pikotools/convert/text.cpp

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

/*
 * Copyright (c) 2017-2021, 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.
 */

#include <cstddef>
#include "text.h"


namespace PT
{

// white_chars table should be sorted (a binary search algorithm is used to find a character)
// we do not treat a new line character (10) as a white character here
// also space (32) and tab (9) are not inserted here
static const wchar_t white_chars_table[] = {
	0x000B, // LINE TABULATION (vertical tabulation)
	0x000C, // FORM FEED (FF)
	0x000D,	// CARRIAGE RETURN (CR) - a character at the end in a dos text file
	0x0085, // NEXT LINE (NEL)
	0x00A0, // NO-BREAK SPACE (old name: NON-BREAKING SPACE)
	0x1680, // OGHAM SPACE MARK
	0x180E, // MONGOLIAN VOWEL SEPARATOR
	0x2000, // EN QUAD
	0x2001, // EM QUAD
	0x2002, // EN SPACE
	0x2003, // EM SPACE
	0x2004, // THREE-PER-EM SPACE
	0x2005, // FOUR-PER-EM SPACE
	0x2006, // SIX-PER-EM SPACE
	0x2007, // FIGURE SPACE
	0x2008, // PUNCTUATION SPACE
	0x2009, // THIN SPACE
	0x200A, // HAIR SPACE
	0x2028, // LINE SEPARATOR
	0x2029, // PARAGRAPH SEPARATOR
	0x202F, // NARROW NO-BREAK SPACE
	0x205F, // MEDIUM MATHEMATICAL SPACE
	0x3000, // IDEOGRAPHIC SPACE
	0xFEFF, // ZERO WIDTH NO-BREAK SPACE
};




/*
	if check_additional_chars is false then we are testing only a space (32), tab (9) and a new line (10) (if treat_new_line_as_white is true)
*/
bool IsWhite(wchar_t c, bool check_additional_chars, bool treat_new_line_as_white)
{
	// space (32) and tab (9) are the most common white chars
	// so we check them at the beginning (optimisation)
	if( c == 32 || c == 9 )
		return true;

	std::size_t len = sizeof(white_chars_table) / sizeof(wchar_t);
	std::size_t o1  = 0;
	std::size_t o2  = len - 1;

	if( c == 10 )
		return treat_new_line_as_white ? true : false;

	if( !check_additional_chars )
		return false;

	if( c < white_chars_table[o1] || c > white_chars_table[o2] )
		return false;

	if( c == white_chars_table[o1] || c == white_chars_table[o2] )
		return true;

	while( o1 + 1 < o2 )
	{
		std::size_t o = (o2 - o1)/2 + o1;

		if( c == white_chars_table[o] )
			return true;

		if( c > white_chars_table[o] )
			o1 = o;
		else
			o2 = o;
	}

return false;
}



bool IsDigit(wchar_t c, int base, int * digit)
{
	int d = 0;

	if( c >= '0' && c <= '9' )
	{
		d = c - '0';
	}
	else
	if( c >= 'a' && c <= 'f' )
	{
		d = c - 'a' + 10;
	}
	else
	if( c >= 'A' && c <= 'F' )
	{
		d = c - 'A' + 10;
	}
	else
	{
		if( digit )
			*digit = d;

		return false;
	}

	if( digit )
		*digit = d;

	return d < base;
}



char ToLower(char c)
{
	return pt_private::ToLowerGeneric(c);
}

wchar_t ToLower(wchar_t c)
{
	return pt_private::ToLowerGeneric(c);
}


char ToUpper(char c)
{
	return pt_private::ToUpperGeneric(c);
}

wchar_t ToUpper(wchar_t c)
{
	return pt_private::ToUpperGeneric(c);

}




void ToLower(std::string & str)
{
	pt_private::ToLowerStrGeneric(str);
}

void ToLower(std::wstring & str)
{
	pt_private::ToLowerStrGeneric(str);
}


void ToUpper(std::string & str)
{
	pt_private::ToLowerStrGeneric(str);
}

void ToUpper(std::wstring & str)
{
	pt_private::ToLowerStrGeneric(str);
}






}