mirror of
https://github.com/LadybirdBrowser/ladybird.git
synced 2024-11-25 00:50:22 +00:00
c1b452f754
This patch implements a Unicode-safe substring method, which can be used when offset and length should be specified in actual characters instead of bytes. This can be used to mitigate issues where a string is split in the middle of a UTF-8 multi-byte character, which leads to invalid UTF-8. Furthermore, it implements to common shorthands for substring methods which take only an offset and return the substring until the end of the string.
104 lines
2.7 KiB
C++
104 lines
2.7 KiB
C++
/*
|
|
* Copyright (c) 2019-2020, Sergey Bugaev <bugaevc@serenityos.org>
|
|
* Copyright (c) 2021, Max Wipfli <mail@maxwipfli.ch>
|
|
*
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <AK/StringView.h>
|
|
#include <AK/Types.h>
|
|
|
|
namespace AK {
|
|
|
|
class Utf8View;
|
|
|
|
class Utf8CodepointIterator {
|
|
friend class Utf8View;
|
|
|
|
public:
|
|
Utf8CodepointIterator() = default;
|
|
~Utf8CodepointIterator() = default;
|
|
|
|
bool operator==(const Utf8CodepointIterator&) const;
|
|
bool operator!=(const Utf8CodepointIterator&) const;
|
|
Utf8CodepointIterator& operator++();
|
|
u32 operator*() const;
|
|
|
|
ssize_t operator-(const Utf8CodepointIterator& other) const
|
|
{
|
|
return m_ptr - other.m_ptr;
|
|
}
|
|
|
|
size_t code_point_length_in_bytes() const;
|
|
bool done() const { return m_length == 0; }
|
|
|
|
private:
|
|
Utf8CodepointIterator(const unsigned char*, size_t);
|
|
const unsigned char* m_ptr { nullptr };
|
|
size_t m_length;
|
|
};
|
|
|
|
class Utf8View {
|
|
public:
|
|
using Iterator = Utf8CodepointIterator;
|
|
|
|
Utf8View() = default;
|
|
explicit Utf8View(const String&);
|
|
explicit Utf8View(const StringView&);
|
|
explicit Utf8View(const char*);
|
|
~Utf8View() = default;
|
|
|
|
const StringView& as_string() const { return m_string; }
|
|
|
|
Utf8CodepointIterator begin() const;
|
|
Utf8CodepointIterator end() const;
|
|
|
|
const unsigned char* bytes() const { return begin_ptr(); }
|
|
size_t byte_length() const { return m_string.length(); }
|
|
size_t byte_offset_of(const Utf8CodepointIterator&) const;
|
|
|
|
Utf8View substring_view(size_t byte_offset, size_t byte_length) const;
|
|
Utf8View substring_view(size_t byte_offset) const { return substring_view(byte_offset, byte_length() - byte_offset); }
|
|
Utf8View unicode_substring_view(size_t codepoint_offset, size_t codepoint_length) const;
|
|
Utf8View unicode_substring_view(size_t codepoint_offset) const { return unicode_substring_view(codepoint_offset, length() - codepoint_offset); }
|
|
|
|
bool is_empty() const { return m_string.is_empty(); }
|
|
bool starts_with(const Utf8View&) const;
|
|
|
|
size_t iterator_offset(const Utf8CodepointIterator& it) const
|
|
{
|
|
return byte_offset_of(it);
|
|
}
|
|
|
|
bool validate(size_t& valid_bytes) const;
|
|
bool validate() const
|
|
{
|
|
size_t valid_bytes;
|
|
return validate(valid_bytes);
|
|
}
|
|
|
|
size_t length() const
|
|
{
|
|
if (!m_have_length) {
|
|
m_length = calculate_length();
|
|
m_have_length = true;
|
|
}
|
|
return m_length;
|
|
}
|
|
|
|
private:
|
|
const unsigned char* begin_ptr() const;
|
|
const unsigned char* end_ptr() const;
|
|
size_t calculate_length() const;
|
|
|
|
StringView m_string;
|
|
mutable size_t m_length { 0 };
|
|
mutable bool m_have_length { false };
|
|
};
|
|
|
|
}
|
|
|
|
using AK::Utf8CodepointIterator;
|
|
using AK::Utf8View;
|