Some potentially useful Unicode constants for use in C++ code

some_unicode_consts.cpp

//
// Created on 2026.04.23
// some potentially useful string constants and the 'std::ostream& operator<<' overloaded for 'std::u8string_view'
// NOTE: keep this file utf-8 encoded
//

#pragma once

#ifndef UNICODE_STRING_CONSTS_H
#define UNICODE_STRING_CONSTS_H

#include <string>
#include <string_view>          // needed for ‘std::string_view’, and for ‘"…"sv’ operator
#include <ostream>

using namespace std::string_view_literals;
using namespace std::string_literals;

namespace ktp_str_consts {
    // WARNING !!!  'string_view' does NOT guarantee that the fragment cut by '.substr' will end with the char '\\0'

    constexpr std::string_view DIGITS = "0123456789"sv;
    constexpr std::string_view BIN_DIGITS = "01"sv;
    constexpr std::string_view OCT_DIGITS = "01234567"sv;

    constexpr std::string_view HEX_LETTERS_UPPERCASE = "ABCDEF"sv;
    constexpr std::string_view HEX_LETTERS_LOWERCASE = "abcdef"sv;
    constexpr std::string_view HEX_LETTERS = "ABCDEFabcdef"sv;

    constexpr std::string_view HEX_DIGITS_UPPERCASE = "0123456789ABCDEF"sv;     // DIGITS + HEX_LETTERS_UPPERCASE;
    constexpr std::string_view HEX_DIGITS_LOWERCASE = "0123456789abcdef"sv;     // DIGITS + HEX_LETTERS_LOWERCASE;
    constexpr std::string_view HEX_DIGITS = "0123456789ABCDEFabcdef"sv;         // DIGITS + HEX_LETTERS;

    constexpr std::string_view ASCII_UPPERCASE = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"sv;
    constexpr std::string_view ASCII_LOWERCASE = "abcdefghijklmnopqrstuvwxyz"sv;
    constexpr std::string_view ASCII_LETTERS =
        "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"sv;   // sorted according to ASCII rules - uppercase 1st!

    constexpr std::string_view ASCII_PUNCTUATION = "!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"sv;  // sorted by ASCII codes
    constexpr std::string_view ASCII_WHITESPACE = "\t\n\v\f\r "sv;  // DEC: TAB 9, NL/LF 10, VT 11, FF 12, CR 13, SPC 32
                                                                    // see also U_SPACES below…
    constexpr std::string_view ASCII_CONTROL_CHARS = "\007\010\033\177"sv;  // BEL 7, BSP 8, ESC 27, DEL 127
    // Only ctrl chars that are likely to be found in texts/terminals were given – excluding those for transmission etc.
    // The NUL 0 char had to be removed because C/C++ treated it as the end of string and didn't iterate over the rest.

    constexpr std::u8string_view DE_UPPERCASE = u8"ÄÖÜẞ"sv;
    constexpr std::u8string_view DE_LOWERCASE = u8"äöüß"sv;
    constexpr std::u8string_view DE_LETTERS = u8"ÄäÖöÜüẞß"sv;   // sorted in DE order
    constexpr std::u8string_view DE_ALL_LETTERS =               // sorted in DE order: uppercase 1st, DE after ASCII
        u8"AaÄäBbCcDdEeFfGgHhIiJjKkLlMmNnOoÖöPpQqRrSsẞßTtUuÜüVvWwXxYyZz"sv;

    constexpr std::u8string_view PL_UPPERCASE = u8"ĄĆĘŁŃÓŚŹŻ"sv;
    constexpr std::u8string_view PL_LOWERCASE = u8"ąćęłńóśźż"sv;
    constexpr std::u8string_view PL_LETTERS = u8"ąĄćĆęĘłŁńŃóÓśŚźŹżŻ"sv; // sorted according to Polish rules
    constexpr std::u8string_view PL_ALL_LETTERS =   // sorted according to Polish rules - lowercase 1st, PL after ASCII
        u8"aAąĄbBcCćĆdDeEęĘfFgGhHiIjJkKlLłŁmMnNńŃoOóÓpPqQrRsSśŚtTuUvVwWxXyYzZźŹżŻ"sv;

