|
was_utf8_buf_too_small - will be true if the utf8 buffer is too small
|
|
if this flag is true then utf8_written is equal to zero
|
|
was_error - will be true if there is an error when converting (there was an incorrect wide character)
|
|
(was_error will not be true if the utf8 buffer is too small)
|
|
*/
|
|
size_t wide_one_to_utf8(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)
|
|
{
|
|
int z;
|
|
bool correct;
|
|
size_t chars;
|
|
|
|
utf8_written = 0;
|
|
was_utf8_buf_too_small = false;
|
|
chars = wide_to_int(wide_string, string_len, z, correct);
|
|
|
|
if( correct )
|
|
{
|
|
utf8_written = int_to_utf8(z, utf8, utf8_len);
|
|
|
|
if( utf8_written == 0 )
|
|
was_utf8_buf_too_small = true;
|
|
}
|
|
else
|
|
{
|
|
if( mode == 1 )
|
|
{
|
|
utf8_written = int_to_utf8(0xFFFD, utf8, utf8_len); // U+FFFD "replacement character"
|
|
|
|
if( utf8_written == 0 )
|
|
was_utf8_buf_too_small = true;
|
|
}
|
|
|
|
was_error = true;
|
|
}
|
|
|
|
return chars;
|
|
}
|
|
|
|
|
|
|
|
/*!
|
|
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
|
|
*/
|
|
size_t wide_one_to_utf8(const wchar_t * wide_string, size_t string_len, std::string & utf8, bool & was_error, int mode)
|
|
{
|
|
int z;
|
|
bool correct;
|
|
size_t chars;
|
|
|
|
chars = wide_to_int(wide_string, string_len, z, correct);
|
|
|
|
if( correct )
|
|
correct = int_to_utf8(z, utf8, false) != 0;
|
|
|
|
if( !correct )
|
|
{
|
|
if( mode == 1 )
|
|
int_to_utf8(0xFFFD, utf8, false); // U+FFFD "replacement character"
|
|
|
|
was_error = true;
|
|
}
|
|
|
|
return chars;
|
|
}
|
|
|
|
|
|
|
|
/*!
|
|
an auxiliary function for converting from wide characters to UTF-8
|
|
|
|
returns how many wide characters were used
|
|
if wide_string has at least one character then the return value is always greater than zero too
|
|
*/
|
|
size_t wide_one_to_utf8(const wchar_t * wide_string, std::string & utf8, bool & was_error, int mode)
|
|
{
|
|
int z;
|
|
bool correct;
|
|
size_t chars;
|
|
|
|
chars = wide_to_int(wide_string, z, correct);
|
|
|
|
if( correct )
|
|
correct = int_to_utf8(z, utf8, false) != 0;
|
|
|
|
if( !correct )
|
|
{
|
|
if( mode == 1 )
|
|
int_to_utf8(0xFFFD, utf8, false); // U+FFFD "replacement character"
|
|
|
|
was_error = true;
|
|
}
|
|
|
|
return chars;
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
} // namespace private_namespace
|
|
|
|
} // namespace pt
|
|
|
|
|
|
|