551 lines
12 KiB
C++
551 lines
12 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) 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.
|
|
*
|
|
*/
|
|
|
|
#include <cstddef>
|
|
#include "text.h"
|
|
#include "text_private.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 is_white(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 is_digit(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;
|
|
}
|
|
|
|
|
|
const char * skip_white(const char * str, bool check_additional_chars, bool treat_new_line_as_white)
|
|
{
|
|
return pt_private::skip_white_generic(str, check_additional_chars, treat_new_line_as_white);
|
|
}
|
|
|
|
const wchar_t * skip_white(const wchar_t * str, bool check_additional_chars, bool treat_new_line_as_white)
|
|
{
|
|
return pt_private::skip_white_generic(str, check_additional_chars, treat_new_line_as_white);
|
|
}
|
|
|
|
const char * skip_white_from_back(const char * str_begin, const char * str_end, bool check_additional_chars, bool treat_new_line_as_white)
|
|
{
|
|
return pt_private::skip_white_from_back_generic(str_begin, str_end, check_additional_chars, treat_new_line_as_white);
|
|
}
|
|
|
|
const wchar_t * skip_white_from_back(const wchar_t * str_begin, const wchar_t * str_end, bool check_additional_chars, bool treat_new_line_as_white)
|
|
{
|
|
return pt_private::skip_white_from_back_generic(str_begin, str_end, check_additional_chars, treat_new_line_as_white);
|
|
}
|
|
|
|
const char * skip_white_from_back(const char * str, bool check_additional_chars, bool treat_new_line_as_white)
|
|
{
|
|
return pt_private::skip_white_from_back_generic(str, check_additional_chars, treat_new_line_as_white);
|
|
}
|
|
|
|
const wchar_t * skip_white_from_back(const wchar_t * str, bool check_additional_chars, bool treat_new_line_as_white)
|
|
{
|
|
return pt_private::skip_white_from_back_generic(str, check_additional_chars, treat_new_line_as_white);
|
|
}
|
|
|
|
|
|
|
|
|
|
char to_lower(char c)
|
|
{
|
|
return pt_private::to_lower_generic(c);
|
|
}
|
|
|
|
wchar_t to_lower(wchar_t c)
|
|
{
|
|
return pt_private::to_lower_generic(c);
|
|
}
|
|
|
|
|
|
char to_upper(char c)
|
|
{
|
|
return pt_private::to_upper_generic(c);
|
|
}
|
|
|
|
wchar_t to_upper(wchar_t c)
|
|
{
|
|
return pt_private::to_upper_generic(c);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void to_lower_emplace(std::string & str)
|
|
{
|
|
pt_private::to_lower_str_generic(str);
|
|
}
|
|
|
|
|
|
void to_lower_emplace(std::wstring & str)
|
|
{
|
|
pt_private::to_lower_str_generic(str);
|
|
}
|
|
|
|
|
|
void to_upper_emplace(std::string & str)
|
|
{
|
|
pt_private::to_upper_str_generic(str);
|
|
}
|
|
|
|
|
|
void to_upper_emplace(std::wstring & str)
|
|
{
|
|
pt_private::to_upper_str_generic(str);
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
std::string to_lower(const std::string & str)
|
|
{
|
|
std::string res(str);
|
|
to_lower_emplace(res);
|
|
|
|
return res;
|
|
}
|
|
|
|
|
|
std::wstring to_lower(const std::wstring & str)
|
|
{
|
|
std::wstring res(str);
|
|
to_lower_emplace(res);
|
|
|
|
return res;
|
|
}
|
|
|
|
|
|
std::string to_upper(const std::string & str)
|
|
{
|
|
std::string res(str);
|
|
to_upper_emplace(res);
|
|
|
|
return res;
|
|
}
|
|
|
|
|
|
std::wstring to_upper(const std::wstring & str)
|
|
{
|
|
std::wstring res(str);
|
|
to_upper_emplace(res);
|
|
|
|
return res;
|
|
}
|
|
|
|
|
|
|
|
int compare(const char * str1, const char * str2)
|
|
{
|
|
return pt_private::compare_generic(str1, str2);
|
|
}
|
|
|
|
int compare(const wchar_t * str1, const wchar_t * str2)
|
|
{
|
|
