unicode_normalization.hpp

// Copyright Take Vos 2020.
// Distributed under the Boost Software License, Version 1.0.
// (See accompanying file LICENSE_1_0.txt or copy at https://www.boost.org/LICENSE_1_0.txt)
 
#pragma once
 
#include "unicode_decomposition_type.hpp"
#include "../cast.hpp"
#include "../algorithm.hpp"
#include <cstdint>
#include <string>
#include <string_view>
 
namespace hi::inline v1 {
 
enum class unicode_normalization_mask {
    decompose_canonical = 1 << to_underlying(unicode_decomposition_type::canonical),
    decompose_font = 1 << to_underlying(unicode_decomposition_type::font),
    decompose_no_break = 1 << to_underlying(unicode_decomposition_type::no_break),
    decompose_arabic = 1 << to_underlying(unicode_decomposition_type::arabic),
    decompose_circle = 1 << to_underlying(unicode_decomposition_type::circle),
    decompose_math = 1 << to_underlying(unicode_decomposition_type::math),
    decompose_asian = 1 << to_underlying(unicode_decomposition_type::asian),
    decompose_compat = 1 << to_underlying(unicode_decomposition_type::compat),
 
    decompose_hangul = 1 << 8,
 
    compose_hangul = 1 << 9,
 
    decompose_control = 1 << 10,
 
    compose_CRLF = 1 << 11,
 
    decompose_newline_to_PS = 1 << 12,
 
    decompose_newline_to_LF = 1 << 13,
 
    decompose_newline_to_CRLF = 1 << 14,
 
    decompose_newline_to_SP = 1 << 15,
 
    decompose_newline = decompose_newline_to_PS | decompose_newline_to_LF | decompose_newline_to_CRLF | decompose_newline_to_SP,
 
    NFD = decompose_canonical | decompose_hangul | compose_hangul,
 
    NFKD = NFD | decompose_font | decompose_no_break | decompose_arabic | decompose_circle | decompose_math | decompose_asian |
        decompose_compat,
};
 
[[nodiscard]] constexpr unicode_normalization_mask decompose_newline_to(char32_t new_line_char) noexcept
{
    switch (new_line_char) {
    case U'\n': return unicode_normalization_mask::decompose_newline_to_LF;
    case U'\r': return unicode_normalization_mask::decompose_newline_to_CRLF;
    case U'\u2029': return unicode_normalization_mask::decompose_newline_to_PS;
    case U' ': return unicode_normalization_mask::decompose_newline_to_SP;
    default: hi_no_default();
    }
}
 
[[nodiscard]] constexpr bool any(unicode_normalization_mask const &rhs) noexcept
{
    return static_cast<bool>(to_underlying(rhs));
}
 
[[nodiscard]] constexpr unicode_normalization_mask
operator|(unicode_normalization_mask const &lhs, unicode_normalization_mask const &rhs) noexcept
{
    return static_cast<unicode_normalization_mask>(to_underlying(lhs) | to_underlying(rhs));
}
 
[[nodiscard]] constexpr unicode_normalization_mask
operator&(unicode_normalization_mask const &lhs, unicode_normalization_mask const &rhs) noexcept
{
    return static_cast<unicode_normalization_mask>(to_underlying(lhs) & to_underlying(rhs));
}
 
[[nodiscard]] constexpr unicode_normalization_mask
operator&(unicode_normalization_mask const &lhs, unicode_decomposition_type const &rhs) noexcept
{
    return static_cast<unicode_normalization_mask>(to_underlying(lhs) & (1 << to_underlying(rhs)));
}
 
std::u32string
unicode_NFD(std::u32string_view text, unicode_normalization_mask normalization_mask = unicode_normalization_mask::NFD) noexcept;
 
[[nodiscard]] std::u32string
unicode_NFC(std::u32string_view text, unicode_normalization_mask normalization_mask = unicode_normalization_mask::NFD) noexcept;
 
std::u32string
unicode_NFKD(std::u32string_view text, unicode_normalization_mask normalization_mask = unicode_normalization_mask::NFKD) noexcept;
 
std::u32string
unicode_NFKC(std::u32string_view text, unicode_normalization_mask normalization_mask = unicode_normalization_mask::NFKD) noexcept;
 
} // namespace hi::inline v1