Header lexy/code_point.hpp

Class lexy::code_point

lexy/code_point.hpp
namespace lexy
{
    class code_point
    {
    public:
        constexpr code_point() noexcept;
        constexpr explicit code_point(char32_t value) noexcept;

        constexpr char32_t value() const noexcept;

        //=== classification ===//
        constexpr bool is_ascii() const noexcept;
        constexpr bool is_bmp() const noexcept;
        constexpr bool is_valid() const noexcept;

        constexpr bool is_control() const noexcept;
        constexpr bool is_surrogate() const noexcept;
        constexpr bool is_private_use() const noexcept;
        constexpr bool is_noncharacter() const noexcept;

        constexpr bool is_scalar() const noexcept;

        //=== general category ===//
        enum general_category_t;

        constexpr general_category_t general_category() const;

        struct gc-group;
        // gc-group constants, see below.

        //=== comparison ===//
        friend constexpr bool operator==(code_point lhs, code_point rhs) noexcept;
        friend constexpr bool operator!=(code_point lhs, code_point rhs) noexcept;
    };
}

A single Unicode code point.

It is a simple wrapper over a char32_t.

Constructors

lexy/code_point.hpp
constexpr code_point() noexcept;                        (1)
constexpr explicit code_point(char32_t value) noexcept; (2)
  1. Creates an invalid code point.

  2. Creates the code point with the specified value.

Classification

lexy/code_point.hpp
constexpr bool is_ascii() const noexcept; (1)
constexpr bool is_bmp() const noexcept;   (2)
constexpr bool is_valid() const noexcept; (3)
  1. Returns true if the code point is ASCII (0x00-0x7F), false otherwise.

  2. Returns true if the code point is in the Unicode BMP (0x0000-0xFFFF), false otherwise.

  3. Returns true if the code point is a value in the Unicode codespace (⇐ 0x10’FFFF), false otherwise.

lexy/code_point.hpp
constexpr bool is_control() const noexcept;      (1)
constexpr bool is_surrogate() const noexcept;    (2)
constexpr bool is_private_use() const noexcept;  (3)
constexpr bool is_noncharacter() const noexcept; (4)
  1. Returns true if the code point’s general category is Cc (control), false otherwise.

  2. Returns true if the code point’s general category is Cs (surrogate), false otherwise.

  3. Returns true if the code point’s general category is Co (private-use), false otherwise.

  4. Returns true if the code point’s general category is Cn (not assigned) and the code point is not reserved, false otherwise.

Note
Those are all of the general categories that are stable. As such, they are available without the Unicode database.
lexy/code_point.hpp
constexpr bool is_scalar() const noexcept
{
    return is_valid() && !is_surrogate();
}

Returns true if the code point is valid and not a surrogate, false otherwise.

General Category

lexy/code_point.hpp
enum general_category_t
{
    // Enum values written in the same line are aliases.

    Lu, uppercase_letter,
    Ll, lowercase_letter,
    Lt, titlecase_letter,
    Lm, modifier_letter,
    Lo, other_letter,

    Mn, nonspacing_mark,
    Mc, spaing_mark,
    Me, enclosing_mark,

    Nd, decimal_number,
    Nl, letter_number,
    No, other_number,

    Pc, connector_punctuation,
    Pd, dash_punctuation,
    Ps, open_punctuation,
    Pe, closing_punctuation,
    Pi, initial_puncutation,
    Pf, final_puncutation,
    Po, other_punctuation,

    Sm, math_symbol,
    Sc, currency_symbol,
    Sk, modifier_symbol,
    So, other_symbol,

    Zs, space_separator,
    Zl, line_separator,
    Zp, paragraph_separator,

    Cc, control,
    Cf, format,
    Cs, surrogate,
    Co, private_use,
    Cn, unassigned,
};

constexpr general_category_t general_category() const;

Returns the general category of the code point.

This function requires the Unicode database.

lexy/code_point.hpp
struct gc-group
{
    friend constexpr bool operator==(gc-group group, general_category_t cat);
    friend constexpr bool operator==(general_category_t cat, gc-group group);

    friend constexpr bool operator!=(gc-group group, general_category_t cat);
    friend constexpr bool operator!=(general_category_t cat, gc-group group);
};

static constexpr gc-group LC;                 // LC = Lu, Ll, Lt
static constexpr gc-group cased_letter = LC;

static constexpr gc-group L;                  // L = Lu, Ll, Lt, Lm, Lo
static constexpr gc-group letter = L;

static constexpr gc-group M;                  // M = Mn, Mc, Me
static constexpr gc-group mark = M;

static constexpr gc-group N;                  // N = Nd, Nl, No
static constexpr gc-group number = N;

static constexpr gc-group P;                  // P = Pc, Pd, Ps, Pe, Pi, Pf, Po
static constexpr gc-group punctuation = P;

static constexpr gc-group Z;                  // Z = Zs, Zl, Zp
static constexpr gc-group separator = Z;

static constexpr gc-group C;                  // C = Cc, Cf, Cs, Co, Cn
static constexpr gc-group other;

Tag objects to check for a specific Unicode category. They have an overloaded operator== and operator!= with the general_category_t and can be used to check that a code point category is in the group.

This can be done without the Unicode database, but the category of a code point requires the Unicode database.