pikotools/src/convert/text.h

/*
 * 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) 2017-2022, 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_convert_text
#define headerfile_pikotools_src_convert_text

#include <string>


namespace pt
{

bool is_white(wchar_t c, bool check_additional_chars = true, bool treat_new_line_as_white = true);
bool is_digit(wchar_t c, int base = 10, int * digit = 0);


// IMPROVEME add tests
template<typename HexStringPointerType, typename BytesStringType>
bool hex_string_pointer_to_bytes(const HexStringPointerType * hex_string, BytesStringType & bytes, bool clear_bytes = true)
{
	bool converted_correctly = true;
	size_t i = 0;

	if( clear_bytes )
		bytes.clear();

	for( ; converted_correctly && hex_string[i] != 0 && hex_string[i+1] != 0 ; i += 2)
	{
		int c1, c2;

		converted_correctly = converted_correctly && is_digit(hex_string[i],   16, &c1);
		converted_correctly = converted_correctly && is_digit(hex_string[i+1], 16, &c2);

		if( converted_correctly )
		{
			bytes += (char)(unsigned char)(((c1 << 4) | c2));
		}
	}

	if( hex_string[i] != 0 )
	{
		// one digit has left
		converted_correctly = false;
	}

	return converted_correctly;
}


// IMPROVEME add tests
template<typename HexStringType, typename BytesStringType>
bool hex_string_to_bytes(const HexStringType & hex_string, BytesStringType & bytes, bool clear_bytes = true)
{
	return hex_string_pointer_to_bytes(hex_string.c_str(), bytes, clear_bytes);
}



const char *    skip_white(const char * str,    bool check_additional_chars = true, bool treat_new_line_as_white = true);
const wchar_t * skip_white(const wchar_t * str, bool check_additional_chars = true, bool treat_new_line_as_white = true);



/*
 *
 * str_end is pointing at the end of the string (the last item + one)
 *
 * return value is a pointer to the first white character after a non-white character at the end
 * or to the last+one if there is no any white characters
 *
 */
const char *    skip_white_from_back(const char * str_begin,    const char * str_end,    bool check_additional_chars = true, bool treat_new_line_as_white = true);
const wchar_t * skip_white_from_back(const wchar_t * str_begin, const wchar_t * str_end, bool check_additional_chars = true, bool treat_new_line_as_white = true);

const char *    skip_white_from_back(const char * str,    bool check_additional_chars = true, bool treat_new_line_as_white = true);
const wchar_t * skip_white_from_back(const wchar_t * str, bool check_additional_chars = true, bool treat_new_line_as_white = true);



char    to_lower(char c);
wchar_t to_lower(wchar_t c);

char    to_upper(char c);
wchar_t to_upper(wchar_t c);

void to_lower_emplace(std::string & str);
void to_lower_emplace(std::wstring & str);

void to_upper_emplace(std::string & str);
void to_upper_emplace(std::wstring & str);

std::string  to_lower(const std::string & str);
std::wstring to_lower(const std::wstring & str);

std::string  to_upper(const std::string & str);
std::wstring to_upper(const std::wstring & str);


int compare(const char * str1, const char * str2);
int compare(const wchar_t * str1, const wchar_t * str2);

int compare(const std::string & str1, const std::string & str2);
int compare(const std::wstring & str1, const std::wstring & str2);

int compare(const char * str1_begin, const char * str1_end, const char * str2);
int compare(const wchar_t * str1_begin, const wchar_t * str1_end, const wchar_t * str2);


/*
 * compare no case
 */
int compare_nc(const char * str1, const char * str2);
int compare_nc(const wchar_t * str1, const wchar_t * str2);

int compare_nc(const std::string & str1, const std::string & str2);
int compare_nc(const std::wstring & str1, const std::wstring & str2);

int compare_nc(const char * str1_begin, const char * str1_end, const char * str2);
int compare_nc(const wchar_t * str1_begin, const wchar_t * str1_end, const wchar_t * str2);



bool is_equal(const char * str1, const char * str2);
bool is_equal(const wchar_t * str1, const wchar_t * str2);

bool is_equal(const std::string & str1, const std::string & str2);
bool is_equal(const std::wstring & str1, const std::wstring & str2);

bool is_equal(const char * str1_begin, const char * str1_end, const char * str2);
bool is_equal(const wchar_t * str1_begin, const wchar_t * str1_end, const wchar_t * str2);

bool is_equal_nc(const char * str1, const char * str2);
bool is_equal_nc(const wchar_t * str1, const wchar_t * str2);

bool is_equal_nc(const std::string & str1, const std::string & str2);
bool is_equal_nc(const std::wstring & str1, const std::wstring & str2);

bool is_equal_nc(const char * str1_begin, const char * str1_end, const char * str2);
bool is_equal_nc(const wchar_t * str1_begin, const wchar_t * str1_end, const wchar_t * str2);


bool is_substr(const char * short_str,    const char * long_str);
bool is_substr(const wchar_t * short_str, const wchar_t * long_str);

bool is_substr(const std::string & short_str,  const std::string & long_str);
bool is_substr(const std::wstring & short_str, const std::wstring & long_str);

bool is_substr_nc(const char * short_str,    const char * long_str);
bool is_substr_nc(const wchar_t * short_str, const wchar_t * long_str);

bool is_substr_nc(const std::string & short_str,  const std::string & long_str);
bool is_substr_nc(const std::wstring & short_str, const std::wstring & long_str);


void trim_first_white(std::string & str, bool check_additional_chars = true, bool treat_new_line_as_white = true);
void trim_first_white(std::wstring & str, bool check_additional_chars = true, bool treat_new_line_as_white = true);

void trim_last_white(std::string & str, bool check_additional_chars = true, bool treat_new_line_as_white = true);
void trim_last_white(std::wstring & str, bool check_additional_chars = true, bool treat_new_line_as_white = true);

void trim_white(std::string & str, bool check_additional_chars = true, bool treat_new_line_as_white = true);
void trim_white(std::wstring & str, bool check_additional_chars = true, bool treat_new_line_as_white = true);

void trim_first(std::string & str, wchar_t c);
void trim_first(std::wstring & str, wchar_t c);

void trim_last(std::string & str, wchar_t c);
void trim_last(std::wstring & str, wchar_t c);

void trim(std::string & str, wchar_t c);
void trim(std::wstring & str, wchar_t c);




}


#endif