return pt_private::compare_generic(str1, str2);
|
|
}
|
|
|
|
int compare(const std::string & str1, const std::string & str2)
|
|
{
|
|
return pt_private::compare_str_generic(str1, str2);
|
|
}
|
|
|
|
int compare(const std::wstring & str1, const std::wstring & str2)
|
|
{
|
|
return pt_private::compare_str_generic(str1, str2);
|
|
}
|
|
|
|
int compare(const char * str1_begin, const char * str1_end, const char * str2)
|
|
{
|
|
return pt_private::compare_generic(str1_begin, str1_end, str2);
|
|
}
|
|
|
|
int compare(const wchar_t * str1_begin, const wchar_t * str1_end, const wchar_t * str2)
|
|
{
|
|
return pt_private::compare_generic(str1_begin, str1_end, str2);
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
int compare_nc(const char * str1, const char * str2)
|
|
{
|
|
return pt_private::compare_nc_generic(str1, str2);
|
|
}
|
|
|
|
int compare_nc(const wchar_t * str1, const wchar_t * str2)
|
|
{
|
|
return pt_private::compare_nc_generic(str1, str2);
|
|
}
|
|
|
|
int compare_nc(const std::string & str1, const std::string & str2)
|
|
{
|
|
return pt_private::compare_nc_str_generic(str1, str2);
|
|
}
|
|
|
|
int compare_nc(const std::wstring & str1, const std::wstring & str2)
|
|
{
|
|
return pt_private::compare_nc_str_generic(str1, str2);
|
|
}
|
|
|
|
int compare_nc(const char * str1_begin, const char * str1_end, const char * str2)
|
|
{
|
|
return pt_private::compare_nc_generic(str1_begin, str1_end, str2);
|
|
}
|
|
|
|
int compare_nc(const wchar_t * str1_begin, const wchar_t * str1_end, const wchar_t * str2)
|
|
{
|
|
return pt_private::compare_nc_generic(str1_begin, str1_end, str2);
|
|
}
|
|
|
|
|
|
bool is_equal(const char * str1, const char * str2)
|
|
{
|
|
return pt_private::compare_generic(str1, str2) == 0;
|
|
}
|
|
|
|
bool is_equal(const wchar_t * str1, const wchar_t * str2)
|
|
{
|
|
return pt_private::compare_generic(str1, str2) == 0;
|
|
}
|
|
|
|
|
|
bool is_equal(const std::string & str1, const std::string & str2)
|
|
{
|
|
return is_equal(str1.c_str(), str2.c_str());
|
|
}
|
|
|
|
|
|
bool is_equal(const std::wstring & str1, const std::wstring & str2)
|
|
{
|
|
return is_equal(str1.c_str(), str2.c_str());
|
|
}
|
|
|
|
|
|
|
|
bool is_equal(const char * str1_begin, const char * str1_end, const char * str2)
|
|
{
|
|
return pt_private::compare_generic(str1_begin, str1_end, str2) == 0;
|
|
}
|
|
|
|
|
|
bool is_equal(const wchar_t * str1_begin, const wchar_t * str1_end, const wchar_t * str2)
|
|
{
|
|
return pt_private::compare_generic(str1_begin, str1_end, str2) == 0;
|
|
}
|
|
|
|
|
|
bool is_equal_nc(const char * str1, const char * str2)
|
|
{
|
|
return pt_private::compare_nc_generic(str1, str2) == 0;
|
|
}
|
|
|
|
|
|
bool is_equal_nc(const wchar_t * str1, const wchar_t * str2)
|
|
{
|
|
return pt_private::compare_nc_generic(str1, str2) == 0;
|
|
}
|
|
|
|
|
|
bool is_equal_nc(const std::string & str1, const std::string & str2)
|
|
{
|
|
return is_equal_nc(str1.c_str(), str2.c_str());
|
|
}
|
|
|
|
|
|
bool is_equal_nc(const std::wstring & str1, const std::wstring & str2)
|
|
{
|
|
return is_equal_nc(str1.c_str(), str2.c_str());
|
|
}
|
|
|
|
|
|
bool is_equal_nc(const char * str1_begin, const char * str1_end, const char * str2)
|
|
{
|
|
return pt_private::compare_nc_generic(str1_begin, str1_end, str2) == 0;
|
|
}
|
|
|
|
|
|
bool is_equal_nc(const wchar_t * str1_begin, const wchar_t * str1_end, const wchar_t * str2)
|
|
{
|
|
return pt_private::compare_nc_generic(str1_begin, str1_end, str2) == 0;
|
|
}
|
|
|
|
|
|
|
|
|
|
bool is_substr(const char * short_str, const char * long_str)