    // the U_BRACKETS_VERTICAL constexpr, after the first 3 chars, contains 3 groups of two (2) zero-width symbols,
    // that look like brackets () {} [], but vertically, and after these, the last 20 chars - 29 utf8 chars in total
    constexpr std::u8string_view U_BRACKETS_VERTICAL =      // adjacent strings are combined into one
        u8"⎴⎵⎶" // 3 chars - the '⎶' is unpaired
        u8"⏜⏝"      // " ⏜  ⏝ " (expanded version with spaces added; just for illustration)
        u8"⏞⏟"      // " ⏞  ⏟ "
        u8"⏠⏡"      // " ⏠  ⏡ "
        u8"︗︘︵︶︷︸︹︺︻︼︽︾︿﹀﹁﹂﹃﹄﹇﹈"sv; // 20 characters - all paired; 'sv' at the end of all strings

    constexpr std::u8string_view U_BRACKETS_HORIZONTAL =    // adjacent strings are combined into one
        u8"()<>[]{|}༺༻༼༽᚛᚜⁅⁆⁽⁾₍₎⌈⌉⌊⌋⌜⌝⌞⌟〈〉"   // 31 chars - the '|' is unpaired
        u8"⎛⎜⎝⎞⎟⎠⎡⎢⎣⎤⎥⎦⎧⎨⎩⎪⎫⎬⎭⎰⎱⎸⎹"         // 23 chars - 6 groups of 3 chars, 1 upaired char '⎪' and 2 pairs '⎰⎱⎸⎹'
        u8"❨❩❪❫❬❭❮❯❰❱❲❳❴❵⟅⟆⟓⟔"                  // 18 chars - all paired
        u8"⟦⟧⟨⟩⟪⟫⟬⟭⟮⟯⦃⦄⦅⦆⦇⦈⦉⦊⦋⦌⦍⦎⦏⦐⦑⦒⦓⦔⦕⦖⦗⦘⧘⧙⧚⧛⧼⧽⸂⸃⸄⸅⸉⸊⸌⸍⸜⸝⸢⸣⸤⸥⸦⸧⸨⸩⹕⹖⹗⹘⹙⹚⹛⹜"   // 64 chars - all paired
        u8"〈〉《》「」『』【】〔〕〖〗〘〙〚〛﴾﴿﹙﹚﹛﹜﹝﹞（）＜＞［］｛｝｟｠｢｣"sv; // 38 full-width chars - all paired

    constexpr std::u8string_view U_DEGREES = u8"\u00b0\u2103\u2109"sv;          // ° ℃ ℉, sorted by Unicode value
    constexpr std::u8string_view U_PRIMES = u8"ʹʺ′″‴‵‶‷⁗"sv;    // ‘prime(s)’ symbol(s), sorted by Unicode values
                                /*
                                    U+02B9 ʹ MODIFIER LETTER PRIME
                                    U+02BA ʺ MODIFIER LETTER DOUBLE PRIME
                                    U+2032 ′ PRIME (&prime;) - foot/feet, arch minute(s)
                                    U+2033 ″ DOUBLE PRIME (&Prime;) - inch/inches, arch second(s)
                                    U+2034 ‴ TRIPLE PRIME (&tprime;)
                                    U+2035 ‵ REVERSED PRIME (&backprime;, &bprime;)
                                    U+2036 ‶ REVERSED DOUBLE PRIME
                                    U+2037 ‷ REVERSED TRIPLE PRIME
                                    U+2057 ⁗ QUADRUPLE PRIME (&qprime;)
                                */
    constexpr std::u8string_view U_QUOTATIONS = u8"\"\',«»‘’‚‛“”„‟‹›〝〞"sv;      // sorted by Unicode value

