mirror of
https://github.com/LadybirdBrowser/ladybird.git
synced 2024-11-22 15:40:19 +00:00
9b83cd1abf
Also includes a way to transcode from and to UTF-8 strings.
113 lines
2.9 KiB
C++
113 lines
2.9 KiB
C++
/*
|
|
* Copyright (c) 2021, Tim Flynn <trflynn89@pm.me>
|
|
*
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <AK/Forward.h>
|
|
#include <AK/Optional.h>
|
|
#include <AK/Span.h>
|
|
#include <AK/String.h>
|
|
#include <AK/Types.h>
|
|
#include <AK/Vector.h>
|
|
|
|
namespace AK {
|
|
|
|
Vector<u16> utf8_to_utf16(StringView const&);
|
|
Vector<u16> utf8_to_utf16(Utf8View const&);
|
|
|
|
class Utf16View;
|
|
|
|
class Utf16CodePointIterator {
|
|
friend class Utf16View;
|
|
|
|
public:
|
|
Utf16CodePointIterator() = default;
|
|
~Utf16CodePointIterator() = default;
|
|
|
|
bool operator==(Utf16CodePointIterator const& other) const
|
|
{
|
|
return (m_ptr == other.m_ptr) && (m_remaining_code_units == other.m_remaining_code_units);
|
|
}
|
|
|
|
bool operator!=(Utf16CodePointIterator const& other) const
|
|
{
|
|
return !(*this == other);
|
|
}
|
|
|
|
Utf16CodePointIterator& operator++();
|
|
u32 operator*() const;
|
|
|
|
size_t length_in_code_units() const;
|
|
|
|
private:
|
|
Utf16CodePointIterator(u16 const* ptr, size_t length)
|
|
: m_ptr(ptr)
|
|
, m_remaining_code_units(length)
|
|
{
|
|
}
|
|
|
|
u16 const* m_ptr { nullptr };
|
|
size_t m_remaining_code_units { 0 };
|
|
};
|
|
|
|
class Utf16View {
|
|
public:
|
|
static bool is_high_surrogate(u16);
|
|
static bool is_low_surrogate(u16);
|
|
static u32 decode_surrogate_pair(u16 high_surrogate, u16 low_surrogate);
|
|
|
|
Utf16View() = default;
|
|
~Utf16View() = default;
|
|
|
|
explicit Utf16View(Span<u16 const> code_units)
|
|
: m_code_units(code_units)
|
|
{
|
|
}
|
|
|
|
Utf16View& operator=(Utf16View const&) = default;
|
|
Utf16View& operator=(Utf16View&&) = default;
|
|
bool operator==(Utf16View const& other) const;
|
|
|
|
enum class AllowInvalidCodeUnits {
|
|
Yes,
|
|
No,
|
|
};
|
|
|
|
String to_utf8(AllowInvalidCodeUnits = AllowInvalidCodeUnits::No) const;
|
|
|
|
bool is_empty() const { return m_code_units.is_empty(); }
|
|
size_t length_in_code_units() const { return m_code_units.size(); }
|
|
size_t length_in_code_points() const;
|
|
|
|
Utf16CodePointIterator begin() const { return { begin_ptr(), m_code_units.size() }; }
|
|
Utf16CodePointIterator end() const { return { end_ptr(), 0 }; }
|
|
|
|
u16 const* data() const { return m_code_units.data(); }
|
|
u16 code_unit_at(size_t index) const;
|
|
|
|
Utf16View substring_view(size_t code_unit_offset, size_t code_unit_length) const;
|
|
Utf16View substring_view(size_t code_unit_offset) const { return substring_view(code_unit_offset, length_in_code_units() - code_unit_offset); }
|
|
|
|
bool validate(size_t& valid_code_units) const;
|
|
bool validate() const
|
|
{
|
|
size_t valid_code_units;
|
|
return validate(valid_code_units);
|
|
}
|
|
|
|
private:
|
|
u16 const* begin_ptr() const { return m_code_units.data(); }
|
|
u16 const* end_ptr() const { return begin_ptr() + m_code_units.size(); }
|
|
|
|
size_t calculate_length_in_code_points() const;
|
|
|
|
Span<u16 const> m_code_units;
|
|
mutable Optional<size_t> m_length_in_code_points;
|
|
};
|
|
|
|
}
|
|
|
|
using AK::Utf16View;
|