|
|
{
|
|
return pt_private::is_substr_generic(short_str, long_str);
|
|
}
|
|
|
|
|
|
bool is_substr(const wchar_t * short_str, const wchar_t * long_str)
|
|
{
|
|
return pt_private::is_substr_generic(short_str, long_str);
|
|
}
|
|
|
|
|
|
bool is_substr(const std::string & short_str, const std::string & long_str)
|
|
{
|
|
return is_substr(short_str.c_str(), long_str.c_str());
|
|
}
|
|
|
|
|
|
bool is_substr(const std::wstring & short_str, const std::wstring & long_str)
|
|
{
|
|
return is_substr(short_str.c_str(), long_str.c_str());
|
|
}
|
|
|
|
|
|
bool is_substr_nc(const char * short_str, const char * long_str)
|
|
{
|
|
return pt_private::is_substr_nc_generic(short_str, long_str);
|
|
}
|
|
|
|
bool is_substr_nc(const wchar_t * short_str, const wchar_t * long_str)
|
|
{
|
|
return pt_private::is_substr_nc_generic(short_str, long_str);
|
|
}
|
|
|
|
|
|
bool is_substr_nc(const std::string & short_str, const std::string & long_str)
|
|
{
|
|
return pt_private::is_substr_nc_generic(short_str.c_str(), long_str.c_str());
|
|
}
|
|
|
|
|
|
bool is_substr_nc(const std::wstring & short_str, const std::wstring & long_str)
|
|
{
|
|
return pt_private::is_substr_nc_generic(short_str.c_str(), long_str.c_str());
|
|
}
|
|
|
|
|
|
void trim_first_white(std::string & str, bool check_additional_chars, bool treat_new_line_as_white)
|
|
{
|
|
pt_private::trim_first_white_generic(str, check_additional_chars, treat_new_line_as_white);
|
|
}
|
|
|
|
|
|
void trim_first_white(std::wstring & str, bool check_additional_chars, bool treat_new_line_as_white)
|
|
{
|
|
pt_private::trim_first_white_generic(str, check_additional_chars, treat_new_line_as_white);
|
|
}
|
|
|
|
|
|
void trim_last_white(std::string & str, bool check_additional_chars, bool treat_new_line_as_white)
|
|
{
|
|
pt_private::trim_last_white_generic(str, check_additional_chars, treat_new_line_as_white);
|
|
}
|
|
|
|
|
|
void trim_last_white(std::wstring & str, bool check_additional_chars, bool treat_new_line_as_white)
|
|
{
|
|
pt_private::trim_last_white_generic(str, check_additional_chars, treat_new_line_as_white);
|
|
}
|
|
|
|
|
|
void trim_white(std::string & str, bool check_additional_chars, bool treat_new_line_as_white)
|
|
{
|
|
pt_private::trim_white_generic(str, check_additional_chars, treat_new_line_as_white);
|
|
}
|
|
|
|
|
|
void trim_white(std::wstring & str, bool check_additional_chars, bool treat_new_line_as_white)
|
|
{
|
|
pt_private::trim_white_generic(str, check_additional_chars, treat_new_line_as_white);
|
|
}
|
|
|
|
|
|
void trim_first(std::string & str, wchar_t c)
|
|
{
|
|
pt_private::trim_first_generic(str, c);
|
|
}
|
|
|
|
|
|
void trim_first(std::wstring & str, wchar_t c)
|
|
{
|
|
pt_private::trim_first_generic(str, c);
|
|
}
|
|
|
|
|
|
void trim_last(std::string & str, wchar_t c)
|
|
{
|
|
pt_private::trim_last_generic(str, c);
|
|
}
|
|
|
|
|
|
void trim_last(std::wstring & str, wchar_t c)
|
|
{
|
|
pt_private::trim_last_generic(str, c);
|
|
}
|
|
|
|
|
|
void trim(std::string & str, wchar_t c)
|
|
{
|
|
pt_private::trim_generic(str, c);
|
|
}
|
|
|
|
|
|
void trim(std::wstring & str, wchar_t c)
|
|
{
|
|
pt_private::trim_generic(str, c);
|
|
}
|
|
|
|
|
|
void trim_last_new_lines(std::string & str, bool check_carriage_return_too)
|
|
{
|
|
pt_private::trim_last_generic(str, '\n', check_carriage_return_too, '\r');
|
|
}
|
|
|
|
|
|
void trim_last_new_lines(std::wstring & str, bool check_carriage_return_too)
|
|
{
|
|
pt_private::trim_last_generic(str, '\n', check_carriage_return_too, '\r');
|
|
}
|
|
|
|
|
|
|
|
}
|
|
|
|
|