    constexpr std::u8string_view U_SPACES =     // Unicode common spaces (Space Separator - Zs) - 19 chars
        u8"\u0020"  // space (SP): The standard spacebar space.
        u8"\u00A0"  // no-break space (NBSP): Prevents a line break between words.
        u8"\u1680"  // ogham space mark: Used in Ogham script.
        u8"\u180e"  // mongolian vowel separator.
        u8"\u2000"  // en quad: width is 1/2 em.
        u8"\u2001"  // em quad: width is roughly the size of the font's point size 1 em.
        u8"\u2002"  // en space: (ENSP) width is 1/2 em, equal to (u2000).
        u8"\u2003"  // em space: (EMSP) width is 1 em.
        u8"\u2004"  // three-per-em space: 1/3 em.
        u8"\u2005"  // four-per-em space: 1/4 em.
        u8"\u2006"  // six-per-em space: 1/6 em.
        u8"\u2007"  // figure space: width of a digit/number.
        u8"\u2008"  // punctuation space: Width of a comma/period.
        u8"\u2009"  // thin space: a narrow space.
        u8"\u200A"  // hair space: very narrow space.
        u8"\u202F"  // narrow no-break space (NNBSP): Narrow non-breaking space.
        u8"\u205F"  // medium mathematical space (MMSP): Used in math formulas.
        u8"\u3000"  // ideographic space: space used in CJK (Chinese, Japanese, Korean) text.
        u8"\uFEFF"sv; // zero width no-break space (ZWNBS), often used as Byte Order Mark (BOM).



} // namespace ktp_str_consts

// right now (2025.04), standard c++23 'std::ostream& operator <<' does NOT work with 'std::u8string_view' (u8sv)
// btw…  we use 'os.write(… , … ) here (with the explicit length),
// because using just: 'std::cout << reinterpret_cast<const char*>(u8sv.data()) << std::endl;'
// works unpredictable e.g. when the u8sv is created as part of larger string/string_view with '*.substr()',
// and is not ended with the '\\0' char… - it may output all chars to the end of original string/string_view

/*  // btw… for both these operators to work properly in Windows console, we should run the code:
#ifdef _WIN32
    SetConsoleCP(CP_UTF8); // console input CP
    SetConsoleOutputCP(CP_UTF8); // console output CP
#endif
*/

std::ostream& operator<<(std::ostream& os, const std::u8string_view& u8sv) {
    return os.write(reinterpret_cast<const char*>(u8sv.data()), u8sv.size());
}

std::ostream& operator<<(std::ostream& os, const std::u8string& u8s) {
    return os.write(reinterpret_cast<const char*>(u8s.data()), u8s.size());
}

// probably the '<<' operator should be also overloaded for u16string_view/u32string_view,
// but I don't need that right now


/*
 *  related topics: (possibly for future constants purposes)
 *  sample unicode homoglyphs:
 *      https://github.com/codebox/homoglyph/tree/master
 *      https://github.com/codebox/homoglyph/blob/master/raw_data/chars.txt
 *      https://github.com/codebox/homoglyph/blob/master/raw_data/char_codes.txt
 *  ligatures:
 *      https://en.wikipedia.org/wiki/Ligature_(writing)
 *      https://en.wikipedia.org/wiki/List_of_Latin-script_letters#Digraphs_and_Ligatures
 *  multigraphs:
 *      https://en.wikipedia.org/wiki/Multigraph_(orthography)
 *      https://en.wikipedia.org/wiki/Digraph_(orthography)
 *      https://en.wikipedia.org/wiki/List_of_Latin-script_digraphs
 *      https://en.wikipedia.org/wiki/Trigraph_(orthography)
 *      https://en.wikipedia.org/wiki/List_of_Latin-script_trigraphs
 *      https://en.wikipedia.org/wiki/Tetragraph
 *      https://en.wikipedia.org/wiki/Pentagraph
 *      https://en.wikipedia.org/wiki/Hexagraph
 *      https://en.wikipedia.org/wiki/Heptagraph
 */

#endif //UNICODE_STRING_CONSTS_H